[
  {
    "title": "Accuracy",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - EM",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "MMLU"
        }
      },
      {
        "value": "BoolQ - EM",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - F1",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - F1",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - F1",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - F1",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "QuAC"
        }
      },
      {
        "value": "HellaSwag - EM",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "OpenbookQA - EM",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "TruthfulQA - EM",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "MS MARCO (regular) - RR@10",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nRR@10: Mean reciprocal rank at 10 in information retrieval.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "RR@10",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (TREC) - NDCG@10",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nNDCG@10: Normalized discounted cumulative gain at 10 in information retrieval.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "NDCG@10",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "CNN/DailyMail - ROUGE-2",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nROUGE-2: Average ROUGE score [(Lin, 2004)](https://aclanthology.org/W04-1013/) based on 2-gram overlap.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "ROUGE-2",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - ROUGE-2",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nROUGE-2: Average ROUGE score [(Lin, 2004)](https://aclanthology.org/W04-1013/) based on 2-gram overlap.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "ROUGE-2",
          "run_group": "XSUM"
        }
      },
      {
        "value": "IMDB - EM",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - EM",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - EM",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5165029827884389,
          "markdown": false
        },
        {
          "value": 0.2593684210526315,
          "description": "min=0.19, mean=0.259, max=0.35, sum=3.891 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7756666666666666,
          "description": "min=0.766, mean=0.776, max=0.786, sum=2.327 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6950442680690715,
          "description": "min=0.689, mean=0.695, max=0.698, sum=2.085 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.292925597463953,
          "description": "min=0.288, mean=0.293, max=0.302, sum=0.879 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5952126219349451,
          "description": "min=0.593, mean=0.595, max=0.598, sum=1.786 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35828264870222454,
          "description": "min=0.348, mean=0.358, max=0.372, sum=1.075 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.765,
          "description": "min=0.765, mean=0.765, max=0.765, sum=0.765 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.534,
          "description": "min=0.534, mean=0.534, max=0.534, sum=0.534 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1748216106014271,
          "description": "min=0.157, mean=0.175, max=0.187, sum=0.524 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21012843915343896,
          "description": "min=0.173, mean=0.21, max=0.234, sum=0.63 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3629986373891198,
          "description": "min=0.316, mean=0.363, max=0.406, sum=1.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14356477602115186,
          "description": "min=0.137, mean=0.144, max=0.157, sum=0.861 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12934834917323101,
          "description": "min=0.128, mean=0.129, max=0.131, sum=0.776 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9433333333333334,
          "description": "min=0.934, mean=0.943, max=0.951, sum=2.83 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5530211100027326,
          "description": "min=0.03, mean=0.553, max=0.968, sum=29.863 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6810606060606061,
          "description": "min=0.225, mean=0.681, max=0.975, sum=22.475 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.28522343606986267,
          "markdown": false
        },
        {
          "value": 0.2411345029239766,
          "description": "min=0.2, mean=0.241, max=0.298, sum=3.617 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6833333333333332,
          "description": "min=0.652, mean=0.683, max=0.709, sum=2.05 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6233776985224148,
          "description": "min=0.612, mean=0.623, max=0.634, sum=1.87 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19018060381534987,
          "description": "min=0.182, mean=0.19, max=0.196, sum=0.571 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5321738626871023,
          "description": "min=0.5, mean=0.532, max=0.571, sum=1.597 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32775258493199966,
          "description": "min=0.322, mean=0.328, max=0.336, sum=0.983 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7,
          "description": "min=0.7, mean=0.7, max=0.7, sum=0.7 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.514,
          "description": "min=0.514, mean=0.514, max=0.514, sum=0.514 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1967380224260958,
          "description": "min=0.19, mean=0.197, max=0.2, sum=0.59 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1469416666666666,
          "description": "min=0.12, mean=0.147, max=0.178, sum=0.441 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2923798848690971,
          "description": "min=0.266, mean=0.292, max=0.338, sum=0.877 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13373993742545268,
          "description": "min=0.123, mean=0.134, max=0.147, sum=0.802 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10197081870092557,
          "description": "min=0.095, mean=0.102, max=0.107, sum=0.612 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9563333333333333,
          "description": "min=0.951, mean=0.956, max=0.962, sum=2.869 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5317295220953334,
          "description": "min=0, mean=0.532, max=0.996, sum=28.713 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5454545454545454,
          "description": "min=0.15, mean=0.545, max=0.95, sum=18 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4326352237399234,
          "markdown": false
        },
        {
          "value": 0.2697894736842105,
          "description": "min=0.2, mean=0.27, max=0.35, sum=4.047 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7216666666666667,
          "description": "min=0.712, mean=0.722, max=0.733, sum=2.165 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6718376857694667,
          "description": "min=0.664, mean=0.672, max=0.68, sum=2.016 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23340639901403326,
          "description": "min=0.229, mean=0.233, max=0.239, sum=0.7 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.577833816591653,
          "description": "min=0.561, mean=0.578, max=0.59, sum=1.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36235811080321456,
          "description": "min=0.355, mean=0.362, max=0.372, sum=1.087 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.739,
          "description": "min=0.739, mean=0.739, max=0.739, sum=0.739 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.52,
          "description": "min=0.52, mean=0.52, max=0.52, sum=0.52 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19317023445463813,
          "description": "min=0.171, mean=0.193, max=0.217, sum=0.58 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1609592592592591,
          "description": "min=0.152, mean=0.161, max=0.179, sum=0.483 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3405754555729712,
          "description": "min=0.31, mean=0.341, max=0.389, sum=1.022 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14308855635721543,
          "description": "min=0.127, mean=0.143, max=0.163, sum=0.859 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12219343352396624,
          "description": "min=0.118, mean=0.122, max=0.127, sum=0.733 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.953,
          "description": "min=0.947, mean=0.953, max=0.957, sum=2.859 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5286950663987461,
          "description": "min=0.014, mean=0.529, max=0.991, sum=28.55 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6575757575757576,
          "description": "min=0.2, mean=0.658, max=0.975, sum=21.7 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7063959185743808,
          "markdown": false
        },
        {
          "value": 0.4451461988304094,
          "description": "min=0.23, mean=0.445, max=0.8, sum=6.677 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8123333333333332,
          "description": "min=0.799, mean=0.812, max=0.823, sum=2.437 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7253230639897296,
          "description": "min=0.712, mean=0.725, max=0.736, sum=2.176 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33747923162904164,
          "description": "min=0.332, mean=0.337, max=0.341, sum=1.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6245416926486138,
          "description": "min=0.622, mean=0.625, max=0.628, sum=1.874 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3924659267286062,
          "description": "min=0.375, mean=0.392, max=0.411, sum=1.177 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.764,
          "description": "min=0.764, mean=0.764, max=0.764, sum=0.764 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.56,
          "description": "min=0.56, mean=0.56, max=0.56, sum=0.56 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30581039755351686,
          "description": "min=0.266, mean=0.306, max=0.333, sum=0.917 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28512698412698373,
          "description": "min=0.264, mean=0.285, max=0.316, sum=0.855 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4599017899356203,
          "description": "min=0.401, mean=0.46, max=0.51, sum=1.38 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14579152541311485,
          "description": "min=0.14, mean=0.146, max=0.152, sum=0.875 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15183761248617533,
          "description": "min=0.149, mean=0.152, max=0.157, sum=0.911 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9573333333333333,
          "description": "min=0.947, mean=0.957, max=0.964, sum=2.872 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5463201945533748,
          "description": "min=0.008, mean=0.546, max=1, sum=29.501 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6787878787878787,
          "description": "min=0.225, mean=0.679, max=0.95, sum=22.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8243826668326112,
          "markdown": false
        },
        {
          "value": 0.4804912280701755,
          "description": "min=0.23, mean=0.48, max=0.83, sum=7.207 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8290000000000001,
          "description": "min=0.818, mean=0.829, max=0.838, sum=2.487 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7331791563395393,
          "description": "min=0.715, mean=0.733, max=0.757, sum=2.2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38528324996995494,
          "description": "min=0.384, mean=0.385, max=0.387, sum=1.156 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6690001436292841,
          "description": "min=0.65, mean=0.669, max=0.681, sum=2.007 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43492149096530447,
          "description": "min=0.426, mean=0.435, max=0.446, sum=1.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.788,
          "description": "min=0.788, mean=0.788, max=0.788, sum=0.788 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.558,
          "description": "min=0.558, mean=0.558, max=0.558, sum=0.558 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.437308868501529,
          "description": "min=0.367, mean=0.437, max=0.485, sum=1.312 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39838425925925874,
          "description": "min=0.396, mean=0.398, max=0.401, sum=1.195 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6606283875315079,
          "description": "min=0.62, mean=0.661, max=0.706, sum=1.982 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14873979657445188,
          "description": "min=0.142, mean=0.149, max=0.157, sum=0.892 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1815971021083342,
          "description": "min=0.177, mean=0.182, max=0.186, sum=1.09 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.9383333333333334,
          "description": "min=0.936, mean=0.938, max=0.943, sum=2.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5704720622532924,
          "description": "min=0.011, mean=0.57, max=1, sum=30.805 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7462121212121212,
          "description": "min=0.225, mean=0.746, max=0.975, sum=24.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7432468914567079,
          "markdown": false
        },
        {
          "value": 0.4753216374269006,
          "description": "min=0.24, mean=0.475, max=0.81, sum=7.13 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.826,
          "description": "min=0.816, mean=0.826, max=0.832, sum=2.478 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7367678034918216,
          "description": "min=0.732, mean=0.737, max=0.744, sum=2.21 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35608961086227614,
          "description": "min=0.35, mean=0.356, max=0.362, sum=1.068 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.63945619404969,
          "description": "min=0.627, mean=0.639, max=0.649, sum=1.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41818940888320744,
          "description": "min=0.412, mean=0.418, max=0.429, sum=1.255 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.781,
          "description": "min=0.781, mean=0.781, max=0.781, sum=0.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.542,
          "description": "min=0.542, mean=0.542, max=0.542, sum=0.542 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34760448521916415,
          "description": "min=0.287, mean=0.348, max=0.384, sum=1.043 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.293012698412698,
          "description": "min=0.253, mean=0.293, max=0.322, sum=0.879 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5142425752510611,
          "description": "min=0.473, mean=0.514, max=0.577, sum=1.543 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1441329847421396,
          "description": "min=0.131, mean=0.144, max=0.153, sum=0.865 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16746454971003769,
          "description": "min=0.164, mean=0.167, max=0.173, sum=1.005 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9380000000000001,
          "description": "min=0.926, mean=0.938, max=0.954, sum=2.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5467607242969372,
          "description": "min=0.011, mean=0.547, max=0.998, sum=29.525 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7121212121212122,
          "description": "min=0.225, mean=0.712, max=0.975, sum=23.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5529619064657997,
          "markdown": false
        },
        {
          "value": 0.3385263157894737,
          "description": "min=0.211, mean=0.339, max=0.5, sum=5.078 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7423333333333333,
          "description": "min=0.737, mean=0.742, max=0.747, sum=2.227 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27352070416795754,
          "description": "min=0.269, mean=0.274, max=0.28, sum=0.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5887470680751371,
          "description": "min=0.576, mean=0.589, max=0.605, sum=1.766 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.729,
          "description": "min=0.729, mean=0.729, max=0.729, sum=0.729 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.53,
          "description": "min=0.53, mean=0.53, max=0.53, sum=0.53 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24464831804281348,
          "description": "min=0.22, mean=0.245, max=0.283, sum=0.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24691190476190447,
          "description": "min=0.24, mean=0.247, max=0.257, sum=0.741 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46440079625084785,
          "description": "min=0.454, mean=0.464, max=0.479, sum=1.393 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13556600054734838,
          "description": "min=0.122, mean=0.136, max=0.15, sum=0.813 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14213537701038914,
          "description": "min=0.14, mean=0.142, max=0.145, sum=0.853 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9563333333333333,
          "description": "min=0.952, mean=0.956, max=0.96, sum=2.869 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.570363037071474,
          "description": "min=0.149, mean=0.57, max=0.909, sum=30.8 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.621969696969697,
          "description": "min=0.25, mean=0.622, max=0.975, sum=20.525 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.31543317793317793,
          "markdown": false
        },
        {
          "value": 0.26969590643274854,
          "description": "min=0.193, mean=0.27, max=0.32, sum=4.045 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7186666666666666,
          "description": "min=0.7, mean=0.719, max=0.74, sum=2.156 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6049013874612709,
          "description": "min=0.577, mean=0.605, max=0.633, sum=1.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20215793100472382,
          "description": "min=0.197, mean=0.202, max=0.206, sum=0.606 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.568290192606122,
          "description": "min=0.563, mean=0.568, max=0.577, sum=1.705 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33425135386825994,
          "description": "min=0.317, mean=0.334, max=0.362, sum=1.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18246687054026503,
          "description": "min=0.165, mean=0.182, max=0.194, sum=0.547 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.11015829341805718,
          "description": "min=0.048, mean=0.11, max=0.147, sum=0.661 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10459269195035266,
          "description": "min=0.101, mean=0.105, max=0.107, sum=0.628 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9393333333333334,
          "description": "min=0.931, mean=0.939, max=0.949, sum=2.818 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5439265299811482,
          "description": "min=0.003, mean=0.544, max=1, sum=29.372 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47348484848484856,
          "description": "min=0.025, mean=0.473, max=0.975, sum=15.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4850135975135975,
          "markdown": false
        },
        {
          "value": 0.3207134502923977,
          "description": "min=0.23, mean=0.321, max=0.49, sum=4.811 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7666666666666666,
          "description": "min=0.752, mean=0.767, max=0.794, sum=2.3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6648176345749386,
          "description": "min=0.637, mean=0.665, max=0.684, sum=1.994 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2539039625532921,
          "description": "min=0.252, mean=0.254, max=0.257, sum=0.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6088545938518363,
          "description": "min=0.606, mean=0.609, max=0.611, sum=1.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34883471967390484,
          "description": "min=0.34, mean=0.349, max=0.363, sum=1.047 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22069317023445464,
          "description": "min=0.208, mean=0.221, max=0.231, sum=0.662 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.13891887964814623,
          "description": "min=0.117, mean=0.139, max=0.15, sum=0.834 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12368215181184398,
          "description": "min=0.122, mean=0.124, max=0.126, sum=0.742 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9473333333333334,
          "description": "min=0.944, mean=0.947, max=0.951, sum=2.842 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5236261108930882,
          "description": "min=0.014, mean=0.524, max=0.997, sum=28.276 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5227272727272727,
          "description": "min=0, mean=0.523, max=0.925, sum=17.25 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6615918803418803,
          "markdown": false
        },
        {
          "value": 0.380140350877193,
          "description": "min=0.22, mean=0.38, max=0.61, sum=5.702 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.775,
          "description": "min=0.748, mean=0.775, max=0.795, sum=2.325 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7110305793621826,
          "description": "min=0.687, mean=0.711, max=0.742, sum=2.133 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2926781683691718,
          "description": "min=0.281, mean=0.293, max=0.299, sum=0.878 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6485668687165839,
          "description": "min=0.644, mean=0.649, max=0.656, sum=1.946 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3702008493627174,
          "description": "min=0.364, mean=0.37, max=0.378, sum=1.111 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22222222222222224,
          "description": "min=0.2, mean=0.222, max=0.258, sum=0.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1498047386264843,
          "description": "min=0.133, mean=0.15, max=0.16, sum=0.899 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13556479499002097,
          "description": "min=0.133, mean=0.136, max=0.14, sum=0.813 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9593333333333333,
          "description": "min=0.957, mean=0.959, max=0.961, sum=2.878 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5616798875930525,
          "description": "min=0.049, mean=0.562, max=0.984, sum=30.331 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.653030303030303,
          "description": "min=0, mean=0.653, max=0.975, sum=21.55 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7803774182806441,
          "markdown": false
        },
        {
          "value": 0.4813099415204679,
          "description": "min=0.25, mean=0.481, max=0.78, sum=7.22 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8153333333333332,
          "description": "min=0.814, mean=0.815, max=0.816, sum=2.446 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7284241208279414,
          "description": "min=0.692, mean=0.728, max=0.748, sum=2.185 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28770839185717706,
          "description": "min=0.279, mean=0.288, max=0.295, sum=0.863 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6863918123779369,
          "description": "min=0.682, mean=0.686, max=0.693, sum=2.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4312201844030335,
          "description": "min=0.41, mean=0.431, max=0.443, sum=1.294 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.807,
          "description": "min=0.807, mean=0.807, max=0.807, sum=0.807 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.558,
          "description": "min=0.558, mean=0.558, max=0.558, sum=0.558 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3681192660550459,
          "description": "min=0.298, mean=0.368, max=0.408, sum=1.472 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.34, mean=0.382, max=0.407, sum=1.146 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.625, mean=0.642, max=0.66, sum=1.925 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15449688907981599,
          "description": "min=0.142, mean=0.154, max=0.17, sum=0.927 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13392385517213046,
          "description": "min=0.131, mean=0.134, max=0.137, sum=0.804 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.934,
          "description": "min=0.924, mean=0.934, max=0.948, sum=2.802 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6095331322572063,
          "description": "min=0.182, mean=0.61, max=0.939, sum=32.915 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6992424242424242,
          "description": "min=0.225, mean=0.699, max=0.95, sum=23.075 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.44607321557752594,
          "markdown": false
        },
        {
          "value": 0.2987017543859649,
          "description": "min=0.19, mean=0.299, max=0.42, sum=4.481 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7040000000000001,
          "description": "min=0.659, mean=0.704, max=0.728, sum=2.112 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6620518686271105,
          "description": "min=0.631, mean=0.662, max=0.695, sum=1.986 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21589243939833572,
          "description": "min=0.208, mean=0.216, max=0.221, sum=0.648 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.621320604327637,
          "description": "min=0.61, mean=0.621, max=0.628, sum=1.864 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3606360965163296,
          "description": "min=0.342, mean=0.361, max=0.375, sum=1.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.744,
          "description": "min=0.744, mean=0.744, max=0.744, sum=0.744 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.534,
          "description": "min=0.534, mean=0.534, max=0.534, sum=0.534 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20489296636085627,
          "description": "min=0.197, mean=0.205, max=0.211, sum=0.82 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23619986772486745,
          "description": "min=0.212, mean=0.236, max=0.256, sum=0.709 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38615935723643413,
          "description": "min=0.364, mean=0.386, max=0.429, sum=1.158 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07964224289081669,
          "description": "min=0.052, mean=0.08, max=0.118, sum=0.478 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02985413936051232,
          "description": "min=0.022, mean=0.03, max=0.038, sum=0.179 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9453333333333335,
          "description": "min=0.936, mean=0.945, max=0.95, sum=2.836 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6197528530817317,
          "description": "min=0.293, mean=0.62, max=0.92, sum=33.467 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5916666666666667,
          "description": "min=0.25, mean=0.592, max=0.975, sum=19.525 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.19708624708624708,
          "markdown": false
        },
        {
          "value": 0.4065029239766082,
          "description": "min=0.25, mean=0.407, max=0.67, sum=6.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.15117621047324786,
          "description": "min=0.139, mean=0.151, max=0.158, sum=0.454 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038946978500322554,
          "description": "min=0.038, mean=0.039, max=0.04, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18971369502803082,
          "description": "min=0.171, mean=0.19, max=0.203, sum=0.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12076857161291804,
          "description": "min=0.121, mean=0.121, max=0.121, sum=0.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3769113149847095,
          "description": "min=0.347, mean=0.377, max=0.411, sum=1.508 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.12159925414659652,
          "description": "min=0.121, mean=0.122, max=0.122, sum=0.73 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.08989113376628662,
          "description": "min=0.07, mean=0.09, max=0.103, sum=0.539 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.20733333333333334,
          "description": "min=0.181, mean=0.207, max=0.26, sum=0.622 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.23396994868903603,
          "description": "min=0, mean=0.234, max=0.985, sum=12.634 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11818181818181818,
          "description": "min=0, mean=0.118, max=0.775, sum=3.9 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5595464787344654,
          "markdown": false
        },
        {
          "value": 0.35304093567251466,
          "description": "min=0.228, mean=0.353, max=0.56, sum=5.296 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7176666666666667,
          "description": "min=0.702, mean=0.718, max=0.74, sum=2.153 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6501331541221922,
          "description": "min=0.593, mean=0.65, max=0.688, sum=1.95 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3124717413604066,
          "description": "min=0.302, mean=0.312, max=0.32, sum=0.937 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5951499201979565,
          "description": "min=0.576, mean=0.595, max=0.607, sum=1.785 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36059731045912713,
          "description": "min=0.355, mean=0.361, max=0.365, sum=1.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.811,
          "description": "min=0.811, mean=0.811, max=0.811, sum=0.811 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.55,
          "description": "min=0.55, mean=0.55, max=0.55, sum=0.55 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19775739041794085,
          "description": "min=0.177, mean=0.198, max=0.225, sum=0.593 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2733447089947086,
          "description": "min=0.252, mean=0.273, max=0.294, sum=0.82 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.459226881551946,
          "description": "min=0.429, mean=0.459, max=0.479, sum=1.378 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.143547837896566,
          "description": "min=0.14, mean=0.144, max=0.146, sum=0.861 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12917079649271251,
          "description": "min=0.125, mean=0.129, max=0.134, sum=0.775 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9556666666666667,
          "description": "min=0.941, mean=0.956, max=0.965, sum=2.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5319700111376142,
          "description": "min=0.001, mean=0.532, max=1, sum=28.726 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6325757575757576,
          "description": "min=0.1, mean=0.633, max=0.95, sum=20.875 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37183516277474843,
          "markdown": false
        },
        {
          "value": 0.32356725146198834,
          "description": "min=0.19, mean=0.324, max=0.4, sum=4.854 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7253333333333334,
          "description": "min=0.705, mean=0.725, max=0.738, sum=2.176 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.624678200139377,
          "description": "min=0.581, mean=0.625, max=0.647, sum=1.874 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23175077334067687,
          "description": "min=0.227, mean=0.232, max=0.235, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.573258747332884,
          "description": "min=0.553, mean=0.573, max=0.584, sum=1.72 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33835866373160145,
          "description": "min=0.335, mean=0.338, max=0.343, sum=1.015 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.736,
          "description": "min=0.736, mean=0.736, max=0.736, sum=0.736 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.542,
          "description": "min=0.542, mean=0.542, max=0.542, sum=0.542 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18144750254842,
          "description": "min=0.161, mean=0.181, max=0.2, sum=0.544 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19025052910052884,
          "description": "min=0.164, mean=0.19, max=0.212, sum=0.571 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33048901656890556,
          "description": "min=0.292, mean=0.33, max=0.382, sum=0.991 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1262919703390697,
          "description": "min=0.115, mean=0.126, max=0.134, sum=0.758 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10823442092664227,
          "description": "min=0.106, mean=0.108, max=0.11, sum=0.649 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9333333333333332,
          "description": "min=0.929, mean=0.933, max=0.94, sum=2.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5073150250264348,
          "description": "min=0, mean=0.507, max=1, sum=27.395 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5962121212121212,
          "description": "min=0, mean=0.596, max=0.975, sum=19.675 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.22967173202677932,
          "markdown": false
        },
        {
          "value": 0.27880701754385967,
          "description": "min=0.18, mean=0.279, max=0.36, sum=4.182 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.659,
          "description": "min=0.65, mean=0.659, max=0.667, sum=1.977 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5590333932164692,
          "description": "min=0.54, mean=0.559, max=0.572, sum=1.677 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17655959873766028,
          "description": "min=0.173, mean=0.177, max=0.179, sum=0.53 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5040781943652259,
          "description": "min=0.482, mean=0.504, max=0.516, sum=1.512 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2791948993600369,
          "description": "min=0.273, mean=0.279, max=0.287, sum=0.838 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.706,
          "description": "min=0.706, mean=0.706, max=0.706, sum=0.706 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.496,
          "description": "min=0.496, mean=0.496, max=0.496, sum=0.496 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19011213047910294,
          "description": "min=0.176, mean=0.19, max=0.203, sum=0.57 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15197089947089945,
          "description": "min=0.143, mean=0.152, max=0.161, sum=0.456 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37403469141231543,
          "description": "min=0.337, mean=0.374, max=0.416, sum=1.122 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0765619671692878,
          "description": "min=0.03, mean=0.077, max=0.111, sum=0.459 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08741649673627487,
          "description": "min=0.086, mean=0.087, max=0.09, sum=0.524 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.935,
          "description": "min=0.917, mean=0.935, max=0.947, sum=2.805 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5038003954437769,
          "description": "min=0, mean=0.504, max=1, sum=27.205 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5196969696969697,
          "description": "min=0.125, mean=0.52, max=0.975, sum=17.15 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10872045517206808,
          "markdown": false
        },
        {
          "value": 0.2642105263157895,
          "description": "min=0.18, mean=0.264, max=0.42, sum=3.963 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45733333333333337,
          "description": "min=0.447, mean=0.457, max=0.464, sum=1.372 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2936660764833447,
          "description": "min=0.281, mean=0.294, max=0.309, sum=0.881 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07815149344119439,
          "description": "min=0.072, mean=0.078, max=0.082, sum=0.234 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30947350123458284,
          "description": "min=0.291, mean=0.309, max=0.334, sum=0.928 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21856445938515437,
          "description": "min=0.208, mean=0.219, max=0.238, sum=0.656 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.483,
          "description": "min=0.483, mean=0.483, max=0.483, sum=0.483 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.348,
          "description": "min=0.348, mean=0.348, max=0.348, sum=0.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2166156982670744,
          "description": "min=0.202, mean=0.217, max=0.226, sum=0.65 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3036973447248717,
          "description": "min=0.258, mean=0.304, max=0.338, sum=0.911 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06279952717010456,
          "description": "min=0.031, mean=0.063, max=0.087, sum=0.377 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03319446640797243,
          "description": "min=0.031, mean=0.033, max=0.037, sum=0.199 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5783333333333334,
          "description": "min=0.53, mean=0.578, max=0.618, sum=1.735 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.501142240168329,
          "description": "min=0, mean=0.501, max=1, sum=27.062 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4916666666666666,
          "description": "min=0, mean=0.492, max=0.975, sum=16.225 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6639509209274226,
          "markdown": false
        },
        {
          "value": 0.382046783625731,
          "description": "min=0.21, mean=0.382, max=0.67, sum=5.731 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7616666666666667,
          "description": "min=0.761, mean=0.762, max=0.763, sum=2.285 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6723598356227277,
          "description": "min=0.607, mean=0.672, max=0.708, sum=2.017 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3609734437844736,
          "description": "min=0.359, mean=0.361, max=0.365, sum=1.083 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6284877270198662,
          "description": "min=0.619, mean=0.628, max=0.634, sum=1.885 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37415221820631106,
          "description": "min=0.367, mean=0.374, max=0.378, sum=1.122 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.81,
          "description": "min=0.81, mean=0.81, max=0.81, sum=0.81 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.588,
          "description": "min=0.588, mean=0.588, max=0.588, sum=0.588 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1692150866462793,
          "description": "min=0.164, mean=0.169, max=0.179, sum=0.508 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3150321428571424,
          "description": "min=0.291, mean=0.315, max=0.351, sum=0.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5499286754082369,
          "description": "min=0.526, mean=0.55, max=0.573, sum=1.65 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15325621824244975,
          "description": "min=0.153, mean=0.153, max=0.154, sum=0.92 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15313966866470055,
          "description": "min=0.148, mean=0.153, max=0.158, sum=0.919 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.956,
          "description": "min=0.941, mean=0.956, max=0.965, sum=2.868 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5244336728226668,
          "description": "min=0.035, mean=0.524, max=0.968, sum=28.319 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6242424242424242,
          "description": "min=0, mean=0.624, max=0.975, sum=20.6 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.312071752867081,
          "markdown": false
        },
        {
          "value": 0.25371929824561407,
          "description": "min=0.18, mean=0.254, max=0.32, sum=3.806 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6999999999999998,
          "description": "min=0.693, mean=0.7, max=0.704, sum=2.1 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6104216313972795,
          "description": "min=0.57, mean=0.61, max=0.642, sum=1.831 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19916851476433625,
          "description": "min=0.193, mean=0.199, max=0.203, sum=0.598 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5169831729768286,
          "description": "min=0.506, mean=0.517, max=0.536, sum=1.551 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3139272618104655,
          "description": "min=0.297, mean=0.314, max=0.328, sum=0.942 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.726,
          "description": "min=0.726, mean=0.726, max=0.726, sum=0.726 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.538,
          "description": "min=0.538, mean=0.538, max=0.538, sum=0.538 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21508664627930685,
          "description": "min=0.19, mean=0.215, max=0.237, sum=0.645 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17504999999999982,
          "description": "min=0.147, mean=0.175, max=0.195, sum=0.525 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3726465618083979,
          "description": "min=0.329, mean=0.373, max=0.4, sum=1.118 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12134685317448057,
          "description": "min=0.116, mean=0.121, max=0.13, sum=0.728 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09926459738428924,
          "description": "min=0.095, mean=0.099, max=0.106, sum=0.596 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9346666666666666,
          "description": "min=0.917, mean=0.935, max=0.947, sum=2.804 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5003468352676104,
          "description": "min=0, mean=0.5, max=1, sum=27.019 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5909090909090909,
          "description": "min=0.1, mean=0.591, max=0.975, sum=19.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6752100195179311,
          "markdown": false
        },
        {
          "value": 0.4063157894736842,
          "description": "min=0.26, mean=0.406, max=0.63, sum=6.095 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.798,
          "description": "min=0.791, mean=0.798, max=0.809, sum=2.394 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7092117887564008,
          "description": "min=0.707, mean=0.709, max=0.712, sum=2.128 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22903269434220863,
          "description": "min=0.227, mean=0.229, max=0.233, sum=0.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7174919222528219,
          "description": "min=0.714, mean=0.717, max=0.724, sum=2.152 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3750505324067839,
          "description": "min=0.371, mean=0.375, max=0.379, sum=1.125 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.752,
          "description": "min=0.752, mean=0.752, max=0.752, sum=0.752 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.55,
          "description": "min=0.55, mean=0.55, max=0.55, sum=0.55 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20336391437308868,
          "description": "min=0.197, mean=0.203, max=0.213, sum=0.61 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4335433862433858,
          "description": "min=0.423, mean=0.434, max=0.444, sum=1.301 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7094155817648372,
          "description": "min=0.702, mean=0.709, max=0.717, sum=2.128 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1531133640458751,
          "description": "min=0.15, mean=0.153, max=0.158, sum=0.919 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12168793716134936,
          "description": "min=0.122, mean=0.122, max=0.122, sum=0.73 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9606666666666666,
          "description": "min=0.959, mean=0.961, max=0.962, sum=2.882 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5401857171017724,
          "description": "min=0.009, mean=0.54, max=1, sum=29.17 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6340909090909091,
          "description": "min=0.05, mean=0.634, max=0.975, sum=20.925 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8744906806902775,
          "markdown": false
        },
        {
          "value": 0.4523859649122807,
          "description": "min=0.23, mean=0.452, max=0.79, sum=6.786 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8563333333333333,
          "description": "min=0.849, mean=0.856, max=0.86, sum=2.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7516743554902381,
          "description": "min=0.744, mean=0.752, max=0.763, sum=2.255 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.372119520982551,
          "description": "min=0.369, mean=0.372, max=0.374, sum=1.116 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7599222726809981,
          "description": "min=0.755, mean=0.76, max=0.763, sum=2.28 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4320163638545449,
          "description": "min=0.429, mean=0.432, max=0.435, sum=1.296 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.811,
          "description": "min=0.811, mean=0.811, max=0.811, sum=0.811 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.582,
          "description": "min=0.582, mean=0.582, max=0.582, sum=0.582 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26911314984709483,
          "description": "min=0.265, mean=0.269, max=0.275, sum=0.807 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47209722222222167,
          "description": "min=0.467, mean=0.472, max=0.477, sum=1.416 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7622522766616928,
          "description": "min=0.761, mean=0.762, max=0.765, sum=2.287 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.16105469330622088,
          "description": "min=0.156, mean=0.161, max=0.167, sum=0.966 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.1522429514759537,
          "description": "min=0.147, mean=0.152, max=0.156, sum=0.913 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9603333333333333,
          "description": "min=0.955, mean=0.96, max=0.965, sum=2.881 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6014458410180621,
          "description": "min=0.254, mean=0.601, max=0.86, sum=32.478 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666665,
          "description": "min=0.025, mean=0.667, max=0.975, sum=22.0 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.27275385383526374,
          "markdown": false
        },
        {
          "value": 0.2485497076023392,
          "description": "min=0.14, mean=0.249, max=0.3, sum=3.728 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6486666666666667,
          "description": "min=0.646, mean=0.649, max=0.65, sum=1.946 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5446919680699259,
          "description": "min=0.54, mean=0.545, max=0.554, sum=1.634 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15586888782485156,
          "description": "min=0.146, mean=0.156, max=0.164, sum=0.468 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5589065746807944,
          "description": "min=0.548, mean=0.559, max=0.57, sum=1.677 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32958641317723636,
          "description": "min=0.322, mean=0.33, max=0.335, sum=0.989 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.663,
          "description": "min=0.663, mean=0.663, max=0.663, sum=0.663 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.514,
          "description": "min=0.514, mean=0.514, max=0.514, sum=0.514 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19915902140672784,
          "description": "min=0.187, mean=0.199, max=0.213, sum=0.797 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15220198412698396,
          "description": "min=0.127, mean=0.152, max=0.17, sum=0.457 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34502499414653504,
          "description": "min=0.315, mean=0.345, max=0.362, sum=1.035 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.131094325408915,
          "description": "min=0.127, mean=0.131, max=0.135, sum=0.787 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09551241988195992,
          "description": "min=0.093, mean=0.096, max=0.097, sum=0.573 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9386666666666666,
          "description": "min=0.932, mean=0.939, max=0.946, sum=2.816 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5196367037603835,
          "description": "min=0.002, mean=0.52, max=1, sum=28.06 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.618939393939394,
          "description": "min=0.275, mean=0.619, max=0.975, sum=20.425 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.35097193430410895,
          "markdown": false
        },
        {
          "value": 0.2764093567251462,
          "description": "min=0.21, mean=0.276, max=0.351, sum=4.146 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6826666666666666,
          "description": "min=0.659, mean=0.683, max=0.714, sum=2.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5989155523803277,
          "description": "min=0.558, mean=0.599, max=0.623, sum=1.797 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19254965218224493,
          "description": "min=0.189, mean=0.193, max=0.195, sum=0.578 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5960813295706039,
          "description": "min=0.581, mean=0.596, max=0.608, sum=1.788 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32649980387164573,
          "description": "min=0.32, mean=0.326, max=0.335, sum=0.979 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.718,
          "description": "min=0.718, mean=0.718, max=0.718, sum=0.718 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.524,
          "description": "min=0.524, mean=0.524, max=0.524, sum=0.524 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21597859327217125,
          "description": "min=0.205, mean=0.216, max=0.225, sum=0.864 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1836826719576717,
          "description": "min=0.171, mean=0.184, max=0.203, sum=0.551 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39824533946123547,
          "description": "min=0.37, mean=0.398, max=0.436, sum=1.195 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1229527711325032,
          "description": "min=0.108, mean=0.123, max=0.138, sum=0.738 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1016126399650617,
          "description": "min=0.098, mean=0.102, max=0.105, sum=0.61 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.948,
          "description": "min=0.946, mean=0.948, max=0.95, sum=2.844 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5162631490290198,
          "description": "min=0, mean=0.516, max=1, sum=27.878 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5045454545454544,
          "description": "min=0.025, mean=0.505, max=0.975, sum=16.65 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1955944055944056,
          "markdown": false
        },
        {
          "value": 0.236140350877193,
          "description": "min=0.16, mean=0.236, max=0.281, sum=1.181 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.631,
          "description": "min=0.631, mean=0.631, max=0.631, sum=0.631 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5283875705600286,
          "description": "min=0.528, mean=0.528, max=0.528, sum=0.528 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1423693053393691,
          "description": "min=0.142, mean=0.142, max=0.142, sum=0.142 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5389134144419736,
          "description": "min=0.539, mean=0.539, max=0.539, sum=0.539 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29627572534795094,
          "description": "min=0.296, mean=0.296, max=0.296, sum=0.296 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21253822629969418,
          "description": "min=0.213, mean=0.213, max=0.213, sum=0.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.928,
          "description": "min=0.928, mean=0.928, max=0.928, sum=0.928 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5114925990252345,
          "description": "min=0.02, mean=0.511, max=0.988, sum=9.207 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5022727272727273,
          "description": "min=0.175, mean=0.502, max=0.975, sum=5.525 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2567832167832168,
          "markdown": false
        },
        {
          "value": 0.2736491228070176,
          "description": "min=0.2, mean=0.274, max=0.3, sum=1.368 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.662,
          "description": "min=0.662, mean=0.662, max=0.662, sum=0.662 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.596267382288008,
          "description": "min=0.596, mean=0.596, max=0.596, sum=0.596 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1748199047375899,
          "description": "min=0.175, mean=0.175, max=0.175, sum=0.175 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5808228645869867,
          "description": "min=0.581, mean=0.581, max=0.581, sum=0.581 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31301963957108403,
          "description": "min=0.313, mean=0.313, max=0.313, sum=0.313 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17737003058103976,
          "description": "min=0.177, mean=0.177, max=0.177, sum=0.177 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.931,
          "description": "min=0.931, mean=0.931, max=0.931, sum=0.931 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5311784878341985,
          "description": "min=0.03, mean=0.531, max=0.988, sum=9.561 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5136363636363638,
          "description": "min=0.175, mean=0.514, max=0.975, sum=5.65 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.13136169386169386,
          "markdown": false
        },
        {
          "value": 0.290280701754386,
          "description": "min=0.211, mean=0.29, max=0.4, sum=4.354 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7610000000000001,
          "description": "min=0.732, mean=0.761, max=0.803, sum=2.283 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08557843872358002,
          "description": "min=0.086, mean=0.086, max=0.086, sum=0.257 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1937878037306998,
          "description": "min=0.19, mean=0.194, max=0.196, sum=0.581 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47732108444385024,
          "description": "min=0.278, mean=0.477, max=0.588, sum=1.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11593672613200567,
          "description": "min=0.116, mean=0.116, max=0.116, sum=0.348 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.13302752293577982,
          "description": "min=0.104, mean=0.133, max=0.15, sum=0.532 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.04281294372676351,
          "description": "min=0.043, mean=0.043, max=0.043, sum=0.257 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.014554209854519893,
          "description": "min=0.008, mean=0.015, max=0.018, sum=0.087 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.379,
          "description": "min=0.248, mean=0.379, max=0.568, sum=1.137 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.508559974744749,
          "description": "min=0, mean=0.509, max=0.998, sum=27.462 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3696969696969697,
          "description": "min=0, mean=0.37, max=0.925, sum=12.2 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.16721542346542348,
          "markdown": false
        },
        {
          "value": 0.2912046783625731,
          "description": "min=0.2, mean=0.291, max=0.39, sum=4.368 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7456666666666667,
          "description": "min=0.717, mean=0.746, max=0.762, sum=2.237 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08275131240180192,
          "description": "min=0.083, mean=0.083, max=0.083, sum=0.248 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20415858389554079,
          "description": "min=0.2, mean=0.204, max=0.21, sum=0.612 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34921603097227966,
          "description": "min=0.195, mean=0.349, max=0.432, sum=1.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14442668001629816,
          "description": "min=0.144, mean=0.144, max=0.144, sum=0.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1930428134556575,
          "description": "min=0.162, mean=0.193, max=0.232, sum=0.772 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.03035211632851485,
          "description": "min=0.03, mean=0.03, max=0.03, sum=0.182 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05756648627728908,
          "description": "min=0.049, mean=0.058, max=0.066, sum=0.345 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33666666666666667,
          "description": "min=0.13, mean=0.337, max=0.556, sum=1.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5212239591952971,
          "description": "min=0, mean=0.521, max=1, sum=28.146 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4037878787878788,
          "description": "min=0, mean=0.404, max=0.95, sum=13.325 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6094557642718794,
          "markdown": false
        },
        {
          "value": 0.31836257309941524,
          "description": "min=0.21, mean=0.318, max=0.48, sum=4.775 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.793,
          "description": "min=0.777, mean=0.793, max=0.813, sum=2.379 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6709892371426799,
          "description": "min=0.657, mean=0.671, max=0.692, sum=2.013 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29657703951335807,
          "description": "min=0.294, mean=0.297, max=0.301, sum=0.89 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6148767153993112,
          "description": "min=0.607, mean=0.615, max=0.619, sum=1.845 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3600846532918798,
          "description": "min=0.347, mean=0.36, max=0.369, sum=1.08 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.791,
          "description": "min=0.791, mean=0.791, max=0.791, sum=0.791 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.586,
          "description": "min=0.586, mean=0.586, max=0.586, sum=0.586 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2503822629969419,
          "description": "min=0.228, mean=0.25, max=0.269, sum=1.002 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2878354497354492,
          "description": "min=0.257, mean=0.288, max=0.316, sum=0.864 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4480793689593227,
          "description": "min=0.425, mean=0.448, max=0.467, sum=1.344 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14586366164046674,
          "description": "min=0.132, mean=0.146, max=0.156, sum=0.875 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1548653970323593,
          "description": "min=0.153, mean=0.155, max=0.158, sum=0.929 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9473333333333334,
          "description": "min=0.932, mean=0.947, max=0.96, sum=2.842 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5046425022583836,
          "description": "min=0, mean=0.505, max=1, sum=27.251 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6060606060606061,
          "description": "min=0.075, mean=0.606, max=0.975, sum=20 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.44801020899289806,
          "markdown": false
        },
        {
          "value": 0.2760350877192982,
          "description": "min=0.2, mean=0.276, max=0.37, sum=4.141 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7603333333333332,
          "description": "min=0.753, mean=0.76, max=0.764, sum=2.281 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.637551822715129,
          "description": "min=0.618, mean=0.638, max=0.655, sum=1.913 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2579327702222522,
          "description": "min=0.254, mean=0.258, max=0.262, sum=0.774 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5959786340023702,
          "description": "min=0.582, mean=0.596, max=0.615, sum=1.788 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35657623955671697,
          "description": "min=0.35, mean=0.357, max=0.366, sum=1.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.745,
          "description": "min=0.745, mean=0.745, max=0.745, sum=0.745 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.534,
          "description": "min=0.534, mean=0.534, max=0.534, sum=0.534 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2010703363914373,
          "description": "min=0.185, mean=0.201, max=0.22, sum=0.804 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23709537037037,
          "description": "min=0.231, mean=0.237, max=0.243, sum=0.711 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4820255726730058,
          "description": "min=0.467, mean=0.482, max=0.511, sum=1.446 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13597018102878652,
          "description": "min=0.119, mean=0.136, max=0.149, sum=0.816 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12620143781407123,
          "description": "min=0.123, mean=0.126, max=0.131, sum=0.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9173333333333334,
          "description": "min=0.906, mean=0.917, max=0.926, sum=2.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5055866744567273,
          "description": "min=0, mean=0.506, max=1, sum=27.302 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5568181818181818,
          "description": "min=0.175, mean=0.557, max=0.975, sum=18.375 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5326806526806527,
          "markdown": false
        },
        {
          "value": 0.3206315789473684,
          "description": "min=0.23, mean=0.321, max=0.45, sum=1.603 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.756,
          "description": "min=0.756, mean=0.756, max=0.756, sum=0.756 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6690944911304447,
          "description": "min=0.669, mean=0.669, max=0.669, sum=0.669 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29745644726385995,
          "description": "min=0.297, mean=0.297, max=0.297, sum=0.297 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5886348232463635,
          "description": "min=0.589, mean=0.589, max=0.589, sum=0.589 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33763770634554185,
          "description": "min=0.338, mean=0.338, max=0.338, sum=0.338 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2798165137614679,
          "description": "min=0.28, mean=0.28, max=0.28, sum=0.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.947,
          "description": "min=0.947, mean=0.947, max=0.947, sum=0.947 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5627943545773191,
          "description": "min=0.015, mean=0.563, max=0.99, sum=10.13 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5727272727272728,
          "description": "min=0.125, mean=0.573, max=0.975, sum=6.3 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5946853146853147,
          "markdown": false
        },
        {
          "value": 0.422140350877193,
          "description": "min=0.2, mean=0.422, max=0.76, sum=2.111 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.714,
          "description": "min=0.714, mean=0.714, max=0.714, sum=0.714 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7111626297039972,
          "description": "min=0.711, mean=0.711, max=0.711, sum=0.711 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34584547097727125,
          "description": "min=0.346, mean=0.346, max=0.346, sum=0.346 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6143420698403745,
          "description": "min=0.614, mean=0.614, max=0.614, sum=0.614 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3474516304630864,
          "description": "min=0.347, mean=0.347, max=0.347, sum=0.347 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3241590214067278,
          "description": "min=0.324, mean=0.324, max=0.324, sum=0.324 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.928,
          "description": "min=0.928, mean=0.928, max=0.928, sum=0.928 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5998140813785037,
          "description": "min=0.118, mean=0.6, max=0.947, sum=10.797 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6431818181818181,
          "description": "min=0.125, mean=0.643, max=0.925, sum=7.075 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7812820512820513,
          "markdown": false
        },
        {
          "value": 0.531438596491228,
          "description": "min=0.33, mean=0.531, max=0.83, sum=2.657 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.861,
          "description": "min=0.861, mean=0.861, max=0.861, sum=0.861 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7524749208145961,
          "description": "min=0.752, mean=0.752, max=0.752, sum=0.752 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4083274852237871,
          "description": "min=0.408, mean=0.408, max=0.408, sum=0.408 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6655955471819576,
          "description": "min=0.666, mean=0.666, max=0.666, sum=0.666 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.390156560201708,
          "description": "min=0.39, mean=0.39, max=0.39, sum=0.39 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3440366972477064,
          "description": "min=0.344, mean=0.344, max=0.344, sum=0.344 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.927,
          "description": "min=0.927, mean=0.927, max=0.927, sum=0.927 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5493014806179074,
          "description": "min=0.027, mean=0.549, max=0.998, sum=9.887 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7522727272727271,
          "description": "min=0.15, mean=0.752, max=1, sum=8.275 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9082517482517483,
          "markdown": false
        },
        {
          "value": 0.5837192982456141,
          "description": "min=0.34, mean=0.584, max=0.89, sum=2.919 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.871,
          "description": "min=0.871, mean=0.871, max=0.871, sum=0.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7548659428655667,
          "description": "min=0.755, mean=0.755, max=0.755, sum=0.755 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4314303194563885,
          "description": "min=0.431, mean=0.431, max=0.431, sum=0.431 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6720953416517841,
          "description": "min=0.672, mean=0.672, max=0.672, sum=0.672 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40132178362618626,
          "description": "min=0.401, mean=0.401, max=0.401, sum=0.401 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5076452599388379,
          "description": "min=0.508, mean=0.508, max=0.508, sum=0.508 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.962,
          "description": "min=0.962, mean=0.962, max=0.962, sum=0.962 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6546180489949494,
          "description": "min=0.395, mean=0.655, max=0.863, sum=11.783 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7022727272727273,
          "description": "min=0.125, mean=0.702, max=0.975, sum=7.725 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6073193473193473,
          "markdown": false
        },
        {
          "value": 0.43066666666666664,
          "description": "min=0.28, mean=0.431, max=0.64, sum=2.153 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.762,
          "description": "min=0.762, mean=0.762, max=0.762, sum=0.762 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6912328056597693,
          "description": "min=0.691, mean=0.691, max=0.691, sum=0.691 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3366110398011615,
          "description": "min=0.337, mean=0.337, max=0.337, sum=0.337 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6112848863529475,
          "description": "min=0.611, mean=0.611, max=0.611, sum=0.611 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4062205885783288,
          "description": "min=0.406, mean=0.406, max=0.406, sum=0.406 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27217125382262997,
          "description": "min=0.272, mean=0.272, max=0.272, sum=0.272 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.907,
          "description": "min=0.907, mean=0.907, max=0.907, sum=0.907 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5615523097089101,
          "description": "min=0.025, mean=0.562, max=1, sum=10.108 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6431818181818182,
          "description": "min=0.125, mean=0.643, max=0.95, sum=7.075 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.823006993006993,
          "markdown": false
        },
        {
          "value": 0.5066666666666666,
          "description": "min=0.28, mean=0.507, max=0.84, sum=2.533 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.811,
          "description": "min=0.811, mean=0.811, max=0.811, sum=0.811 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7439992251158487,
          "description": "min=0.744, mean=0.744, max=0.744, sum=0.744 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37588825185909286,
          "description": "min=0.376, mean=0.376, max=0.376, sum=0.376 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6373024911911921,
          "description": "min=0.637, mean=0.637, max=0.637, sum=0.637 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4238387754529942,
          "description": "min=0.424, mean=0.424, max=0.424, sum=0.424 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3302752293577982,
          "description": "min=0.33, mean=0.33, max=0.33, sum=0.33 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.962,
          "description": "min=0.962, mean=0.962, max=0.962, sum=0.962 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5877401407873276,
          "description": "min=0.087, mean=0.588, max=0.968, sum=10.579 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7068181818181818,
          "description": "min=0.1, mean=0.707, max=0.975, sum=7.775 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9435198135198135,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5817192982456141,
          "description": "min=0.29, mean=0.582, max=0.92, sum=2.909 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.886,
          "description": "min=0.886, mean=0.886, max=0.886, sum=0.886 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7699314267415824,
          "description": "min=0.77, mean=0.77, max=0.77, sum=0.77 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.458395947831016,
          "description": "min=0.458, mean=0.458, max=0.458, sum=0.458 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.674174388268844,
          "description": "min=0.674, mean=0.674, max=0.674, sum=0.674 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4843505704844856,
          "description": "min=0.484, mean=0.484, max=0.484, sum=0.484 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5535168195718655,
          "description": "min=0.554, mean=0.554, max=0.554, sum=0.554 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.961,
          "description": "min=0.961, mean=0.961, max=0.961, sum=0.961 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.651853345601779,
          "description": "min=0.337, mean=0.652, max=0.919, sum=11.733 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7272727272727273,
          "description": "min=0.125, mean=0.727, max=0.975, sum=8 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3808857808857809,
          "markdown": false
        },
        {
          "value": 0.38463157894736844,
          "description": "min=0.263, mean=0.385, max=0.6, sum=1.923 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.778,
          "description": "min=0.778, mean=0.778, max=0.778, sum=0.778 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3959807777296956,
          "description": "min=0.396, mean=0.396, max=0.396, sum=0.396 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26569791663552056,
          "description": "min=0.266, mean=0.266, max=0.266, sum=0.266 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.592462252918689,
          "description": "min=0.592, mean=0.592, max=0.592, sum=0.592 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26997517612561206,
          "description": "min=0.27, mean=0.27, max=0.27, sum=0.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.24311926605504589,
          "description": "min=0.243, mean=0.243, max=0.243, sum=0.243 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.738,
          "description": "min=0.738, mean=0.738, max=0.738, sum=0.738 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5657741546600875,
          "description": "min=0.158, mean=0.566, max=0.939, sum=10.184 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48636363636363633,
          "description": "min=0, mean=0.486, max=0.9, sum=5.35 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6252680652680652,
          "markdown": false
        },
        {
          "value": 0.43361403508771934,
          "description": "min=0.228, mean=0.434, max=0.7, sum=2.168 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.76,
          "description": "min=0.76, mean=0.76, max=0.76, sum=0.76 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6431800151411557,
          "description": "min=0.643, mean=0.643, max=0.643, sum=0.643 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28671400990537294,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6339236797183677,
          "description": "min=0.634, mean=0.634, max=0.634, sum=0.634 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3922306090321485,
          "description": "min=0.392, mean=0.392, max=0.392, sum=0.392 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.29204892966360857,
          "description": "min=0.292, mean=0.292, max=0.292, sum=0.292 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.916,
          "description": "min=0.916, mean=0.916, max=0.916, sum=0.916 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6203561688884051,
          "description": "min=0.154, mean=0.62, max=0.98, sum=11.166 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6931818181818181,
          "description": "min=0.275, mean=0.693, max=0.975, sum=7.625 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7063170163170163,
          "markdown": false
        },
        {
          "value": 0.4616491228070176,
          "description": "min=0.298, mean=0.462, max=0.72, sum=2.308 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.808,
          "description": "min=0.808, mean=0.808, max=0.808, sum=0.808 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6906914174160148,
          "description": "min=0.691, mean=0.691, max=0.691, sum=0.691 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3458332386611444,
          "description": "min=0.346, mean=0.346, max=0.346, sum=0.346 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6864980252374564,
          "description": "min=0.686, mean=0.686, max=0.686, sum=0.686 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4027140466606994,
          "description": "min=0.403, mean=0.403, max=0.403, sum=0.403 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3853211009174312,
          "description": "min=0.385, mean=0.385, max=0.385, sum=0.385 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.762,
          "description": "min=0.762, mean=0.762, max=0.762, sum=0.762 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6445516645582552,
          "description": "min=0.247, mean=0.645, max=0.946, sum=11.602 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6568181818181819,
          "description": "min=0.175, mean=0.657, max=0.9, sum=7.225 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8840326340326341,
          "markdown": false
        },
        {
          "value": 0.5722456140350877,
          "description": "min=0.28, mean=0.572, max=0.84, sum=2.861 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.874,
          "description": "min=0.874, mean=0.874, max=0.874, sum=0.874 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7164585897241792,
          "description": "min=0.716, mean=0.716, max=0.716, sum=0.716 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36478844260172427,
          "description": "min=0.365, mean=0.365, max=0.365, sum=0.365 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6865605057711931,
          "description": "min=0.687, mean=0.687, max=0.687, sum=0.687 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42323632648753373,
          "description": "min=0.423, mean=0.423, max=0.423, sum=0.423 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.42201834862385323,
          "description": "min=0.422, mean=0.422, max=0.422, sum=0.422 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.962,
          "description": "min=0.962, mean=0.962, max=0.962, sum=0.962 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6244310554225627,
          "description": "min=0.219, mean=0.624, max=0.874, sum=11.24 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7068181818181818,
          "description": "min=0.1, mean=0.707, max=0.975, sum=7.775 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7865257969227658,
          "markdown": false
        },
        {
          "value": 0.46898245614035083,
          "description": "min=0.24, mean=0.469, max=0.78, sum=7.035 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8093333333333333,
          "description": "min=0.798, mean=0.809, max=0.829, sum=2.428 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7219452089083314,
          "description": "min=0.692, mean=0.722, max=0.743, sum=2.166 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38385680917548265,
          "description": "min=0.375, mean=0.384, max=0.389, sum=1.152 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.642142619854249,
          "description": "min=0.617, mean=0.642, max=0.656, sum=1.926 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39034737650499157,
          "description": "min=0.388, mean=0.39, max=0.393, sum=1.171 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.799,
          "description": "min=0.799, mean=0.799, max=0.799, sum=0.799 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.562,
          "description": "min=0.562, mean=0.562, max=0.562, sum=0.562 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2507645259938838,
          "description": "min=0.22, mean=0.251, max=0.275, sum=0.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37719854497354444,
          "description": "min=0.368, mean=0.377, max=0.394, sum=1.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6431699764013751,
          "description": "min=0.621, mean=0.643, max=0.662, sum=1.93 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16092678908070457,
          "description": "min=0.151, mean=0.161, max=0.166, sum=0.966 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1688228543371916,
          "description": "min=0.162, mean=0.169, max=0.172, sum=1.013 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9406666666666667,
          "description": "min=0.939, mean=0.941, max=0.942, sum=2.822 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6013271328698659,
          "description": "min=0.171, mean=0.601, max=0.983, sum=32.472 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6787878787878788,
          "description": "min=0.025, mean=0.679, max=0.975, sum=22.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3092148246173552,
          "markdown": false
        },
        {
          "value": 0.24178947368421053,
          "description": "min=0.2, mean=0.242, max=0.35, sum=3.627 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6983333333333334,
          "description": "min=0.685, mean=0.698, max=0.709, sum=2.095 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6309132248806418,
          "description": "min=0.612, mean=0.631, max=0.644, sum=1.893 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21042251985011806,
          "description": "min=0.202, mean=0.21, max=0.225, sum=0.631 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5610321289166954,
          "description": "min=0.532, mean=0.561, max=0.585, sum=1.683 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3448201896547902,
          "description": "min=0.334, mean=0.345, max=0.365, sum=1.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.704,
          "description": "min=0.704, mean=0.704, max=0.704, sum=0.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.478,
          "description": "min=0.478, mean=0.478, max=0.478, sum=0.478 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.156, mean=0.167, max=0.173, sum=0.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.158334656084656,
          "description": "min=0.124, mean=0.158, max=0.185, sum=0.475 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3324723538542003,
          "description": "min=0.273, mean=0.332, max=0.382, sum=0.997 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1462274163608441,
          "description": "min=0.139, mean=0.146, max=0.157, sum=0.877 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1101479270159234,
          "description": "min=0.107, mean=0.11, max=0.113, sum=0.661 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9273333333333333,
          "description": "min=0.923, mean=0.927, max=0.934, sum=2.782 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5315000485883316,
          "description": "min=0.053, mean=0.532, max=0.955, sum=28.701 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.525,
          "description": "min=0.025, mean=0.525, max=0.975, sum=17.325 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5377003529238652,
          "markdown": false
        },
        {
          "value": 0.4224093567251462,
          "description": "min=0.26, mean=0.422, max=0.7, sum=6.336 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7223333333333333,
          "description": "min=0.679, mean=0.722, max=0.77, sum=2.167 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6868798106625772,
          "description": "min=0.664, mean=0.687, max=0.706, sum=2.061 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3285762190205979,
          "description": "min=0.321, mean=0.329, max=0.338, sum=0.986 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6245969015358845,
          "description": "min=0.599, mean=0.625, max=0.65, sum=1.874 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.36039253109386227,
          "description": "min=0.354, mean=0.36, max=0.367, sum=1.081 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.775,
          "description": "min=0.775, mean=0.775, max=0.775, sum=0.775 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.586,
          "description": "min=0.586, mean=0.586, max=0.586, sum=0.586 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.19367991845056065,
          "description": "min=0.182, mean=0.194, max=0.213, sum=0.581 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21072870370370347,
          "description": "min=0.205, mean=0.211, max=0.221, sum=0.632 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3781975078250463,
          "description": "min=0.343, mean=0.378, max=0.397, sum=1.135 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12705516417412407,
          "description": "min=0.087, mean=0.127, max=0.14, sum=0.889 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12634226115121253,
          "description": "min=0.045, mean=0.126, max=0.144, sum=0.884 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9333333333333332,
          "description": "min=0.925, mean=0.933, max=0.942, sum=2.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5319088175117064,
          "description": "min=0.006, mean=0.532, max=1, sum=28.723 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6424242424242425,
          "description": "min=0.1, mean=0.642, max=0.975, sum=21.2 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2473793361116081,
          "markdown": false
        },
        {
          "value": 0.24280701754385967,
          "description": "min=0.19, mean=0.243, max=0.29, sum=3.642 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6563333333333333,
          "description": "min=0.597, mean=0.656, max=0.704, sum=1.969 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6044087313123448,
          "description": "min=0.588, mean=0.604, max=0.632, sum=1.813 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19881514626363717,
          "description": "min=0.194, mean=0.199, max=0.203, sum=0.596 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5515039669865899,
          "description": "min=0.521, mean=0.552, max=0.568, sum=1.655 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3211056138652355,
          "description": "min=0.312, mean=0.321, max=0.335, sum=0.963 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.682,
          "description": "min=0.682, mean=0.682, max=0.682, sum=0.682 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.502,
          "description": "min=0.502, mean=0.502, max=0.502, sum=0.502 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23190621814475024,
          "description": "min=0.222, mean=0.232, max=0.251, sum=0.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16186494708994695,
          "description": "min=0.14, mean=0.162, max=0.189, sum=0.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29959792504491484,
          "description": "min=0.279, mean=0.3, max=0.31, sum=0.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11266846087672235,
          "description": "min=0.038, mean=0.113, max=0.141, sum=0.789 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09082699642721448,
          "description": "min=0.035, mean=0.091, max=0.104, sum=0.636 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8893333333333334,
          "description": "min=0.831, mean=0.889, max=0.939, sum=2.668 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5385829045066699,
          "description": "min=0.012, mean=0.539, max=1, sum=29.083 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49015151515151517,
          "description": "min=0, mean=0.49, max=0.975, sum=16.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1140042776096725,
          "markdown": false
        },
        {
          "value": 0.23451461988304095,
          "description": "min=0.17, mean=0.235, max=0.35, sum=3.518 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5743333333333334,
          "description": "min=0.52, mean=0.574, max=0.623, sum=1.723 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4913412520282267,
          "description": "min=0.468, mean=0.491, max=0.525, sum=1.474 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11901597572121592,
          "description": "min=0.115, mean=0.119, max=0.123, sum=0.357 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.45128402165249315,
          "description": "min=0.435, mean=0.451, max=0.47, sum=1.354 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2726420179052807,
          "description": "min=0.263, mean=0.273, max=0.282, sum=0.818 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.555,
          "description": "min=0.555, mean=0.555, max=0.555, sum=0.555 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.438,
          "description": "min=0.438, mean=0.438, max=0.438, sum=0.438 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1875637104994903,
          "description": "min=0.174, mean=0.188, max=0.196, sum=0.563 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12228915343915343,
          "description": "min=0.093, mean=0.122, max=0.145, sum=0.367 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3165150970076857,
          "description": "min=0.291, mean=0.317, max=0.362, sum=0.95 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07872053043189091,
          "description": "min=0.016, mean=0.079, max=0.147, sum=0.472 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.045488352989199364,
          "description": "min=0.041, mean=0.045, max=0.054, sum=0.273 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5973333333333333,
          "description": "min=0.5, mean=0.597, max=0.646, sum=1.792 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5189735240834931,
          "description": "min=0.005, mean=0.519, max=0.996, sum=28.025 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45530303030303027,
          "description": "min=0.025, mean=0.455, max=0.975, sum=15.025 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10832839875178585,
          "markdown": false
        },
        {
          "value": 0.24276023391812865,
          "description": "min=0.132, mean=0.243, max=0.32, sum=3.641 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5810000000000001,
          "description": "min=0.525, mean=0.581, max=0.627, sum=1.743 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.32610438211460974,
          "description": "min=0.311, mean=0.326, max=0.35, sum=0.978 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08247067130127021,
          "description": "min=0.081, mean=0.082, max=0.083, sum=0.247 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3651114721289241,
          "description": "min=0.35, mean=0.365, max=0.379, sum=1.095 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2415563587627719,
          "description": "min=0.226, mean=0.242, max=0.267, sum=0.725 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.435,
          "description": "min=0.435, mean=0.435, max=0.435, sum=0.435 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.38,
          "description": "min=0.38, mean=0.38, max=0.38, sum=0.38 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21508664627930682,
          "description": "min=0.206, mean=0.215, max=0.222, sum=0.645 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10209867724867722,
          "description": "min=0.063, mean=0.102, max=0.156, sum=0.306 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2902649241990923,
          "description": "min=0.184, mean=0.29, max=0.427, sum=0.871 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09024169266442018,
          "description": "min=0.046, mean=0.09, max=0.116, sum=0.541 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.022368869296828752,
          "description": "min=0.012, mean=0.022, max=0.034, sum=0.134 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8489999999999999,
          "description": "min=0.834, mean=0.849, max=0.861, sum=2.547 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5166605735360243,
          "description": "min=0, mean=0.517, max=1, sum=27.9 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42348484848484846,
          "description": "min=0, mean=0.423, max=0.975, sum=13.975 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8715995749939716,
          "markdown": false
        },
        {
          "value": 0.568830409356725,
          "description": "min=0.28, mean=0.569, max=0.86, sum=8.532 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.879, mean=0.881, max=0.883, sum=2.644 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7270632910132128,
          "description": "min=0.703, mean=0.727, max=0.747, sum=2.181 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4063842801483763,
          "description": "min=0.397, mean=0.406, max=0.413, sum=1.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7702290061206396,
          "description": "min=0.768, mean=0.77, max=0.773, sum=2.311 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5247817678036986,
          "description": "min=0.496, mean=0.525, max=0.54, sum=1.574 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.822,
          "description": "min=0.822, mean=0.822, max=0.822, sum=0.822 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.646,
          "description": "min=0.646, mean=0.646, max=0.646, sum=0.646 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5932721712538226,
          "description": "min=0.558, mean=0.593, max=0.615, sum=1.78 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36773716931216915,
          "description": "min=0.353, mean=0.368, max=0.389, sum=1.103 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6437915218204088,
          "description": "min=0.611, mean=0.644, max=0.662, sum=1.931 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.155913292357307,
          "description": "min=0.151, mean=0.156, max=0.16, sum=0.935 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12395799815526115,
          "description": "min=0.122, mean=0.124, max=0.126, sum=0.744 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8483333333333333,
          "description": "min=0.828, mean=0.848, max=0.881, sum=2.545 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6844225905300101,
          "description": "min=0.52, mean=0.684, max=0.863, sum=36.959 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7590909090909093,
          "description": "min=0.075, mean=0.759, max=0.95, sum=25.05 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9050278807908814,
          "markdown": false
        },
        {
          "value": 0.5676491228070175,
          "description": "min=0.26, mean=0.568, max=0.86, sum=8.515 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8769999999999999,
          "description": "min=0.872, mean=0.877, max=0.883, sum=2.631 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7271738722981128,
          "description": "min=0.711, mean=0.727, max=0.752, sum=2.182 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3830923328890669,
          "description": "min=0.367, mean=0.383, max=0.394, sum=1.149 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7131585271286972,
          "description": "min=0.71, mean=0.713, max=0.716, sum=2.139 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.44514668415537656,
          "description": "min=0.435, mean=0.445, max=0.451, sum=1.335 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.815,
          "description": "min=0.815, mean=0.815, max=0.815, sum=0.815 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.594,
          "description": "min=0.594, mean=0.594, max=0.594, sum=0.594 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6095820591233435,
          "description": "min=0.596, mean=0.61, max=0.63, sum=1.829 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42053584656084597,
          "description": "min=0.407, mean=0.421, max=0.437, sum=1.262 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6636685030000556,
          "description": "min=0.642, mean=0.664, max=0.685, sum=1.991 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15336788305541946,
          "description": "min=0.148, mean=0.153, max=0.156, sum=1.074 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14371193275718439,
          "description": "min=0.087, mean=0.144, max=0.161, sum=1.006 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9476666666666667,
          "description": "min=0.945, mean=0.948, max=0.953, sum=2.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6683929228495211,
          "description": "min=0.4, mean=0.668, max=0.876, sum=36.093 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7325757575757575,
          "description": "min=0.15, mean=0.733, max=0.975, sum=24.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3597458066590436,
          "markdown": false
        },
        {
          "value": 0.23721637426900585,
          "description": "min=0.21, mean=0.237, max=0.298, sum=3.558 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6203333333333334,
          "description": "min=0.591, mean=0.62, max=0.638, sum=1.861 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5819233043307469,
          "description": "min=0.55, mean=0.582, max=0.63, sum=1.746 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1751433877883095,
          "description": "min=0.167, mean=0.175, max=0.179, sum=0.525 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5713593297545252,
          "description": "min=0.536, mean=0.571, max=0.599, sum=1.714 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3579111587300226,
          "description": "min=0.341, mean=0.358, max=0.383, sum=1.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.676,
          "description": "min=0.676, mean=0.676, max=0.676, sum=0.676 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.514,
          "description": "min=0.514, mean=0.514, max=0.514, sum=0.514 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25739041794087664,
          "description": "min=0.231, mean=0.257, max=0.301, sum=0.772 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2712138888888885,
          "description": "min=0.256, mean=0.271, max=0.287, sum=0.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5072420607794633,
          "description": "min=0.476, mean=0.507, max=0.545, sum=1.522 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15158358384113974,
          "description": "min=0.144, mean=0.152, max=0.159, sum=1.061 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07609664536826453,
          "description": "min=0.056, mean=0.076, max=0.081, sum=0.533 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9226666666666667,
          "description": "min=0.915, mean=0.923, max=0.927, sum=2.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5372764016545788,
          "description": "min=0.04, mean=0.537, max=0.93, sum=29.013 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48939393939393944,
          "description": "min=0, mean=0.489, max=0.85, sum=16.15 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.22864975506973562,
          "markdown": false
        },
        {
          "value": 0.22873684210526318,
          "description": "min=0.11, mean=0.229, max=0.325, sum=3.431 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.451,
          "description": "min=0.414, mean=0.451, max=0.477, sum=1.353 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.42935871198092457,
          "description": "min=0.412, mean=0.429, max=0.463, sum=1.288 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0698091759277551,
          "description": "min=0.066, mean=0.07, max=0.073, sum=0.209 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.32956771250253863,
          "description": "min=0.296, mean=0.33, max=0.355, sum=0.989 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.28404493978619966,
          "description": "min=0.279, mean=0.284, max=0.288, sum=0.852 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.561,
          "description": "min=0.561, mean=0.561, max=0.561, sum=0.561 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.452,
          "description": "min=0.452, mean=0.452, max=0.452, sum=0.452 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2329255861365953,
          "description": "min=0.2, mean=0.233, max=0.274, sum=0.699 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20756798941798923,
          "description": "min=0.185, mean=0.208, max=0.25, sum=0.623 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4491612384841603,
          "description": "min=0.42, mean=0.449, max=0.493, sum=1.347 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15113064899436832,
          "description": "min=0.147, mean=0.151, max=0.155, sum=0.907 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.045770027269419145,
          "description": "min=0.044, mean=0.046, max=0.047, sum=0.275 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9126666666666666,
          "description": "min=0.902, mean=0.913, max=0.921, sum=2.738 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4990845178180247,
          "description": "min=0, mean=0.499, max=1, sum=26.951 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5090909090909091,
          "description": "min=0.125, mean=0.509, max=0.925, sum=16.8 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10733700566674705,
          "markdown": false
        },
        {
          "value": 0.23770760233918128,
          "description": "min=0.14, mean=0.238, max=0.31, sum=3.566 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46399999999999997,
          "description": "min=0.405, mean=0.464, max=0.503, sum=1.392 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23810811048034744,
          "description": "min=0.22, mean=0.238, max=0.273, sum=0.714 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.024961683090918712,
          "description": "min=0.02, mean=0.025, max=0.033, sum=0.075 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1488303775311016,
          "description": "min=0.06, mean=0.149, max=0.193, sum=0.446 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1756100119695796,
          "description": "min=0.14, mean=0.176, max=0.203, sum=0.527 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.429,
          "description": "min=0.429, mean=0.429, max=0.429, sum=0.429 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.346,
          "description": "min=0.346, mean=0.346, max=0.346, sum=0.346 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2319062181447503,
          "description": "min=0.216, mean=0.232, max=0.263, sum=0.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13440859788359785,
          "description": "min=0.096, mean=0.134, max=0.158, sum=0.403 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3015757422504311,
          "description": "min=0.21, mean=0.302, max=0.353, sum=0.905 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13557948114099697,
          "description": "min=0.134, mean=0.136, max=0.137, sum=0.813 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03440737413897677,
          "description": "min=0.034, mean=0.034, max=0.036, sum=0.206 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8220000000000001,
          "description": "min=0.776, mean=0.822, max=0.853, sum=2.466 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5033288956325118,
          "description": "min=0, mean=0.503, max=1, sum=27.18 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40606060606060607,
          "description": "min=0.05, mean=0.406, max=0.975, sum=13.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7602564102564102,
          "markdown": false
        },
        {
          "value": 0.5897543859649124,
          "description": "min=0.3, mean=0.59, max=0.85, sum=2.949 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.74,
          "description": "min=0.74, mean=0.74, max=0.74, sum=0.74 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6630439822107776,
          "description": "min=0.663, mean=0.663, max=0.663, sum=0.663 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3900994573752802,
          "description": "min=0.39, mean=0.39, max=0.39, sum=0.39 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6243318756027569,
          "description": "min=0.624, mean=0.624, max=0.624, sum=0.624 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5119523356427028,
          "description": "min=0.512, mean=0.512, max=0.512, sum=0.512 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6085626911314985,
          "description": "min=0.609, mean=0.609, max=0.609, sum=0.609 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.899,
          "description": "min=0.899, mean=0.899, max=0.899, sum=0.899 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6741025816848591,
          "description": "min=0.528, mean=0.674, max=0.824, sum=12.134 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7681818181818181,
          "description": "min=0.3, mean=0.768, max=0.975, sum=8.45 (11)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.782960372960373,
          "markdown": false
        },
        {
          "value": 0.3909122807017544,
          "description": "min=0.2, mean=0.391, max=0.73, sum=1.955 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.87,
          "description": "min=0.87, mean=0.87, max=0.87, sum=0.87 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.625078363047123,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34763874576261045,
          "description": "min=0.348, mean=0.348, max=0.348, sum=0.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6747780561838135,
          "description": "min=0.675, mean=0.675, max=0.675, sum=0.675 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4849593724666123,
          "description": "min=0.485, mean=0.485, max=0.485, sum=0.485 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3394495412844037,
          "description": "min=0.339, mean=0.339, max=0.339, sum=0.339 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.943,
          "description": "min=0.943, mean=0.943, max=0.943, sum=0.943 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6963552742267919,
          "description": "min=0.48, mean=0.696, max=0.874, sum=12.534 (18)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7477272727272727,
          "description": "min=0.275, mean=0.748, max=0.95, sum=8.225 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.31081585081585084,
          "markdown": false
        },
        {
          "value": 0.26287719298245615,
          "description": "min=0.24, mean=0.263, max=0.3, sum=1.314 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.685,
          "description": "min=0.685, mean=0.685, max=0.685, sum=0.685 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5551120381419948,
          "description": "min=0.555, mean=0.555, max=0.555, sum=0.555 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20673467958073993,
          "description": "min=0.207, mean=0.207, max=0.207, sum=0.207 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5199511399231157,
          "description": "min=0.52, mean=0.52, max=0.52, sum=0.52 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30891004509326025,
          "description": "min=0.309, mean=0.309, max=0.309, sum=0.309 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27675840978593275,
          "description": "min=0.277, mean=0.277, max=0.277, sum=0.277 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.907,
          "description": "min=0.907, mean=0.907, max=0.907, sum=0.907 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5487407984760391,
          "description": "min=0.013, mean=0.549, max=0.996, sum=9.877 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5022727272727273,
          "description": "min=0.225, mean=0.502, max=0.975, sum=5.525 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3660839160839161,
          "markdown": false
        },
        {
          "value": 0.2573684210526316,
          "description": "min=0.22, mean=0.257, max=0.29, sum=1.287 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.677,
          "description": "min=0.677, mean=0.677, max=0.677, sum=0.677 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6375767780843438,
          "description": "min=0.638, mean=0.638, max=0.638, sum=0.638 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20314101934470832,
          "description": "min=0.203, mean=0.203, max=0.203, sum=0.203 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6371355382438308,
          "description": "min=0.637, mean=0.637, max=0.637, sum=0.637 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25898520339697034,
          "description": "min=0.259, mean=0.259, max=0.259, sum=0.259 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.20795107033639143,
          "description": "min=0.208, mean=0.208, max=0.208, sum=0.208 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.894,
          "description": "min=0.894, mean=0.894, max=0.894, sum=0.894 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5494742914173579,
          "description": "min=0.028, mean=0.549, max=0.997, sum=9.891 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6613636363636363,
          "description": "min=0.2, mean=0.661, max=0.975, sum=7.275 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3780652680652681,
          "markdown": false
        },
        {
          "value": 0.30161403508771933,
          "description": "min=0.228, mean=0.302, max=0.38, sum=1.508 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.713,
          "description": "min=0.713, mean=0.713, max=0.713, sum=0.713 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6173357069497865,
          "description": "min=0.617, mean=0.617, max=0.617, sum=0.617 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25027831218099883,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5862983431396707,
          "description": "min=0.586, mean=0.586, max=0.586, sum=0.586 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.336496127393405,
          "description": "min=0.336, mean=0.336, max=0.336, sum=0.336 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.20489296636085627,
          "description": "min=0.205, mean=0.205, max=0.205, sum=0.205 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.752,
          "description": "min=0.752, mean=0.752, max=0.752, sum=0.752 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5465441142294091,
          "description": "min=0.064, mean=0.547, max=0.954, sum=9.838 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6477272727272727,
          "description": "min=0.3, mean=0.648, max=0.925, sum=7.125 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5242424242424243,
          "markdown": false
        },
        {
          "value": 0.3631228070175439,
          "description": "min=0.246, mean=0.363, max=0.52, sum=1.816 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.705,
          "description": "min=0.705, mean=0.705, max=0.705, sum=0.705 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6376816720476394,
          "description": "min=0.638, mean=0.638, max=0.638, sum=0.638 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23236488690139467,
          "description": "min=0.232, mean=0.232, max=0.232, sum=0.232 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6591840694814133,
          "description": "min=0.659, mean=0.659, max=0.659, sum=0.659 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25964870962223413,
          "description": "min=0.26, mean=0.26, max=0.26, sum=0.26 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.24311926605504589,
          "description": "min=0.243, mean=0.243, max=0.243, sum=0.243 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.927,
          "description": "min=0.927, mean=0.927, max=0.927, sum=0.927 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6644837448405944,
          "description": "min=0.487, mean=0.664, max=0.77, sum=11.961 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6954545454545454,
          "description": "min=0.175, mean=0.695, max=0.925, sum=7.65 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7144988344988346,
          "markdown": false
        },
        {
          "value": 0.43666666666666665,
          "description": "min=0.25, mean=0.437, max=0.68, sum=2.183 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.704,
          "description": "min=0.704, mean=0.704, max=0.704, sum=0.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7315258420006264,
          "description": "min=0.732, mean=0.732, max=0.732, sum=0.732 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3468734458863885,
          "description": "min=0.347, mean=0.347, max=0.347, sum=0.347 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6729405976420344,
          "description": "min=0.673, mean=0.673, max=0.673, sum=0.673 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3930689917110709,
          "description": "min=0.393, mean=0.393, max=0.393, sum=0.393 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2308868501529052,
          "description": "min=0.231, mean=0.231, max=0.231, sum=0.231 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.959,
          "description": "min=0.959, mean=0.959, max=0.959, sum=0.959 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5990207236768709,
          "description": "min=0.121, mean=0.599, max=0.951, sum=10.782 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7227272727272727,
          "description": "min=0.45, mean=0.723, max=0.975, sum=7.95 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7163869463869464,
          "markdown": false
        },
        {
          "value": 0.44442105263157894,
          "description": "min=0.3, mean=0.444, max=0.64, sum=2.222 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.85,
          "description": "min=0.85, mean=0.85, max=0.85, sum=0.85 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.732860816220429,
          "description": "min=0.733, mean=0.733, max=0.733, sum=0.733 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30444485292857587,
          "description": "min=0.304, mean=0.304, max=0.304, sum=0.304 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6971634986316374,
          "description": "min=0.697, mean=0.697, max=0.697, sum=0.697 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3273435542079152,
          "description": "min=0.327, mean=0.327, max=0.327, sum=0.327 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23394495412844038,
          "description": "min=0.234, mean=0.234, max=0.234, sum=0.234 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.956,
          "description": "min=0.956, mean=0.956, max=0.956, sum=0.956 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5731373267021187,
          "description": "min=0.119, mean=0.573, max=0.967, sum=10.316 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6795454545454546,
          "description": "min=0.425, mean=0.68, max=0.9, sum=7.475 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37834498834498836,
          "markdown": false
        },
        {
          "value": 0.2863859649122807,
          "description": "min=0.17, mean=0.286, max=0.39, sum=1.432 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.753,
          "description": "min=0.753, mean=0.753, max=0.753, sum=0.753 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6209478967260336,
          "description": "min=0.621, mean=0.621, max=0.621, sum=0.621 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2852044605455856,
          "description": "min=0.285, mean=0.285, max=0.285, sum=0.285 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5794767771699627,
          "description": "min=0.579, mean=0.579, max=0.579, sum=0.579 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33169657619480786,
          "description": "min=0.332, mean=0.332, max=0.332, sum=0.332 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23394495412844038,
          "description": "min=0.234, mean=0.234, max=0.234, sum=0.234 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.836,
          "description": "min=0.836, mean=0.836, max=0.836, sum=0.836 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.514285115880326,
          "description": "min=0, mean=0.514, max=0.999, sum=9.257 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6022727272727273,
          "description": "min=0.15, mean=0.602, max=0.975, sum=6.625 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.24405594405594408,
          "markdown": false
        },
        {
          "value": 0.27487719298245616,
          "description": "min=0.21, mean=0.275, max=0.34, sum=1.374 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.72,
          "description": "min=0.72, mean=0.72, max=0.72, sum=0.72 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47631318018835694,
          "description": "min=0.476, mean=0.476, max=0.476, sum=0.476 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19423837841693925,
          "description": "min=0.194, mean=0.194, max=0.194, sum=0.194 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4488741825125809,
          "description": "min=0.449, mean=0.449, max=0.449, sum=0.449 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3112985430771873,
          "description": "min=0.311, mean=0.311, max=0.311, sum=0.311 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21253822629969418,
          "description": "min=0.213, mean=0.213, max=0.213, sum=0.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.852,
          "description": "min=0.852, mean=0.852, max=0.852, sum=0.852 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5110619645302352,
          "description": "min=0, mean=0.511, max=1, sum=9.199 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5227272727272727,
          "description": "min=0.15, mean=0.523, max=0.975, sum=5.75 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7293939393939394,
          "markdown": false
        },
        {
          "value": 0.5089122807017544,
          "description": "min=0.32, mean=0.509, max=0.79, sum=2.545 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.819,
          "description": "min=0.819, mean=0.819, max=0.819, sum=0.819 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.672629994827555,
          "description": "min=0.673, mean=0.673, max=0.673, sum=0.673 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3922286302507637,
          "description": "min=0.392, mean=0.392, max=0.392, sum=0.392 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6752524626108722,
          "description": "min=0.675, mean=0.675, max=0.675, sum=0.675 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3072562796722192,
          "description": "min=0.307, mean=0.307, max=0.307, sum=0.307 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3532110091743119,
          "description": "min=0.353, mean=0.353, max=0.353, sum=0.353 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.959,
          "description": "min=0.959, mean=0.959, max=0.959, sum=0.959 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5519820772776194,
          "description": "min=0.098, mean=0.552, max=0.969, sum=9.936 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6613636363636363,
          "description": "min=0.2, mean=0.661, max=0.975, sum=7.275 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7265501165501166,
          "markdown": false
        },
        {
          "value": 0.49663157894736837,
          "description": "min=0.263, mean=0.497, max=0.82, sum=2.483 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.829,
          "description": "min=0.829, mean=0.829, max=0.829, sum=0.829 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6246600584363529,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37689838878898235,
          "description": "min=0.377, mean=0.377, max=0.377, sum=0.377 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6659348439709132,
          "description": "min=0.666, mean=0.666, max=0.666, sum=0.666 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3706704040370772,
          "description": "min=0.371, mean=0.371, max=0.371, sum=0.371 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3837920489296636,
          "description": "min=0.384, mean=0.384, max=0.384, sum=0.384 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.959,
          "description": "min=0.959, mean=0.959, max=0.959, sum=0.959 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6027411858798014,
          "description": "min=0.203, mean=0.603, max=0.918, sum=10.849 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5863636363636364,
          "description": "min=0.175, mean=0.586, max=0.925, sum=6.45 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5121212121212121,
          "markdown": false
        },
        {
          "value": 0.34397660818713455,
          "description": "min=0.23, mean=0.344, max=0.47, sum=5.16 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7836666666666666,
          "description": "min=0.729, mean=0.784, max=0.819, sum=2.351 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7059235974790917,
          "description": "min=0.655, mean=0.706, max=0.736, sum=2.118 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1482175345664494,
          "description": "min=0.142, mean=0.148, max=0.152, sum=0.445 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6424303381577149,
          "description": "min=0.639, mean=0.642, max=0.649, sum=1.927 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27163837981654376,
          "description": "min=0.23, mean=0.272, max=0.297, sum=0.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21827217125382264,
          "description": "min=0.185, mean=0.218, max=0.232, sum=0.873 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15439675741311426,
          "description": "min=0.144, mean=0.154, max=0.166, sum=0.926 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13238582006427588,
          "description": "min=0.131, mean=0.132, max=0.134, sum=0.794 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9546666666666667,
          "description": "min=0.946, mean=0.955, max=0.961, sum=2.864 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5003578260748177,
          "description": "min=0, mean=0.5, max=1, sum=27.019 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5977272727272727,
          "description": "min=0, mean=0.598, max=0.975, sum=19.725 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5684537684537685,
          "markdown": false
        },
        {
          "value": 0.4027251461988304,
          "description": "min=0.23, mean=0.403, max=0.7, sum=6.041 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7513333333333333,
          "description": "min=0.698, mean=0.751, max=0.798, sum=2.254 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49645549460257793,
          "description": "min=0.253, mean=0.496, max=0.636, sum=1.489 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3299616590453583,
          "description": "min=0.32, mean=0.33, max=0.337, sum=0.99 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6821060817435397,
          "description": "min=0.678, mean=0.682, max=0.688, sum=2.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4333990885086254,
          "description": "min=0.423, mean=0.433, max=0.447, sum=1.3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18501529051987767,
          "description": "min=0.18, mean=0.185, max=0.19, sum=0.555 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15159639975836045,
          "description": "min=0.142, mean=0.152, max=0.165, sum=0.455 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10396752069043724,
          "description": "min=0.1, mean=0.104, max=0.106, sum=0.312 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9403333333333332,
          "description": "min=0.936, mean=0.94, max=0.946, sum=2.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5551156886935099,
          "description": "min=0, mean=0.555, max=0.877, sum=29.976 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6515151515151515,
          "description": "min=0.275, mean=0.652, max=0.95, sum=21.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.732464505191778,
          "markdown": false
        },
        {
          "value": 0.6090994152046784,
          "description": "min=0.35, mean=0.609, max=0.88, sum=9.136 (15)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.8963333333333333,
          "description": "min=0.894, mean=0.896, max=0.898, sum=2.689 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7418788396572448,
          "description": "min=0.732, mean=0.742, max=0.748, sum=2.226 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41268555506883464,
          "description": "min=0.406, mean=0.413, max=0.418, sum=1.238 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.4729079939924856,
          "description": "min=0.459, mean=0.473, max=0.488, sum=1.419 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6156982670744139,
          "description": "min=0.601, mean=0.616, max=0.63, sum=1.847 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.04906511219852586,
          "description": "min=0, mean=0.049, max=0.147, sum=0.147 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14911545457419603,
          "description": "min=0.144, mean=0.149, max=0.157, sum=0.447 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9353333333333333,
          "description": "min=0.928, mean=0.935, max=0.939, sum=2.806 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.007510704420678352,
          "description": "min=0, mean=0.008, max=0.344, sum=0.406 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7007575757575758,
          "description": "min=0, mean=0.701, max=0.975, sum=23.125 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.07453865578865579,
          "markdown": false
        },
        {
          "value": 0.2433684210526316,
          "description": "min=0.2, mean=0.243, max=0.28, sum=3.651 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.634,
          "description": "min=0.631, mean=0.634, max=0.64, sum=1.902 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2521219532517845,
          "description": "min=0.213, mean=0.252, max=0.297, sum=0.756 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06813388957535708,
          "description": "min=0.068, mean=0.068, max=0.069, sum=0.204 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2265558450613029,
          "description": "min=0.197, mean=0.227, max=0.258, sum=0.68 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16181110110332023,
          "description": "min=0.156, mean=0.162, max=0.172, sum=0.485 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2018348623853211,
          "description": "min=0.197, mean=0.202, max=0.203, sum=0.807 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.01716275077615623,
          "description": "min=0.009, mean=0.017, max=0.022, sum=0.103 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02059148148915427,
          "description": "min=0.019, mean=0.021, max=0.022, sum=0.124 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8363333333333333,
          "description": "min=0.776, mean=0.836, max=0.876, sum=2.509 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48977295239520197,
          "description": "min=0, mean=0.49, max=1, sum=26.448 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39545454545454545,
          "description": "min=0, mean=0.395, max=0.975, sum=13.05 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_accuracy.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_accuracy.json"
      }
    ],
    "name": "accuracy"
  },
  {
    "title": "Calibration",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - ECE (10-bin)",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "MMLU"
        }
      },
      {
        "value": "BoolQ - ECE (10-bin)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - ECE (10-bin)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - ECE (10-bin)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - ECE (10-bin)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - ECE (10-bin)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "HellaSwag - ECE (10-bin)",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "OpenbookQA - ECE (10-bin)",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "TruthfulQA - ECE (10-bin)",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "IMDB - ECE (10-bin)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - ECE (10-bin)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - ECE (10-bin)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n10-bin expected calibration error: The average difference between the model's confidence and accuracy, averaged across 10 bins where each bin contains an equal number of points (only computed for classification tasks). Warning - not reliable for small datasets (e.g., with < 300 examples) because each bin will have very few examples.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "ECE (10-bin)",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6662512419912975,
          "markdown": false
        },
        {
          "value": 0.13067986008352367,
          "description": "min=0.074, mean=0.131, max=0.172, sum=1.96 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21546167732589497,
          "description": "min=0.205, mean=0.215, max=0.223, sum=0.646 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.033635629206676086,
          "description": "min=0.028, mean=0.034, max=0.042, sum=0.101 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.035434924784030764,
          "description": "min=0.029, mean=0.035, max=0.042, sum=0.106 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06491976505236641,
          "description": "min=0.058, mean=0.065, max=0.069, sum=0.195 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04341080368618692,
          "description": "min=0.042, mean=0.043, max=0.045, sum=0.13 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21741807730831492,
          "description": "min=0.217, mean=0.217, max=0.217, sum=0.217 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25015305244306557,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11285677982128534,
          "description": "min=0.099, mean=0.113, max=0.123, sum=0.339 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06375881576094916,
          "description": "min=0.06, mean=0.064, max=0.072, sum=0.191 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26979933840430187,
          "description": "min=0.048, mean=0.27, max=0.587, sum=14.569 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2281177870147751,
          "description": "min=0.103, mean=0.228, max=0.595, sum=7.528 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6383920923698907,
          "markdown": false
        },
        {
          "value": 0.12277396117394333,
          "description": "min=0.051, mean=0.123, max=0.181, sum=1.842 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10621693084730484,
          "description": "min=0.085, mean=0.106, max=0.133, sum=0.319 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04554705251298522,
          "description": "min=0.042, mean=0.046, max=0.048, sum=0.137 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01549922748171477,
          "description": "min=0.013, mean=0.015, max=0.017, sum=0.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08597598507389619,
          "description": "min=0.075, mean=0.086, max=0.093, sum=0.258 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02431531680637249,
          "description": "min=0.016, mean=0.024, max=0.033, sum=0.073 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19173198668049052,
          "description": "min=0.192, mean=0.192, max=0.192, sum=0.192 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24986668171933007,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11232689963932652,
          "description": "min=0.105, mean=0.112, max=0.121, sum=0.337 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21314336064172376,
          "description": "min=0.196, mean=0.213, max=0.234, sum=0.639 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37680252478263027,
          "description": "min=0.073, mean=0.377, max=0.573, sum=20.347 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2689468403025133,
          "description": "min=0.134, mean=0.269, max=0.513, sum=8.875 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6221919576066971,
          "markdown": false
        },
        {
          "value": 0.11389257817699022,
          "description": "min=0.063, mean=0.114, max=0.154, sum=1.708 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15409092997354776,
          "description": "min=0.139, mean=0.154, max=0.169, sum=0.462 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04705310707412085,
          "description": "min=0.039, mean=0.047, max=0.062, sum=0.141 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.028955351873343083,
          "description": "min=0.027, mean=0.029, max=0.03, sum=0.087 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08114120238748938,
          "description": "min=0.073, mean=0.081, max=0.097, sum=0.243 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03571925908384949,
          "description": "min=0.019, mean=0.036, max=0.06, sum=0.107 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21338082493857388,
          "description": "min=0.213, mean=0.213, max=0.213, sum=0.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25849314658751343,
          "description": "min=0.258, mean=0.258, max=0.258, sum=0.258 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09083831911084679,
          "description": "min=0.064, mean=0.091, max=0.109, sum=0.273 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15775206410447826,
          "description": "min=0.152, mean=0.158, max=0.166, sum=0.473 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4075612338805137,
          "description": "min=0.228, mean=0.408, max=0.593, sum=22.008 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24386423436086976,
          "description": "min=0.113, mean=0.244, max=0.466, sum=8.048 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6340622537431048,
          "markdown": false
        },
        {
          "value": 0.13930239849591303,
          "description": "min=0.067, mean=0.139, max=0.205, sum=2.09 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16655399552246586,
          "description": "min=0.155, mean=0.167, max=0.185, sum=0.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.040831012535009516,
          "description": "min=0.034, mean=0.041, max=0.05, sum=0.122 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.035782131071618734,
          "description": "min=0.031, mean=0.036, max=0.043, sum=0.107 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06520649617008285,
          "description": "min=0.051, mean=0.065, max=0.075, sum=0.196 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04046561186462396,
          "description": "min=0.031, mean=0.04, max=0.051, sum=0.121 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2263163700416937,
          "description": "min=0.226, mean=0.226, max=0.226, sum=0.226 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21479287621696264,
          "description": "min=0.215, mean=0.215, max=0.215, sum=0.215 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1233746034244333,
          "description": "min=0.101, mean=0.123, max=0.157, sum=0.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13573735378803647,
          "description": "min=0.119, mean=0.136, max=0.165, sum=0.407 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37604932471578795,
          "description": "min=0.131, mean=0.376, max=0.649, sum=20.307 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23434348116913628,
          "description": "min=0.095, mean=0.234, max=0.473, sum=7.733 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6597594819611471,
          "markdown": false
        },
        {
          "value": 0.13723997934779486,
          "description": "min=0.056, mean=0.137, max=0.248, sum=2.059 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17545319159294462,
          "description": "min=0.163, mean=0.175, max=0.198, sum=0.526 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07310994320832209,
          "description": "min=0.068, mean=0.073, max=0.076, sum=0.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.018133452831606698,
          "description": "min=0.018, mean=0.018, max=0.019, sum=0.054 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07345259187429393,
          "description": "min=0.071, mean=0.073, max=0.076, sum=0.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03466023181877799,
          "description": "min=0.032, mean=0.035, max=0.037, sum=0.104 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.06751578986419772,
          "description": "min=0.049, mean=0.068, max=0.095, sum=0.203 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18203122522171636,
          "description": "min=0.157, mean=0.182, max=0.199, sum=0.546 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31411210820302815,
          "description": "min=0.07, mean=0.314, max=0.578, sum=16.962 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2177038585857703,
          "description": "min=0.126, mean=0.218, max=0.683, sum=7.184 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6300647548566143,
          "markdown": false
        },
        {
          "value": 0.13373539597087636,
          "description": "min=0.076, mean=0.134, max=0.172, sum=2.006 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20883844550071148,
          "description": "min=0.179, mean=0.209, max=0.243, sum=0.627 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12569343029680938,
          "description": "min=0.107, mean=0.126, max=0.158, sum=0.377 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01803156970695322,
          "description": "min=0.016, mean=0.018, max=0.019, sum=0.054 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06257440554546793,
          "description": "min=0.053, mean=0.063, max=0.072, sum=0.188 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03491339390127312,
          "description": "min=0.027, mean=0.035, max=0.04, sum=0.105 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.09707246189445913,
          "description": "min=0.073, mean=0.097, max=0.142, sum=0.291 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11088831926219649,
          "description": "min=0.088, mean=0.111, max=0.153, sum=0.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38073513412444826,
          "description": "min=0.097, mean=0.381, max=0.605, sum=20.56 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23222744852932867,
          "description": "min=0.119, mean=0.232, max=0.581, sum=7.664 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6435013876040703,
          "markdown": false
        },
        {
          "value": 0.1406708954092635,
          "description": "min=0.06, mean=0.141, max=0.219, sum=2.11 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14720347227904834,
          "description": "min=0.126, mean=0.147, max=0.165, sum=0.442 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.01399000614897039,
          "description": "min=0.008, mean=0.014, max=0.021, sum=0.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08428284450081218,
          "description": "min=0.081, mean=0.084, max=0.089, sum=0.253 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.1021312296645796,
          "description": "min=0.043, mean=0.102, max=0.134, sum=0.306 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17816129477822015,
          "description": "min=0.153, mean=0.178, max=0.201, sum=0.534 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19026595574841215,
          "description": "min=0.033, mean=0.19, max=0.41, sum=10.274 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25356461082010057,
          "description": "min=0.128, mean=0.254, max=0.441, sum=8.368 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6405642923219241,
          "markdown": false
        },
        {
          "value": 0.110752611571227,
          "description": "min=0.087, mean=0.111, max=0.157, sum=1.661 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06557915095556173,
          "description": "min=0.056, mean=0.066, max=0.084, sum=0.197 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04822831549746422,
          "description": "min=0.04, mean=0.048, max=0.063, sum=0.145 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04534548194935659,
          "description": "min=0.039, mean=0.045, max=0.054, sum=0.136 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07013609628734997,
          "description": "min=0.068, mean=0.07, max=0.074, sum=0.21 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09821008405024316,
          "description": "min=0.068, mean=0.098, max=0.131, sum=0.295 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.08144933240589737,
          "description": "min=0.069, mean=0.081, max=0.095, sum=0.244 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23165086222498446,
          "description": "min=0.187, mean=0.232, max=0.257, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2796625331945748,
          "description": "min=0.071, mean=0.28, max=0.632, sum=15.102 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29014727083072167,
          "description": "min=0.115, mean=0.29, max=0.826, sum=9.575 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5765957446808511,
          "markdown": false
        },
        {
          "value": 0.1348564339845485,
          "description": "min=0.075, mean=0.135, max=0.225, sum=2.023 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1289354797828563,
          "description": "min=0.11, mean=0.129, max=0.154, sum=0.387 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.046063826868188405,
          "description": "min=0.043, mean=0.046, max=0.047, sum=0.138 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02157162838647707,
          "description": "min=0.018, mean=0.022, max=0.024, sum=0.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08979897901208977,
          "description": "min=0.08, mean=0.09, max=0.095, sum=0.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09561324552236967,
          "description": "min=0.081, mean=0.096, max=0.116, sum=0.287 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.0641638452052097,
          "description": "min=0.057, mean=0.064, max=0.068, sum=0.192 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2038815444945483,
          "description": "min=0.177, mean=0.204, max=0.232, sum=0.612 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35941964376806523,
          "description": "min=0.112, mean=0.359, max=0.619, sum=19.409 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2902057183123561,
          "description": "min=0.143, mean=0.29, max=0.954, sum=9.577 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6242368177613321,
          "markdown": false
        },
        {
          "value": 0.15396738685964684,
          "description": "min=0.122, mean=0.154, max=0.217, sum=2.31 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08277086924611576,
          "description": "min=0.06, mean=0.083, max=0.111, sum=0.248 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04915634481869984,
          "description": "min=0.036, mean=0.049, max=0.061, sum=0.147 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04112615448004484,
          "description": "min=0.035, mean=0.041, max=0.045, sum=0.123 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07410001302901324,
          "description": "min=0.07, mean=0.074, max=0.077, sum=0.222 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05820640656843105,
          "description": "min=0.054, mean=0.058, max=0.061, sum=0.175 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.09195091586715554,
          "description": "min=0.072, mean=0.092, max=0.102, sum=0.276 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1730084935772459,
          "description": "min=0.137, mean=0.173, max=0.222, sum=0.519 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27240452987490027,
          "description": "min=0.051, mean=0.272, max=0.563, sum=14.71 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.238277000839632,
          "description": "min=0.072, mean=0.238, max=1, sum=7.863 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "min=0.063, mean=0.144, max=0.262, sum=2.165 (15)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.035, mean=0.038, max=0.041, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.052, mean=0.09, max=0.14, sum=0.27 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.108, mean=0.121, max=0.128, sum=0.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.048, mean=0.067, max=0.088, sum=0.2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.034, mean=0.039, max=0.048, sum=0.116 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.32, mean=0.32, max=0.32, sum=0.32 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.244, mean=0.244, max=0.244, sum=0.244 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.052, mean=0.127, max=0.196, sum=0.507 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.01, mean=0.015, max=0.024, sum=0.045 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.048, mean=0.179, max=0.449, sum=9.655 (54)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.071, mean=0.212, max=0.648, sum=7.002 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3480016788296159,
          "markdown": false
        },
        {
          "value": 0.13690038983912287,
          "description": "min=0.115, mean=0.137, max=0.173, sum=2.054 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2086643852555177,
          "description": "min=0.153, mean=0.209, max=0.247, sum=0.626 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2374266630696186,
          "description": "min=0.231, mean=0.237, max=0.242, sum=0.712 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11564225453050514,
          "description": "min=0.11, mean=0.116, max=0.118, sum=0.347 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3469801265406112,
          "description": "min=0.338, mean=0.347, max=0.36, sum=1.041 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1222163558834574,
          "description": "min=0.103, mean=0.122, max=0.142, sum=0.367 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2926428762465171,
          "description": "min=0.293, mean=0.293, max=0.293, sum=0.293 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24842661648577113,
          "description": "min=0.248, mean=0.248, max=0.248, sum=0.248 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09624512475777981,
          "description": "min=0.053, mean=0.096, max=0.128, sum=0.385 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3430318396761201,
          "description": "min=0.305, mean=0.343, max=0.41, sum=1.029 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26189371110201226,
          "description": "min=0.069, mean=0.262, max=0.456, sum=14.142 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4396262000869267,
          "description": "min=0.246, mean=0.44, max=0.775, sum=14.508 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7577474560592045,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.16765379656947835,
          "description": "min=0.074, mean=0.168, max=0.3, sum=2.515 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32218942300251074,
          "description": "min=0.208, mean=0.322, max=0.435, sum=0.967 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 4.2543589701120735e-05,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.521055021161368e-09,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 9.644610962286308e-05,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0005015010499976317,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15413479575183991,
          "description": "min=0.1, mean=0.154, max=0.234, sum=0.617 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29061500207311436,
          "description": "min=0.207, mean=0.291, max=0.36, sum=0.872 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.30797595023001567,
          "description": "min=0.067, mean=0.308, max=0.574, sum=16.631 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08607203532710274,
          "description": "min=0.0, mean=0.086, max=0.573, sum=2.84 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5427202179052317,
          "markdown": false
        },
        {
          "value": 0.14945785718149934,
          "description": "min=0.089, mean=0.149, max=0.246, sum=2.242 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039674216829776156,
          "description": "min=0.037, mean=0.04, max=0.043, sum=0.119 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.061654179655226814,
          "description": "min=0.048, mean=0.062, max=0.079, sum=0.185 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06770990173751885,
          "description": "min=0.061, mean=0.068, max=0.073, sum=0.203 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08482055822987211,
          "description": "min=0.075, mean=0.085, max=0.099, sum=0.254 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06703451532890617,
          "description": "min=0.066, mean=0.067, max=0.07, sum=0.201 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34142560211110756,
          "description": "min=0.341, mean=0.341, max=0.341, sum=0.341 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23470136403728084,
          "description": "min=0.235, mean=0.235, max=0.235, sum=0.235 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0994665665272844,
          "description": "min=0.075, mean=0.099, max=0.119, sum=0.298 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06875792133691605,
          "description": "min=0.05, mean=0.069, max=0.081, sum=0.206 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32664532725883244,
          "description": "min=0.051, mean=0.327, max=0.708, sum=17.639 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.274053604040966,
          "description": "min=0.093, mean=0.274, max=0.825, sum=9.044 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6524936901131783,
          "markdown": false
        },
        {
          "value": 0.11188578153206447,
          "description": "min=0.075, mean=0.112, max=0.151, sum=1.678 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08825401206422555,
          "description": "min=0.066, mean=0.088, max=0.106, sum=0.265 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03650754887085305,
          "description": "min=0.032, mean=0.037, max=0.044, sum=0.11 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.024639111727299556,
          "description": "min=0.02, mean=0.025, max=0.032, sum=0.074 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14321248401208217,
          "description": "min=0.117, mean=0.143, max=0.158, sum=0.43 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03288362014267938,
          "description": "min=0.03, mean=0.033, max=0.036, sum=0.099 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28820318504565584,
          "description": "min=0.288, mean=0.288, max=0.288, sum=0.288 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2254334966206393,
          "description": "min=0.225, mean=0.225, max=0.225, sum=0.225 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10528939288118344,
          "description": "min=0.097, mean=0.105, max=0.117, sum=0.316 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13199349625828075,
          "description": "min=0.098, mean=0.132, max=0.183, sum=0.396 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38365386942886265,
          "description": "min=0.1, mean=0.384, max=0.705, sum=20.717 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26679166027291745,
          "description": "min=0.115, mean=0.267, max=1, sum=8.804 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5098117312502142,
          "markdown": false
        },
        {
          "value": 0.11350786269483934,
          "description": "min=0.067, mean=0.114, max=0.164, sum=1.703 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08218351589951171,
          "description": "min=0.069, mean=0.082, max=0.093, sum=0.247 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.046946382998353055,
          "description": "min=0.043, mean=0.047, max=0.055, sum=0.141 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.025653079993217736,
          "description": "min=0.018, mean=0.026, max=0.036, sum=0.077 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14175015381424005,
          "description": "min=0.129, mean=0.142, max=0.154, sum=0.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04829561557428013,
          "description": "min=0.042, mean=0.048, max=0.061, sum=0.145 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2707363482287178,
          "description": "min=0.271, mean=0.271, max=0.271, sum=0.271 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27530956848832144,
          "description": "min=0.275, mean=0.275, max=0.275, sum=0.275 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09386032214108035,
          "description": "min=0.082, mean=0.094, max=0.109, sum=0.282 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.360155737743892,
          "description": "min=0.335, mean=0.36, max=0.394, sum=1.08 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45870054566126006,
          "description": "min=0.176, mean=0.459, max=0.641, sum=24.77 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3038351531350353,
          "description": "min=0.151, mean=0.304, max=0.849, sum=10.027 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6085000742339626,
          "markdown": false
        },
        {
          "value": 0.13602108170852936,
          "description": "min=0.049, mean=0.136, max=0.202, sum=2.04 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09496766959019069,
          "description": "min=0.072, mean=0.095, max=0.124, sum=0.285 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031094283389380417,
          "description": "min=0.029, mean=0.031, max=0.033, sum=0.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.023328620693919305,
          "description": "min=0.02, mean=0.023, max=0.027, sum=0.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.198062019189297,
          "description": "min=0.18, mean=0.198, max=0.221, sum=0.594 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.035862172954873824,
          "description": "min=0.03, mean=0.036, max=0.042, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08312318484699062,
          "description": "min=0.083, mean=0.083, max=0.083, sum=0.083 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37852917669250147,
          "description": "min=0.379, mean=0.379, max=0.379, sum=0.379 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07625390965133329,
          "description": "min=0.059, mean=0.076, max=0.098, sum=0.229 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13354341899719424,
          "description": "min=0.085, mean=0.134, max=0.174, sum=0.401 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4864679961449666,
          "description": "min=0.201, mean=0.486, max=0.8, sum=26.269 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23374335739699753,
          "description": "min=0.084, mean=0.234, max=0.631, sum=7.714 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5846823928461301,
          "markdown": false
        },
        {
          "value": 0.14305203655556303,
          "description": "min=0.104, mean=0.143, max=0.197, sum=2.146 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05127903463780418,
          "description": "min=0.037, mean=0.051, max=0.062, sum=0.154 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.059183266964369506,
          "description": "min=0.042, mean=0.059, max=0.072, sum=0.178 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05430103491623906,
          "description": "min=0.044, mean=0.054, max=0.064, sum=0.163 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07296237131206641,
          "description": "min=0.064, mean=0.073, max=0.08, sum=0.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06295082132498765,
          "description": "min=0.053, mean=0.063, max=0.072, sum=0.189 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3332417863062664,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20665896753536225,
          "description": "min=0.207, mean=0.207, max=0.207, sum=0.207 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21105124875435366,
          "description": "min=0.18, mean=0.211, max=0.233, sum=0.633 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06908904600115551,
          "description": "min=0.05, mean=0.069, max=0.082, sum=0.207 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3129455444585645,
          "description": "min=0.056, mean=0.313, max=0.651, sum=16.899 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2501605016965272,
          "description": "min=0.078, mean=0.25, max=1, sum=8.255 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6010395609917657,
          "markdown": false
        },
        {
          "value": 0.11272299343238619,
          "description": "min=0.055, mean=0.113, max=0.167, sum=1.691 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09459272512018041,
          "description": "min=0.088, mean=0.095, max=0.105, sum=0.284 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02834267942109429,
          "description": "min=0.027, mean=0.028, max=0.03, sum=0.085 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01475928497137971,
          "description": "min=0.006, mean=0.015, max=0.02, sum=0.044 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2327617365925914,
          "description": "min=0.181, mean=0.233, max=0.27, sum=0.698 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04129669890931466,
          "description": "min=0.029, mean=0.041, max=0.062, sum=0.124 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2814688190554964,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2303402231123461,
          "description": "min=0.23, mean=0.23, max=0.23, sum=0.23 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07993899696218487,
          "description": "min=0.057, mean=0.08, max=0.106, sum=0.24 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3598306140598746,
          "description": "min=0.335, mean=0.36, max=0.394, sum=1.079 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4873543575629644,
          "description": "min=0.265, mean=0.487, max=0.736, sum=26.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25263340417043,
          "description": "min=0.11, mean=0.253, max=0.545, sum=8.337 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5291111339523303,
          "markdown": false
        },
        {
          "value": 0.1551609000421963,
          "description": "min=0.103, mean=0.155, max=0.243, sum=2.327 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0594622129465324,
          "description": "min=0.048, mean=0.059, max=0.069, sum=0.178 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07599807506781359,
          "description": "min=0.075, mean=0.076, max=0.077, sum=0.228 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04227945276969597,
          "description": "min=0.04, mean=0.042, max=0.046, sum=0.127 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.057325907163997956,
          "description": "min=0.045, mean=0.057, max=0.074, sum=0.172 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06185077042352865,
          "description": "min=0.054, mean=0.062, max=0.067, sum=0.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2926835489814197,
          "description": "min=0.293, mean=0.293, max=0.293, sum=0.293 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2504061981122775,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3001833323753285,
          "description": "min=0.275, mean=0.3, max=0.332, sum=0.901 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.014204038428277976,
          "description": "min=0.011, mean=0.014, max=0.019, sum=0.043 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3578234752080933,
          "description": "min=0.113, mean=0.358, max=0.735, sum=19.322 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2744070774220778,
          "description": "min=0.05, mean=0.274, max=0.84, sum=9.055 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5963856625666678,
          "markdown": false
        },
        {
          "value": 0.18282231471159943,
          "description": "min=0.099, mean=0.183, max=0.338, sum=2.742 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02302613493537822,
          "description": "min=0.018, mean=0.023, max=0.026, sum=0.069 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.05761424791814445,
          "description": "min=0.051, mean=0.058, max=0.067, sum=0.173 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08377931898267306,
          "description": "min=0.075, mean=0.084, max=0.091, sum=0.251 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05602757611120105,
          "description": "min=0.044, mean=0.056, max=0.063, sum=0.168 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06049762085119498,
          "description": "min=0.043, mean=0.06, max=0.073, sum=0.181 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3246923611213033,
          "description": "min=0.325, mean=0.325, max=0.325, sum=0.325 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23111297495969485,
          "description": "min=0.231, mean=0.231, max=0.231, sum=0.231 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31095945192078733,
          "description": "min=0.272, mean=0.311, max=0.338, sum=0.933 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.015015056118517703,
          "description": "min=0.011, mean=0.015, max=0.02, sum=0.045 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16066140880534402,
          "description": "min=0.054, mean=0.161, max=0.416, sum=8.676 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26172447899775947,
          "description": "min=0.041, mean=0.262, max=0.96, sum=8.637 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4640964584689531,
          "markdown": false
        },
        {
          "value": 0.11546362297486105,
          "description": "min=0.062, mean=0.115, max=0.149, sum=1.732 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.062432673938629946,
          "description": "min=0.043, mean=0.062, max=0.086, sum=0.187 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19883043691040034,
          "description": "min=0.189, mean=0.199, max=0.211, sum=0.596 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07464671252737104,
          "description": "min=0.069, mean=0.075, max=0.079, sum=0.224 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3539383109024162,
          "description": "min=0.346, mean=0.354, max=0.358, sum=1.062 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13037730069459044,
          "description": "min=0.104, mean=0.13, max=0.169, sum=0.391 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2332919292558098,
          "description": "min=0.233, mean=0.233, max=0.233, sum=0.233 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2353362549897216,
          "description": "min=0.235, mean=0.235, max=0.235, sum=0.235 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07772735423117484,
          "description": "min=0.056, mean=0.078, max=0.103, sum=0.311 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2945110955018834,
          "description": "min=0.285, mean=0.295, max=0.311, sum=0.884 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40880926893677766,
          "description": "min=0.075, mean=0.409, max=0.626, sum=22.076 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3888407166022056,
          "description": "min=0.116, mean=0.389, max=0.975, sum=12.832 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4215761012322838,
          "markdown": false
        },
        {
          "value": 0.12205035764205192,
          "description": "min=0.094, mean=0.122, max=0.145, sum=1.831 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19500535688345313,
          "description": "min=0.168, mean=0.195, max=0.238, sum=0.585 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2239646545151891,
          "description": "min=0.2, mean=0.224, max=0.244, sum=0.672 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10315653555419742,
          "description": "min=0.099, mean=0.103, max=0.106, sum=0.309 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37278118995003706,
          "description": "min=0.371, mean=0.373, max=0.375, sum=1.118 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11494333135422596,
          "description": "min=0.105, mean=0.115, max=0.129, sum=0.345 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2773372160584027,
          "description": "min=0.277, mean=0.277, max=0.277, sum=0.277 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23249621701719156,
          "description": "min=0.232, mean=0.232, max=0.232, sum=0.232 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.057891800582365614,
          "description": "min=0.051, mean=0.058, max=0.068, sum=0.232 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22988586030197733,
          "description": "min=0.189, mean=0.23, max=0.269, sum=0.69 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4443373993811643,
          "description": "min=0.26, mean=0.444, max=0.593, sum=23.994 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3243919141625793,
          "description": "min=0.067, mean=0.324, max=0.975, sum=10.705 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4304810360777058,
          "markdown": false
        },
        {
          "value": 0.1364262799156796,
          "description": "min=0.064, mean=0.136, max=0.2, sum=0.682 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10596147166386737,
          "description": "min=0.106, mean=0.106, max=0.106, sum=0.106 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21689349381563713,
          "description": "min=0.217, mean=0.217, max=0.217, sum=0.217 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06999999827276561,
          "description": "min=0.07, mean=0.07, max=0.07, sum=0.07 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3689977017786239,
          "description": "min=0.369, mean=0.369, max=0.369, sum=0.369 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09977223409937552,
          "description": "min=0.1, mean=0.1, max=0.1, sum=0.1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.07613907039385276,
          "description": "min=0.076, mean=0.076, max=0.076, sum=0.076 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3016994708797646,
          "description": "min=0.302, mean=0.302, max=0.302, sum=0.302 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25858613851508827,
          "description": "min=0.074, mean=0.259, max=0.508, sum=4.655 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5016937882323235,
          "description": "min=0.175, mean=0.502, max=0.975, sum=5.519 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37428307123034227,
          "markdown": false
        },
        {
          "value": 0.11132961223278444,
          "description": "min=0.092, mean=0.111, max=0.166, sum=0.557 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13986557582802048,
          "description": "min=0.14, mean=0.14, max=0.14, sum=0.14 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2394289121866973,
          "description": "min=0.239, mean=0.239, max=0.239, sum=0.239 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09399996958029097,
          "description": "min=0.094, mean=0.094, max=0.094, sum=0.094 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3899944090149843,
          "description": "min=0.39, mean=0.39, max=0.39, sum=0.39 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1383150544527575,
          "description": "min=0.138, mean=0.138, max=0.138, sum=0.138 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.09363268995646454,
          "description": "min=0.094, mean=0.094, max=0.094, sum=0.094 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34150363639115,
          "description": "min=0.342, mean=0.342, max=0.342, sum=0.342 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2965193799633309,
          "description": "min=0.138, mean=0.297, max=0.479, sum=5.337 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5135614568346981,
          "description": "min=0.175, mean=0.514, max=0.975, sum=5.649 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.43469010175763184,
          "markdown": false
        },
        {
          "value": 0.1514046561108303,
          "description": "min=0.1, mean=0.151, max=0.242, sum=2.271 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43269382093398495,
          "description": "min=0.348, mean=0.433, max=0.512, sum=1.298 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.06672937578031e-11,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.07599999619350188,
          "description": "min=0.07, mean=0.076, max=0.082, sum=0.228 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23900003883193166,
          "description": "min=0.051, mean=0.239, max=0.356, sum=0.717 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.908717030577995e-09,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1434693835940009,
          "description": "min=0.109, mean=0.143, max=0.195, sum=0.574 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23573461605966659,
          "description": "min=0.108, mean=0.236, max=0.374, sum=0.707 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3799801119037254,
          "description": "min=0.108, mean=0.38, max=0.553, sum=20.519 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36667176546312147,
          "description": "min=0.0, mean=0.367, max=0.925, sum=12.1 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.464477335800185,
          "markdown": false
        },
        {
          "value": 0.13362255376880447,
          "description": "min=0.084, mean=0.134, max=0.202, sum=2.004 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45980755585445926,
          "description": "min=0.416, mean=0.46, max=0.512, sum=1.379 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.840114578300129e-06,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09200000000000001,
          "description": "min=0.088, mean=0.092, max=0.095, sum=0.276 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17899999902043598,
          "description": "min=0.028, mean=0.179, max=0.258, sum=0.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.00013015946539738277,
          "description": "min=0.0, mean=0.0, max=0.0, sum=0.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.12460869505528777,
          "description": "min=0.096, mean=0.125, max=0.139, sum=0.498 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22500123786419848,
          "description": "min=0.037, mean=0.225, max=0.41, sum=0.675 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40373338964571226,
          "description": "min=0.123, mean=0.404, max=0.585, sum=21.802 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40084433515818857,
          "description": "min=0.0, mean=0.401, max=0.95, sum=13.228 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.33807716905928437,
          "markdown": false
        },
        {
          "value": 0.14714449343481936,
          "description": "min=0.115, mean=0.147, max=0.194, sum=2.207 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19360710050007168,
          "description": "min=0.177, mean=0.194, max=0.218, sum=0.581 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25442494535286947,
          "description": "min=0.25, mean=0.254, max=0.261, sum=0.763 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17321815784980257,
          "description": "min=0.169, mean=0.173, max=0.178, sum=0.52 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3723122842871363,
          "description": "min=0.365, mean=0.372, max=0.38, sum=1.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14774672207107284,
          "description": "min=0.128, mean=0.148, max=0.173, sum=0.443 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.324637159664446,
          "description": "min=0.325, mean=0.325, max=0.325, sum=0.325 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20889829455743214,
          "description": "min=0.209, mean=0.209, max=0.209, sum=0.209 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05404322346973557,
          "description": "min=0.042, mean=0.054, max=0.061, sum=0.216 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18962950165784687,
          "description": "min=0.164, mean=0.19, max=0.216, sum=0.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46216217374926066,
          "description": "min=0.226, mean=0.462, max=0.633, sum=24.957 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35168585204039804,
          "description": "min=0.1, mean=0.352, max=0.74, sum=11.606 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2888771827640159,
          "markdown": false
        },
        {
          "value": 0.13542563946906333,
          "description": "min=0.101, mean=0.135, max=0.172, sum=2.031 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20047176103986394,
          "description": "min=0.193, mean=0.2, max=0.206, sum=0.601 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2445466042880168,
          "description": "min=0.224, mean=0.245, max=0.264, sum=0.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14107540425227785,
          "description": "min=0.134, mean=0.141, max=0.149, sum=0.423 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38437204570087863,
          "description": "min=0.379, mean=0.384, max=0.387, sum=1.153 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15357329550060583,
          "description": "min=0.135, mean=0.154, max=0.176, sum=0.461 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29326475041918015,
          "description": "min=0.293, mean=0.293, max=0.293, sum=0.293 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2373615873422732,
          "description": "min=0.237, mean=0.237, max=0.237, sum=0.237 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07328356622626138,
          "description": "min=0.047, mean=0.073, max=0.084, sum=0.293 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30155451934186406,
          "description": "min=0.289, mean=0.302, max=0.327, sum=0.905 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47391416538592424,
          "description": "min=0.299, mean=0.474, max=0.666, sum=25.591 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.468339884912531,
          "description": "min=0.126, mean=0.468, max=0.975, sum=15.455 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "min=0.063, mean=0.111, max=0.138, sum=0.557 (5)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.292, mean=0.292, max=0.292, sum=0.292 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.265, mean=0.265, max=0.265, sum=0.265 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.176, mean=0.176, max=0.176, sum=0.176 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.402, mean=0.402, max=0.402, sum=0.402 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.114, mean=0.114, max=0.114, sum=0.114 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "min=0.057, mean=0.057, max=0.057, sum=0.057 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.336, mean=0.336, max=0.336, sum=0.336 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.13, mean=0.334, max=0.562, sum=6.012 (18)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.122, mean=0.572, max=0.975, sum=6.295 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "min=0.127, mean=0.15, max=0.18, sum=0.748 (5)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.078, mean=0.078, max=0.078, sum=0.078 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.293, mean=0.293, max=0.293, sum=0.293 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.227, mean=0.227, max=0.227, sum=0.227 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.414, mean=0.414, max=0.414, sum=0.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.172, mean=0.172, max=0.172, sum=0.172 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "min=0.193, mean=0.193, max=0.193, sum=0.193 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.302, mean=0.302, max=0.302, sum=0.302 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.098, mean=0.295, max=0.455, sum=5.305 (18)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.132, mean=0.644, max=0.925, sum=7.081 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "min=0.051, mean=0.093, max=0.139, sum=0.464 (5)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.164, mean=0.164, max=0.164, sum=0.164 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.296, mean=0.296, max=0.296, sum=0.296 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.264, mean=0.264, max=0.264, sum=0.264 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.451, mean=0.451, max=0.451, sum=0.451 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.146, mean=0.146, max=0.146, sum=0.146 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "min=0.15, mean=0.15, max=0.15, sum=0.15 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.255, mean=0.255, max=0.255, sum=0.255 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.161, mean=0.4, max=0.513, sum=7.208 (18)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.156, mean=0.753, max=1.0, sum=8.279 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "min=0.215, mean=0.215, max=0.215, sum=0.215 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "min=0.116, mean=0.116, max=0.116, sum=0.116 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "min=0.098, mean=0.323, max=0.788, sum=4.519 (14)",
          "style": {},
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3335337650323774,
          "markdown": false
        },
        {
          "value": 0.23428857555005617,
          "description": "min=0.151, mean=0.234, max=0.32, sum=1.171 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3432802705941571,
          "description": "min=0.343, mean=0.343, max=0.343, sum=0.343 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.045878175333070315,
          "description": "min=0.046, mean=0.046, max=0.046, sum=0.046 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13434354583448904,
          "description": "min=0.134, mean=0.134, max=0.134, sum=0.134 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23769723451909555,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04026034301598206,
          "description": "min=0.04, mean=0.04, max=0.04, sum=0.04 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3750196178145884,
          "description": "min=0.375, mean=0.375, max=0.375, sum=0.375 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28073357253102127,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3515610942498128,
          "description": "min=0.162, mean=0.352, max=0.606, sum=6.328 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3296795633615674,
          "description": "min=0.004, mean=0.33, max=0.711, sum=3.626 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.20388529139685477,
          "markdown": false
        },
        {
          "value": 0.17593793416924502,
          "description": "min=0.121, mean=0.176, max=0.315, sum=0.88 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.322404542566261,
          "description": "min=0.322, mean=0.322, max=0.322, sum=0.322 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08355639800803456,
          "description": "min=0.084, mean=0.084, max=0.084, sum=0.084 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16180078530132275,
          "description": "min=0.162, mean=0.162, max=0.162, sum=0.162 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41328409267406696,
          "description": "min=0.413, mean=0.413, max=0.413, sum=0.413 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10940664349880716,
          "description": "min=0.109, mean=0.109, max=0.109, sum=0.109 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22667464300561196,
          "description": "min=0.227, mean=0.227, max=0.227, sum=0.227 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34781631358579634,
          "description": "min=0.348, mean=0.348, max=0.348, sum=0.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3464227204141308,
          "description": "min=0.13, mean=0.346, max=0.589, sum=6.236 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6009008385490167,
          "description": "min=0.126, mean=0.601, max=0.963, sum=6.61 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.27488436632747454,
          "markdown": false
        },
        {
          "value": 0.19445587267296924,
          "description": "min=0.156, mean=0.194, max=0.246, sum=0.972 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15912327464389103,
          "description": "min=0.159, mean=0.159, max=0.159, sum=0.159 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25677737638719905,
          "description": "min=0.257, mean=0.257, max=0.257, sum=0.257 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20199999735253094,
          "description": "min=0.202, mean=0.202, max=0.202, sum=0.202 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4297157164166979,
          "description": "min=0.43, mean=0.43, max=0.43, sum=0.43 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10339686685910766,
          "description": "min=0.103, mean=0.103, max=0.103, sum=0.103 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.31581376966800645,
          "description": "min=0.316, mean=0.316, max=0.316, sum=0.316 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18259660460611343,
          "description": "min=0.183, mean=0.183, max=0.183, sum=0.183 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25325054290553783,
          "description": "min=0.086, mean=0.253, max=0.415, sum=4.559 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37612291287489436,
          "description": "min=0.212, mean=0.376, max=0.701, sum=4.137 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6152996196936993,
          "markdown": false
        },
        {
          "value": 0.12722994020701678,
          "description": "min=0.073, mean=0.127, max=0.202, sum=1.908 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04811928896988451,
          "description": "min=0.017, mean=0.048, max=0.088, sum=0.144 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05012197972633472,
          "description": "min=0.026, mean=0.05, max=0.075, sum=0.15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039723290660202144,
          "description": "min=0.038, mean=0.04, max=0.041, sum=0.119 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07490014228309726,
          "description": "min=0.071, mean=0.075, max=0.078, sum=0.225 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08020003145494241,
          "description": "min=0.059, mean=0.08, max=0.106, sum=0.241 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32242755675811835,
          "description": "min=0.322, mean=0.322, max=0.322, sum=0.322 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2425759072363007,
          "description": "min=0.243, mean=0.243, max=0.243, sum=0.243 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22594889867402287,
          "description": "min=0.174, mean=0.226, max=0.252, sum=0.678 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08729270886734875,
          "description": "min=0.065, mean=0.087, max=0.106, sum=0.262 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2132557883443423,
          "description": "min=0.058, mean=0.213, max=0.447, sum=11.516 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24392205141094134,
          "description": "min=0.089, mean=0.244, max=0.908, sum=8.049 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.60170195635043,
          "markdown": false
        },
        {
          "value": 0.13220035950695058,
          "description": "min=0.103, mean=0.132, max=0.175, sum=1.983 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06514212406382298,
          "description": "min=0.063, mean=0.065, max=0.067, sum=0.195 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0461090042242735,
          "description": "min=0.045, mean=0.046, max=0.047, sum=0.138 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031006448164221535,
          "description": "min=0.028, mean=0.031, max=0.033, sum=0.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08866228023213817,
          "description": "min=0.071, mean=0.089, max=0.108, sum=0.266 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.056431419773363155,
          "description": "min=0.046, mean=0.056, max=0.064, sum=0.169 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2676753668258396,
          "description": "min=0.268, mean=0.268, max=0.268, sum=0.268 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28175565698884514,
          "description": "min=0.282, mean=0.282, max=0.282, sum=0.282 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11656099093897697,
          "description": "min=0.101, mean=0.117, max=0.128, sum=0.35 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11832833491942714,
          "description": "min=0.093, mean=0.118, max=0.136, sum=0.355 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24778001352805415,
          "description": "min=0.052, mean=0.248, max=0.54, sum=13.38 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31351556505949635,
          "description": "min=0.103, mean=0.314, max=0.912, sum=10.346 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5745594499834401,
          "markdown": false
        },
        {
          "value": 0.13175836488041992,
          "description": "min=0.093, mean=0.132, max=0.18, sum=1.976 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07164645838795872,
          "description": "min=0.047, mean=0.072, max=0.103, sum=0.215 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.06738212205854943,
          "description": "min=0.041, mean=0.067, max=0.109, sum=0.202 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06060614220397647,
          "description": "min=0.054, mean=0.061, max=0.07, sum=0.182 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.07854855230782792,
          "description": "min=0.06, mean=0.079, max=0.1, sum=0.236 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.06797808745527684,
          "description": "min=0.066, mean=0.068, max=0.071, sum=0.204 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.30968673998386337,
          "description": "min=0.31, mean=0.31, max=0.31, sum=0.31 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20443749582919374,
          "description": "min=0.204, mean=0.204, max=0.204, sum=0.204 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21061421693460983,
          "description": "min=0.186, mean=0.211, max=0.224, sum=0.632 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12610548329130192,
          "description": "min=0.104, mean=0.126, max=0.166, sum=0.378 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3960964912577608,
          "description": "min=0.083, mean=0.396, max=0.664, sum=21.389 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22206849861217967,
          "description": "min=0.073, mean=0.222, max=0.806, sum=7.328 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6031752149929763,
          "markdown": false
        },
        {
          "value": 0.1380385889615569,
          "description": "min=0.069, mean=0.138, max=0.238, sum=2.071 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07881150352718548,
          "description": "min=0.051, mean=0.079, max=0.115, sum=0.236 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.044936394093581626,
          "description": "min=0.031, mean=0.045, max=0.056, sum=0.135 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01724854000741595,
          "description": "min=0.014, mean=0.017, max=0.022, sum=0.052 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.13427394452181574,
          "description": "min=0.123, mean=0.134, max=0.149, sum=0.403 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.04303687950629059,
          "description": "min=0.033, mean=0.043, max=0.055, sum=0.129 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24965148877506194,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25956257561884827,
          "description": "min=0.26, mean=0.26, max=0.26, sum=0.26 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.06204978796421436,
          "description": "min=0.05, mean=0.062, max=0.072, sum=0.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25871248887630766,
          "description": "min=0.231, mean=0.259, max=0.285, sum=0.776 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29307434802498333,
          "description": "min=0.042, mean=0.293, max=0.601, sum=15.826 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31939577693629423,
          "description": "min=0.054, mean=0.319, max=0.977, sum=10.54 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5876917234841996,
          "markdown": false
        },
        {
          "value": 0.13954639548632583,
          "description": "min=0.095, mean=0.14, max=0.179, sum=2.093 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06758031979129187,
          "description": "min=0.036, mean=0.068, max=0.089, sum=0.203 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.027162479976532598,
          "description": "min=0.025, mean=0.027, max=0.03, sum=0.081 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01603851394023659,
          "description": "min=0.012, mean=0.016, max=0.023, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14681748032197228,
          "description": "min=0.141, mean=0.147, max=0.153, sum=0.44 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.04533749534838898,
          "description": "min=0.03, mean=0.045, max=0.065, sum=0.136 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14430034567571584,
          "description": "min=0.144, mean=0.144, max=0.144, sum=0.144 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3000308921028506,
          "description": "min=0.3, mean=0.3, max=0.3, sum=0.3 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14198207765086143,
          "description": "min=0.13, mean=0.142, max=0.164, sum=0.426 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2122386190139247,
          "description": "min=0.161, mean=0.212, max=0.289, sum=0.637 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30968147474692964,
          "description": "min=0.063, mean=0.31, max=0.598, sum=16.723 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28570502706051176,
          "description": "min=0.1, mean=0.286, max=0.455, sum=9.428 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6164902182478501,
          "markdown": false
        },
        {
          "value": 0.1282115692539908,
          "description": "min=0.049, mean=0.128, max=0.186, sum=1.923 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06655133808072823,
          "description": "min=0.049, mean=0.067, max=0.09, sum=0.2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.04605131521940172,
          "description": "min=0.034, mean=0.046, max=0.064, sum=0.138 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02767630939495112,
          "description": "min=0.024, mean=0.028, max=0.034, sum=0.083 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.17953919898525875,
          "description": "min=0.168, mean=0.18, max=0.188, sum=0.539 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.039442503431989094,
          "description": "min=0.022, mean=0.039, max=0.059, sum=0.118 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.057406609088416535,
          "description": "min=0.057, mean=0.057, max=0.057, sum=0.057 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3457887658657961,
          "description": "min=0.346, mean=0.346, max=0.346, sum=0.346 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.07105251349575469,
          "description": "min=0.06, mean=0.071, max=0.086, sum=0.213 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2737600797307666,
          "description": "min=0.223, mean=0.274, max=0.332, sum=0.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35537087067123496,
          "description": "min=0.096, mean=0.355, max=0.704, sum=19.19 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2684712140450576,
          "description": "min=0.066, mean=0.268, max=0.696, sum=8.86 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4065137447036923,
          "markdown": false
        },
        {
          "value": 0.31740378740673564,
          "description": "min=0.127, mean=0.317, max=0.54, sum=4.761 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09835218401604591,
          "description": "min=0.097, mean=0.098, max=0.099, sum=0.295 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3702182824812234,
          "description": "min=0.346, mean=0.37, max=0.389, sum=1.111 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28562303267045125,
          "description": "min=0.27, mean=0.286, max=0.299, sum=0.857 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3230345144505907,
          "description": "min=0.318, mean=0.323, max=0.331, sum=0.969 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2696184343953211,
          "description": "min=0.259, mean=0.27, max=0.279, sum=0.809 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2781634038368795,
          "description": "min=0.278, mean=0.278, max=0.278, sum=0.278 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21592533141452896,
          "description": "min=0.216, mean=0.216, max=0.216, sum=0.216 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3477434253470754,
          "description": "min=0.329, mean=0.348, max=0.373, sum=1.043 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11283562591578779,
          "description": "min=0.086, mean=0.113, max=0.132, sum=0.339 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29207184855040197,
          "description": "min=0.12, mean=0.292, max=0.449, sum=15.772 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2029109351449743,
          "description": "min=0.037, mean=0.203, max=0.736, sum=6.696 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4743236143945364,
          "markdown": false
        },
        {
          "value": 0.17629729974248792,
          "description": "min=0.064, mean=0.176, max=0.264, sum=2.644 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06391934132499137,
          "description": "min=0.057, mean=0.064, max=0.068, sum=0.192 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2393596998509794,
          "description": "min=0.214, mean=0.239, max=0.268, sum=0.718 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34056739358291327,
          "description": "min=0.315, mean=0.341, max=0.356, sum=1.022 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24207582378172995,
          "description": "min=0.233, mean=0.242, max=0.247, sum=0.726 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27378530130603257,
          "description": "min=0.234, mean=0.274, max=0.301, sum=0.821 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2864163850455534,
          "description": "min=0.286, mean=0.286, max=0.286, sum=0.286 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23789749910476482,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.19868497875362334,
          "description": "min=0.167, mean=0.199, max=0.232, sum=0.596 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03076843904734194,
          "description": "min=0.029, mean=0.031, max=0.033, sum=0.092 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18286487616515196,
          "description": "min=0.018, mean=0.183, max=0.424, sum=9.875 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21210473630230625,
          "description": "min=0.043, mean=0.212, max=0.586, sum=6.999 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.33452535946368817,
          "markdown": false
        },
        {
          "value": 0.4624557415628211,
          "description": "min=0.298, mean=0.462, max=0.534, sum=6.937 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.252648729019218,
          "description": "min=0.239, mean=0.253, max=0.279, sum=0.758 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.22125645338584943,
          "description": "min=0.198, mean=0.221, max=0.233, sum=0.664 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25269080261254767,
          "description": "min=0.233, mean=0.253, max=0.264, sum=0.758 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21613185314031233,
          "description": "min=0.215, mean=0.216, max=0.217, sum=0.648 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25427485237899866,
          "description": "min=0.237, mean=0.254, max=0.272, sum=0.763 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.15281579026404526,
          "description": "min=0.153, mean=0.153, max=0.153, sum=0.153 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3206023655720099,
          "description": "min=0.321, mean=0.321, max=0.321, sum=0.321 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.35539796883884156,
          "description": "min=0.321, mean=0.355, max=0.375, sum=1.066 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03108408690404522,
          "description": "min=0.027, mean=0.031, max=0.034, sum=0.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26204430696260744,
          "description": "min=0.049, mean=0.262, max=0.674, sum=14.15 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40879785924457385,
          "description": "min=0.079, mean=0.409, max=1, sum=13.49 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.27686841173581844,
          "markdown": false
        },
        {
          "value": 0.31056724427484883,
          "description": "min=0.16, mean=0.311, max=0.472, sum=4.659 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34372183455656985,
          "description": "min=0.318, mean=0.344, max=0.371, sum=1.031 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.18581698260430923,
          "description": "min=0.158, mean=0.186, max=0.215, sum=0.557 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5224886706365456,
          "description": "min=0.505, mean=0.522, max=0.555, sum=1.567 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.38493664744185446,
          "description": "min=0.346, mean=0.385, max=0.427, sum=1.155 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2399406998223789,
          "description": "min=0.224, mean=0.24, max=0.25, sum=0.72 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.08291053064819098,
          "description": "min=0.083, mean=0.083, max=0.083, sum=0.083 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.36220844968968424,
          "description": "min=0.362, mean=0.362, max=0.362, sum=0.362 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2505684624777335,
          "description": "min=0.202, mean=0.251, max=0.279, sum=0.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038396495508375095,
          "description": "min=0.028, mean=0.038, max=0.05, sum=0.115 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49936533676896183,
          "description": "min=0.092, mean=0.499, max=0.911, sum=26.966 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2950696376748286,
          "description": "min=0.102, mean=0.295, max=0.541, sum=9.737 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.17139908178298557,
          "markdown": false
        },
        {
          "value": 0.5062965949265723,
          "description": "min=0.357, mean=0.506, max=0.666, sum=7.594 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34632807207915267,
          "description": "min=0.257, mean=0.346, max=0.483, sum=1.039 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.318718698868713,
          "description": "min=0.248, mean=0.319, max=0.386, sum=0.956 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7640868917536278,
          "description": "min=0.751, mean=0.764, max=0.789, sum=2.292 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6905918803748641,
          "description": "min=0.6, mean=0.691, max=0.866, sum=2.072 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2675195450588613,
          "description": "min=0.16, mean=0.268, max=0.362, sum=0.803 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1034689985203878,
          "description": "min=0.103, mean=0.103, max=0.103, sum=0.103 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4870210553256142,
          "description": "min=0.487, mean=0.487, max=0.487, sum=0.487 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.46507296315502505,
          "description": "min=0.418, mean=0.465, max=0.495, sum=1.395 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08977338148861268,
          "description": "min=0.053, mean=0.09, max=0.142, sum=0.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47860750507636396,
          "description": "min=0.012, mean=0.479, max=0.985, sum=25.845 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47311876061285835,
          "description": "min=0.018, mean=0.473, max=0.891, sum=15.613 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4387141535615171,
          "markdown": false
        },
        {
          "value": 0.11506526711032969,
          "description": "min=0.082, mean=0.115, max=0.149, sum=0.575 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1865846445420437,
          "description": "min=0.187, mean=0.187, max=0.187, sum=0.187 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2338003327407993,
          "description": "min=0.234, mean=0.234, max=0.234, sum=0.234 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1159999973291356,
          "description": "min=0.116, mean=0.116, max=0.116, sum=0.116 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34498406074093657,
          "description": "min=0.345, mean=0.345, max=0.345, sum=0.345 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07775925403447285,
          "description": "min=0.078, mean=0.078, max=0.078, sum=0.078 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.04833037892853392,
          "description": "min=0.048, mean=0.048, max=0.048, sum=0.048 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.24822902119068743,
          "description": "min=0.248, mean=0.248, max=0.248, sum=0.248 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3030711579633833,
          "description": "min=0.105, mean=0.303, max=0.532, sum=5.455 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5021656428017803,
          "description": "min=0.225, mean=0.502, max=0.975, sum=5.524 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37183163737280295,
          "markdown": false
        },
        {
          "value": 0.1238999810101579,
          "description": "min=0.09, mean=0.124, max=0.157, sum=0.619 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14082220350962116,
          "description": "min=0.141, mean=0.141, max=0.141, sum=0.141 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25351615672342864,
          "description": "min=0.254, mean=0.254, max=0.254, sum=0.254 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12000000000000001,
          "description": "min=0.12, mean=0.12, max=0.12, sum=0.12 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4539999913132661,
          "description": "min=0.454, mean=0.454, max=0.454, sum=0.454 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09989902749544036,
          "description": "min=0.1, mean=0.1, max=0.1, sum=0.1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.09733177984986514,
          "description": "min=0.097, mean=0.097, max=0.097, sum=0.097 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04045821313550608,
          "description": "min=0.04, mean=0.04, max=0.04, sum=0.04 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3833406193329736,
          "description": "min=0.09, mean=0.383, max=0.8, sum=6.9 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6612967467806994,
          "description": "min=0.2, mean=0.661, max=0.975, sum=7.274 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.40883441258094355,
          "markdown": false
        },
        {
          "value": 0.09791468112621773,
          "description": "min=0.08, mean=0.098, max=0.13, sum=0.49 (5)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.1268200294718189,
          "description": "min=0.127, mean=0.127, max=0.127, sum=0.127 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27605359630786236,
          "description": "min=0.276, mean=0.276, max=0.276, sum=0.276 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12699960693149975,
          "description": "min=0.127, mean=0.127, max=0.127, sum=0.127 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39598996118757757,
          "description": "min=0.396, mean=0.396, max=0.396, sum=0.396 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13131742636553145,
          "description": "min=0.131, mean=0.131, max=0.131, sum=0.131 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.06284277332135296,
          "description": "min=0.063, mean=0.063, max=0.063, sum=0.063 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20649886073889429,
          "description": "min=0.206, mean=0.206, max=0.206, sum=0.206 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3047575712176879,
          "description": "min=0.109, mean=0.305, max=0.471, sum=5.486 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6475429539256364,
          "description": "min=0.3, mean=0.648, max=0.925, sum=7.123 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.38751156336725257,
          "markdown": false
        },
        {
          "value": 0.14292977551638825,
          "description": "min=0.092, mean=0.143, max=0.182, sum=0.715 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.034644312737608846,
          "description": "min=0.035, mean=0.035, max=0.035, sum=0.035 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24703559378209236,
          "description": "min=0.247, mean=0.247, max=0.247, sum=0.247 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14200000000000002,
          "description": "min=0.142, mean=0.142, max=0.142, sum=0.142 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4659999973351183,
          "description": "min=0.466, mean=0.466, max=0.466, sum=0.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07389119661461117,
          "description": "min=0.074, mean=0.074, max=0.074, sum=0.074 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23215642305686054,
          "description": "min=0.232, mean=0.232, max=0.232, sum=0.232 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15862422483580252,
          "description": "min=0.159, mean=0.159, max=0.159, sum=0.159 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10174488153691034,
          "description": "min=0.035, mean=0.102, max=0.234, sum=1.831 (18)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.69518288885631,
          "description": "min=0.175, mean=0.695, max=0.925, sum=7.647 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6523126734505088,
          "markdown": false
        },
        {
          "value": 0.12760096192658882,
          "description": "min=0.075, mean=0.128, max=0.196, sum=1.914 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1710477879835662,
          "description": "min=0.111, mean=0.171, max=0.205, sum=0.513 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03732324115716399,
          "description": "min=0.027, mean=0.037, max=0.058, sum=0.112 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021760896948719733,
          "description": "min=0.02, mean=0.022, max=0.023, sum=0.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07592608066404687,
          "description": "min=0.071, mean=0.076, max=0.082, sum=0.228 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02731272826999052,
          "description": "min=0.012, mean=0.027, max=0.043, sum=0.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.08770199071414088,
          "description": "min=0.04, mean=0.088, max=0.12, sum=0.351 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18041748611363093,
          "description": "min=0.117, mean=0.18, max=0.225, sum=0.541 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4864398714978027,
          "description": "min=0.22, mean=0.486, max=0.749, sum=26.268 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.225785860693393,
          "description": "min=0.045, mean=0.226, max=0.392, sum=7.451 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.40175763182238666,
          "markdown": false
        },
        {
          "value": 0.7076962372990694,
          "description": "min=0.619, mean=0.708, max=0.769, sum=10.615 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14717484078898194,
          "description": "min=0.114, mean=0.147, max=0.167, sum=0.442 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05960283323299867,
          "description": "min=0.029, mean=0.06, max=0.101, sum=0.179 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.019790335675494927,
          "description": "min=0.019, mean=0.02, max=0.02, sum=0.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08637064333353452,
          "description": "min=0.069, mean=0.086, max=0.12, sum=0.259 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.028959032200530792,
          "description": "min=0.012, mean=0.029, max=0.039, sum=0.087 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6789622806094777,
          "description": "min=0.621, mean=0.679, max=0.751, sum=2.716 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41834259640752514,
          "description": "min=0.369, mean=0.418, max=0.496, sum=1.255 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43669079652569004,
          "description": "min=0.108, mean=0.437, max=0.784, sum=23.581 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2780574023642052,
          "description": "min=0.011, mean=0.278, max=0.881, sum=9.176 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_calibration.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_calibration.json"
      }
    ],
    "name": "calibration"
  },
  {
    "title": "Robustness",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - EM (Robustness)",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "MMLU",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "BoolQ - EM (Robustness)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "BoolQ",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "NarrativeQA - F1 (Robustness)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NarrativeQA",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - F1 (Robustness)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (closed-book)",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - F1 (Robustness)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (open-book)",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "QuAC - F1 (Robustness)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "QuAC",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "HellaSwag - EM (Robustness)",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "HellaSwag",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "OpenbookQA - EM (Robustness)",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "OpenbookQA",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "TruthfulQA - EM (Robustness)",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "TruthfulQA",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "MS MARCO (regular) - RR@10 (Robustness)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nRR@10: Mean reciprocal rank at 10 in information retrieval.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "RR@10",
          "run_group": "MS MARCO (regular)",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "MS MARCO (TREC) - NDCG@10 (Robustness)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nNDCG@10: Normalized discounted cumulative gain at 10 in information retrieval.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "NDCG@10",
          "run_group": "MS MARCO (TREC)",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "IMDB - EM (Robustness)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "IMDB",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "CivilComments - EM (Robustness)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "CivilComments",
          "perturbation": "Robustness"
        }
      },
      {
        "value": "RAFT - EM (Robustness)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Robustness: Computes worst case over different robustness perturbations (misspellings, formatting, contrast sets).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "RAFT",
          "perturbation": "Robustness"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4518627645991383,
          "markdown": false
        },
        {
          "value": 0.22085380116959066,
          "description": "min=0.15, mean=0.221, max=0.31, sum=3.313 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6496666666666667,
          "description": "min=0.635, mean=0.65, max=0.659, sum=1.949 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5232968431666949,
          "description": "min=0.448, mean=0.523, max=0.573, sum=1.57 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17889901825749613,
          "description": "min=0.177, mean=0.179, max=0.183, sum=0.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5031073713472458,
          "description": "min=0.487, mean=0.503, max=0.515, sum=1.509 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22242500588714678,
          "description": "min=0.216, mean=0.222, max=0.232, sum=0.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.726,
          "description": "min=0.726, mean=0.726, max=0.726, sum=0.726 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43,
          "description": "min=0.43, mean=0.43, max=0.43, sum=0.43 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15392456676860347,
          "description": "min=0.13, mean=0.154, max=0.176, sum=0.462 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14417447089947086,
          "description": "min=0.131, mean=0.144, max=0.157, sum=0.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3070790784160127,
          "description": "min=0.276, mean=0.307, max=0.347, sum=0.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9226666666666666,
          "description": "min=0.917, mean=0.923, max=0.934, sum=2.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2712865813183887,
          "description": "min=0.027, mean=0.271, max=0.732, sum=14.649 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5545454545454546,
          "description": "min=0.025, mean=0.555, max=0.875, sum=18.3 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29777282413544925,
          "markdown": false
        },
        {
          "value": 0.20011695906432747,
          "description": "min=0.16, mean=0.2, max=0.272, sum=3.002 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5670000000000001,
          "description": "min=0.539, mean=0.567, max=0.603, sum=1.701 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4003895179156612,
          "description": "min=0.341, mean=0.4, max=0.438, sum=1.201 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.097632746101742,
          "description": "min=0.092, mean=0.098, max=0.106, sum=0.293 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4099829032840138,
          "description": "min=0.361, mean=0.41, max=0.455, sum=1.23 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19699898429353593,
          "description": "min=0.186, mean=0.197, max=0.209, sum=0.591 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.646,
          "description": "min=0.646, mean=0.646, max=0.646, sum=0.646 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.412,
          "description": "min=0.412, mean=0.412, max=0.412, sum=0.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15494393476044852,
          "description": "min=0.138, mean=0.155, max=0.168, sum=0.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10499510582010585,
          "description": "min=0.089, mean=0.105, max=0.128, sum=0.315 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24769351383898738,
          "description": "min=0.231, mean=0.248, max=0.274, sum=0.743 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.932,
          "description": "min=0.927, mean=0.932, max=0.936, sum=2.796 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4438230435194026,
          "description": "min=0, mean=0.444, max=0.984, sum=23.966 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4431818181818182,
          "description": "min=0.025, mean=0.443, max=0.95, sum=14.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4225080073800875,
          "markdown": false
        },
        {
          "value": 0.22511111111111112,
          "description": "min=0.15, mean=0.225, max=0.27, sum=3.377 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6429999999999999,
          "description": "min=0.632, mean=0.643, max=0.658, sum=1.929 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47749086119263257,
          "description": "min=0.409, mean=0.477, max=0.522, sum=1.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17025794044565556,
          "description": "min=0.164, mean=0.17, max=0.175, sum=0.511 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4776074011626843,
          "description": "min=0.449, mean=0.478, max=0.494, sum=1.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21921244416502939,
          "description": "min=0.215, mean=0.219, max=0.227, sum=0.658 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.695,
          "description": "min=0.695, mean=0.695, max=0.695, sum=0.695 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.424,
          "description": "min=0.424, mean=0.424, max=0.424, sum=0.424 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1416921508664628,
          "description": "min=0.116, mean=0.142, max=0.159, sum=0.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12069748677248683,
          "description": "min=0.105, mean=0.121, max=0.133, sum=0.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29680328755123014,
          "description": "min=0.27, mean=0.297, max=0.328, sum=0.89 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9406666666666667,
          "description": "min=0.932, mean=0.941, max=0.948, sum=2.822 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41686056018907397,
          "description": "min=0.014, mean=0.417, max=0.938, sum=22.51 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5128787878787878,
          "description": "min=0.025, mean=0.513, max=0.775, sum=16.925 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7106770870953296,
          "markdown": false
        },
        {
          "value": 0.39245614035087717,
          "description": "min=0.2, mean=0.392, max=0.73, sum=5.887 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6923333333333334,
          "description": "min=0.669, mean=0.692, max=0.714, sum=2.077 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5646966401263148,
          "description": "min=0.484, mean=0.565, max=0.616, sum=1.694 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2349124459413927,
          "description": "min=0.23, mean=0.235, max=0.241, sum=0.705 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5603824984507094,
          "description": "min=0.556, mean=0.56, max=0.568, sum=1.681 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2506588392587418,
          "description": "min=0.232, mean=0.251, max=0.261, sum=0.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.732,
          "description": "min=0.732, mean=0.732, max=0.732, sum=0.732 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.474,
          "description": "min=0.474, mean=0.474, max=0.474, sum=0.474 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25178389398572887,
          "description": "min=0.216, mean=0.252, max=0.294, sum=0.755 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22205343915343892,
          "description": "min=0.207, mean=0.222, max=0.244, sum=0.666 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40738421631598776,
          "description": "min=0.361, mean=0.407, max=0.448, sum=1.222 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9470000000000001,
          "description": "min=0.931, mean=0.947, max=0.955, sum=2.841 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49514299676627055,
          "description": "min=0, mean=0.495, max=0.995, sum=26.738 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5545454545454547,
          "description": "min=0.025, mean=0.555, max=0.925, sum=18.3 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7910296229539834,
          "markdown": false
        },
        {
          "value": 0.41671345029239765,
          "description": "min=0.17, mean=0.417, max=0.75, sum=6.251 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7293333333333333,
          "description": "min=0.72, mean=0.729, max=0.736, sum=2.188 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6601600341725052,
          "description": "min=0.627, mean=0.66, max=0.69, sum=1.98 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3150688575152197,
          "description": "min=0.31, mean=0.315, max=0.318, sum=0.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5985032886794094,
          "description": "min=0.576, mean=0.599, max=0.616, sum=1.796 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3135172870245195,
          "description": "min=0.31, mean=0.314, max=0.316, sum=0.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.754,
          "description": "min=0.754, mean=0.754, max=0.754, sum=0.754 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47,
          "description": "min=0.47, mean=0.47, max=0.47, sum=0.47 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38990825688073394,
          "description": "min=0.326, mean=0.39, max=0.43, sum=1.17 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3372691798941794,
          "description": "min=0.333, mean=0.337, max=0.343, sum=1.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6069545244562901,
          "description": "min=0.569, mean=0.607, max=0.639, sum=1.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.896,
          "description": "min=0.878, mean=0.896, max=0.916, sum=2.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4485846578472439,
          "description": "min=0.009, mean=0.449, max=0.979, sum=24.224 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6901515151515151,
          "description": "min=0.225, mean=0.69, max=0.95, sum=22.775 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7641047680536001,
          "markdown": false
        },
        {
          "value": 0.41120467836257313,
          "description": "min=0.22, mean=0.411, max=0.68, sum=6.168 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.729,
          "description": "min=0.714, mean=0.729, max=0.743, sum=2.187 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5834381641862693,
          "description": "min=0.49, mean=0.583, max=0.65, sum=1.75 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28458982309414393,
          "description": "min=0.277, mean=0.285, max=0.29, sum=0.854 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5635162273229849,
          "description": "min=0.555, mean=0.564, max=0.568, sum=1.691 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27557303329747496,
          "description": "min=0.271, mean=0.276, max=0.281, sum=0.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.755,
          "description": "min=0.755, mean=0.755, max=0.755, sum=0.755 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.474,
          "description": "min=0.474, mean=0.474, max=0.474, sum=0.474 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29255861365953106,
          "description": "min=0.245, mean=0.293, max=0.326, sum=0.878 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22687976190476158,
          "description": "min=0.18, mean=0.227, max=0.253, sum=0.681 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42305953691791237,
          "description": "min=0.406, mean=0.423, max=0.451, sum=1.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9279999999999999,
          "description": "min=0.915, mean=0.928, max=0.949, sum=2.784 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4875180109221431,
          "description": "min=0, mean=0.488, max=0.986, sum=26.326 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6181818181818182,
          "description": "min=0.025, mean=0.618, max=0.875, sum=20.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5267325431952796,
          "markdown": false
        },
        {
          "value": 0.2625146198830409,
          "description": "min=0.17, mean=0.263, max=0.42, sum=3.938 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6073333333333334,
          "description": "min=0.602, mean=0.607, max=0.615, sum=1.822 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18733342573827472,
          "description": "min=0.177, mean=0.187, max=0.195, sum=0.562 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5031846716563587,
          "description": "min=0.485, mean=0.503, max=0.529, sum=1.51 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.687,
          "description": "min=0.687, mean=0.687, max=0.687, sum=0.687 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.448,
          "description": "min=0.448, mean=0.448, max=0.448, sum=0.448 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20998980632008157,
          "description": "min=0.197, mean=0.21, max=0.228, sum=0.63 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1774849206349205,
          "description": "min=0.168, mean=0.177, max=0.186, sum=0.532 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39737317282374035,
          "description": "min=0.391, mean=0.397, max=0.403, sum=1.192 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9406666666666667,
          "description": "min=0.935, mean=0.941, max=0.946, sum=2.822 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4686089323926605,
          "description": "min=0.116, mean=0.469, max=0.844, sum=25.305 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49772727272727263,
          "description": "min=0, mean=0.498, max=0.975, sum=16.425 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.31855477855477854,
          "markdown": false
        },
        {
          "value": 0.1826549707602339,
          "description": "min=0.1, mean=0.183, max=0.27, sum=2.74 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.655,
          "description": "min=0.643, mean=0.655, max=0.673, sum=1.965 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4761726989393548,
          "description": "min=0.444, mean=0.476, max=0.505, sum=1.429 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1628593597054443,
          "description": "min=0.157, mean=0.163, max=0.168, sum=0.489 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4912891920785376,
          "description": "min=0.484, mean=0.491, max=0.498, sum=1.474 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18543862521458307,
          "description": "min=0.166, mean=0.185, max=0.212, sum=0.556 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.11162079510703364,
          "description": "min=0.107, mean=0.112, max=0.118, sum=0.335 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.8873333333333333,
          "description": "min=0.864, mean=0.887, max=0.918, sum=2.662 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.416268791059841,
          "description": "min=0, mean=0.416, max=0.99, sum=22.479 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4015151515151515,
          "description": "min=0, mean=0.402, max=0.975, sum=13.25 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.42993006993006994,
          "markdown": false
        },
        {
          "value": 0.23008187134502922,
          "description": "min=0.1, mean=0.23, max=0.37, sum=3.451 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6586666666666666,
          "description": "min=0.637, mean=0.659, max=0.7, sum=1.976 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.513450295883327,
          "description": "min=0.481, mean=0.513, max=0.539, sum=1.54 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.211552896733343,
          "description": "min=0.205, mean=0.212, max=0.218, sum=0.635 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5239378524073847,
          "description": "min=0.515, mean=0.524, max=0.537, sum=1.572 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1926796273359054,
          "description": "min=0.188, mean=0.193, max=0.201, sum=0.578 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15137614678899083,
          "description": "min=0.139, mean=0.151, max=0.161, sum=0.454 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9199999999999999,
          "description": "min=0.913, mean=0.92, max=0.933, sum=2.76 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36816849425853654,
          "description": "min=0.011, mean=0.368, max=0.874, sum=19.881 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43636363636363645,
          "description": "min=0, mean=0.436, max=0.825, sum=14.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5464102564102564,
          "markdown": false
        },
        {
          "value": 0.2547368421052632,
          "description": "min=0.08, mean=0.255, max=0.51, sum=3.821 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6653333333333333,
          "description": "min=0.624, mean=0.665, max=0.693, sum=1.996 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5902392957151222,
          "description": "min=0.557, mean=0.59, max=0.617, sum=1.771 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25230806968086933,
          "description": "min=0.243, mean=0.252, max=0.261, sum=0.757 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5861072363623724,
          "description": "min=0.576, mean=0.586, max=0.593, sum=1.758 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23311906486145426,
          "description": "min=0.221, mean=0.233, max=0.24, sum=0.699 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.10601427115188583,
          "description": "min=0.092, mean=0.106, max=0.121, sum=0.318 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9323333333333333,
          "description": "min=0.931, mean=0.932, max=0.934, sum=2.797 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26255411827214337,
          "description": "min=0.035, mean=0.263, max=0.67, sum=14.178 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5636363636363637,
          "description": "min=0, mean=0.564, max=0.975, sum=18.6 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8178973356392711,
          "markdown": false
        },
        {
          "value": 0.43421052631578944,
          "description": "min=0.17, mean=0.434, max=0.76, sum=6.513 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7563333333333334,
          "description": "min=0.751, mean=0.756, max=0.76, sum=2.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6634443166549867,
          "description": "min=0.622, mean=0.663, max=0.693, sum=1.99 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24480135198778494,
          "description": "min=0.239, mean=0.245, max=0.248, sum=0.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6323821508652113,
          "description": "min=0.608, mean=0.632, max=0.646, sum=1.897 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31252831855461766,
          "description": "min=0.303, mean=0.313, max=0.324, sum=0.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.766,
          "description": "min=0.766, mean=0.766, max=0.766, sum=0.766 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.472,
          "description": "min=0.472, mean=0.472, max=0.472, sum=0.472 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3260703363914373,
          "description": "min=0.263, mean=0.326, max=0.388, sum=1.304 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.28, mean=0.308, max=0.326, sum=0.925 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.589, mean=0.592, max=0.594, sum=1.776 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9276666666666666,
          "description": "min=0.921, mean=0.928, max=0.94, sum=2.783 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5139820592784173,
          "description": "min=0.105, mean=0.514, max=0.854, sum=27.755 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6000000000000001,
          "description": "min=0.225, mean=0.6, max=0.95, sum=19.8 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5409357605686861,
          "markdown": false
        },
        {
          "value": 0.25025730994152046,
          "description": "min=0.167, mean=0.25, max=0.38, sum=3.754 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.642,
          "description": "min=0.595, mean=0.642, max=0.674, sum=1.926 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5303029858435905,
          "description": "min=0.468, mean=0.53, max=0.574, sum=1.591 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18537100322417385,
          "description": "min=0.18, mean=0.185, max=0.19, sum=0.556 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5582069622847597,
          "description": "min=0.547, mean=0.558, max=0.569, sum=1.675 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23376457225319638,
          "description": "min=0.229, mean=0.234, max=0.24, sum=0.701 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.699,
          "description": "min=0.699, mean=0.699, max=0.699, sum=0.699 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.438,
          "description": "min=0.438, mean=0.438, max=0.438, sum=0.438 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1834862385321101,
          "description": "min=0.168, mean=0.183, max=0.206, sum=0.734 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18996269841269822,
          "description": "min=0.158, mean=0.19, max=0.218, sum=0.57 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33254039819149694,
          "description": "min=0.304, mean=0.333, max=0.385, sum=0.998 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9203333333333333,
          "description": "min=0.907, mean=0.92, max=0.927, sum=2.761 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46652660062188434,
          "description": "min=0.088, mean=0.467, max=0.827, sum=25.192 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5265151515151515,
          "description": "min=0.175, mean=0.527, max=0.95, sum=17.375 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2275932400932401,
          "markdown": false
        },
        {
          "value": 0.37832748538011696,
          "description": "min=0.25, mean=0.378, max=0.62, sum=5.675 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.09874765137769782,
          "description": "min=0.087, mean=0.099, max=0.105, sum=0.296 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.030683511825215847,
          "description": "min=0.03, mean=0.031, max=0.032, sum=0.092 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12220564653363493,
          "description": "min=0.101, mean=0.122, max=0.135, sum=0.367 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07065126152546952,
          "description": "min=0.071, mean=0.071, max=0.071, sum=0.212 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3650611620795107,
          "description": "min=0.33, mean=0.365, max=0.411, sum=1.46 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17033333333333334,
          "description": "min=0.13, mean=0.17, max=0.227, sum=0.511 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.0871064519307774,
          "description": "min=0, mean=0.087, max=0.824, sum=4.704 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08484848484848484,
          "description": "min=0, mean=0.085, max=0.775, sum=2.8 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5061059259613209,
          "markdown": false
        },
        {
          "value": 0.28992982456140354,
          "description": "min=0.158, mean=0.29, max=0.51, sum=4.349 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.614,
          "description": "min=0.601, mean=0.614, max=0.622, sum=1.842 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38251983624053415,
          "description": "min=0.331, mean=0.383, max=0.42, sum=1.148 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23753663022529162,
          "description": "min=0.233, mean=0.238, max=0.241, sum=0.713 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4713418135089589,
          "description": "min=0.411, mean=0.471, max=0.518, sum=1.414 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2154779030326859,
          "description": "min=0.214, mean=0.215, max=0.216, sum=0.646 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.759,
          "description": "min=0.759, mean=0.759, max=0.759, sum=0.759 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.448,
          "description": "min=0.448, mean=0.448, max=0.448, sum=0.448 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15137614678899083,
          "description": "min=0.122, mean=0.151, max=0.182, sum=0.454 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20732857142857117,
          "description": "min=0.191, mean=0.207, max=0.223, sum=0.622 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39663320695609633,
          "description": "min=0.371, mean=0.397, max=0.414, sum=1.19 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9226666666666667,
          "description": "min=0.907, mean=0.923, max=0.933, sum=2.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31971446667223646,
          "description": "min=0, mean=0.32, max=0.817, sum=17.265 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5628787878787879,
          "description": "min=0, mean=0.563, max=0.925, sum=18.575 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3450884302942145,
          "markdown": false
        },
        {
          "value": 0.25327485380116954,
          "description": "min=0.15, mean=0.253, max=0.35, sum=3.799 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.545,
          "description": "min=0.514, mean=0.545, max=0.566, sum=1.635 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3573511654752053,
          "description": "min=0.318, mean=0.357, max=0.38, sum=1.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17161461010403287,
          "description": "min=0.16, mean=0.172, max=0.18, sum=0.515 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3470084296370371,
          "description": "min=0.287, mean=0.347, max=0.38, sum=1.041 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20424911828028136,
          "description": "min=0.197, mean=0.204, max=0.211, sum=0.613 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.687,
          "description": "min=0.687, mean=0.687, max=0.687, sum=0.687 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43,
          "description": "min=0.43, mean=0.43, max=0.43, sum=0.43 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15392456676860344,
          "description": "min=0.141, mean=0.154, max=0.173, sum=0.462 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1300338624338624,
          "description": "min=0.109, mean=0.13, max=0.147, sum=0.39 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2574506868270638,
          "description": "min=0.195, mean=0.257, max=0.323, sum=0.772 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.902,
          "description": "min=0.895, mean=0.902, max=0.91, sum=2.706 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3329825600043121,
          "description": "min=0, mean=0.333, max=0.95, sum=17.981 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49015151515151517,
          "description": "min=0, mean=0.49, max=0.975, sum=16.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.18793903538063716,
          "markdown": false
        },
        {
          "value": 0.18368421052631578,
          "description": "min=0.09, mean=0.184, max=0.24, sum=2.755 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5619999999999999,
          "description": "min=0.556, mean=0.562, max=0.573, sum=1.686 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29964626689663526,
          "description": "min=0.283, mean=0.3, max=0.315, sum=0.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10170384904294616,
          "description": "min=0.097, mean=0.102, max=0.104, sum=0.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26631844818771483,
          "description": "min=0.226, mean=0.266, max=0.292, sum=0.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14398518012537756,
          "description": "min=0.12, mean=0.144, max=0.157, sum=0.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.651,
          "description": "min=0.651, mean=0.651, max=0.651, sum=0.651 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.382,
          "description": "min=0.382, mean=0.382, max=0.382, sum=0.382 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1493374108053007,
          "description": "min=0.127, mean=0.149, max=0.168, sum=0.448 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10871957671957677,
          "description": "min=0.101, mean=0.109, max=0.12, sum=0.326 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31504083631376195,
          "description": "min=0.294, mean=0.315, max=0.354, sum=0.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8886666666666666,
          "description": "min=0.878, mean=0.889, max=0.897, sum=2.666 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13632694985889793,
          "description": "min=0, mean=0.136, max=0.736, sum=7.362 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3848484848484848,
          "description": "min=0, mean=0.385, max=0.975, sum=12.7 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1469566826886926,
          "markdown": false
        },
        {
          "value": 0.22644444444444442,
          "description": "min=0.13, mean=0.226, max=0.42, sum=3.397 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.361,
          "description": "min=0.352, mean=0.361, max=0.378, sum=1.083 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07821074014295328,
          "description": "min=0.076, mean=0.078, max=0.081, sum=0.235 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.025009279663584086,
          "description": "min=0.024, mean=0.025, max=0.027, sum=0.075 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07408175909872887,
          "description": "min=0.066, mean=0.074, max=0.08, sum=0.222 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09766108203425072,
          "description": "min=0.094, mean=0.098, max=0.101, sum=0.293 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.405,
          "description": "min=0.405, mean=0.405, max=0.405, sum=0.405 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.238,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2038735983690112,
          "description": "min=0.2, mean=0.204, max=0.211, sum=0.612 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2521940956196658,
          "description": "min=0.22, mean=0.252, max=0.287, sum=0.757 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4726666666666666,
          "description": "min=0.447, mean=0.473, max=0.498, sum=1.418 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4342847473494527,
          "description": "min=0, mean=0.434, max=1, sum=23.451 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40303030303030307,
          "description": "min=0, mean=0.403, max=0.975, sum=13.3 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5964421748070247,
          "markdown": false
        },
        {
          "value": 0.29933333333333334,
          "description": "min=0.12, mean=0.299, max=0.6, sum=4.49 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7176666666666667,
          "description": "min=0.712, mean=0.718, max=0.722, sum=2.153 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3901906178600691,
          "description": "min=0.313, mean=0.39, max=0.434, sum=1.171 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28349840532468856,
          "description": "min=0.276, mean=0.283, max=0.288, sum=0.85 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.532530651706331,
          "description": "min=0.49, mean=0.533, max=0.555, sum=1.598 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22865454547247813,
          "description": "min=0.221, mean=0.229, max=0.234, sum=0.686 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.764,
          "description": "min=0.764, mean=0.764, max=0.764, sum=0.764 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.482,
          "description": "min=0.482, mean=0.482, max=0.482, sum=0.482 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1162079510703364,
          "description": "min=0.106, mean=0.116, max=0.13, sum=0.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24177817460317433,
          "description": "min=0.201, mean=0.242, max=0.292, sum=0.725 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48206153384583117,
          "description": "min=0.449, mean=0.482, max=0.527, sum=1.446 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.923,
          "description": "min=0.907, mean=0.923, max=0.933, sum=2.769 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.408272754767954,
          "description": "min=0.012, mean=0.408, max=0.908, sum=22.047 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48863636363636365,
          "description": "min=0, mean=0.489, max=0.925, sum=16.125 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.26965587249235745,
          "markdown": false
        },
        {
          "value": 0.20667836257309943,
          "description": "min=0.15, mean=0.207, max=0.25, sum=3.1 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.54,
          "description": "min=0.508, mean=0.54, max=0.568, sum=1.62 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2960125312478054,
          "description": "min=0.265, mean=0.296, max=0.321, sum=0.888 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10457862657700777,
          "description": "min=0.099, mean=0.105, max=0.11, sum=0.314 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22177043436006846,
          "description": "min=0.164, mean=0.222, max=0.282, sum=0.665 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15189850694469184,
          "description": "min=0.127, mean=0.152, max=0.171, sum=0.456 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.687,
          "description": "min=0.687, mean=0.687, max=0.687, sum=0.687 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.414,
          "description": "min=0.414, mean=0.414, max=0.414, sum=0.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17023445463812437,
          "description": "min=0.156, mean=0.17, max=0.19, sum=0.511 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12963544973544971,
          "description": "min=0.11, mean=0.13, max=0.144, sum=0.389 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3140445596258007,
          "description": "min=0.265, mean=0.314, max=0.339, sum=0.942 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8883333333333333,
          "description": "min=0.878, mean=0.888, max=0.896, sum=2.665 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35349935695509527,
          "description": "min=0, mean=0.353, max=0.931, sum=19.089 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5015151515151515,
          "description": "min=0.025, mean=0.502, max=0.975, sum=16.55 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6159776448986682,
          "markdown": false
        },
        {
          "value": 0.33394152046783626,
          "description": "min=0.2, mean=0.334, max=0.54, sum=5.009 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7253333333333334,
          "description": "min=0.715, mean=0.725, max=0.743, sum=2.176 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5285770759196127,
          "description": "min=0.515, mean=0.529, max=0.539, sum=1.586 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.163031767310864,
          "description": "min=0.156, mean=0.163, max=0.171, sum=0.489 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6050162193677248,
          "description": "min=0.596, mean=0.605, max=0.616, sum=1.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17034790269142241,
          "description": "min=0.159, mean=0.17, max=0.178, sum=0.511 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.696,
          "description": "min=0.696, mean=0.696, max=0.696, sum=0.696 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.448,
          "description": "min=0.448, mean=0.448, max=0.448, sum=0.448 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17074413863404692,
          "description": "min=0.168, mean=0.171, max=0.174, sum=0.512 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.386937698412698,
          "description": "min=0.372, mean=0.387, max=0.401, sum=1.161 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6845367765287401,
          "description": "min=0.68, mean=0.685, max=0.689, sum=2.054 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9206666666666669,
          "description": "min=0.917, mean=0.921, max=0.925, sum=2.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46778473308233626,
          "description": "min=0, mean=0.468, max=1, sum=25.26 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5522727272727274,
          "description": "min=0, mean=0.552, max=0.975, sum=18.225 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8502739196287583,
          "markdown": false
        },
        {
          "value": 0.38711111111111113,
          "description": "min=0.15, mean=0.387, max=0.73, sum=5.807 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8106666666666666,
          "description": "min=0.806, mean=0.811, max=0.816, sum=2.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5702997988620334,
          "description": "min=0.566, mean=0.57, max=0.578, sum=1.711 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28891923018489013,
          "description": "min=0.286, mean=0.289, max=0.294, sum=0.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6786112890887687,
          "description": "min=0.669, mean=0.679, max=0.685, sum=2.036 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23825281130135667,
          "description": "min=0.236, mean=0.238, max=0.24, sum=0.715 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.774,
          "description": "min=0.774, mean=0.774, max=0.774, sum=0.774 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.492,
          "description": "min=0.492, mean=0.492, max=0.492, sum=0.492 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2293577981651376,
          "description": "min=0.226, mean=0.229, max=0.231, sum=0.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43439140211640154,
          "description": "min=0.429, mean=0.434, max=0.438, sum=1.303 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7339375978505934,
          "description": "min=0.726, mean=0.734, max=0.743, sum=2.202 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.9330000000000002,
          "description": "min=0.929, mean=0.933, max=0.936, sum=2.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5345588668880686,
          "description": "min=0.205, mean=0.535, max=0.84, sum=28.866 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5992424242424242,
          "description": "min=0, mean=0.599, max=0.975, sum=19.775 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29051104623963353,
          "markdown": false
        },
        {
          "value": 0.2174502923976608,
          "description": "min=0.11, mean=0.217, max=0.28, sum=3.262 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.621,
          "description": "min=0.608, mean=0.621, max=0.631, sum=1.863 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1349521611222693,
          "description": "min=0.099, mean=0.135, max=0.156, sum=0.405 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09933930594531819,
          "description": "min=0.09, mean=0.099, max=0.109, sum=0.298 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22767804828628146,
          "description": "min=0.185, mean=0.228, max=0.265, sum=0.683 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14672783806116493,
          "description": "min=0.14, mean=0.147, max=0.155, sum=0.44 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.619,
          "description": "min=0.619, mean=0.619, max=0.619, sum=0.619 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.398,
          "description": "min=0.398, mean=0.398, max=0.398, sum=0.398 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1811926605504587,
          "description": "min=0.157, mean=0.181, max=0.209, sum=0.725 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11636587301587299,
          "description": "min=0.094, mean=0.116, max=0.131, sum=0.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3190834142643501,
          "description": "min=0.29, mean=0.319, max=0.336, sum=0.957 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.903,
          "description": "min=0.895, mean=0.903, max=0.908, sum=2.709 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4184575354873046,
          "description": "min=0, mean=0.418, max=1, sum=22.597 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5303030303030303,
          "description": "min=0.1, mean=0.53, max=0.975, sum=17.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3361523348731358,
          "markdown": false
        },
        {
          "value": 0.1888421052631579,
          "description": "min=0.149, mean=0.189, max=0.24, sum=2.833 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.551,
          "description": "min=0.548, mean=0.551, max=0.556, sum=1.653 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4211068794456416,
          "description": "min=0.378, mean=0.421, max=0.443, sum=1.263 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1325934362402064,
          "description": "min=0.125, mean=0.133, max=0.14, sum=0.398 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4524359199313521,
          "description": "min=0.429, mean=0.452, max=0.48, sum=1.357 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19141062427574787,
          "description": "min=0.176, mean=0.191, max=0.202, sum=0.574 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.661,
          "description": "min=0.661, mean=0.661, max=0.661, sum=0.661 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.414,
          "description": "min=0.414, mean=0.414, max=0.414, sum=0.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17507645259938837,
          "description": "min=0.144, mean=0.175, max=0.225, sum=0.7 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09600105820105831,
          "description": "min=0.082, mean=0.096, max=0.107, sum=0.288 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3510422646487042,
          "description": "min=0.338, mean=0.351, max=0.365, sum=1.053 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9119999999999999,
          "description": "min=0.906, mean=0.912, max=0.921, sum=2.736 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4796354739742704,
          "description": "min=0, mean=0.48, max=1, sum=25.9 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39924242424242423,
          "description": "min=0, mean=0.399, max=0.975, sum=13.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1820979020979021,
          "markdown": false
        },
        {
          "value": 0.20063157894736844,
          "description": "min=0.12, mean=0.201, max=0.263, sum=1.003 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.527,
          "description": "min=0.527, mean=0.527, max=0.527, sum=0.527 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31250255336597976,
          "description": "min=0.313, mean=0.313, max=0.313, sum=0.313 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09385332819874069,
          "description": "min=0.094, mean=0.094, max=0.094, sum=0.094 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39128308105054077,
          "description": "min=0.391, mean=0.391, max=0.391, sum=0.391 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17097990289529255,
          "description": "min=0.171, mean=0.171, max=0.171, sum=0.171 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.13914373088685014,
          "description": "min=0.139, mean=0.139, max=0.139, sum=0.139 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.871,
          "description": "min=0.871, mean=0.871, max=0.871, sum=0.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3628308048007681,
          "description": "min=0.013, mean=0.363, max=0.915, sum=6.531 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3772727272727272,
          "description": "min=0.075, mean=0.377, max=0.975, sum=4.15 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.27195804195804196,
          "markdown": false
        },
        {
          "value": 0.22035087719298244,
          "description": "min=0.17, mean=0.22, max=0.28, sum=1.102 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.51,
          "description": "min=0.51, mean=0.51, max=0.51, sum=0.51 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42022169799567144,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10849928114746796,
          "description": "min=0.108, mean=0.108, max=0.108, sum=0.108 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46990137932247006,
          "description": "min=0.47, mean=0.47, max=0.47, sum=0.47 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17120890749036072,
          "description": "min=0.171, mean=0.171, max=0.171, sum=0.171 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.13761467889908258,
          "description": "min=0.138, mean=0.138, max=0.138, sum=0.138 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.854,
          "description": "min=0.854, mean=0.854, max=0.854, sum=0.854 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41812542395705293,
          "description": "min=0.02, mean=0.418, max=0.973, sum=7.526 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45,
          "description": "min=0, mean=0.45, max=0.975, sum=4.95 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.16445221445221445,
          "markdown": false
        },
        {
          "value": 0.25776608187134503,
          "description": "min=0.19, mean=0.258, max=0.38, sum=3.866 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6503333333333333,
          "description": "min=0.624, mean=0.65, max=0.688, sum=1.951 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04518225074755041,
          "description": "min=0.045, mean=0.045, max=0.045, sum=0.136 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15251804391476487,
          "description": "min=0.146, mean=0.153, max=0.159, sum=0.458 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0710016541484974,
          "description": "min=0.047, mean=0.071, max=0.107, sum=0.213 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06378325242260692,
          "description": "min=0.064, mean=0.064, max=0.064, sum=0.191 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.12232415902140673,
          "description": "min=0.09, mean=0.122, max=0.148, sum=0.489 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3036666666666667,
          "description": "min=0.17, mean=0.304, max=0.51, sum=0.911 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39212772273586344,
          "description": "min=0, mean=0.392, max=0.991, sum=21.175 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33106060606060606,
          "description": "min=0, mean=0.331, max=0.875, sum=10.925 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2572027972027972,
          "markdown": false
        },
        {
          "value": 0.2719415204678362,
          "description": "min=0.2, mean=0.272, max=0.37, sum=4.079 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.646,
          "description": "min=0.638, mean=0.646, max=0.651, sum=1.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05920683866208649,
          "description": "min=0.059, mean=0.059, max=0.059, sum=0.178 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1409495030072503,
          "description": "min=0.139, mean=0.141, max=0.143, sum=0.423 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2906387285430619,
          "description": "min=0.154, mean=0.291, max=0.365, sum=0.872 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11096938073772407,
          "description": "min=0.111, mean=0.111, max=0.111, sum=0.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17775229357798167,
          "description": "min=0.162, mean=0.178, max=0.209, sum=0.711 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27566666666666667,
          "description": "min=0.091, mean=0.276, max=0.485, sum=0.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4498711194026963,
          "description": "min=0, mean=0.45, max=0.983, sum=24.293 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3492424242424242,
          "description": "min=0, mean=0.349, max=0.95, sum=11.525 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5191448151403657,
          "markdown": false
        },
        {
          "value": 0.2698479532163743,
          "description": "min=0.13, mean=0.27, max=0.45, sum=4.048 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.623,
          "description": "min=0.584, mean=0.623, max=0.662, sum=1.869 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4090933797146052,
          "description": "min=0.365, mean=0.409, max=0.447, sum=1.227 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2076699169323979,
          "description": "min=0.202, mean=0.208, max=0.213, sum=0.623 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40794279599736244,
          "description": "min=0.382, mean=0.408, max=0.445, sum=1.224 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2000302607507829,
          "description": "min=0.194, mean=0.2, max=0.209, sum=0.6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.744,
          "description": "min=0.744, mean=0.744, max=0.744, sum=0.744 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.488,
          "description": "min=0.488, mean=0.488, max=0.488, sum=0.488 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20451070336391436,
          "description": "min=0.167, mean=0.205, max=0.249, sum=0.818 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23496613756613724,
          "description": "min=0.198, mean=0.235, max=0.263, sum=0.705 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4083455179340017,
          "description": "min=0.386, mean=0.408, max=0.422, sum=1.225 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9186666666666667,
          "description": "min=0.904, mean=0.919, max=0.937, sum=2.756 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18428995439708568,
          "description": "min=0, mean=0.184, max=0.769, sum=9.952 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4803030303030303,
          "description": "min=0, mean=0.48, max=0.975, sum=15.85 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.43828848200372117,
          "markdown": false
        },
        {
          "value": 0.21610526315789472,
          "description": "min=0.13, mean=0.216, max=0.32, sum=3.242 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6829999999999999,
          "description": "min=0.666, mean=0.683, max=0.701, sum=2.049 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39653941552028354,
          "description": "min=0.364, mean=0.397, max=0.421, sum=1.19 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20625206311676839,
          "description": "min=0.2, mean=0.206, max=0.216, sum=0.619 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45767430702477907,
          "description": "min=0.419, mean=0.458, max=0.503, sum=1.373 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19914898808715295,
          "description": "min=0.177, mean=0.199, max=0.217, sum=0.597 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.699,
          "description": "min=0.699, mean=0.699, max=0.699, sum=0.699 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45,
          "description": "min=0.45, mean=0.45, max=0.45, sum=0.45 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1735474006116208,
          "description": "min=0.135, mean=0.174, max=0.206, sum=0.694 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1788788359788358,
          "description": "min=0.175, mean=0.179, max=0.187, sum=0.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.436684763137285,
          "description": "min=0.421, mean=0.437, max=0.46, sum=1.31 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8863333333333333,
          "description": "min=0.872, mean=0.886, max=0.901, sum=2.659 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30478947142198615,
          "description": "min=0, mean=0.305, max=0.939, sum=16.459 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4045454545454546,
          "description": "min=0.025, mean=0.405, max=0.85, sum=13.35 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.567972027972028,
          "markdown": false
        },
        {
          "value": 0.2676140350877193,
          "description": "min=0.18, mean=0.268, max=0.36, sum=1.338 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.688,
          "description": "min=0.688, mean=0.688, max=0.688, sum=0.688 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48451305318378857,
          "description": "min=0.485, mean=0.485, max=0.485, sum=0.485 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22150747696392029,
          "description": "min=0.222, mean=0.222, max=0.222, sum=0.222 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5190244505397503,
          "description": "min=0.519, mean=0.519, max=0.519, sum=0.519 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22309180806281237,
          "description": "min=0.223, mean=0.223, max=0.223, sum=0.223 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22935779816513763,
          "description": "min=0.229, mean=0.229, max=0.229, sum=0.229 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.897,
          "description": "min=0.897, mean=0.897, max=0.897, sum=0.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4924249260198337,
          "description": "min=0.012, mean=0.492, max=0.958, sum=8.864 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4863636363636364,
          "description": "min=0, mean=0.486, max=0.95, sum=5.35 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6374592074592075,
          "markdown": false
        },
        {
          "value": 0.3696140350877193,
          "description": "min=0.14, mean=0.37, max=0.68, sum=1.848 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.67,
          "description": "min=0.67, mean=0.67, max=0.67, sum=0.67 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.543905538434645,
          "description": "min=0.544, mean=0.544, max=0.544, sum=0.544 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27211691617574163,
          "description": "min=0.272, mean=0.272, max=0.272, sum=0.272 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5559403134593146,
          "description": "min=0.556, mean=0.556, max=0.556, sum=0.556 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19407861446110536,
          "description": "min=0.194, mean=0.194, max=0.194, sum=0.194 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27370030581039756,
          "description": "min=0.274, mean=0.274, max=0.274, sum=0.274 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.875,
          "description": "min=0.875, mean=0.875, max=0.875, sum=0.875 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.529079897678074,
          "description": "min=0.079, mean=0.529, max=0.947, sum=9.523 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5590909090909091,
          "description": "min=0, mean=0.559, max=0.9, sum=6.15 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8149650349650349,
          "markdown": false
        },
        {
          "value": 0.4609122807017544,
          "description": "min=0.22, mean=0.461, max=0.82, sum=2.305 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.791,
          "description": "min=0.791, mean=0.791, max=0.791, sum=0.791 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6105202153922532,
          "description": "min=0.611, mean=0.611, max=0.611, sum=0.611 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36029476515740994,
          "description": "min=0.36, mean=0.36, max=0.36, sum=0.36 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6123442768470954,
          "description": "min=0.612, mean=0.612, max=0.612, sum=0.612 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27320176375521127,
          "description": "min=0.273, mean=0.273, max=0.273, sum=0.273 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.28134556574923547,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.893,
          "description": "min=0.893, mean=0.893, max=0.893, sum=0.893 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.503044804739656,
          "description": "min=0.016, mean=0.503, max=0.97, sum=9.055 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6704545454545454,
          "description": "min=0.05, mean=0.67, max=0.95, sum=7.375 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8851981351981352,
          "markdown": false
        },
        {
          "value": 0.5036842105263158,
          "description": "min=0.27, mean=0.504, max=0.81, sum=2.518 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.84,
          "description": "min=0.84, mean=0.84, max=0.84, sum=0.84 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5674436891870642,
          "description": "min=0.567, mean=0.567, max=0.567, sum=0.567 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3875883665002626,
          "description": "min=0.388, mean=0.388, max=0.388, sum=0.388 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.623794662165915,
          "description": "min=0.624, mean=0.624, max=0.624, sum=0.624 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2748605351114493,
          "description": "min=0.275, mean=0.275, max=0.275, sum=0.275 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.44801223241590216,
          "description": "min=0.448, mean=0.448, max=0.448, sum=0.448 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.935,
          "description": "min=0.935, mean=0.935, max=0.935, sum=0.935 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.565986035612513,
          "description": "min=0.247, mean=0.566, max=0.853, sum=10.188 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6545454545454545,
          "description": "min=0, mean=0.655, max=0.975, sum=7.2 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6437529137529138,
          "markdown": false
        },
        {
          "value": 0.37312280701754386,
          "description": "min=0.22, mean=0.373, max=0.57, sum=1.866 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.676,
          "description": "min=0.676, mean=0.676, max=0.676, sum=0.676 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5726018964106345,
          "description": "min=0.573, mean=0.573, max=0.573, sum=0.573 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2606038875824225,
          "description": "min=0.261, mean=0.261, max=0.261, sum=0.261 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5010811862440044,
          "description": "min=0.501, mean=0.501, max=0.501, sum=0.501 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27069315379336467,
          "description": "min=0.271, mean=0.271, max=0.271, sum=0.271 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23394495412844038,
          "description": "min=0.234, mean=0.234, max=0.234, sum=0.234 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.808,
          "description": "min=0.808, mean=0.808, max=0.808, sum=0.808 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5155612610622284,
          "description": "min=0.025, mean=0.516, max=0.989, sum=9.28 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5727272727272728,
          "description": "min=0.05, mean=0.573, max=0.875, sum=6.3 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8231701631701632,
          "markdown": false
        },
        {
          "value": 0.44438596491228066,
          "description": "min=0.22, mean=0.444, max=0.76, sum=2.222 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.753,
          "description": "min=0.753, mean=0.753, max=0.753, sum=0.753 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.681791424099214,
          "description": "min=0.682, mean=0.682, max=0.682, sum=0.682 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3243542710528751,
          "description": "min=0.324, mean=0.324, max=0.324, sum=0.324 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5631882717621935,
          "description": "min=0.563, mean=0.563, max=0.563, sum=0.563 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2939019916232739,
          "description": "min=0.294, mean=0.294, max=0.294, sum=0.294 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2874617737003058,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.954,
          "description": "min=0.954, mean=0.954, max=0.954, sum=0.954 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.47042658911281887,
          "description": "min=0.022, mean=0.47, max=0.958, sum=8.468 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6522727272727272,
          "description": "min=0.05, mean=0.652, max=0.95, sum=7.175 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9649184149184149,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5451929824561403,
          "description": "min=0.22, mean=0.545, max=0.9, sum=2.726 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.863,
          "description": "min=0.863, mean=0.863, max=0.863, sum=0.863 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7215317388650366,
          "description": "min=0.722, mean=0.722, max=0.722, sum=0.722 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.42009390434309946,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6385366212170214,
          "description": "min=0.639, mean=0.639, max=0.639, sum=0.639 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36189050917141447,
          "description": "min=0.362, mean=0.362, max=0.362, sum=0.362 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.46788990825688076,
          "description": "min=0.468, mean=0.468, max=0.468, sum=0.468 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.949,
          "description": "min=0.949, mean=0.949, max=0.949, sum=0.949 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5899239945803259,
          "description": "min=0.272, mean=0.59, max=0.884, sum=10.619 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6727272727272727,
          "description": "min=0.075, mean=0.673, max=0.975, sum=7.4 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37923076923076926,
          "markdown": false
        },
        {
          "value": 0.32410526315789473,
          "description": "min=0.18, mean=0.324, max=0.52, sum=1.621 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.643,
          "description": "min=0.643, mean=0.643, max=0.643, sum=0.643 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24590950452109447,
          "description": "min=0.246, mean=0.246, max=0.246, sum=0.246 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20255716308011695,
          "description": "min=0.203, mean=0.203, max=0.203, sum=0.203 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4912677371744195,
          "description": "min=0.491, mean=0.491, max=0.491, sum=0.491 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1604861950978603,
          "description": "min=0.16, mean=0.16, max=0.16, sum=0.16 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.19877675840978593,
          "description": "min=0.199, mean=0.199, max=0.199, sum=0.199 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.561,
          "description": "min=0.561, mean=0.561, max=0.561, sum=0.561 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4818807145268457,
          "description": "min=0.133, mean=0.482, max=0.844, sum=8.674 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42045454545454536,
          "description": "min=0, mean=0.42, max=0.875, sum=4.625 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.662027972027972,
          "markdown": false
        },
        {
          "value": 0.3710877192982456,
          "description": "min=0.175, mean=0.371, max=0.65, sum=1.855 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.672,
          "description": "min=0.672, mean=0.672, max=0.672, sum=0.672 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.499695916561912,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.213860378689308,
          "description": "min=0.214, mean=0.214, max=0.214, sum=0.214 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5393637207184442,
          "description": "min=0.539, mean=0.539, max=0.539, sum=0.539 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24986961512093836,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.25840978593272174,
          "description": "min=0.258, mean=0.258, max=0.258, sum=0.258 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.882,
          "description": "min=0.882, mean=0.882, max=0.882, sum=0.882 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5427815962078022,
          "description": "min=0.125, mean=0.543, max=0.918, sum=9.77 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6000000000000001,
          "description": "min=0, mean=0.6, max=0.85, sum=6.6 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7320745920745921,
          "markdown": false
        },
        {
          "value": 0.4133684210526316,
          "description": "min=0.237, mean=0.413, max=0.69, sum=2.067 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.757,
          "description": "min=0.757, mean=0.757, max=0.757, sum=0.757 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5253621693457193,
          "description": "min=0.525, mean=0.525, max=0.525, sum=0.525 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2732835109469542,
          "description": "min=0.273, mean=0.273, max=0.273, sum=0.273 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6205537766211775,
          "description": "min=0.621, mean=0.621, max=0.621, sum=0.621 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24738453163162216,
          "description": "min=0.247, mean=0.247, max=0.247, sum=0.247 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3409785932721712,
          "description": "min=0.341, mean=0.341, max=0.341, sum=0.341 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.674,
          "description": "min=0.674, mean=0.674, max=0.674, sum=0.674 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5932501359027997,
          "description": "min=0.177, mean=0.593, max=0.932, sum=10.679 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5909090909090909,
          "description": "min=0.025, mean=0.591, max=0.875, sum=6.5 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8963869463869464,
          "markdown": false
        },
        {
          "value": 0.5332280701754385,
          "description": "min=0.24, mean=0.533, max=0.82, sum=2.666 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.837,
          "description": "min=0.837, mean=0.837, max=0.837, sum=0.837 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6485445694648198,
          "description": "min=0.649, mean=0.649, max=0.649, sum=0.649 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3052498746141498,
          "description": "min=0.305, mean=0.305, max=0.305, sum=0.305 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6314234953832969,
          "description": "min=0.631, mean=0.631, max=0.631, sum=0.631 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3098633908730089,
          "description": "min=0.31, mean=0.31, max=0.31, sum=0.31 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3394495412844037,
          "description": "min=0.339, mean=0.339, max=0.339, sum=0.339 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.954,
          "description": "min=0.954, mean=0.954, max=0.954, sum=0.954 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5205335787071343,
          "description": "min=0.123, mean=0.521, max=0.842, sum=9.37 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6522727272727272,
          "description": "min=0.025, mean=0.652, max=0.975, sum=7.175 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6503510949562118,
          "markdown": false
        },
        {
          "value": 0.40336842105263154,
          "description": "min=0.15, mean=0.403, max=0.75, sum=6.051 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7326666666666667,
          "description": "min=0.724, mean=0.733, max=0.747, sum=2.198 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31894751591392195,
          "description": "min=0.22, mean=0.319, max=0.405, sum=0.957 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3074701383832172,
          "description": "min=0.291, mean=0.307, max=0.322, sum=0.922 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5253631735860874,
          "description": "min=0.483, mean=0.525, max=0.549, sum=1.576 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19421481147358363,
          "description": "min=0.183, mean=0.194, max=0.203, sum=0.583 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.757,
          "description": "min=0.757, mean=0.757, max=0.757, sum=0.757 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.476,
          "description": "min=0.476, mean=0.476, max=0.476, sum=0.476 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20234454638124363,
          "description": "min=0.187, mean=0.202, max=0.217, sum=0.607 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28667883597883553,
          "description": "min=0.264, mean=0.287, max=0.315, sum=0.86 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5653481865448796,
          "description": "min=0.54, mean=0.565, max=0.586, sum=1.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9210000000000002,
          "description": "min=0.92, mean=0.921, max=0.922, sum=2.763 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4093704023963013,
          "description": "min=0.069, mean=0.409, max=0.689, sum=22.106 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5446969696969698,
          "description": "min=0, mean=0.545, max=0.85, sum=17.975 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2395553093550869,
          "markdown": false
        },
        {
          "value": 0.1694970760233918,
          "description": "min=0.09, mean=0.169, max=0.24, sum=2.542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.638,
          "description": "min=0.623, mean=0.638, max=0.653, sum=1.914 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35196743378602896,
          "description": "min=0.314, mean=0.352, max=0.375, sum=1.056 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.149387882661448,
          "description": "min=0.144, mean=0.149, max=0.159, sum=0.448 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2985499982493553,
          "description": "min=0.215, mean=0.299, max=0.355, sum=0.896 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1590786964332521,
          "description": "min=0.143, mean=0.159, max=0.17, sum=0.477 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.656,
          "description": "min=0.656, mean=0.656, max=0.656, sum=0.656 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.408,
          "description": "min=0.408, mean=0.408, max=0.408, sum=0.408 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13608562691131498,
          "description": "min=0.128, mean=0.136, max=0.148, sum=0.408 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1048433862433863,
          "description": "min=0.074, mean=0.105, max=0.125, sum=0.315 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2783978738136928,
          "description": "min=0.227, mean=0.278, max=0.312, sum=0.835 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8956666666666667,
          "description": "min=0.883, mean=0.896, max=0.909, sum=2.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.336456419012055,
          "description": "min=0.022, mean=0.336, max=0.831, sum=18.169 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4446969696969697,
          "description": "min=0, mean=0.445, max=0.95, sum=14.675 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5094878610451469,
          "markdown": false
        },
        {
          "value": 0.3401169590643275,
          "description": "min=0.17, mean=0.34, max=0.6, sum=5.102 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6393333333333334,
          "description": "min=0.592, mean=0.639, max=0.677, sum=1.918 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4976057829109271,
          "description": "min=0.476, mean=0.498, max=0.52, sum=1.493 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2562420226045557,
          "description": "min=0.251, mean=0.256, max=0.264, sum=0.769 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5211614334906893,
          "description": "min=0.48, mean=0.521, max=0.561, sum=1.563 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20766668147064418,
          "description": "min=0.197, mean=0.208, max=0.217, sum=0.623 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.738,
          "description": "min=0.738, mean=0.738, max=0.738, sum=0.738 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.474,
          "description": "min=0.474, mean=0.474, max=0.474, sum=0.474 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14475025484199797,
          "description": "min=0.131, mean=0.145, max=0.162, sum=0.434 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15391111111111108,
          "description": "min=0.15, mean=0.154, max=0.157, sum=0.462 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3320850067305285,
          "description": "min=0.31, mean=0.332, max=0.352, sum=0.996 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8733333333333334,
          "description": "min=0.855, mean=0.873, max=0.89, sum=2.62 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.461098863197608,
          "description": "min=0, mean=0.461, max=1, sum=24.899 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5045454545454545,
          "description": "min=0.025, mean=0.505, max=0.975, sum=16.65 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.23139443056017028,
          "markdown": false
        },
        {
          "value": 0.1902923976608187,
          "description": "min=0.1, mean=0.19, max=0.263, sum=2.854 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.545,
          "description": "min=0.484, mean=0.545, max=0.599, sum=1.635 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.36665112128820915,
          "description": "min=0.352, mean=0.367, max=0.39, sum=1.1 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1262678947150161,
          "description": "min=0.118, mean=0.126, max=0.133, sum=0.379 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.33838638278361,
          "description": "min=0.28, mean=0.338, max=0.381, sum=1.015 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1711623480279509,
          "description": "min=0.164, mean=0.171, max=0.178, sum=0.513 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.632,
          "description": "min=0.632, mean=0.632, max=0.632, sum=0.632 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.396,
          "description": "min=0.396, mean=0.396, max=0.396, sum=0.396 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1855249745158002,
          "description": "min=0.167, mean=0.186, max=0.214, sum=0.557 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10991481481481481,
          "description": "min=0.086, mean=0.11, max=0.14, sum=0.33 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25287196320995325,
          "description": "min=0.25, mean=0.253, max=0.254, sum=0.759 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8033333333333333,
          "description": "min=0.716, mean=0.803, max=0.892, sum=2.41 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3471901723680723,
          "description": "min=0.002, mean=0.347, max=1, sum=18.748 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4128787878787879,
          "description": "min=0, mean=0.413, max=0.975, sum=13.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.11687598645329457,
          "markdown": false
        },
        {
          "value": 0.165906432748538,
          "description": "min=0.09, mean=0.166, max=0.24, sum=2.489 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47700000000000004,
          "description": "min=0.432, mean=0.477, max=0.522, sum=1.431 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2547490737014401,
          "description": "min=0.232, mean=0.255, max=0.266, sum=0.764 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06829400341950241,
          "description": "min=0.063, mean=0.068, max=0.072, sum=0.205 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21249077319847984,
          "description": "min=0.211, mean=0.212, max=0.214, sum=0.637 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14927279809816305,
          "description": "min=0.141, mean=0.149, max=0.156, sum=0.448 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.489,
          "description": "min=0.489, mean=0.489, max=0.489, sum=0.489 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.314,
          "description": "min=0.314, mean=0.314, max=0.314, sum=0.314 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1620795107033639,
          "description": "min=0.141, mean=0.162, max=0.183, sum=0.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07291031746031752,
          "description": "min=0.055, mean=0.073, max=0.086, sum=0.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24641961891165112,
          "description": "min=0.206, mean=0.246, max=0.285, sum=0.739 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.476, mean=0.5, max=0.512, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40032672585199003,
          "description": "min=0, mean=0.4, max=0.996, sum=21.618 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40909090909090906,
          "description": "min=0, mean=0.409, max=0.975, sum=13.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10196623917424807,
          "markdown": false
        },
        {
          "value": 0.20357894736842103,
          "description": "min=0.105, mean=0.204, max=0.28, sum=3.054 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.461,
          "description": "min=0.349, mean=0.461, max=0.549, sum=1.383 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.10413260236022294,
          "description": "min=0.094, mean=0.104, max=0.11, sum=0.312 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.030523107267064337,
          "description": "min=0.029, mean=0.031, max=0.033, sum=0.092 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.04293332221345858,
          "description": "min=0.042, mean=0.043, max=0.044, sum=0.129 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.09165527832991893,
          "description": "min=0.082, mean=0.092, max=0.098, sum=0.275 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.37,
          "description": "min=0.37, mean=0.37, max=0.37, sum=0.37 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27,
          "description": "min=0.27, mean=0.27, max=0.27, sum=0.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1671763506625892,
          "description": "min=0.154, mean=0.167, max=0.179, sum=0.502 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07152063492063503,
          "description": "min=0.039, mean=0.072, max=0.111, sum=0.215 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24715427563243078,
          "description": "min=0.148, mean=0.247, max=0.358, sum=0.741 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7006666666666668,
          "description": "min=0.663, mean=0.701, max=0.737, sum=2.102 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42132444064350366,
          "description": "min=0, mean=0.421, max=1, sum=22.752 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3446969696969697,
          "description": "min=0, mean=0.345, max=0.975, sum=11.375 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9095617026651509,
          "markdown": false
        },
        {
          "value": 0.5167953216374268,
          "description": "min=0.19, mean=0.517, max=0.84, sum=7.752 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8576666666666667,
          "description": "min=0.851, mean=0.858, max=0.864, sum=2.573 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6939161040603179,
          "description": "min=0.673, mean=0.694, max=0.713, sum=2.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36865975256659933,
          "description": "min=0.36, mean=0.369, max=0.376, sum=1.106 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7304543451569532,
          "description": "min=0.729, mean=0.73, max=0.733, sum=2.191 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4199382541834728,
          "description": "min=0.401, mean=0.42, max=0.432, sum=1.26 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.798,
          "description": "min=0.798, mean=0.798, max=0.798, sum=0.798 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.572,
          "description": "min=0.572, mean=0.572, max=0.572, sum=0.572 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5163098878695208,
          "description": "min=0.479, mean=0.516, max=0.54, sum=1.549 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3037781746031745,
          "description": "min=0.292, mean=0.304, max=0.319, sum=0.911 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6160995919712035,
          "description": "min=0.578, mean=0.616, max=0.645, sum=1.848 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7793333333333333,
          "description": "min=0.749, mean=0.779, max=0.827, sum=2.338 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5940672674614373,
          "description": "min=0.366, mean=0.594, max=0.838, sum=32.08 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7136363636363635,
          "description": "min=0.05, mean=0.714, max=0.95, sum=23.55 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9158568720860156,
          "markdown": false
        },
        {
          "value": 0.5245380116959065,
          "description": "min=0.23, mean=0.525, max=0.83, sum=7.868 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8410000000000001,
          "description": "min=0.834, mean=0.841, max=0.854, sum=2.523 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6382180079306305,
          "description": "min=0.61, mean=0.638, max=0.663, sum=1.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29853007347043187,
          "description": "min=0.279, mean=0.299, max=0.31, sum=0.896 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6645627340843298,
          "description": "min=0.66, mean=0.665, max=0.67, sum=1.994 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3193910892114107,
          "description": "min=0.313, mean=0.319, max=0.331, sum=0.958 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.776,
          "description": "min=0.776, mean=0.776, max=0.776, sum=0.776 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.52,
          "description": "min=0.52, mean=0.52, max=0.52, sum=0.52 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5468909276248726,
          "description": "min=0.517, mean=0.547, max=0.573, sum=1.641 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3435873015873012,
          "description": "min=0.327, mean=0.344, max=0.366, sum=1.031 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.627999061572698,
          "description": "min=0.615, mean=0.628, max=0.641, sum=1.884 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9253333333333332,
          "description": "min=0.898, mean=0.925, max=0.946, sum=2.776 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5673997819699065,
          "description": "min=0.287, mean=0.567, max=0.838, sum=30.64 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.665909090909091,
          "description": "min=0, mean=0.666, max=0.975, sum=21.975 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.336998226097225,
          "markdown": false
        },
        {
          "value": 0.22019883040935673,
          "description": "min=0.16, mean=0.22, max=0.272, sum=3.303 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5493333333333332,
          "description": "min=0.519, mean=0.549, max=0.566, sum=1.648 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.33989457936851464,
          "description": "min=0.299, mean=0.34, max=0.38, sum=1.02 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12098406641539787,
          "description": "min=0.116, mean=0.121, max=0.124, sum=0.363 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4152585116053236,
          "description": "min=0.365, mean=0.415, max=0.445, sum=1.246 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.16872479684813432,
          "description": "min=0.166, mean=0.169, max=0.173, sum=0.506 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.625,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.424,
          "description": "min=0.424, mean=0.424, max=0.424, sum=0.424 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23496432212028542,
          "description": "min=0.206, mean=0.235, max=0.284, sum=0.705 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1980144179894178,
          "description": "min=0.171, mean=0.198, max=0.222, sum=0.594 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4437543283018195,
          "description": "min=0.393, mean=0.444, max=0.486, sum=1.331 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8806666666666666,
          "description": "min=0.876, mean=0.881, max=0.887, sum=2.642 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12877898867890694,
          "description": "min=0, mean=0.129, max=0.39, sum=6.954 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3992424242424243,
          "description": "min=0, mean=0.399, max=0.775, sum=13.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.22569775422945612,
          "markdown": false
        },
        {
          "value": 0.18602339181286548,
          "description": "min=0.1, mean=0.186, max=0.228, sum=2.79 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38366666666666666,
          "description": "min=0.339, mean=0.384, max=0.412, sum=1.151 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.12577588570182116,
          "description": "min=0.101, mean=0.126, max=0.154, sum=0.377 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039736972833954616,
          "description": "min=0.039, mean=0.04, max=0.041, sum=0.119 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.15066474277626352,
          "description": "min=0.139, mean=0.151, max=0.169, sum=0.452 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.08703476784265192,
          "description": "min=0.083, mean=0.087, max=0.091, sum=0.261 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.468,
          "description": "min=0.468, mean=0.468, max=0.468, sum=0.468 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.39,
          "description": "min=0.39, mean=0.39, max=0.39, sum=0.39 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.19520897043832822,
          "description": "min=0.156, mean=0.195, max=0.252, sum=0.586 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12212023809523809,
          "description": "min=0.099, mean=0.122, max=0.16, sum=0.366 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35630094105473137,
          "description": "min=0.315, mean=0.356, max=0.413, sum=1.069 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.844,
          "description": "min=0.821, mean=0.844, max=0.868, sum=2.532 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4988821054609162,
          "description": "min=0, mean=0.499, max=1, sum=26.94 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38257575757575757,
          "description": "min=0.025, mean=0.383, max=0.925, sum=12.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10508470024599056,
          "markdown": false
        },
        {
          "value": 0.17768421052631578,
          "description": "min=0.08, mean=0.178, max=0.28, sum=2.665 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33233333333333337,
          "description": "min=0.316, mean=0.332, max=0.362, sum=0.997 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.05828828370185365,
          "description": "min=0.049, mean=0.058, max=0.075, sum=0.175 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.007711173104376766,
          "description": "min=0.007, mean=0.008, max=0.009, sum=0.023 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.033837452909760764,
          "description": "min=0.01, mean=0.034, max=0.062, sum=0.102 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.06713428098997175,
          "description": "min=0.054, mean=0.067, max=0.074, sum=0.201 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.32,
          "description": "min=0.32, mean=0.32, max=0.32, sum=0.32 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.248,
          "description": "min=0.248, mean=0.248, max=0.248, sum=0.248 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.17533129459734964,
          "description": "min=0.165, mean=0.175, max=0.194, sum=0.526 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06911044973544983,
          "description": "min=0.044, mean=0.069, max=0.091, sum=0.207 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2521954718959493,
          "description": "min=0.172, mean=0.252, max=0.302, sum=0.757 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7160000000000001,
          "description": "min=0.663, mean=0.716, max=0.744, sum=2.148 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4910745197871521,
          "description": "min=0, mean=0.491, max=1, sum=26.518 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3348484848484849,
          "description": "min=0, mean=0.335, max=0.925, sum=11.05 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8156643356643357,
          "markdown": false
        },
        {
          "value": 0.5254736842105263,
          "description": "min=0.23, mean=0.525, max=0.79, sum=2.627 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.66,
          "description": "min=0.66, mean=0.66, max=0.66, sum=0.66 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6017866194784781,
          "description": "min=0.602, mean=0.602, max=0.602, sum=0.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32682585209770315,
          "description": "min=0.327, mean=0.327, max=0.327, sum=0.327 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5559619230719722,
          "description": "min=0.556, mean=0.556, max=0.556, sum=0.556 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41122249859183385,
          "description": "min=0.411, mean=0.411, max=0.411, sum=0.411 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5657492354740061,
          "description": "min=0.566, mean=0.566, max=0.566, sum=0.566 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.857,
          "description": "min=0.857, mean=0.857, max=0.857, sum=0.857 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6045521523734413,
          "description": "min=0.394, mean=0.605, max=0.824, sum=10.882 (18)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7045454545454546,
          "description": "min=0.2, mean=0.705, max=0.975, sum=7.75 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7622144522144523,
          "markdown": false
        },
        {
          "value": 0.2623859649122807,
          "description": "min=0.1, mean=0.262, max=0.49, sum=1.312 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.845,
          "description": "min=0.845, mean=0.845, max=0.845, sum=0.845 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5658549915417233,
          "description": "min=0.566, mean=0.566, max=0.566, sum=0.566 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28373438775512194,
          "description": "min=0.284, mean=0.284, max=0.284, sum=0.284 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6060594363127481,
          "description": "min=0.606, mean=0.606, max=0.606, sum=0.606 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3712446607257685,
          "description": "min=0.371, mean=0.371, max=0.371, sum=0.371 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18654434250764526,
          "description": "min=0.187, mean=0.187, max=0.187, sum=0.187 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.916,
          "description": "min=0.916, mean=0.916, max=0.916, sum=0.916 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5638779146224463,
          "description": "min=0.206, mean=0.564, max=0.863, sum=10.15 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6772727272727272,
          "description": "min=0.15, mean=0.677, max=0.95, sum=7.45 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.293006993006993,
          "markdown": false
        },
        {
          "value": 0.2168421052631579,
          "description": "min=0.184, mean=0.217, max=0.29, sum=1.084 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.585,
          "description": "min=0.585, mean=0.585, max=0.585, sum=0.585 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3460535146763825,
          "description": "min=0.346, mean=0.346, max=0.346, sum=0.346 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1341635313992508,
          "description": "min=0.134, mean=0.134, max=0.134, sum=0.134 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3964044537010397,
          "description": "min=0.396, mean=0.396, max=0.396, sum=0.396 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17735561911839576,
          "description": "min=0.177, mean=0.177, max=0.177, sum=0.177 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22629969418960244,
          "description": "min=0.226, mean=0.226, max=0.226, sum=0.226 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.843,
          "description": "min=0.843, mean=0.843, max=0.843, sum=0.843 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3358431190860201,
          "description": "min=0, mean=0.336, max=0.996, sum=6.045 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4272727272727273,
          "description": "min=0, mean=0.427, max=0.975, sum=4.7 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3874825174825175,
          "markdown": false
        },
        {
          "value": 0.21785964912280703,
          "description": "min=0.18, mean=0.218, max=0.23, sum=1.089 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.629,
          "description": "min=0.629, mean=0.629, max=0.629, sum=0.629 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4034697604028265,
          "description": "min=0.403, mean=0.403, max=0.403, sum=0.403 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13162030419976034,
          "description": "min=0.132, mean=0.132, max=0.132, sum=0.132 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5356772534642628,
          "description": "min=0.536, mean=0.536, max=0.536, sum=0.536 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1368222933188553,
          "description": "min=0.137, mean=0.137, max=0.137, sum=0.137 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.172782874617737,
          "description": "min=0.173, mean=0.173, max=0.173, sum=0.173 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.852,
          "description": "min=0.852, mean=0.852, max=0.852, sum=0.852 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5058374710841333,
          "description": "min=0, mean=0.506, max=0.993, sum=9.105 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5477272727272727,
          "description": "min=0.075, mean=0.548, max=0.95, sum=6.025 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3311188811188811,
          "markdown": false
        },
        {
          "value": 0.2501052631578947,
          "description": "min=0.2, mean=0.25, max=0.33, sum=1.251 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.569,
          "description": "min=0.569, mean=0.569, max=0.569, sum=0.569 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4240469400392869,
          "description": "min=0.424, mean=0.424, max=0.424, sum=0.424 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1665503977180178,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47226706838923,
          "description": "min=0.472, mean=0.472, max=0.472, sum=0.472 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18577129287689287,
          "description": "min=0.186, mean=0.186, max=0.186, sum=0.186 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.172782874617737,
          "description": "min=0.173, mean=0.173, max=0.173, sum=0.173 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.56,
          "description": "min=0.56, mean=0.56, max=0.56, sum=0.56 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4011569280490217,
          "description": "min=0.054, mean=0.401, max=0.835, sum=7.221 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48863636363636365,
          "description": "min=0, mean=0.489, max=0.925, sum=5.375 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4953146853146853,
          "markdown": false
        },
        {
          "value": 0.2910877192982456,
          "description": "min=0.175, mean=0.291, max=0.46, sum=1.455 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.599,
          "description": "min=0.599, mean=0.599, max=0.599, sum=0.599 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4816661888359549,
          "description": "min=0.482, mean=0.482, max=0.482, sum=0.482 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13717330495393032,
          "description": "min=0.137, mean=0.137, max=0.137, sum=0.137 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5468327185577326,
          "description": "min=0.547, mean=0.547, max=0.547, sum=0.547 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16438450644529176,
          "description": "min=0.164, mean=0.164, max=0.164, sum=0.164 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.19724770642201836,
          "description": "min=0.197, mean=0.197, max=0.197, sum=0.197 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.82,
          "description": "min=0.82, mean=0.82, max=0.82, sum=0.82 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5272697486345442,
          "description": "min=0.277, mean=0.527, max=0.77, sum=9.491 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6045454545454546,
          "description": "min=0.175, mean=0.605, max=0.9, sum=6.65 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6966666666666667,
          "markdown": false
        },
        {
          "value": 0.38087719298245615,
          "description": "min=0.25, mean=0.381, max=0.6, sum=1.904 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.656,
          "description": "min=0.656, mean=0.656, max=0.656, sum=0.656 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5840358182644836,
          "description": "min=0.584, mean=0.584, max=0.584, sum=0.584 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2720121639433268,
          "description": "min=0.272, mean=0.272, max=0.272, sum=0.272 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6094875286076354,
          "description": "min=0.609, mean=0.609, max=0.609, sum=0.609 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23071567735549398,
          "description": "min=0.231, mean=0.231, max=0.231, sum=0.231 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17737003058103976,
          "description": "min=0.177, mean=0.177, max=0.177, sum=0.177 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.942,
          "description": "min=0.942, mean=0.942, max=0.942, sum=0.942 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4837936253587437,
          "description": "min=0.112, mean=0.484, max=0.81, sum=8.708 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5795454545454546,
          "description": "min=0.075, mean=0.58, max=0.975, sum=6.375 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6561072261072262,
          "markdown": false
        },
        {
          "value": 0.3826315789473684,
          "description": "min=0.22, mean=0.383, max=0.59, sum=1.913 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.77,
          "description": "min=0.77, mean=0.77, max=0.77, sum=0.77 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6233490338408667,
          "description": "min=0.623, mean=0.623, max=0.623, sum=0.623 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20213849058578032,
          "description": "min=0.202, mean=0.202, max=0.202, sum=0.202 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6065652552159236,
          "description": "min=0.607, mean=0.607, max=0.607, sum=0.607 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20366013650654988,
          "description": "min=0.204, mean=0.204, max=0.204, sum=0.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17737003058103976,
          "description": "min=0.177, mean=0.177, max=0.177, sum=0.177 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.942,
          "description": "min=0.942, mean=0.942, max=0.942, sum=0.942 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40848129232892094,
          "description": "min=0.042, mean=0.408, max=0.867, sum=7.353 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5477272727272727,
          "description": "min=0.075, mean=0.548, max=0.875, sum=6.025 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4253379953379953,
          "markdown": false
        },
        {
          "value": 0.23610526315789473,
          "description": "min=0.13, mean=0.236, max=0.37, sum=1.181 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.65,
          "description": "min=0.65, mean=0.65, max=0.65, sum=0.65 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4358401092976052,
          "description": "min=0.436, mean=0.436, max=0.436, sum=0.436 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18513134554094532,
          "description": "min=0.185, mean=0.185, max=0.185, sum=0.185 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4889733445855735,
          "description": "min=0.489, mean=0.489, max=0.489, sum=0.489 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16389145934637706,
          "description": "min=0.164, mean=0.164, max=0.164, sum=0.164 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.20489296636085627,
          "description": "min=0.205, mean=0.205, max=0.205, sum=0.205 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.692,
          "description": "min=0.692, mean=0.692, max=0.692, sum=0.692 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4850751828621894,
          "description": "min=0, mean=0.485, max=0.999, sum=8.731 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5159090909090908,
          "description": "min=0.025, mean=0.516, max=0.975, sum=5.675 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3032867132867133,
          "markdown": false
        },
        {
          "value": 0.24961403508771932,
          "description": "min=0.2, mean=0.25, max=0.32, sum=1.248 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.593,
          "description": "min=0.593, mean=0.593, max=0.593, sum=0.593 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2582769089885097,
          "description": "min=0.258, mean=0.258, max=0.258, sum=0.258 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1322266230747346,
          "description": "min=0.132, mean=0.132, max=0.132, sum=0.132 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32667933185026377,
          "description": "min=0.327, mean=0.327, max=0.327, sum=0.327 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1789889679486199,
          "description": "min=0.179, mean=0.179, max=0.179, sum=0.179 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.16972477064220184,
          "description": "min=0.17, mean=0.17, max=0.17, sum=0.17 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.759,
          "description": "min=0.759, mean=0.759, max=0.759, sum=0.759 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4871679045873981,
          "description": "min=0, mean=0.487, max=0.999, sum=8.769 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4454545454545454,
          "description": "min=0.15, mean=0.445, max=0.975, sum=4.9 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7051048951048952,
          "markdown": false
        },
        {
          "value": 0.4566315789473684,
          "description": "min=0.26, mean=0.457, max=0.76, sum=2.283 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.763,
          "description": "min=0.763, mean=0.763, max=0.763, sum=0.763 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5574684493620005,
          "description": "min=0.557, mean=0.557, max=0.557, sum=0.557 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32850713007659726,
          "description": "min=0.329, mean=0.329, max=0.329, sum=0.329 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5930765119599164,
          "description": "min=0.593, mean=0.593, max=0.593, sum=0.593 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16237264946195393,
          "description": "min=0.162, mean=0.162, max=0.162, sum=0.162 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.30275229357798167,
          "description": "min=0.303, mean=0.303, max=0.303, sum=0.303 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.935,
          "description": "min=0.935, mean=0.935, max=0.935, sum=0.935 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4118677862671613,
          "description": "min=0.037, mean=0.412, max=0.827, sum=7.414 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5863636363636363,
          "description": "min=0, mean=0.586, max=0.975, sum=6.45 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7631002331002331,
          "markdown": false
        },
        {
          "value": 0.44561403508771924,
          "description": "min=0.228, mean=0.446, max=0.78, sum=2.228 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.781,
          "description": "min=0.781, mean=0.781, max=0.781, sum=0.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5082425698893845,
          "description": "min=0.508, mean=0.508, max=0.508, sum=0.508 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33514492181201283,
          "description": "min=0.335, mean=0.335, max=0.335, sum=0.335 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5912781280483248,
          "description": "min=0.591, mean=0.591, max=0.591, sum=0.591 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21167117057056115,
          "description": "min=0.212, mean=0.212, max=0.212, sum=0.212 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3379204892966361,
          "description": "min=0.338, mean=0.338, max=0.338, sum=0.338 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.938,
          "description": "min=0.938, mean=0.938, max=0.938, sum=0.938 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5230033316869794,
          "description": "min=0.135, mean=0.523, max=0.864, sum=9.414 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5227272727272726,
          "description": "min=0.025, mean=0.523, max=0.875, sum=5.75 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6465501165501165,
          "markdown": false
        },
        {
          "value": 0.3203859649122807,
          "description": "min=0.17, mean=0.32, max=0.44, sum=4.806 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7276666666666668,
          "description": "min=0.68, mean=0.728, max=0.758, sum=2.183 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6293880948208791,
          "description": "min=0.531, mean=0.629, max=0.682, sum=1.888 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11665134142344884,
          "description": "min=0.11, mean=0.117, max=0.122, sum=0.35 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5998399895408899,
          "description": "min=0.592, mean=0.6, max=0.608, sum=1.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19293634470384977,
          "description": "min=0.178, mean=0.193, max=0.202, sum=0.579 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.19610091743119268,
          "description": "min=0.147, mean=0.196, max=0.229, sum=0.784 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9380000000000001,
          "description": "min=0.921, mean=0.938, max=0.955, sum=2.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5000703286326241,
          "description": "min=0, mean=0.5, max=1, sum=27.004 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5772727272727272,
          "description": "min=0, mean=0.577, max=0.975, sum=19.05 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5224242424242425,
          "markdown": false
        },
        {
          "value": 0.34819883040935673,
          "description": "min=0.14, mean=0.348, max=0.65, sum=5.223 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6556666666666667,
          "description": "min=0.564, mean=0.656, max=0.719, sum=1.967 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3173185298582432,
          "description": "min=0.091, mean=0.317, max=0.444, sum=0.952 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2667976861519438,
          "description": "min=0.257, mean=0.267, max=0.272, sum=0.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5669828313348768,
          "description": "min=0.52, mean=0.567, max=0.61, sum=1.701 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24761534139298128,
          "description": "min=0.23, mean=0.248, max=0.258, sum=0.743 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1513761467889908,
          "description": "min=0.148, mean=0.151, max=0.154, sum=0.454 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.906,
          "description": "min=0.898, mean=0.906, max=0.916, sum=2.718 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4432801514699601,
          "description": "min=0, mean=0.443, max=0.774, sum=23.937 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5181818181818182,
          "description": "min=0.05, mean=0.518, max=0.95, sum=17.1 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8206682206682206,
          "markdown": false
        },
        {
          "value": 0.5662339181286549,
          "description": "min=0.29, mean=0.566, max=0.86, sum=8.494 (15)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.878,
          "description": "min=0.875, mean=0.878, max=0.88, sum=2.634 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6719021727640991,
          "description": "min=0.667, mean=0.672, max=0.68, sum=2.016 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3629707081568259,
          "description": "min=0.355, mean=0.363, max=0.368, sum=1.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.38348793103386436,
          "description": "min=0.379, mean=0.383, max=0.392, sum=1.15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5682976554536188,
          "description": "min=0.554, mean=0.568, max=0.584, sum=1.705 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9043333333333333,
          "description": "min=0.896, mean=0.904, max=0.909, sum=2.713 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.006429753618269135,
          "description": "min=0, mean=0.006, max=0.319, sum=0.347 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6772727272727272,
          "description": "min=0, mean=0.677, max=0.975, sum=22.35 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.20536130536130537,
          "markdown": false
        },
        {
          "value": 0.2433684210526316,
          "description": "min=0.2, mean=0.243, max=0.28, sum=3.651 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.566,
          "description": "min=0.437, mean=0.566, max=0.631, sum=1.698 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08788676556219112,
          "description": "min=0.078, mean=0.088, max=0.096, sum=0.264 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04678550801735826,
          "description": "min=0.045, mean=0.047, max=0.05, sum=0.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12496123369617401,
          "description": "min=0.111, mean=0.125, max=0.146, sum=0.375 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0795025876916194,
          "description": "min=0.077, mean=0.08, max=0.082, sum=0.239 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2018348623853211,
          "description": "min=0.197, mean=0.202, max=0.203, sum=0.807 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.7193333333333333,
          "description": "min=0.578, mean=0.719, max=0.79, sum=2.158 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4631081891632545,
          "description": "min=0, mean=0.463, max=1, sum=25.008 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21136363636363636,
          "description": "min=0, mean=0.211, max=0.65, sum=6.975 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_robustness.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_robustness.json"
      }
    ],
    "name": "robustness"
  },
  {
    "title": "Fairness",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - EM (Fairness)",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "MMLU",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "BoolQ - EM (Fairness)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "BoolQ",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "NarrativeQA - F1 (Fairness)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NarrativeQA",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - F1 (Fairness)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (closed-book)",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - F1 (Fairness)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "NaturalQuestions (open-book)",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "QuAC - F1 (Fairness)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nF1: Average F1 score in terms of word overlap between the model output and correct reference.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "F1",
          "run_group": "QuAC",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "HellaSwag - EM (Fairness)",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "HellaSwag",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "OpenbookQA - EM (Fairness)",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "OpenbookQA",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "TruthfulQA - EM (Fairness)",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\nExact match: Fraction of instances that the predicted output matches a correct reference exactly.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "TruthfulQA",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "MS MARCO (regular) - RR@10 (Fairness)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nRR@10: Mean reciprocal rank at 10 in information retrieval.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "RR@10",
          "run_group": "MS MARCO (regular)",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "MS MARCO (TREC) - NDCG@10 (Fairness)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nNDCG@10: Normalized discounted cumulative gain at 10 in information retrieval.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "NDCG@10",
          "run_group": "MS MARCO (TREC)",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "IMDB - EM (Fairness)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "IMDB",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "CivilComments - EM (Fairness)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "CivilComments",
          "perturbation": "Fairness"
        }
      },
      {
        "value": "RAFT - EM (Fairness)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nQuasi-exact match: Fraction of instances that the predicted output matches a correct reference up to light processing.\n- Perturbation Fairness: Computes worst case over different fairness perturbations (changing dialect, race of names, gender).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "EM",
          "run_group": "RAFT",
          "perturbation": "Fairness"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.48803949109844547,
          "markdown": false
        },
        {
          "value": 0.23635087719298245,
          "description": "min=0.17, mean=0.236, max=0.33, sum=3.545 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7093333333333334,
          "description": "min=0.693, mean=0.709, max=0.73, sum=2.128 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5811269391716133,
          "description": "min=0.566, mean=0.581, max=0.592, sum=1.743 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23456155611286555,
          "description": "min=0.227, mean=0.235, max=0.239, sum=0.704 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5399104355251988,
          "description": "min=0.54, mean=0.54, max=0.54, sum=1.62 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2682228394530809,
          "description": "min=0.263, mean=0.268, max=0.275, sum=0.805 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.614,
          "description": "min=0.614, mean=0.614, max=0.614, sum=0.614 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.466,
          "description": "min=0.466, mean=0.466, max=0.466, sum=0.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15596330275229356,
          "description": "min=0.142, mean=0.156, max=0.168, sum=0.468 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17989272486772476,
          "description": "min=0.151, mean=0.18, max=0.202, sum=0.54 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34798299201075195,
          "description": "min=0.308, mean=0.348, max=0.386, sum=1.044 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9323333333333333,
          "description": "min=0.922, mean=0.932, max=0.941, sum=2.797 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4782106548652487,
          "description": "min=0.006, mean=0.478, max=0.958, sum=25.823 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6227272727272728,
          "description": "min=0.125, mean=0.623, max=0.975, sum=20.55 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.27467778791471786,
          "markdown": false
        },
        {
          "value": 0.2039415204678363,
          "description": "min=0.16, mean=0.204, max=0.23, sum=3.059 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6223333333333333,
          "description": "min=0.591, mean=0.622, max=0.651, sum=1.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5126679432053903,
          "description": "min=0.496, mean=0.513, max=0.524, sum=1.538 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14648226412007787,
          "description": "min=0.14, mean=0.146, max=0.151, sum=0.439 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4695231845662433,
          "description": "min=0.44, mean=0.47, max=0.508, sum=1.409 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24062000532402938,
          "description": "min=0.227, mean=0.241, max=0.256, sum=0.722 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.528,
          "description": "min=0.528, mean=0.528, max=0.528, sum=0.528 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.444,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17380224260958207,
          "description": "min=0.159, mean=0.174, max=0.182, sum=0.521 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11706984126984123,
          "description": "min=0.096, mean=0.117, max=0.143, sum=0.351 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2804651230679189,
          "description": "min=0.258, mean=0.28, max=0.322, sum=0.841 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9463333333333334,
          "description": "min=0.939, mean=0.946, max=0.951, sum=2.839 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4468037461427085,
          "description": "min=0, mean=0.447, max=0.962, sum=24.127 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5106060606060605,
          "description": "min=0.15, mean=0.511, max=0.95, sum=16.85 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4539316449216338,
          "markdown": false
        },
        {
          "value": 0.23159064327485382,
          "description": "min=0.158, mean=0.232, max=0.29, sum=3.474 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6783333333333333,
          "description": "min=0.656, mean=0.678, max=0.695, sum=2.035 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5469545337986748,
          "description": "min=0.526, mean=0.547, max=0.563, sum=1.641 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1872477522460834,
          "description": "min=0.185, mean=0.187, max=0.189, sum=0.562 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5209919156580172,
          "description": "min=0.501, mean=0.521, max=0.534, sum=1.563 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27362985580399246,
          "description": "min=0.266, mean=0.274, max=0.282, sum=0.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.58,
          "description": "min=0.58, mean=0.58, max=0.58, sum=0.58 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.472,
          "description": "min=0.472, mean=0.472, max=0.472, sum=0.472 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16309887869520898,
          "description": "min=0.138, mean=0.163, max=0.182, sum=0.489 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1378972222222222,
          "description": "min=0.126, mean=0.138, max=0.155, sum=0.414 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3284974893691146,
          "description": "min=0.296, mean=0.328, max=0.372, sum=0.985 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9463333333333331,
          "description": "min=0.94, mean=0.946, max=0.95, sum=2.839 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4819034071645267,
          "description": "min=0.014, mean=0.482, max=0.962, sum=26.023 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6363636363636364,
          "description": "min=0.175, mean=0.636, max=0.975, sum=21 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6771299149497148,
          "markdown": false
        },
        {
          "value": 0.4094619883040936,
          "description": "min=0.19, mean=0.409, max=0.77, sum=6.142 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7636666666666668,
          "description": "min=0.751, mean=0.764, max=0.784, sum=2.291 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6470593497686433,
          "description": "min=0.622, mean=0.647, max=0.665, sum=1.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.269872960171523,
          "description": "min=0.269, mean=0.27, max=0.27, sum=0.81 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5712438797598854,
          "description": "min=0.562, mean=0.571, max=0.578, sum=1.714 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30759220119907554,
          "description": "min=0.297, mean=0.308, max=0.319, sum=0.923 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.623,
          "description": "min=0.623, mean=0.623, max=0.623, sum=0.623 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.478,
          "description": "min=0.478, mean=0.478, max=0.478, sum=0.478 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24159021406727832,
          "description": "min=0.216, mean=0.242, max=0.271, sum=0.725 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25326719576719553,
          "description": "min=0.23, mean=0.253, max=0.284, sum=0.76 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4346805929346467,
          "description": "min=0.371, mean=0.435, max=0.486, sum=1.304 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9503333333333334,
          "description": "min=0.935, mean=0.95, max=0.959, sum=2.851 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40396201739558046,
          "description": "min=0.005, mean=0.404, max=0.901, sum=21.814 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6371212121212121,
          "description": "min=0.2, mean=0.637, max=0.95, sum=21.025 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8360206534288848,
          "markdown": false
        },
        {
          "value": 0.44997660818713453,
          "description": "min=0.21, mean=0.45, max=0.78, sum=6.75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7916666666666666,
          "description": "min=0.78, mean=0.792, max=0.798, sum=2.375 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6577011654908803,
          "description": "min=0.63, mean=0.658, max=0.69, sum=1.973 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32739768950953246,
          "description": "min=0.326, mean=0.327, max=0.328, sum=0.982 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6201543217700605,
          "description": "min=0.601, mean=0.62, max=0.633, sum=1.86 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34006270092560414,
          "description": "min=0.333, mean=0.34, max=0.348, sum=1.02 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.655,
          "description": "min=0.655, mean=0.655, max=0.655, sum=0.655 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.488,
          "description": "min=0.488, mean=0.488, max=0.488, sum=0.488 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35423037716615696,
          "description": "min=0.289, mean=0.354, max=0.398, sum=1.063 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34235396825396786,
          "description": "min=0.339, mean=0.342, max=0.346, sum=1.027 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6202649047028815,
          "description": "min=0.578, mean=0.62, max=0.66, sum=1.861 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9329999999999999,
          "description": "min=0.928, mean=0.933, max=0.937, sum=2.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5068507198702314,
          "description": "min=0.005, mean=0.507, max=0.995, sum=27.37 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7106060606060605,
          "description": "min=0.225, mean=0.711, max=0.975, sum=23.45 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7037362526239056,
          "markdown": false
        },
        {
          "value": 0.43321637426900583,
          "description": "min=0.23, mean=0.433, max=0.73, sum=6.498 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7799999999999999,
          "description": "min=0.758, mean=0.78, max=0.791, sum=2.34 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6449807868174807,
          "description": "min=0.638, mean=0.645, max=0.651, sum=1.935 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2832503879785802,
          "description": "min=0.276, mean=0.283, max=0.288, sum=0.85 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5839142853000876,
          "description": "min=0.569, mean=0.584, max=0.592, sum=1.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34002521409765923,
          "description": "min=0.335, mean=0.34, max=0.35, sum=1.02 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.632,
          "description": "min=0.632, mean=0.632, max=0.632, sum=0.632 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.466,
          "description": "min=0.466, mean=0.466, max=0.466, sum=0.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2900101936799185,
          "description": "min=0.242, mean=0.29, max=0.32, sum=0.87 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.242712169312169,
          "description": "min=0.206, mean=0.243, max=0.271, sum=0.728 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47089412794287994,
          "description": "min=0.438, mean=0.471, max=0.522, sum=1.413 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9306666666666666,
          "description": "min=0.92, mean=0.931, max=0.951, sum=2.792 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44457169485758724,
          "description": "min=0, mean=0.445, max=0.973, sum=24.007 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6886363636363637,
          "description": "min=0.2, mean=0.689, max=0.975, sum=22.725 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.48311004284307957,
          "markdown": false
        },
        {
          "value": 0.2968421052631579,
          "description": "min=0.167, mean=0.297, max=0.45, sum=4.453 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.685,
          "description": "min=0.675, mean=0.685, max=0.697, sum=2.055 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21726190588701,
          "description": "min=0.215, mean=0.217, max=0.221, sum=0.652 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5388295929563434,
          "description": "min=0.53, mean=0.539, max=0.557, sum=1.616 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.567,
          "description": "min=0.567, mean=0.567, max=0.567, sum=0.567 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45,
          "description": "min=0.45, mean=0.45, max=0.45, sum=0.45 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1962283384301733,
          "description": "min=0.185, mean=0.196, max=0.205, sum=0.589 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21544642857142837,
          "description": "min=0.21, mean=0.215, max=0.221, sum=0.646 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44015360771598083,
          "description": "min=0.432, mean=0.44, max=0.457, sum=1.32 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.945,
          "description": "min=0.941, mean=0.945, max=0.951, sum=2.835 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4028192827891808,
          "description": "min=0.143, mean=0.403, max=0.834, sum=21.752 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5674242424242424,
          "description": "min=0.2, mean=0.567, max=0.975, sum=18.725 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.23762237762237765,
          "markdown": false
        },
        {
          "value": 0.1845730994152047,
          "description": "min=0.09, mean=0.185, max=0.27, sum=2.769 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6526666666666667,
          "description": "min=0.634, mean=0.653, max=0.682, sum=1.958 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4982467496641079,
          "description": "min=0.462, mean=0.498, max=0.532, sum=1.495 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16022586408623682,
          "description": "min=0.156, mean=0.16, max=0.164, sum=0.481 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5114691771549933,
          "description": "min=0.505, mean=0.511, max=0.515, sum=1.534 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2662906470176498,
          "description": "min=0.251, mean=0.266, max=0.284, sum=0.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.12487257900101938,
          "description": "min=0.118, mean=0.125, max=0.13, sum=0.375 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9123333333333333,
          "description": "min=0.902, mean=0.912, max=0.926, sum=2.737 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3967651888403395,
          "description": "min=0, mean=0.397, max=1, sum=21.425 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4454545454545455,
          "description": "min=0, mean=0.445, max=0.975, sum=14.7 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.45142191142191146,
          "markdown": false
        },
        {
          "value": 0.23658479532163745,
          "description": "min=0.14, mean=0.237, max=0.35, sum=3.549 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.711,
          "description": "min=0.692, mean=0.711, max=0.733, sum=2.133 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5321907426131639,
          "description": "min=0.503, mean=0.532, max=0.565, sum=1.597 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21385439000180537,
          "description": "min=0.205, mean=0.214, max=0.22, sum=0.642 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5512241821510145,
          "description": "min=0.548, mean=0.551, max=0.554, sum=1.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2774375608495023,
          "description": "min=0.268, mean=0.277, max=0.295, sum=0.832 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15953109072375127,
          "description": "min=0.144, mean=0.16, max=0.171, sum=0.479 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9369999999999999,
          "description": "min=0.93, mean=0.937, max=0.946, sum=2.811 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4622866273105216,
          "description": "min=0, mean=0.462, max=0.985, sum=24.963 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4893939393939393,
          "description": "min=0, mean=0.489, max=0.925, sum=16.15 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5218648018648019,
          "markdown": false
        },
        {
          "value": 0.2636608187134503,
          "description": "min=0.11, mean=0.264, max=0.51, sum=3.955 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6936666666666667,
          "description": "min=0.66, mean=0.694, max=0.713, sum=2.081 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6025352758861713,
          "description": "min=0.562, mean=0.603, max=0.637, sum=1.808 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24089192251975544,
          "description": "min=0.23, mean=0.241, max=0.25, sum=0.723 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5966421355805813,
          "description": "min=0.583, mean=0.597, max=0.61, sum=1.79 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28824116919086756,
          "description": "min=0.28, mean=0.288, max=0.3, sum=0.865 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.13200815494393475,
          "description": "min=0.128, mean=0.132, max=0.138, sum=0.396 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9493333333333333,
          "description": "min=0.948, mean=0.949, max=0.951, sum=2.848 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4317285215923749,
          "description": "min=0.014, mean=0.432, max=0.912, sum=23.313 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6007575757575758,
          "description": "min=0, mean=0.601, max=0.975, sum=19.825 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7935577862997218,
          "markdown": false
        },
        {
          "value": 0.4467836257309941,
          "description": "min=0.211, mean=0.447, max=0.74, sum=6.702 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7816666666666667,
          "description": "min=0.778, mean=0.782, max=0.788, sum=2.345 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6464650190039823,
          "description": "min=0.614, mean=0.646, max=0.667, sum=1.939 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23855278160903723,
          "description": "min=0.228, mean=0.239, max=0.244, sum=0.716 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6422159112855447,
          "description": "min=0.639, mean=0.642, max=0.646, sum=1.927 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35555313427706087,
          "description": "min=0.338, mean=0.356, max=0.365, sum=1.067 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.695,
          "description": "min=0.695, mean=0.695, max=0.695, sum=0.695 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.482,
          "description": "min=0.482, mean=0.482, max=0.482, sum=0.482 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3004587155963303,
          "description": "min=0.229, mean=0.3, max=0.388, sum=1.202 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.305, mean=0.345, max=0.369, sum=1.036 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "min=0.589, mean=0.609, max=0.63, sum=1.828 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9249999999999999,
          "description": "min=0.918, mean=0.925, max=0.936, sum=2.775 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5117722022150621,
          "description": "min=0.105, mean=0.512, max=0.939, sum=27.636 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6696969696969697,
          "description": "min=0.225, mean=0.67, max=0.95, sum=22.1 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5507003378527294,
          "markdown": false
        },
        {
          "value": 0.27360233918128657,
          "description": "min=0.175, mean=0.274, max=0.38, sum=4.104 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.656,
          "description": "min=0.601, mean=0.656, max=0.693, sum=1.968 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5767895596204061,
          "description": "min=0.535, mean=0.577, max=0.613, sum=1.73 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18669047090402127,
          "description": "min=0.183, mean=0.187, max=0.189, sum=0.56 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5745618824682682,
          "description": "min=0.56, mean=0.575, max=0.585, sum=1.724 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27335853114408787,
          "description": "min=0.265, mean=0.273, max=0.289, sum=0.82 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.585,
          "description": "min=0.585, mean=0.585, max=0.585, sum=0.585 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.482,
          "description": "min=0.482, mean=0.482, max=0.482, sum=0.482 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18616207951070335,
          "description": "min=0.164, mean=0.186, max=0.206, sum=0.745 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2110978835978834,
          "description": "min=0.189, mean=0.211, max=0.231, sum=0.633 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37148573288404924,
          "description": "min=0.345, mean=0.371, max=0.418, sum=1.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9380000000000001,
          "description": "min=0.927, mean=0.938, max=0.946, sum=2.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5460670492526992,
          "description": "min=0.252, mean=0.546, max=0.91, sum=29.488 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5628787878787879,
          "description": "min=0.2, mean=0.563, max=0.975, sum=18.575 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.20273892773892774,
          "markdown": false
        },
        {
          "value": 0.3820701754385965,
          "description": "min=0.25, mean=0.382, max=0.63, sum=5.731 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.0858526263629113,
          "description": "min=0.074, mean=0.086, max=0.093, sum=0.258 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.028132918197666456,
          "description": "min=0.027, mean=0.028, max=0.03, sum=0.084 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13562055302845238,
          "description": "min=0.119, mean=0.136, max=0.151, sum=0.407 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06691720655918869,
          "description": "min=0.067, mean=0.067, max=0.067, sum=0.201 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.34977064220183485,
          "description": "min=0.307, mean=0.35, max=0.411, sum=1.399 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.16833333333333333,
          "description": "min=0.129, mean=0.168, max=0.22, sum=0.505 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.16470832145418626,
          "description": "min=0, mean=0.165, max=0.947, sum=8.894 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10606060606060606,
          "description": "min=0, mean=0.106, max=0.75, sum=3.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5496737226436893,
          "markdown": false
        },
        {
          "value": 0.31526315789473686,
          "description": "min=0.158, mean=0.315, max=0.53, sum=4.729 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.657, mean=0.667, max=0.681, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5478470147843514,
          "description": "min=0.481, mean=0.548, max=0.591, sum=1.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25466316487855734,
          "description": "min=0.248, mean=0.255, max=0.259, sum=0.764 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5348225692810691,
          "description": "min=0.521, mean=0.535, max=0.546, sum=1.604 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2814055112322921,
          "description": "min=0.274, mean=0.281, max=0.287, sum=0.844 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.66,
          "description": "min=0.66, mean=0.66, max=0.66, sum=0.66 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47,
          "description": "min=0.47, mean=0.47, max=0.47, sum=0.47 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1564729867482161,
          "description": "min=0.138, mean=0.156, max=0.182, sum=0.469 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23262777777777743,
          "description": "min=0.211, mean=0.233, max=0.251, sum=0.698 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4307144032412258,
          "description": "min=0.394, mean=0.431, max=0.457, sum=1.292 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9486666666666667,
          "description": "min=0.93, mean=0.949, max=0.96, sum=2.846 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4787922217178853,
          "description": "min=0.001, mean=0.479, max=1, sum=25.855 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5984848484848486,
          "description": "min=0.05, mean=0.598, max=0.95, sum=19.75 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3621096552687209,
          "markdown": false
        },
        {
          "value": 0.2809590643274854,
          "description": "min=0.14, mean=0.281, max=0.38, sum=4.214 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6756666666666667,
          "description": "min=0.653, mean=0.676, max=0.695, sum=2.027 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5123186802559418,
          "description": "min=0.466, mean=0.512, max=0.538, sum=1.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17833773739586523,
          "description": "min=0.176, mean=0.178, max=0.181, sum=0.535 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5065982888177307,
          "description": "min=0.489, mean=0.507, max=0.516, sum=1.52 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25613799535824233,
          "description": "min=0.251, mean=0.256, max=0.259, sum=0.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.575,
          "description": "min=0.575, mean=0.575, max=0.575, sum=0.575 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.446,
          "description": "min=0.446, mean=0.446, max=0.446, sum=0.446 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15698267074413863,
          "description": "min=0.142, mean=0.157, max=0.174, sum=0.471 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16423492063492048,
          "description": "min=0.136, mean=0.164, max=0.189, sum=0.493 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3120660241438415,
          "description": "min=0.273, mean=0.312, max=0.361, sum=0.936 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9196666666666666,
          "description": "min=0.912, mean=0.92, max=0.93, sum=2.759 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44290609222735455,
          "description": "min=0, mean=0.443, max=1, sum=23.917 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5643939393939394,
          "description": "min=0, mean=0.564, max=0.975, sum=18.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.26943181031056446,
          "markdown": false
        },
        {
          "value": 0.23653801169590644,
          "description": "min=0.15, mean=0.237, max=0.29, sum=3.548 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5973333333333333,
          "description": "min=0.589, mean=0.597, max=0.61, sum=1.792 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4376922212938658,
          "description": "min=0.416, mean=0.438, max=0.455, sum=1.313 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12565301660951664,
          "description": "min=0.124, mean=0.126, max=0.127, sum=0.377 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4322127161835283,
          "description": "min=0.41, mean=0.432, max=0.444, sum=1.297 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19765650296002213,
          "description": "min=0.186, mean=0.198, max=0.207, sum=0.593 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.525,
          "description": "min=0.525, mean=0.525, max=0.525, sum=0.525 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17380224260958207,
          "description": "min=0.154, mean=0.174, max=0.19, sum=0.521 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13183915343915345,
          "description": "min=0.126, mean=0.132, max=0.136, sum=0.396 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35726921379791293,
          "description": "min=0.321, mean=0.357, max=0.398, sum=1.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9176666666666667,
          "description": "min=0.896, mean=0.918, max=0.936, sum=2.753 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48864261081744575,
          "description": "min=0, mean=0.489, max=1, sum=26.387 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.125, mean=0.5, max=0.975, sum=16.5 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.15386697669576083,
          "markdown": false
        },
        {
          "value": 0.22225730994152046,
          "description": "min=0.1, mean=0.222, max=0.4, sum=3.334 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37366666666666665,
          "description": "min=0.346, mean=0.374, max=0.396, sum=1.121 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17918507973514153,
          "description": "min=0.167, mean=0.179, max=0.197, sum=0.538 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.055406816944260924,
          "description": "min=0.052, mean=0.055, max=0.062, sum=0.166 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21887630944724534,
          "description": "min=0.198, mean=0.219, max=0.246, sum=0.657 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14446776305873513,
          "description": "min=0.135, mean=0.144, max=0.162, sum=0.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.308,
          "description": "min=0.308, mean=0.308, max=0.308, sum=0.308 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28,
          "description": "min=0.28, mean=0.28, max=0.28, sum=0.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20285423037716613,
          "description": "min=0.194, mean=0.203, max=0.214, sum=0.609 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2798487582673837,
          "description": "min=0.228, mean=0.28, max=0.324, sum=0.84 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.518,
          "description": "min=0.49, mean=0.518, max=0.54, sum=1.554 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49526155082406725,
          "description": "min=0, mean=0.495, max=1, sum=26.744 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4515151515151515,
          "description": "min=0, mean=0.452, max=0.975, sum=14.9 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6082341462764155,
          "markdown": false
        },
        {
          "value": 0.31652631578947366,
          "description": "min=0.13, mean=0.317, max=0.57, sum=4.748 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7079999999999999,
          "description": "min=0.702, mean=0.708, max=0.72, sum=2.124 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5530542667501213,
          "description": "min=0.486, mean=0.553, max=0.589, sum=1.659 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.299210546403295,
          "description": "min=0.295, mean=0.299, max=0.303, sum=0.898 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5664508489119625,
          "description": "min=0.548, mean=0.566, max=0.58, sum=1.699 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27469570002834404,
          "description": "min=0.269, mean=0.275, max=0.278, sum=0.824 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.687,
          "description": "min=0.687, mean=0.687, max=0.687, sum=0.687 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1197757390417941,
          "description": "min=0.112, mean=0.12, max=0.124, sum=0.359 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2673071428571425,
          "description": "min=0.239, mean=0.267, max=0.302, sum=0.802 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5216640091882355,
          "description": "min=0.51, mean=0.522, max=0.544, sum=1.565 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.949,
          "description": "min=0.931, mean=0.949, max=0.96, sum=2.847 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41537457925495214,
          "description": "min=0.03, mean=0.415, max=0.875, sum=22.43 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6037878787878787,
          "description": "min=0, mean=0.604, max=0.975, sum=19.925 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.339964744191663,
          "markdown": false
        },
        {
          "value": 0.21994152046783624,
          "description": "min=0.14, mean=0.22, max=0.3, sum=3.299 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6416666666666667,
          "description": "min=0.626, mean=0.642, max=0.652, sum=1.925 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49703931741598933,
          "description": "min=0.441, mean=0.497, max=0.537, sum=1.491 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14913779301489424,
          "description": "min=0.142, mean=0.149, max=0.157, sum=0.447 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44971949324423194,
          "description": "min=0.431, mean=0.45, max=0.473, sum=1.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22939607207059778,
          "description": "min=0.208, mean=0.229, max=0.244, sum=0.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.567,
          "description": "min=0.567, mean=0.567, max=0.567, sum=0.567 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44,
          "description": "min=0.44, mean=0.44, max=0.44, sum=0.44 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18195718654434248,
          "description": "min=0.156, mean=0.182, max=0.205, sum=0.546 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1454550264550264,
          "description": "min=0.123, mean=0.145, max=0.162, sum=0.436 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35251421077315565,
          "description": "min=0.311, mean=0.353, max=0.384, sum=1.058 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9173333333333334,
          "description": "min=0.896, mean=0.917, max=0.936, sum=2.752 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49275536816045606,
          "description": "min=0, mean=0.493, max=1, sum=26.609 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5712121212121212,
          "description": "min=0.1, mean=0.571, max=0.975, sum=18.85 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.66227113635345,
          "markdown": false
        },
        {
          "value": 0.36630409356725147,
          "description": "min=0.2, mean=0.366, max=0.55, sum=5.495 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7479999999999999,
          "description": "min=0.74, mean=0.748, max=0.76, sum=2.244 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5949605221040284,
          "description": "min=0.592, mean=0.595, max=0.6, sum=1.785 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16652011745655915,
          "description": "min=0.165, mean=0.167, max=0.167, sum=0.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6540942012407344,
          "description": "min=0.647, mean=0.654, max=0.66, sum=1.962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2730533859766594,
          "description": "min=0.268, mean=0.273, max=0.279, sum=0.819 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.608,
          "description": "min=0.608, mean=0.608, max=0.608, sum=0.608 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.468,
          "description": "min=0.468, mean=0.468, max=0.468, sum=0.468 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16258919469928643,
          "description": "min=0.154, mean=0.163, max=0.167, sum=0.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4107572751322747,
          "description": "min=0.402, mean=0.411, max=0.42, sum=1.232 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6896233668786421,
          "description": "min=0.68, mean=0.69, max=0.696, sum=2.069 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9503333333333334,
          "description": "min=0.946, mean=0.95, max=0.954, sum=2.851 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4955072296924251,
          "description": "min=0.002, mean=0.496, max=1, sum=26.757 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.609090909090909,
          "description": "min=0.05, mean=0.609, max=0.975, sum=20.1 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8657917351465738,
          "markdown": false
        },
        {
          "value": 0.4071111111111111,
          "description": "min=0.19, mean=0.407, max=0.73, sum=6.107 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8216666666666667,
          "description": "min=0.812, mean=0.822, max=0.827, sum=2.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6566736137653061,
          "description": "min=0.647, mean=0.657, max=0.666, sum=1.97 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29608566298974776,
          "description": "min=0.29, mean=0.296, max=0.301, sum=0.888 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7056823207366739,
          "description": "min=0.7, mean=0.706, max=0.714, sum=2.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31563184414828255,
          "description": "min=0.309, mean=0.316, max=0.322, sum=0.947 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.699,
          "description": "min=0.699, mean=0.699, max=0.699, sum=0.699 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.508,
          "description": "min=0.508, mean=0.508, max=0.508, sum=0.508 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2217125382262997,
          "description": "min=0.219, mean=0.222, max=0.225, sum=0.665 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4498752645502638,
          "description": "min=0.444, mean=0.45, max=0.453, sum=1.35 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7483868294443408,
          "description": "min=0.745, mean=0.748, max=0.752, sum=2.245 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.957,
          "description": "min=0.951, mean=0.957, max=0.96, sum=2.871 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5443897908426464,
          "description": "min=0.222, mean=0.544, max=0.85, sum=29.397 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6272727272727272,
          "description": "min=0.025, mean=0.627, max=0.975, sum=20.7 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2899930436637889,
          "markdown": false
        },
        {
          "value": 0.21961403508771932,
          "description": "min=0.13, mean=0.22, max=0.27, sum=3.294 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6386666666666666,
          "description": "min=0.638, mean=0.639, max=0.64, sum=1.916 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43317656281615613,
          "description": "min=0.417, mean=0.433, max=0.448, sum=1.3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12161534757794057,
          "description": "min=0.112, mean=0.122, max=0.128, sum=0.365 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4930833990161269,
          "description": "min=0.475, mean=0.493, max=0.505, sum=1.479 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2494842989068126,
          "description": "min=0.245, mean=0.249, max=0.258, sum=0.748 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.486,
          "description": "min=0.486, mean=0.486, max=0.486, sum=0.486 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.416,
          "description": "min=0.416, mean=0.416, max=0.416, sum=0.416 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18004587155963303,
          "description": "min=0.156, mean=0.18, max=0.209, sum=0.72 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12886375661375657,
          "description": "min=0.106, mean=0.129, max=0.144, sum=0.387 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3321982457704417,
          "description": "min=0.303, mean=0.332, max=0.348, sum=0.997 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9273333333333333,
          "description": "min=0.92, mean=0.927, max=0.932, sum=2.782 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4880679688031825,
          "description": "min=0, mean=0.488, max=1, sum=26.356 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.593939393939394,
          "description": "min=0.275, mean=0.594, max=0.975, sum=19.6 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3311530516202374,
          "markdown": false
        },
        {
          "value": 0.21518128654970764,
          "description": "min=0.175, mean=0.215, max=0.26, sum=3.228 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.609,
          "description": "min=0.594, mean=0.609, max=0.629, sum=1.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46066534756418576,
          "description": "min=0.419, mean=0.461, max=0.485, sum=1.382 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15381312093617092,
          "description": "min=0.147, mean=0.154, max=0.158, sum=0.461 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.524698076718683,
          "description": "min=0.509, mean=0.525, max=0.537, sum=1.574 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23177797124335245,
          "description": "min=0.224, mean=0.232, max=0.243, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.552,
          "description": "min=0.552, mean=0.552, max=0.552, sum=0.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.438,
          "description": "min=0.438, mean=0.438, max=0.438, sum=0.438 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17851681957186544,
          "description": "min=0.161, mean=0.179, max=0.225, sum=0.714 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1483276455026454,
          "description": "min=0.137, mean=0.148, max=0.163, sum=0.445 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38125183165300675,
          "description": "min=0.347, mean=0.381, max=0.416, sum=1.144 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9283333333333333,
          "description": "min=0.925, mean=0.928, max=0.933, sum=2.785 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4906931444587031,
          "description": "min=0, mean=0.491, max=1, sum=26.497 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47500000000000003,
          "description": "min=0.025, mean=0.475, max=0.975, sum=15.675 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.17121212121212123,
          "markdown": false
        },
        {
          "value": 0.20687719298245613,
          "description": "min=0.14, mean=0.207, max=0.254, sum=1.034 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.552,
          "description": "min=0.552, mean=0.552, max=0.552, sum=0.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38935766339772926,
          "description": "min=0.389, mean=0.389, max=0.389, sum=0.389 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10301926896303132,
          "description": "min=0.103, mean=0.103, max=0.103, sum=0.103 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4640855445555752,
          "description": "min=0.464, mean=0.464, max=0.464, sum=0.464 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19836760191150613,
          "description": "min=0.198, mean=0.198, max=0.198, sum=0.198 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18042813455657492,
          "description": "min=0.18, mean=0.18, max=0.18, sum=0.18 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.911,
          "description": "min=0.911, mean=0.911, max=0.911, sum=0.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33307716875468274,
          "description": "min=0.001, mean=0.333, max=0.927, sum=5.995 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45,
          "description": "min=0.175, mean=0.45, max=0.975, sum=4.95 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.22631701631701634,
          "markdown": false
        },
        {
          "value": 0.2121052631578947,
          "description": "min=0.16, mean=0.212, max=0.29, sum=1.061 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.547,
          "description": "min=0.547, mean=0.547, max=0.547, sum=0.547 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44869513696457247,
          "description": "min=0.449, mean=0.449, max=0.449, sum=0.449 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13109020655004933,
          "description": "min=0.131, mean=0.131, max=0.131, sum=0.131 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5229768252994325,
          "description": "min=0.523, mean=0.523, max=0.523, sum=0.523 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22738715021444486,
          "description": "min=0.227, mean=0.227, max=0.227, sum=0.227 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.154434250764526,
          "description": "min=0.154, mean=0.154, max=0.154, sum=0.154 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.916,
          "description": "min=0.916, mean=0.916, max=0.916, sum=0.916 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44837567354282437,
          "description": "min=0.01, mean=0.448, max=0.985, sum=8.071 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48863636363636365,
          "description": "min=0.15, mean=0.489, max=0.975, sum=5.375 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.14974358974358976,
          "markdown": false
        },
        {
          "value": 0.23500584795321638,
          "description": "min=0.167, mean=0.235, max=0.33, sum=3.525 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7226666666666667,
          "description": "min=0.697, mean=0.723, max=0.766, sum=2.168 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0497772820026842,
          "description": "min=0.05, mean=0.05, max=0.05, sum=0.149 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15857963279707157,
          "description": "min=0.152, mean=0.159, max=0.164, sum=0.476 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42376820534695847,
          "description": "min=0.227, mean=0.424, max=0.532, sum=1.271 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07376443691909672,
          "description": "min=0.074, mean=0.074, max=0.074, sum=0.221 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.10129969418960244,
          "description": "min=0.058, mean=0.101, max=0.136, sum=0.405 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.30333333333333334,
          "description": "min=0.162, mean=0.303, max=0.502, sum=0.91 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32887358622117774,
          "description": "min=0, mean=0.329, max=0.991, sum=17.759 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3507575757575757,
          "description": "min=0, mean=0.351, max=0.85, sum=11.575 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1858974358974359,
          "markdown": false
        },
        {
          "value": 0.2734502923976609,
          "description": "min=0.19, mean=0.273, max=0.36, sum=4.102 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6983333333333334,
          "description": "min=0.672, mean=0.698, max=0.714, sum=2.095 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05305645886768214,
          "description": "min=0.053, mean=0.053, max=0.053, sum=0.159 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16184307849771043,
          "description": "min=0.159, mean=0.162, max=0.167, sum=0.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30281096844711025,
          "description": "min=0.153, mean=0.303, max=0.389, sum=0.908 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10672699918485114,
          "description": "min=0.107, mean=0.107, max=0.107, sum=0.32 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.16169724770642202,
          "description": "min=0.15, mean=0.162, max=0.176, sum=0.647 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2713333333333333,
          "description": "min=0.092, mean=0.271, max=0.484, sum=0.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4225225679997762,
          "description": "min=0, mean=0.423, max=0.975, sum=22.816 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.375,
          "description": "min=0, mean=0.375, max=0.95, sum=12.375 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6221815633384042,
          "markdown": false
        },
        {
          "value": 0.28651461988304094,
          "description": "min=0.167, mean=0.287, max=0.43, sum=4.298 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.731,
          "description": "min=0.712, mean=0.731, max=0.746, sum=2.193 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5725951072978767,
          "description": "min=0.545, mean=0.573, max=0.6, sum=1.718 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2461285688311032,
          "description": "min=0.244, mean=0.246, max=0.248, sum=0.738 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5613201936765554,
          "description": "min=0.557, mean=0.561, max=0.566, sum=1.684 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26591098840755784,
          "description": "min=0.255, mean=0.266, max=0.274, sum=0.798 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.66,
          "description": "min=0.66, mean=0.66, max=0.66, sum=0.66 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2029816513761468,
          "description": "min=0.165, mean=0.203, max=0.249, sum=0.812 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25959669312169276,
          "description": "min=0.229, mean=0.26, max=0.288, sum=0.779 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41868435186381264,
          "description": "min=0.4, mean=0.419, max=0.428, sum=1.256 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9436666666666667,
          "description": "min=0.929, mean=0.944, max=0.958, sum=2.831 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4905409716584098,
          "description": "min=0, mean=0.491, max=1, sum=26.489 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5795454545454547,
          "description": "min=0.075, mean=0.58, max=0.975, sum=19.125 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4763117490592463,
          "markdown": false
        },
        {
          "value": 0.22935672514619884,
          "description": "min=0.18, mean=0.229, max=0.33, sum=3.44 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7103333333333333,
          "description": "min=0.696, mean=0.71, max=0.721, sum=2.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5262433008374211,
          "description": "min=0.497, mean=0.526, max=0.543, sum=1.579 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2180459446078801,
          "description": "min=0.215, mean=0.218, max=0.221, sum=0.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5357020972773482,
          "description": "min=0.52, mean=0.536, max=0.558, sum=1.607 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26839685415319225,
          "description": "min=0.267, mean=0.268, max=0.27, sum=0.805 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.597,
          "description": "min=0.597, mean=0.597, max=0.597, sum=0.597 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.454,
          "description": "min=0.454, mean=0.454, max=0.454, sum=0.454 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17316513761467892,
          "description": "min=0.145, mean=0.173, max=0.206, sum=0.693 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2139329365079363,
          "description": "min=0.21, mean=0.214, max=0.221, sum=0.642 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4706976603850948,
          "description": "min=0.45, mean=0.471, max=0.501, sum=1.412 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9083333333333333,
          "description": "min=0.898, mean=0.908, max=0.919, sum=2.725 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5001070006147802,
          "description": "min=0, mean=0.5, max=1, sum=27.006 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5363636363636364,
          "description": "min=0.175, mean=0.536, max=0.975, sum=17.7 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5526107226107226,
          "markdown": false
        },
        {
          "value": 0.28410526315789475,
          "description": "min=0.19, mean=0.284, max=0.42, sum=1.421 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.71,
          "description": "min=0.71, mean=0.71, max=0.71, sum=0.71 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5523890751544673,
          "description": "min=0.552, mean=0.552, max=0.552, sum=0.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24052468144533276,
          "description": "min=0.241, mean=0.241, max=0.241, sum=0.241 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5368535244140038,
          "description": "min=0.537, mean=0.537, max=0.537, sum=0.537 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2568299506065861,
          "description": "min=0.257, mean=0.257, max=0.257, sum=0.257 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21865443425076453,
          "description": "min=0.219, mean=0.219, max=0.219, sum=0.219 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.936,
          "description": "min=0.936, mean=0.936, max=0.936, sum=0.936 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5047868294149912,
          "description": "min=0.008, mean=0.505, max=0.98, sum=9.086 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5454545454545454,
          "description": "min=0.1, mean=0.545, max=0.975, sum=6 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6022144522144522,
          "markdown": false
        },
        {
          "value": 0.3853684210526316,
          "description": "min=0.18, mean=0.385, max=0.71, sum=1.927 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.666,
          "description": "min=0.666, mean=0.666, max=0.666, sum=0.666 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6277072207288055,
          "description": "min=0.628, mean=0.628, max=0.628, sum=0.628 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28794490645078735,
          "description": "min=0.288, mean=0.288, max=0.288, sum=0.288 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5608161827325524,
          "description": "min=0.561, mean=0.561, max=0.561, sum=0.561 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26734169068478314,
          "description": "min=0.267, mean=0.267, max=0.267, sum=0.267 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23394495412844038,
          "description": "min=0.234, mean=0.234, max=0.234, sum=0.234 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.903,
          "description": "min=0.903, mean=0.903, max=0.903, sum=0.903 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5325232651113918,
          "description": "min=0.054, mean=0.533, max=0.947, sum=9.585 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6045454545454545,
          "description": "min=0.075, mean=0.605, max=0.9, sum=6.65 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8224708624708624,
          "markdown": false
        },
        {
          "value": 0.49617543859649127,
          "description": "min=0.28, mean=0.496, max=0.81, sum=2.481 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.813,
          "description": "min=0.813, mean=0.813, max=0.813, sum=0.813 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6567447414077484,
          "description": "min=0.657, mean=0.657, max=0.657, sum=0.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35638449124084753,
          "description": "min=0.356, mean=0.356, max=0.356, sum=0.356 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6212987885688864,
          "description": "min=0.621, mean=0.621, max=0.621, sum=0.621 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3253423128866467,
          "description": "min=0.325, mean=0.325, max=0.325, sum=0.325 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.26605504587155965,
          "description": "min=0.266, mean=0.266, max=0.266, sum=0.266 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.913,
          "description": "min=0.913, mean=0.913, max=0.913, sum=0.913 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5075946750657245,
          "description": "min=0.006, mean=0.508, max=0.998, sum=9.137 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7181818181818181,
          "description": "min=0.1, mean=0.718, max=0.975, sum=7.9 (11)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9235431235431235,
          "markdown": false
        },
        {
          "value": 0.5514385964912281,
          "description": "min=0.34, mean=0.551, max=0.84, sum=2.757 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.847,
          "description": "min=0.847, mean=0.847, max=0.847, sum=0.847 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6614214785759094,
          "description": "min=0.661, mean=0.661, max=0.661, sum=0.661 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3753249636782112,
          "description": "min=0.375, mean=0.375, max=0.375, sum=0.375 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6326996444457361,
          "description": "min=0.633, mean=0.633, max=0.633, sum=0.633 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33296543407590734,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.42048929663608564,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.953,
          "description": "min=0.953, mean=0.953, max=0.953, sum=0.953 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.57420608635975,
          "description": "min=0.32, mean=0.574, max=0.8, sum=10.336 (18)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6681818181818182,
          "description": "min=0.075, mean=0.668, max=0.975, sum=7.35 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6102097902097903,
          "markdown": false
        },
        {
          "value": 0.392140350877193,
          "description": "min=0.26, mean=0.392, max=0.59, sum=1.961 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.706,
          "description": "min=0.706, mean=0.706, max=0.706, sum=0.706 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5960691234215144,
          "description": "min=0.596, mean=0.596, max=0.596, sum=0.596 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26403309290317406,
          "description": "min=0.264, mean=0.264, max=0.264, sum=0.264 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5499198184166533,
          "description": "min=0.55, mean=0.55, max=0.55, sum=0.55 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32122644280851614,
          "description": "min=0.321, mean=0.321, max=0.321, sum=0.321 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.22324159021406728,
          "description": "min=0.223, mean=0.223, max=0.223, sum=0.223 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.871,
          "description": "min=0.871, mean=0.871, max=0.871, sum=0.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5031757189564859,
          "description": "min=0.01, mean=0.503, max=0.998, sum=9.057 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6090909090909092,
          "description": "min=0.1, mean=0.609, max=0.95, sum=6.7 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8078088578088578,
          "markdown": false
        },
        {
          "value": 0.46614035087719297,
          "description": "min=0.26, mean=0.466, max=0.79, sum=2.331 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.732,
          "description": "min=0.732, mean=0.732, max=0.732, sum=0.732 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6567284210865421,
          "description": "min=0.657, mean=0.657, max=0.657, sum=0.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30927547433853436,
          "description": "min=0.309, mean=0.309, max=0.309, sum=0.309 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5801102053016279,
          "description": "min=0.58, mean=0.58, max=0.58, sum=0.58 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35074944218906556,
          "description": "min=0.351, mean=0.351, max=0.351, sum=0.351 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.27370030581039756,
          "description": "min=0.274, mean=0.274, max=0.274, sum=0.274 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.957,
          "description": "min=0.957, mean=0.957, max=0.957, sum=0.957 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4894481246425394,
          "description": "min=0.006, mean=0.489, max=0.968, sum=8.81 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6727272727272727,
          "description": "min=0.075, mean=0.673, max=0.975, sum=7.4 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9587645687645687,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5571929824561404,
          "description": "min=0.26, mean=0.557, max=0.91, sum=2.786 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.859,
          "description": "min=0.859, mean=0.859, max=0.859, sum=0.859 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.709497495841271,
          "description": "min=0.709, mean=0.709, max=0.709, sum=0.709 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3997609830959401,
          "description": "min=0.4, mean=0.4, max=0.4, sum=0.4 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6365724774019619,
          "description": "min=0.637, mean=0.637, max=0.637, sum=0.637 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4139340894194124,
          "description": "min=0.414, mean=0.414, max=0.414, sum=0.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.43425076452599387,
          "description": "min=0.434, mean=0.434, max=0.434, sum=0.434 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.954,
          "description": "min=0.954, mean=0.954, max=0.954, sum=0.954 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.551334119704094,
          "description": "min=0.125, mean=0.551, max=0.892, sum=9.924 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7,
          "description": "min=0.1, mean=0.7, max=0.975, sum=7.7 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3719114219114219,
          "markdown": false
        },
        {
          "value": 0.34585964912280703,
          "description": "min=0.219, mean=0.346, max=0.53, sum=1.729 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.729,
          "description": "min=0.729, mean=0.729, max=0.729, sum=0.729 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2987402817318288,
          "description": "min=0.299, mean=0.299, max=0.299, sum=0.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20966482260352876,
          "description": "min=0.21, mean=0.21, max=0.21, sum=0.21 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5302078541276196,
          "description": "min=0.53, mean=0.53, max=0.53, sum=0.53 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20395081036123316,
          "description": "min=0.204, mean=0.204, max=0.204, sum=0.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2018348623853211,
          "description": "min=0.202, mean=0.202, max=0.202, sum=0.202 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.699,
          "description": "min=0.699, mean=0.699, max=0.699, sum=0.699 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4828512879651531,
          "description": "min=0.122, mean=0.483, max=0.818, sum=8.691 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45909090909090916,
          "description": "min=0, mean=0.459, max=0.9, sum=5.05 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6221212121212122,
          "markdown": false
        },
        {
          "value": 0.38484210526315793,
          "description": "min=0.184, mean=0.385, max=0.68, sum=1.924 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.67,
          "description": "min=0.67, mean=0.67, max=0.67, sum=0.67 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5528194590567359,
          "description": "min=0.553, mean=0.553, max=0.553, sum=0.553 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22422961995096835,
          "description": "min=0.224, mean=0.224, max=0.224, sum=0.224 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5749345098495453,
          "description": "min=0.575, mean=0.575, max=0.575, sum=0.575 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3036739587215963,
          "description": "min=0.304, mean=0.304, max=0.304, sum=0.304 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.23547400611620795,
          "description": "min=0.235, mean=0.235, max=0.235, sum=0.235 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.906,
          "description": "min=0.906, mean=0.906, max=0.906, sum=0.906 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5635727085389178,
          "description": "min=0.116, mean=0.564, max=0.974, sum=10.144 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6431818181818182,
          "description": "min=0.2, mean=0.643, max=0.975, sum=7.075 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7154545454545455,
          "markdown": false
        },
        {
          "value": 0.4236140350877193,
          "description": "min=0.228, mean=0.424, max=0.7, sum=2.118 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.748,
          "description": "min=0.748, mean=0.748, max=0.748, sum=0.748 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6066076692752655,
          "description": "min=0.607, mean=0.607, max=0.607, sum=0.607 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26608326669652704,
          "description": "min=0.266, mean=0.266, max=0.266, sum=0.266 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6295785534387982,
          "description": "min=0.63, mean=0.63, max=0.63, sum=0.63 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32414193488324744,
          "description": "min=0.324, mean=0.324, max=0.324, sum=0.324 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3149847094801223,
          "description": "min=0.315, mean=0.315, max=0.315, sum=0.315 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.707,
          "description": "min=0.707, mean=0.707, max=0.707, sum=0.707 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5693148383516141,
          "description": "min=0.139, mean=0.569, max=0.946, sum=10.248 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6204545454545454,
          "description": "min=0.125, mean=0.62, max=0.875, sum=6.825 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8611188811188811,
          "markdown": false
        },
        {
          "value": 0.541719298245614,
          "description": "min=0.27, mean=0.542, max=0.83, sum=2.709 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.842,
          "description": "min=0.842, mean=0.842, max=0.842, sum=0.842 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6436697691254157,
          "description": "min=0.644, mean=0.644, max=0.644, sum=0.644 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30018094571517623,
          "description": "min=0.3, mean=0.3, max=0.3, sum=0.3 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6249254915559919,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3528008659962099,
          "description": "min=0.353, mean=0.353, max=0.353, sum=0.353 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3318042813455658,
          "description": "min=0.332, mean=0.332, max=0.332, sum=0.332 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.952,
          "description": "min=0.952, mean=0.952, max=0.952, sum=0.952 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5198588163222009,
          "description": "min=0.06, mean=0.52, max=0.863, sum=9.357 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6636363636363636,
          "description": "min=0.1, mean=0.664, max=0.975, sum=7.3 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7516679834811092,
          "markdown": false
        },
        {
          "value": 0.41770760233918125,
          "description": "min=0.17, mean=0.418, max=0.75, sum=6.266 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7666666666666667,
          "description": "min=0.756, mean=0.767, max=0.777, sum=2.3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6318169391667601,
          "description": "min=0.601, mean=0.632, max=0.664, sum=1.895 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3175020164111731,
          "description": "min=0.306, mean=0.318, max=0.324, sum=0.953 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5979278798197498,
          "description": "min=0.575, mean=0.598, max=0.61, sum=1.794 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3132392185201357,
          "description": "min=0.304, mean=0.313, max=0.32, sum=0.94 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.678,
          "description": "min=0.678, mean=0.678, max=0.678, sum=0.678 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.504,
          "description": "min=0.504, mean=0.504, max=0.504, sum=0.504 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19673802242609584,
          "description": "min=0.177, mean=0.197, max=0.213, sum=0.59 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3414910052910049,
          "description": "min=0.332, mean=0.341, max=0.354, sum=1.024 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6120938886543282,
          "description": "min=0.592, mean=0.612, max=0.629, sum=1.836 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9356666666666666,
          "description": "min=0.933, mean=0.936, max=0.94, sum=2.807 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48044223702694133,
          "description": "min=0.047, mean=0.48, max=0.97, sum=25.944 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6439393939393939,
          "description": "min=0.025, mean=0.644, max=0.975, sum=21.25 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2912077355347656,
          "markdown": false
        },
        {
          "value": 0.2124327485380117,
          "description": "min=0.17, mean=0.212, max=0.31, sum=3.186 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6653333333333333,
          "description": "min=0.649, mean=0.665, max=0.674, sum=1.996 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5173113464127798,
          "description": "min=0.492, mean=0.517, max=0.532, sum=1.552 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16163226517271406,
          "description": "min=0.152, mean=0.162, max=0.17, sum=0.485 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5005776676014201,
          "description": "min=0.463, mean=0.501, max=0.532, sum=1.502 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26693937921563893,
          "description": "min=0.26, mean=0.267, max=0.281, sum=0.801 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.53,
          "description": "min=0.53, mean=0.53, max=0.53, sum=0.53 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.412,
          "description": "min=0.412, mean=0.412, max=0.412, sum=0.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1437308868501529,
          "description": "min=0.133, mean=0.144, max=0.162, sum=0.431 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13970383597883587,
          "description": "min=0.109, mean=0.14, max=0.166, sum=0.419 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31652617829212154,
          "description": "min=0.256, mean=0.317, max=0.363, sum=0.95 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9123333333333333,
          "description": "min=0.904, mean=0.912, max=0.922, sum=2.737 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4728366689674401,
          "description": "min=0.042, mean=0.473, max=0.947, sum=25.533 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5015151515151516,
          "description": "min=0.025, mean=0.502, max=0.975, sum=16.55 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5578754949166518,
          "markdown": false
        },
        {
          "value": 0.3803040935672514,
          "description": "min=0.24, mean=0.38, max=0.61, sum=5.705 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.682,
          "description": "min=0.635, mean=0.682, max=0.729, sum=2.046 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5970096000459133,
          "description": "min=0.556, mean=0.597, max=0.634, sum=1.791 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2760483569290458,
          "description": "min=0.271, mean=0.276, max=0.282, sum=0.828 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5674897299434086,
          "description": "min=0.537, mean=0.567, max=0.594, sum=1.702 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27860575089348755,
          "description": "min=0.264, mean=0.279, max=0.288, sum=0.836 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.641,
          "description": "min=0.641, mean=0.641, max=0.641, sum=0.641 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.502,
          "description": "min=0.502, mean=0.502, max=0.502, sum=0.502 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.15545361875637104,
          "description": "min=0.136, mean=0.155, max=0.185, sum=0.466 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18462896825396802,
          "description": "min=0.179, mean=0.185, max=0.192, sum=0.554 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35718542292055805,
          "description": "min=0.324, mean=0.357, max=0.375, sum=1.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9206666666666669,
          "description": "min=0.917, mean=0.921, max=0.923, sum=2.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4783299102254815,
          "description": "min=0.003, mean=0.478, max=1, sum=25.83 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6045454545454545,
          "description": "min=0.05, mean=0.605, max=0.975, sum=19.95 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.23055057660174458,
          "markdown": false
        },
        {
          "value": 0.21771929824561406,
          "description": "min=0.15, mean=0.218, max=0.281, sum=3.266 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.594,
          "description": "min=0.535, mean=0.594, max=0.631, sum=1.782 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.48150959406800437,
          "description": "min=0.453, mean=0.482, max=0.515, sum=1.445 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14670404179376148,
          "description": "min=0.139, mean=0.147, max=0.151, sum=0.44 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.47851717891712475,
          "description": "min=0.446, mean=0.479, max=0.506, sum=1.436 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24255939370982219,
          "description": "min=0.241, mean=0.243, max=0.245, sum=0.728 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.522,
          "description": "min=0.522, mean=0.522, max=0.522, sum=0.522 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.43,
          "description": "min=0.43, mean=0.43, max=0.43, sum=0.43 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.18603465851172274,
          "description": "min=0.165, mean=0.186, max=0.216, sum=0.558 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14012791005291,
          "description": "min=0.119, mean=0.14, max=0.167, sum=0.42 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2838824123845733,
          "description": "min=0.266, mean=0.284, max=0.295, sum=0.852 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8603333333333333,
          "description": "min=0.792, mean=0.86, max=0.922, sum=2.581 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41152337126555366,
          "description": "min=0, mean=0.412, max=1, sum=22.222 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4734848484848485,
          "description": "min=0, mean=0.473, max=0.975, sum=15.625 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.13375380644568632,
          "markdown": false
        },
        {
          "value": 0.20567251461988303,
          "description": "min=0.14, mean=0.206, max=0.28, sum=3.085 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43566666666666665,
          "description": "min=0.404, mean=0.436, max=0.457, sum=1.307 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3669650821225828,
          "description": "min=0.334, mean=0.367, max=0.396, sum=1.101 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08399089853474369,
          "description": "min=0.079, mean=0.084, max=0.088, sum=0.252 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.381423207180998,
          "description": "min=0.365, mean=0.381, max=0.403, sum=1.144 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20229238580626874,
          "description": "min=0.198, mean=0.202, max=0.205, sum=0.607 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.401,
          "description": "min=0.401, mean=0.401, max=0.401, sum=0.401 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.326,
          "description": "min=0.326, mean=0.326, max=0.326, sum=0.326 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.17787971457696228,
          "description": "min=0.159, mean=0.178, max=0.19, sum=0.534 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10532936507936512,
          "description": "min=0.082, mean=0.105, max=0.123, sum=0.316 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.300592144197253,
          "description": "min=0.275, mean=0.301, max=0.346, sum=0.902 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.534,
          "description": "min=0.489, mean=0.534, max=0.558, sum=1.602 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4735149158411243,
          "description": "min=0, mean=0.474, max=0.994, sum=25.57 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43787878787878787,
          "description": "min=0, mean=0.438, max=0.975, sum=14.45 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10483119031506129,
          "markdown": false
        },
        {
          "value": 0.2103157894736842,
          "description": "min=0.053, mean=0.21, max=0.31, sum=3.155 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5066666666666667,
          "description": "min=0.421, mean=0.507, max=0.575, sum=1.52 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20535614023925777,
          "description": "min=0.191, mean=0.205, max=0.221, sum=0.616 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.057147528877813734,
          "description": "min=0.054, mean=0.057, max=0.061, sum=0.171 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2734675120722885,
          "description": "min=0.269, mean=0.273, max=0.278, sum=0.82 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.16579958101328882,
          "description": "min=0.15, mean=0.166, max=0.187, sum=0.497 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.294,
          "description": "min=0.294, mean=0.294, max=0.294, sum=0.294 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.318,
          "description": "min=0.318, mean=0.318, max=0.318, sum=0.318 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.18450560652395517,
          "description": "min=0.18, mean=0.185, max=0.187, sum=0.554 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08609259259259262,
          "description": "min=0.051, mean=0.086, max=0.134, sum=0.258 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.267882893215826,
          "description": "min=0.17, mean=0.268, max=0.399, sum=0.804 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8056666666666666,
          "description": "min=0.787, mean=0.806, max=0.819, sum=2.417 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.435870046986927,
          "description": "min=0, mean=0.436, max=1, sum=23.537 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3954545454545455,
          "description": "min=0, mean=0.395, max=0.975, sum=13.05 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.9027696441489546,
          "markdown": false
        },
        {
          "value": 0.5369590643274853,
          "description": "min=0.24, mean=0.537, max=0.83, sum=8.054 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.858,
          "description": "min=0.854, mean=0.858, max=0.861, sum=2.574 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6644210581739292,
          "description": "min=0.643, mean=0.664, max=0.682, sum=1.993 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3564629891973459,
          "description": "min=0.349, mean=0.356, max=0.361, sum=1.069 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.7213345530431851,
          "description": "min=0.719, mean=0.721, max=0.725, sum=2.164 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.45040220156517236,
          "description": "min=0.427, mean=0.45, max=0.465, sum=1.351 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.729,
          "description": "min=0.729, mean=0.729, max=0.729, sum=0.729 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.578,
          "description": "min=0.578, mean=0.578, max=0.578, sum=0.578 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.491335372069317,
          "description": "min=0.448, mean=0.491, max=0.521, sum=1.474 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33500119047619026,
          "description": "min=0.322, mean=0.335, max=0.353, sum=1.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6326849780192724,
          "description": "min=0.603, mean=0.633, max=0.652, sum=1.898 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8326666666666666,
          "description": "min=0.814, mean=0.833, max=0.868, sum=2.498 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5588650073949972,
          "description": "min=0.253, mean=0.559, max=0.863, sum=30.179 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7053030303030302,
          "description": "min=0.05, mean=0.705, max=0.95, sum=23.275 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8637256699548135,
          "markdown": false
        },
        {
          "value": 0.5309473684210526,
          "description": "min=0.24, mean=0.531, max=0.82, sum=7.964 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8366666666666666,
          "description": "min=0.829, mean=0.837, max=0.844, sum=2.51 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6459531095726224,
          "description": "min=0.637, mean=0.646, max=0.664, sum=1.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3200640288704773,
          "description": "min=0.311, mean=0.32, max=0.326, sum=0.96 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.658783235208417,
          "description": "min=0.655, mean=0.659, max=0.663, sum=1.976 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3532761321768228,
          "description": "min=0.339, mean=0.353, max=0.363, sum=1.06 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.703,
          "description": "min=0.703, mean=0.703, max=0.703, sum=0.703 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.54,
          "description": "min=0.54, mean=0.54, max=0.54, sum=0.54 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5152905198776758,
          "description": "min=0.48, mean=0.515, max=0.547, sum=1.546 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3732579365079361,
          "description": "min=0.357, mean=0.373, max=0.39, sum=1.12 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6388640932298691,
          "description": "min=0.614, mean=0.639, max=0.663, sum=1.917 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9343333333333333,
          "description": "min=0.919, mean=0.934, max=0.945, sum=2.803 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46278978149694866,
          "description": "min=0.082, mean=0.463, max=0.851, sum=24.991 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6712121212121211,
          "description": "min=0.125, mean=0.671, max=0.975, sum=22.15 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.377271245624972,
          "markdown": false
        },
        {
          "value": 0.23079532163742691,
          "description": "min=0.2, mean=0.231, max=0.281, sum=3.462 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5756666666666667,
          "description": "min=0.543, mean=0.576, max=0.592, sum=1.727 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4630759323159577,
          "description": "min=0.428, mean=0.463, max=0.5, sum=1.389 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13187631785928275,
          "description": "min=0.124, mean=0.132, max=0.139, sum=0.396 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4995085831746681,
          "description": "min=0.464, mean=0.5, max=0.519, sum=1.499 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2548639356870548,
          "description": "min=0.244, mean=0.255, max=0.264, sum=0.765 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.534,
          "description": "min=0.534, mean=0.534, max=0.534, sum=0.534 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.452,
          "description": "min=0.452, mean=0.452, max=0.452, sum=0.452 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23904179408766565,
          "description": "min=0.209, mean=0.239, max=0.286, sum=0.717 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2441616402116399,
          "description": "min=0.231, mean=0.244, max=0.26, sum=0.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4817143719085842,
          "description": "min=0.448, mean=0.482, max=0.523, sum=1.445 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9103333333333333,
          "description": "min=0.903, mean=0.91, max=0.916, sum=2.731 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4710066762167616,
          "description": "min=0.02, mean=0.471, max=0.874, sum=25.434 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45833333333333337,
          "description": "min=0, mean=0.458, max=0.85, sum=15.125 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2438772758572536,
          "markdown": false
        },
        {
          "value": 0.20512280701754387,
          "description": "min=0.09, mean=0.205, max=0.272, sum=3.077 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41,
          "description": "min=0.388, mean=0.41, max=0.43, sum=1.23 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.29864937428822036,
          "description": "min=0.277, mean=0.299, max=0.335, sum=0.896 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05326475617936846,
          "description": "min=0.048, mean=0.053, max=0.057, sum=0.16 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23984494964196315,
          "description": "min=0.209, mean=0.24, max=0.263, sum=0.72 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.19638729492261867,
          "description": "min=0.188, mean=0.196, max=0.202, sum=0.589 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.405,
          "description": "min=0.405, mean=0.405, max=0.405, sum=0.405 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.386,
          "description": "min=0.386, mean=0.386, max=0.386, sum=0.386 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20744138634046894,
          "description": "min=0.173, mean=0.207, max=0.257, sum=0.622 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17431719576719562,
          "description": "min=0.152, mean=0.174, max=0.213, sum=0.523 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4244404820446352,
          "description": "min=0.396, mean=0.424, max=0.469, sum=1.273 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8866666666666667,
          "description": "min=0.871, mean=0.887, max=0.901, sum=2.66 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4988205867192775,
          "description": "min=0, mean=0.499, max=1, sum=26.936 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47500000000000003,
          "description": "min=0.125, mean=0.475, max=0.925, sum=15.675 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.10817286162113748,
          "markdown": false
        },
        {
          "value": 0.201766081871345,
          "description": "min=0.11, mean=0.202, max=0.28, sum=3.026 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37799999999999995,
          "description": "min=0.364, mean=0.378, max=0.397, sum=1.134 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1187630501762329,
          "description": "min=0.11, mean=0.119, max=0.126, sum=0.356 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.012133718750385417,
          "description": "min=0.009, mean=0.012, max=0.018, sum=0.036 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.08303504557607948,
          "description": "min=0.026, mean=0.083, max=0.115, sum=0.249 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.09086419903543015,
          "description": "min=0.063, mean=0.091, max=0.113, sum=0.273 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27,
          "description": "min=0.27, mean=0.27, max=0.27, sum=0.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.266,
          "description": "min=0.266, mean=0.266, max=0.266, sum=0.266 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.191131498470948,
          "description": "min=0.18, mean=0.191, max=0.213, sum=0.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10653478835978836,
          "description": "min=0.071, mean=0.107, max=0.133, sum=0.32 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2757254036023355,
          "description": "min=0.177, mean=0.276, max=0.327, sum=0.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7693333333333333,
          "description": "min=0.724, mean=0.769, max=0.808, sum=2.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49665917233754203,
          "description": "min=0, mean=0.497, max=1, sum=26.82 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3757575757575758,
          "description": "min=0.05, mean=0.376, max=0.975, sum=12.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6617249417249418,
          "markdown": false
        },
        {
          "value": 0.5299649122807017,
          "description": "min=0.26, mean=0.53, max=0.8, sum=2.65 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.666,
          "description": "min=0.666, mean=0.666, max=0.666, sum=0.666 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5846601621436455,
          "description": "min=0.585, mean=0.585, max=0.585, sum=0.585 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3309794595447127,
          "description": "min=0.331, mean=0.331, max=0.331, sum=0.331 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5593911419045751,
          "description": "min=0.559, mean=0.559, max=0.559, sum=0.559 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4167691534016683,
          "description": "min=0.417, mean=0.417, max=0.417, sum=0.417 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5137614678899083,
          "description": "min=0.514, mean=0.514, max=0.514, sum=0.514 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.844,
          "description": "min=0.844, mean=0.844, max=0.844, sum=0.844 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4220761773099496,
          "description": "min=0.024, mean=0.422, max=0.824, sum=7.597 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6886363636363636,
          "description": "min=0.025, mean=0.689, max=0.975, sum=7.575 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7175058275058275,
          "markdown": false
        },
        {
          "value": 0.31312280701754386,
          "description": "min=0.12, mean=0.313, max=0.66, sum=1.566 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.817,
          "description": "min=0.817, mean=0.817, max=0.817, sum=0.817 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.546599991762967,
          "description": "min=0.547, mean=0.547, max=0.547, sum=0.547 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2871379631388369,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6270354958497198,
          "description": "min=0.627, mean=0.627, max=0.627, sum=0.627 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3977545370248786,
          "description": "min=0.398, mean=0.398, max=0.398, sum=0.398 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.25535168195718655,
          "description": "min=0.255, mean=0.255, max=0.255, sum=0.255 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.912,
          "description": "min=0.912, mean=0.912, max=0.912, sum=0.912 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5254285459217098,
          "description": "min=0.133, mean=0.525, max=0.863, sum=9.458 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.640909090909091,
          "description": "min=0.2, mean=0.641, max=0.95, sum=7.05 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.26995337995338,
          "markdown": false
        },
        {
          "value": 0.23210526315789473,
          "description": "min=0.2, mean=0.232, max=0.29, sum=1.161 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.624,
          "description": "min=0.624, mean=0.624, max=0.624, sum=0.624 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42019517663794076,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14546689822682907,
          "description": "min=0.145, mean=0.145, max=0.145, sum=0.145 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4521647378074364,
          "description": "min=0.452, mean=0.452, max=0.452, sum=0.452 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23753496056157644,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.24770642201834864,
          "description": "min=0.248, mean=0.248, max=0.248, sum=0.248 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.89,
          "description": "min=0.89, mean=0.89, max=0.89, sum=0.89 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39345093425226885,
          "description": "min=0, mean=0.393, max=0.996, sum=7.082 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47500000000000003,
          "description": "min=0.175, mean=0.475, max=0.975, sum=5.225 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3690909090909091,
          "markdown": false
        },
        {
          "value": 0.22210526315789475,
          "description": "min=0.18, mean=0.222, max=0.27, sum=1.111 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.648,
          "description": "min=0.648, mean=0.648, max=0.648, sum=0.648 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5060331991298288,
          "description": "min=0.506, mean=0.506, max=0.506, sum=0.506 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1431948167839223,
          "description": "min=0.143, mean=0.143, max=0.143, sum=0.143 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.57068667733919,
          "description": "min=0.571, mean=0.571, max=0.571, sum=0.571 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18270531445590665,
          "description": "min=0.183, mean=0.183, max=0.183, sum=0.183 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.17889908256880735,
          "description": "min=0.179, mean=0.179, max=0.179, sum=0.179 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.876,
          "description": "min=0.876, mean=0.876, max=0.876, sum=0.876 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4990473523687277,
          "description": "min=0, mean=0.499, max=0.985, sum=8.983 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.631818181818182,
          "description": "min=0.175, mean=0.632, max=0.975, sum=6.95 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3233799533799534,
          "markdown": false
        },
        {
          "value": 0.275859649122807,
          "description": "min=0.219, mean=0.276, max=0.34, sum=1.379 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.65,
          "description": "min=0.65, mean=0.65, max=0.65, sum=0.65 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5239003837979788,
          "description": "min=0.524, mean=0.524, max=0.524, sum=0.524 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19300226376410895,
          "description": "min=0.193, mean=0.193, max=0.193, sum=0.193 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5136843159783826,
          "description": "min=0.514, mean=0.514, max=0.514, sum=0.514 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23848247289290064,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.16972477064220184,
          "description": "min=0.17, mean=0.17, max=0.17, sum=0.17 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.694,
          "description": "min=0.694, mean=0.694, max=0.694, sum=0.694 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43087088541137863,
          "description": "min=0.06, mean=0.431, max=0.811, sum=7.756 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5954545454545455,
          "description": "min=0.275, mean=0.595, max=0.925, sum=6.55 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.46615384615384614,
          "markdown": false
        },
        {
          "value": 0.30533333333333335,
          "description": "min=0.167, mean=0.305, max=0.48, sum=1.527 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.616,
          "description": "min=0.616, mean=0.616, max=0.616, sum=0.616 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5062845788047843,
          "description": "min=0.506, mean=0.506, max=0.506, sum=0.506 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16419040044922398,
          "description": "min=0.164, mean=0.164, max=0.164, sum=0.164 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5920301139461878,
          "description": "min=0.592, mean=0.592, max=0.592, sum=0.592 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18079535886869938,
          "description": "min=0.181, mean=0.181, max=0.181, sum=0.181 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1834862385321101,
          "description": "min=0.183, mean=0.183, max=0.183, sum=0.183 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.907,
          "description": "min=0.907, mean=0.907, max=0.907, sum=0.907 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5401968527212513,
          "description": "min=0.25, mean=0.54, max=0.743, sum=9.724 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6704545454545454,
          "description": "min=0.175, mean=0.67, max=0.875, sum=7.375 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7464102564102564,
          "markdown": false
        },
        {
          "value": 0.40989473684210526,
          "description": "min=0.24, mean=0.41, max=0.64, sum=2.049 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.631,
          "description": "min=0.631, mean=0.631, max=0.631, sum=0.631 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6525810359656932,
          "description": "min=0.653, mean=0.653, max=0.653, sum=0.653 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28717918481295357,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6239999868788104,
          "description": "min=0.624, mean=0.624, max=0.624, sum=0.624 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3176438145195143,
          "description": "min=0.318, mean=0.318, max=0.318, sum=0.318 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18960244648318042,
          "description": "min=0.19, mean=0.19, max=0.19, sum=0.19 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.955,
          "description": "min=0.955, mean=0.955, max=0.955, sum=0.955 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5526050039546541,
          "description": "min=0.073, mean=0.553, max=0.939, sum=9.947 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6795454545454546,
          "description": "min=0.35, mean=0.68, max=0.975, sum=7.475 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6874125874125874,
          "markdown": false
        },
        {
          "value": 0.40038596491228073,
          "description": "min=0.24, mean=0.4, max=0.61, sum=2.002 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.807,
          "description": "min=0.807, mean=0.807, max=0.807, sum=0.807 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6330893045624563,
          "description": "min=0.633, mean=0.633, max=0.633, sum=0.633 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23301952773256637,
          "description": "min=0.233, mean=0.233, max=0.233, sum=0.233 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6392400021633227,
          "description": "min=0.639, mean=0.639, max=0.639, sum=0.639 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2519147363869601,
          "description": "min=0.252, mean=0.252, max=0.252, sum=0.252 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.18042813455657492,
          "description": "min=0.18, mean=0.18, max=0.18, sum=0.18 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.944,
          "description": "min=0.944, mean=0.944, max=0.944, sum=0.944 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5271340155324973,
          "description": "min=0.085, mean=0.527, max=0.95, sum=9.488 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6363636363636364,
          "description": "min=0.4, mean=0.636, max=0.825, sum=7 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4469230769230769,
          "markdown": false
        },
        {
          "value": 0.26063157894736844,
          "description": "min=0.15, mean=0.261, max=0.33, sum=1.303 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.702,
          "description": "min=0.702, mean=0.702, max=0.702, sum=0.702 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5199130399003071,
          "description": "min=0.52, mean=0.52, max=0.52, sum=0.52 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2334955595363806,
          "description": "min=0.233, mean=0.233, max=0.233, sum=0.233 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.536571121609654,
          "description": "min=0.537, mean=0.537, max=0.537, sum=0.537 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2622208848575014,
          "description": "min=0.262, mean=0.262, max=0.262, sum=0.262 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.21253822629969418,
          "description": "min=0.213, mean=0.213, max=0.213, sum=0.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.794,
          "description": "min=0.794, mean=0.794, max=0.794, sum=0.794 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49430637095445207,
          "description": "min=0, mean=0.494, max=0.999, sum=8.898 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5545454545454546,
          "description": "min=0.15, mean=0.555, max=0.975, sum=6.1 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2968298368298368,
          "markdown": false
        },
        {
          "value": 0.2613684210526316,
          "description": "min=0.2, mean=0.261, max=0.32, sum=1.307 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.637,
          "description": "min=0.637, mean=0.637, max=0.637, sum=0.637 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3536054591455644,
          "description": "min=0.354, mean=0.354, max=0.354, sum=0.354 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14824932914209746,
          "description": "min=0.148, mean=0.148, max=0.148, sum=0.148 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38333017617065734,
          "description": "min=0.383, mean=0.383, max=0.383, sum=0.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21915649953692506,
          "description": "min=0.219, mean=0.219, max=0.219, sum=0.219 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1834862385321101,
          "description": "min=0.183, mean=0.183, max=0.183, sum=0.183 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.811,
          "description": "min=0.811, mean=0.811, max=0.811, sum=0.811 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5017354752179064,
          "description": "min=0, mean=0.502, max=1, sum=9.031 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.15, mean=0.5, max=0.975, sum=5.5 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6857342657342658,
          "markdown": false
        },
        {
          "value": 0.4803859649122807,
          "description": "min=0.272, mean=0.48, max=0.78, sum=2.402 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.783,
          "description": "min=0.783, mean=0.783, max=0.783, sum=0.783 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5589601433703856,
          "description": "min=0.559, mean=0.559, max=0.559, sum=0.559 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33840782877152153,
          "description": "min=0.338, mean=0.338, max=0.338, sum=0.338 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6251513417645462,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25646510454177246,
          "description": "min=0.256, mean=0.256, max=0.256, sum=0.256 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.29204892966360857,
          "description": "min=0.292, mean=0.292, max=0.292, sum=0.292 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.954,
          "description": "min=0.954, mean=0.954, max=0.954, sum=0.954 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29157916197633543,
          "description": "min=0.098, mean=0.292, max=0.594, sum=5.248 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6113636363636364,
          "description": "min=0.15, mean=0.611, max=0.975, sum=6.725 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7087645687645687,
          "markdown": false
        },
        {
          "value": 0.4658596491228071,
          "description": "min=0.219, mean=0.466, max=0.8, sum=2.329 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.799,
          "description": "min=0.799, mean=0.799, max=0.799, sum=0.799 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.543279669317833,
          "description": "min=0.543, mean=0.543, max=0.543, sum=0.543 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33094416222152356,
          "description": "min=0.331, mean=0.331, max=0.331, sum=0.331 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6067807528449897,
          "description": "min=0.607, mean=0.607, max=0.607, sum=0.607 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3078257563786361,
          "description": "min=0.308, mean=0.308, max=0.308, sum=0.308 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.3119266055045872,
          "description": "min=0.312, mean=0.312, max=0.312, sum=0.312 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.957,
          "description": "min=0.957, mean=0.957, max=0.957, sum=0.957 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4617550507789773,
          "description": "min=0.16, mean=0.462, max=0.762, sum=8.312 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5613636363636363,
          "description": "min=0.175, mean=0.561, max=0.875, sum=6.175 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5133566433566433,
          "markdown": false
        },
        {
          "value": 0.3148771929824561,
          "description": "min=0.22, mean=0.315, max=0.43, sum=4.723 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6896666666666667,
          "description": "min=0.625, mean=0.69, max=0.722, sum=2.069 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6154230898629193,
          "description": "min=0.55, mean=0.615, max=0.656, sum=1.846 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12026039507733897,
          "description": "min=0.112, mean=0.12, max=0.124, sum=0.361 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5967933879081116,
          "description": "min=0.592, mean=0.597, max=0.603, sum=1.79 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20535008777735797,
          "description": "min=0.173, mean=0.205, max=0.225, sum=0.616 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.1915137614678899,
          "description": "min=0.148, mean=0.192, max=0.229, sum=0.766 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.9329999999999999,
          "description": "min=0.92, mean=0.933, max=0.951, sum=2.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4996593325872097,
          "description": "min=0, mean=0.5, max=1, sum=26.982 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.575,
          "description": "min=0, mean=0.575, max=0.975, sum=18.975 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5379254079254079,
          "markdown": false
        },
        {
          "value": 0.3714502923976608,
          "description": "min=0.19, mean=0.371, max=0.66, sum=5.572 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6996666666666668,
          "description": "min=0.636, mean=0.7, max=0.762, sum=2.099 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40467419690737483,
          "description": "min=0.18, mean=0.405, max=0.538, sum=1.214 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.276181640672073,
          "description": "min=0.272, mean=0.276, max=0.282, sum=0.829 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6303513019528806,
          "description": "min=0.621, mean=0.63, max=0.639, sum=1.891 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3370729442565461,
          "description": "min=0.328, mean=0.337, max=0.353, sum=1.011 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15188583078491336,
          "description": "min=0.147, mean=0.152, max=0.157, sum=0.456 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.931,
          "description": "min=0.925, mean=0.931, max=0.94, sum=2.793 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44887663628250224,
          "description": "min=0, mean=0.449, max=0.871, sum=24.239 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6181818181818182,
          "description": "min=0.25, mean=0.618, max=0.925, sum=20.4 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7968401968401968,
          "markdown": false
        },
        {
          "value": 0.5881637426900584,
          "description": "min=0.34, mean=0.588, max=0.86, sum=8.822 (15)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.875,
          "description": "min=0.872, mean=0.875, max=0.878, sum=2.625 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6506183133514157,
          "description": "min=0.64, mean=0.651, max=0.659, sum=1.952 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3624320629787478,
          "description": "min=0.356, mean=0.362, max=0.367, sum=1.087 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.39873411995988545,
          "description": "min=0.394, mean=0.399, max=0.408, sum=1.196 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5417940876656473,
          "description": "min=0.529, mean=0.542, max=0.56, sum=1.625 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.918,
          "description": "min=0.909, mean=0.918, max=0.923, sum=2.754 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.006254555939232581,
          "description": "min=0, mean=0.006, max=0.288, sum=0.338 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6719696969696969,
          "description": "min=0, mean=0.672, max=0.975, sum=22.175 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.16727272727272727,
          "markdown": false
        },
        {
          "value": 0.2433684210526316,
          "description": "min=0.2, mean=0.243, max=0.28, sum=3.651 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5826666666666667,
          "description": "min=0.486, mean=0.583, max=0.631, sum=1.748 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14573784149261218,
          "description": "min=0.131, mean=0.146, max=0.169, sum=0.437 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0516362934670568,
          "description": "min=0.051, mean=0.052, max=0.053, sum=0.155 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1768275232054711,
          "description": "min=0.15, mean=0.177, max=0.207, sum=0.53 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10047785618783804,
          "description": "min=0.092, mean=0.1, max=0.108, sum=0.301 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2018348623853211,
          "description": "min=0.197, mean=0.202, max=0.203, sum=0.807 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.7999999999999999,
          "description": "min=0.709, mean=0.8, max=0.853, sum=2.4 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4556089334763174,
          "description": "min=0, mean=0.456, max=0.998, sum=24.603 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3424242424242424,
          "description": "min=0, mean=0.342, max=0.975, sum=11.3 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_fairness.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_fairness.json"
      }
    ],
    "name": "fairness"
  },
  {
    "title": "Efficiency",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - Denoised inference time (s)",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "MMLU"
        }
      },
      {
        "value": "BoolQ - Denoised inference time (s)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - Denoised inference time (s)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Denoised inference time (s)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Denoised inference time (s)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - Denoised inference time (s)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "HellaSwag - Denoised inference time (s)",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "OpenbookQA - Denoised inference time (s)",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "TruthfulQA - Denoised inference time (s)",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "MS MARCO (regular) - Denoised inference time (s)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Denoised inference time (s)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "CNN/DailyMail - Denoised inference time (s)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - Denoised inference time (s)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "IMDB - Denoised inference time (s)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - Denoised inference time (s)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - Denoised inference time (s)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nDenoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Denoised inference time (s)",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2218311403508772,
          "markdown": false
        },
        {
          "value": 0.4567342927631581,
          "description": "min=0.419, mean=0.457, max=0.511, sum=6.851 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6195252891710069,
          "description": "min=0.55, mean=0.62, max=0.727, sum=1.859 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1261881626564945,
          "description": "min=1.085, mean=1.126, max=1.167, sum=3.379 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.492596863281249,
          "description": "min=0.466, mean=0.493, max=0.536, sum=1.478 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0597537076822923,
          "description": "min=0.931, mean=1.06, max=1.147, sum=3.179 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0642993667534726,
          "description": "min=1.898, mean=2.064, max=2.149, sum=6.193 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2835968515624999,
          "description": "min=0.284, mean=0.284, max=0.284, sum=0.284 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2588512968749986,
          "description": "min=0.259, mean=0.259, max=0.259, sum=0.259 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44282831613149837,
          "description": "min=0.423, mean=0.443, max=0.454, sum=1.328 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.500707514648438,
          "description": "min=0.482, mean=0.501, max=0.52, sum=1.502 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4963945009689923,
          "description": "min=0.477, mean=0.496, max=0.516, sum=1.489 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.777328921804216,
          "description": "min=3.558, mean=3.777, max=3.91, sum=22.664 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6292920332441818,
          "description": "min=1.615, mean=1.629, max=1.648, sum=9.776 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8516515608723956,
          "description": "min=0.682, mean=0.852, max=1.035, sum=2.555 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5523870780537201,
          "description": "min=0.43, mean=0.552, max=0.724, sum=29.829 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6866916923137625,
          "description": "min=0.423, mean=0.687, max=1.043, sum=22.661 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.38930372807017544,
          "markdown": false
        },
        {
          "value": 0.3765351217105263,
          "description": "min=0.348, mean=0.377, max=0.422, sum=5.648 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48513916883680525,
          "description": "min=0.43, mean=0.485, max=0.566, sum=1.455 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7971074946205007,
          "description": "min=0.768, mean=0.797, max=0.829, sum=2.391 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3722484414062495,
          "description": "min=0.355, mean=0.372, max=0.396, sum=1.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7326816432291658,
          "description": "min=0.66, mean=0.733, max=0.784, sum=2.198 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.159840737413194,
          "description": "min=1.105, mean=1.16, max=1.191, sum=3.48 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25286050781250013,
          "description": "min=0.253, mean=0.253, max=0.253, sum=0.253 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2381039843749996,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36458362003058115,
          "description": "min=0.351, mean=0.365, max=0.372, sum=1.094 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3926667591145831,
          "description": "min=0.379, mean=0.393, max=0.406, sum=1.178 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3890438468992247,
          "description": "min=0.376, mean=0.389, max=0.402, sum=1.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.011487112821144,
          "description": "min=1.832, mean=2.011, max=2.216, sum=12.069 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9030293349990619,
          "description": "min=0.896, mean=0.903, max=0.91, sum=5.418 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6371184251302079,
          "description": "min=0.531, mean=0.637, max=0.757, sum=1.911 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43432643222557377,
          "description": "min=0.338, mean=0.434, max=0.564, sum=23.454 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4992617404513889,
          "description": "min=0.312, mean=0.499, max=0.763, sum=16.476 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.31716008771929827,
          "markdown": false
        },
        {
          "value": 0.41104061293859656,
          "description": "min=0.381, mean=0.411, max=0.466, sum=6.166 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5352501416015627,
          "description": "min=0.47, mean=0.535, max=0.624, sum=1.606 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9228662338615026,
          "description": "min=0.892, mean=0.923, max=0.955, sum=2.769 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46640491796874967,
          "description": "min=0.437, mean=0.466, max=0.494, sum=1.399 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8728225097656246,
          "description": "min=0.774, mean=0.873, max=0.927, sum=2.618 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4134776341145843,
          "description": "min=1.302, mean=1.413, max=1.478, sum=4.24 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3304377109375,
          "description": "min=0.33, mean=0.33, max=0.33, sum=0.33 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.280719578125,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39626294915902127,
          "description": "min=0.384, mean=0.396, max=0.403, sum=1.189 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4278073636067708,
          "description": "min=0.415, mean=0.428, max=0.44, sum=1.283 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42392066375968995,
          "description": "min=0.412, mean=0.424, max=0.437, sum=1.272 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.074164002425339,
          "description": "min=1.956, mean=2.074, max=2.263, sum=12.445 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0700079645773009,
          "description": "min=1.055, mean=1.07, max=1.082, sum=6.42 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7321998525390631,
          "description": "min=0.59, mean=0.732, max=0.881, sum=2.197 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48152748003997736,
          "description": "min=0.418, mean=0.482, max=0.621, sum=26.002 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5903971827651516,
          "description": "min=0.401, mean=0.59, max=0.888, sum=19.483 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.13822916666666668,
          "markdown": false
        },
        {
          "value": 0.5775741999040572,
          "description": "min=0.556, mean=0.578, max=0.605, sum=8.664 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6371923081597224,
          "description": "min=0.566, mean=0.637, max=0.75, sum=1.912 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.7223421043622853,
          "description": "min=1.628, mean=1.722, max=1.839, sum=5.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7770150703124993,
          "description": "min=0.751, mean=0.777, max=0.821, sum=2.331 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1015715911458346,
          "description": "min=1.036, mean=1.102, max=1.15, sum=3.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.6939938854166683,
          "description": "min=3.472, mean=3.694, max=4.123, sum=11.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5491151875000004,
          "description": "min=0.549, mean=0.549, max=0.549, sum=0.549 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4465652265625003,
          "description": "min=0.447, mean=0.447, max=0.447, sum=0.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5683649633565078,
          "description": "min=0.503, mean=0.568, max=0.603, sum=2.273 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5778111061197916,
          "description": "min=0.55, mean=0.578, max=0.599, sum=1.733 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5865037397044573,
          "description": "min=0.547, mean=0.587, max=0.608, sum=1.76 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.076441398798879,
          "description": "min=3.898, mean=4.076, max=4.414, sum=24.459 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.408301637575076,
          "description": "min=2.357, mean=2.408, max=2.45, sum=14.45 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7899130366753467,
          "description": "min=0.714, mean=0.79, max=0.897, sum=2.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5939081200798796,
          "description": "min=0.555, mean=0.594, max=0.756, sum=32.071 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8829963013928345,
          "description": "min=0.583, mean=0.883, max=2.075, sum=29.139 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.26823464912280703,
          "markdown": false
        },
        {
          "value": 0.23288457024982262,
          "description": "min=0.135, mean=0.233, max=0.418, sum=3.493 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.852823399183769,
          "description": "min=0.665, mean=0.853, max=1.05, sum=2.558 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5979962524114084,
          "description": "min=2.081, mean=2.598, max=3.427, sum=7.794 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.115412127906084,
          "description": "min=0.931, mean=1.115, max=1.261, sum=3.346 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.546660231937965,
          "description": "min=2.213, mean=2.547, max=2.912, sum=7.64 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.3062709801205585,
          "description": "min=5.124, mean=5.306, max=5.436, sum=15.919 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07493321968615055,
          "description": "min=0.075, mean=0.075, max=0.075, sum=0.075 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03224579076468945,
          "description": "min=0.032, mean=0.032, max=0.032, sum=0.032 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14325443854568073,
          "description": "min=0.084, mean=0.143, max=0.226, sum=0.573 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25680491607178446,
          "description": "min=0.246, mean=0.257, max=0.27, sum=0.77 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24635170979166832,
          "description": "min=0.227, mean=0.246, max=0.271, sum=0.739 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.5842744588340345,
          "description": "min=5.515, mean=5.584, max=5.648, sum=33.506 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.899962288877679,
          "description": "min=3.874, mean=3.9, max=3.923, sum=23.4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5360445948161456,
          "description": "min=3.425, mean=3.536, max=3.659, sum=10.608 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5325854907984409,
          "description": "min=0.316, mean=0.533, max=1.372, sum=28.76 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.86588385979184,
          "description": "min=0.258, mean=1.866, max=3.777, sum=61.574 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.42000000000000004,
          "markdown": false
        },
        {
          "value": 0.1453571324242486,
          "description": "min=0.141, mean=0.145, max=0.149, sum=2.18 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3736038734018803,
          "description": "min=0.366, mean=0.374, max=0.385, sum=1.121 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.9445703822729286,
          "description": "min=0.848, mean=0.945, max=1.053, sum=2.834 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4571279249547553,
          "description": "min=1.309, mean=1.457, max=1.621, sum=4.371 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.8950855693236632,
          "description": "min=2.864, mean=2.895, max=2.953, sum=8.685 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.2385025575706792,
          "description": "min=1.239, mean=1.239, max=1.239, sum=3.716 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.14173421436146078,
          "description": "min=0.133, mean=0.142, max=0.145, sum=0.567 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1.0655231237061773,
          "description": "min=1.057, mean=1.066, max=1.081, sum=6.393 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.5543883131537052,
          "description": "min=0.523, mean=0.554, max=0.571, sum=3.326 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.39343433208828427,
          "description": "min=0.37, mean=0.393, max=0.436, sum=1.18 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.3912135341654548,
          "description": "min=0.328, mean=0.391, max=0.487, sum=21.126 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.586429068475456,
          "description": "min=0.329, mean=0.586, max=0.74, sum=19.352 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1992872807017544,
          "markdown": false
        },
        {
          "value": 0.4885340888157895,
          "description": "min=0.47, mean=0.489, max=0.506, sum=7.328 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5984045305989586,
          "description": "min=0.519, mean=0.598, max=0.705, sum=1.795 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.061820745305164,
          "description": "min=1.025, mean=1.062, max=1.132, sum=3.185 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5647122317708332,
          "description": "min=0.546, mean=0.565, max=0.586, sum=1.694 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0851867500000003,
          "description": "min=0.95, mean=1.085, max=1.249, sum=3.256 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0889632337239585,
          "description": "min=2.057, mean=2.089, max=2.151, sum=6.267 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35889839843750027,
          "description": "min=0.359, mean=0.359, max=0.359, sum=0.359 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3138882968749995,
          "description": "min=0.314, mean=0.314, max=0.314, sum=0.314 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.50081436353211,
          "description": "min=0.49, mean=0.501, max=0.506, sum=1.502 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4985355449218751,
          "description": "min=0.492, mean=0.499, max=0.504, sum=1.496 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.501260492369186,
          "description": "min=0.487, mean=0.501, max=0.511, sum=1.504 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.3373758759723735,
          "description": "min=4.313, mean=4.337, max=4.381, sum=26.024 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.7405486446267702,
          "description": "min=1.735, mean=1.741, max=1.747, sum=10.443 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7963252441406254,
          "description": "min=0.709, mean=0.796, max=0.865, sum=2.389 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5459943267746123,
          "description": "min=0.464, mean=0.546, max=0.711, sum=29.484 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6672338778409089,
          "description": "min=0.458, mean=0.667, max=0.987, sum=22.019 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.40696820175438597,
          "markdown": false
        },
        {
          "value": 0.3167793253495066,
          "description": "min=0.292, mean=0.317, max=0.349, sum=4.752 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4208381308593749,
          "description": "min=0.359, mean=0.421, max=0.505, sum=1.263 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7286962533010564,
          "description": "min=0.693, mean=0.729, max=0.782, sum=2.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33722079557291607,
          "description": "min=0.332, mean=0.337, max=0.343, sum=1.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7738100833333333,
          "description": "min=0.681, mean=0.774, max=0.827, sum=2.321 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.261730263346353,
          "description": "min=1.189, mean=1.262, max=1.309, sum=3.785 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22464337890624972,
          "description": "min=0.225, mean=0.225, max=0.225, sum=0.225 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2014860078125007,
          "description": "min=0.201, mean=0.201, max=0.201, sum=0.201 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3248777191442089,
          "description": "min=0.323, mean=0.325, max=0.328, sum=0.975 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3298234970703125,
          "description": "min=0.322, mean=0.33, max=0.339, sum=0.989 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32664419815891477,
          "description": "min=0.319, mean=0.327, max=0.335, sum=0.98 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.2689930690607114,
          "description": "min=2.097, mean=2.269, max=2.366, sum=13.614 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0751711510617759,
          "description": "min=1.064, mean=1.075, max=1.089, sum=6.451 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5358171357421871,
          "description": "min=0.479, mean=0.536, max=0.62, sum=1.607 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3747284900914756,
          "description": "min=0.29, mean=0.375, max=0.51, sum=20.235 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4443553984670929,
          "description": "min=0.284, mean=0.444, max=0.697, sum=14.664 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5410910087719298,
          "markdown": false
        },
        {
          "value": 0.2806724427425987,
          "description": "min=0.265, mean=0.281, max=0.301, sum=4.21 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34952371158854173,
          "description": "min=0.308, mean=0.35, max=0.402, sum=1.049 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5331198741930753,
          "description": "min=0.525, mean=0.533, max=0.548, sum=1.599 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25938733203125103,
          "description": "min=0.254, mean=0.259, max=0.265, sum=0.778 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5353007499999998,
          "description": "min=0.476, mean=0.535, max=0.583, sum=1.606 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7354030888671875,
          "description": "min=0.664, mean=0.735, max=0.771, sum=2.206 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20370158203125027,
          "description": "min=0.204, mean=0.204, max=0.204, sum=0.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1870674140625,
          "description": "min=0.187, mean=0.187, max=0.187, sum=0.187 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28723167974722846,
          "description": "min=0.287, mean=0.287, max=0.288, sum=0.862 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28909981347656255,
          "description": "min=0.286, mean=0.289, max=0.293, sum=0.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28804701126453486,
          "description": "min=0.285, mean=0.288, max=0.29, sum=0.864 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.199950748558208,
          "description": "min=1.073, mean=1.2, max=1.325, sum=7.2 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7239030526061776,
          "description": "min=0.717, mean=0.724, max=0.732, sum=4.343 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45160390852864607,
          "description": "min=0.404, mean=0.452, max=0.489, sum=1.355 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32067323239104795,
          "description": "min=0.262, mean=0.321, max=0.405, sum=17.316 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3580963386304451,
          "description": "min=0.244, mean=0.358, max=0.532, sum=11.817 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5343333333333333,
          "markdown": false
        },
        {
          "value": 0.284456830180921,
          "description": "min=0.265, mean=0.284, max=0.312, sum=4.267 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36694511328125,
          "description": "min=0.319, mean=0.367, max=0.436, sum=1.101 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5603894916373239,
          "description": "min=0.544, mean=0.56, max=0.583, sum=1.681 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2509381953124994,
          "description": "min=0.246, mean=0.251, max=0.259, sum=0.753 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6049964999999996,
          "description": "min=0.552, mean=0.605, max=0.643, sum=1.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6185995332031252,
          "description": "min=0.611, mean=0.619, max=0.625, sum=1.856 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22341269531249972,
          "description": "min=0.223, mean=0.223, max=0.223, sum=0.223 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2136278906249995,
          "description": "min=0.214, mean=0.214, max=0.214, sum=0.214 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2894203160837155,
          "description": "min=0.287, mean=0.289, max=0.295, sum=0.868 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.29054985767926356,
          "description": "min=0.282, mean=0.291, max=0.303, sum=0.872 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9539734693535404,
          "description": "min=0.781, mean=0.954, max=1.052, sum=5.724 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6416181225868728,
          "description": "min=0.637, mean=0.642, max=0.649, sum=3.85 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45773176757812467,
          "description": "min=0.414, mean=0.458, max=0.52, sum=1.373 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32889709084919744,
          "description": "min=0.264, mean=0.329, max=0.439, sum=17.76 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3599495087594697,
          "description": "min=0.256, mean=0.36, max=0.547, sum=11.878 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6008771929824561,
          "markdown": false
        },
        {
          "value": 0.06997480863135229,
          "description": "min=0.066, mean=0.07, max=0.072, sum=1.05 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49915384031836946,
          "description": "min=0.354, mean=0.499, max=0.575, sum=1.497 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.311420011868712,
          "description": "min=0.988, mean=1.311, max=1.513, sum=3.934 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.77691167926379,
          "description": "min=1.626, mean=1.777, max=1.998, sum=5.331 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.8663324384530373,
          "description": "min=3.687, mean=3.866, max=4.016, sum=11.599 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.3887290514336688,
          "description": "min=1.354, mean=1.389, max=1.411, sum=4.166 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.030294155851006508,
          "description": "min=0.03, mean=0.03, max=0.03, sum=0.03 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.019339164675618026,
          "description": "min=0.019, mean=0.019, max=0.019, sum=0.019 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.043782452828866295,
          "description": "min=0.018, mean=0.044, max=0.053, sum=0.175 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08407480907713127,
          "description": "min=0.081, mean=0.084, max=0.088, sum=0.252 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08053553836682271,
          "description": "min=0.078, mean=0.081, max=0.083, sum=0.242 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 2.0758840914959578,
          "description": "min=1.997, mean=2.076, max=2.172, sum=12.455 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7424737962465443,
          "description": "min=0.73, mean=0.742, max=0.758, sum=4.455 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7011672212481499,
          "description": "min=0.63, mean=0.701, max=0.761, sum=2.104 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30723795570455475,
          "description": "min=0.154, mean=0.307, max=0.494, sum=16.591 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6282604447639349,
          "description": "min=0.107, mean=0.628, max=1.382, sum=20.733 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5141337719298246,
          "markdown": false
        },
        {
          "value": 0.1330090104470642,
          "description": "min=0.093, mean=0.133, max=0.275, sum=1.995 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.772616056262233,
          "description": "min=0.515, mean=0.773, max=1.206, sum=2.318 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4680144681286658,
          "description": "min=0.904, mean=1.468, max=1.998, sum=4.404 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4823250982166127,
          "description": "min=0.381, mean=0.482, max=0.655, sum=1.447 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.1369374864319965,
          "description": "min=1.913, mean=2.137, max=2.288, sum=6.411 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.024874148220674,
          "description": "min=1.906, mean=2.025, max=2.127, sum=6.075 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.025470768198370932,
          "description": "min=0.025, mean=0.025, max=0.025, sum=0.025 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.023963596328905958,
          "description": "min=0.024, mean=0.024, max=0.024, sum=0.024 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08375055263898766,
          "description": "min=0.029, mean=0.084, max=0.133, sum=0.335 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11821914517316674,
          "description": "min=0.111, mean=0.118, max=0.128, sum=0.355 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11621723726407733,
          "description": "min=0.105, mean=0.116, max=0.127, sum=0.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.133056901521097,
          "description": "min=2.104, mean=2.133, max=2.168, sum=12.798 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1163698516910754,
          "description": "min=1.104, mean=1.116, max=1.135, sum=6.698 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.862092325799332,
          "description": "min=0.748, mean=0.862, max=1.078, sum=2.586 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4081493504712871,
          "description": "min=0.253, mean=0.408, max=0.906, sum=22.04 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1562087950381366,
          "description": "min=0.16, mean=1.156, max=2.589, sum=38.155 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4340277777777778,
          "markdown": false
        },
        {
          "value": 0.21847905223539232,
          "description": "min=0.173, mean=0.218, max=0.232, sum=3.277 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27128291567197677,
          "description": "min=0.27, mean=0.271, max=0.272, sum=0.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0544504576125933,
          "description": "min=1.054, mean=1.054, max=1.054, sum=3.163 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.856322434252687,
          "description": "min=2.617, mean=2.856, max=3.211, sum=8.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.84636455836454,
          "description": "min=6.926, mean=12.846, max=24.675, sum=38.539 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0323945961168868,
          "description": "min=1.032, mean=1.032, max=1.032, sum=3.097 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.2095953345265857,
          "description": "min=0.174, mean=0.21, max=0.249, sum=0.838 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1.6543884711070522,
          "description": "min=1.653, mean=1.654, max=1.655, sum=9.926 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.15883249730996,
          "description": "min=1.096, mean=1.159, max=1.283, sum=6.953 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27797461745258367,
          "description": "min=0.276, mean=0.278, max=0.28, sum=0.834 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27030228534077655,
          "description": "min=0.269, mean=0.27, max=0.273, sum=14.596 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4484652494441787,
          "description": "min=0.411, mean=0.448, max=0.835, sum=14.799 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5056944444444444,
          "markdown": false
        },
        {
          "value": 0.18164482078684702,
          "description": "min=0.178, mean=0.182, max=0.184, sum=2.725 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3127442524572212,
          "description": "min=0.292, mean=0.313, max=0.341, sum=0.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1820060481894892,
          "description": "min=1.182, mean=1.182, max=1.182, sum=3.546 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.993551874854462,
          "description": "min=1.912, mean=1.994, max=2.142, sum=5.981 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0931644739895567,
          "description": "min=2.941, mean=3.093, max=3.306, sum=9.279 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.2264695519389521,
          "description": "min=1.226, mean=1.226, max=1.226, sum=3.679 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.16779271445154526,
          "description": "min=0.122, mean=0.168, max=0.183, sum=0.671 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1.1084291968542619,
          "description": "min=1.108, mean=1.108, max=1.109, sum=6.651 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7743015579914415,
          "description": "min=0.771, mean=0.774, max=0.781, sum=4.646 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21490736543138858,
          "description": "min=0.214, mean=0.215, max=0.217, sum=0.645 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2636334561494892,
          "description": "min=0.21, mean=0.264, max=0.45, sum=14.236 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43394225670679076,
          "description": "min=0.316, mean=0.434, max=0.454, sum=14.32 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.24121162280701755,
          "markdown": false
        },
        {
          "value": 0.1195572826114746,
          "description": "min=0.11, mean=0.12, max=0.138, sum=1.793 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.869335141547284,
          "description": "min=0.71, mean=0.869, max=0.954, sum=2.608 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7825779012238017,
          "description": "min=2.375, mean=2.783, max=3.573, sum=8.348 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5482187833781085,
          "description": "min=4.226, mean=4.548, max=4.977, sum=13.645 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.78018927021878,
          "description": "min=6.761, mean=7.78, max=8.516, sum=23.341 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.049007016242971,
          "description": "min=3.951, mean=4.049, max=4.154, sum=12.147 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7096132577732451,
          "description": "min=0.71, mean=0.71, max=0.71, sum=0.71 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03760148134353242,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.038 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1406602569641055,
          "description": "min=0.079, mean=0.141, max=0.246, sum=0.563 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24148347487755295,
          "description": "min=0.229, mean=0.241, max=0.262, sum=0.724 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2261325473631569,
          "description": "min=0.19, mean=0.226, max=0.254, sum=0.678 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.728843353285813,
          "description": "min=4.705, mean=4.729, max=4.742, sum=28.373 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.522969657178858,
          "description": "min=2.509, mean=2.523, max=2.545, sum=15.138 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5747312279142403,
          "description": "min=1.488, mean=1.575, max=1.732, sum=4.724 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4976179389529128,
          "description": "min=0.299, mean=0.498, max=0.974, sum=26.871 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9624239013413396,
          "description": "min=0.403, mean=0.962, max=1.712, sum=31.76 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.466875,
          "markdown": false
        },
        {
          "value": 0.05452067670741475,
          "description": "min=0.041, mean=0.055, max=0.081, sum=0.818 (15)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.8336340090708299,
          "description": "min=0.272, mean=0.834, max=1.907, sum=2.501 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.979606440811339,
          "description": "min=0.939, mean=1.98, max=3.714, sum=5.939 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.611190575244526,
          "description": "min=0.471, mean=0.611, max=0.739, sum=1.834 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.631964569965005,
          "description": "min=2.887, mean=3.632, max=4.314, sum=10.896 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6581093871351746,
          "description": "min=2.636, mean=2.658, max=2.683, sum=7.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9708148735597889,
          "description": "min=0.971, mean=0.971, max=0.971, sum=0.971 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18798254558309685,
          "description": "min=0.188, mean=0.188, max=0.188, sum=0.188 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04074840224276806,
          "description": "min=0.033, mean=0.041, max=0.046, sum=0.163 (4)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.07567241383876121,
          "description": "min=0.066, mean=0.076, max=0.089, sum=0.227 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.10182954292591756,
          "description": "min=0.061, mean=0.102, max=0.183, sum=0.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.971851329588582,
          "description": "min=1.828, mean=1.972, max=2.045, sum=11.831 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8849094198151292,
          "description": "min=0.833, mean=0.885, max=0.939, sum=5.309 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5398914054599924,
          "description": "min=0.515, mean=0.54, max=0.569, sum=1.62 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21220531272072915,
          "description": "min=0.173, mean=0.212, max=0.325, sum=11.459 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8706600076246471,
          "description": "min=0.069, mean=1.871, max=6.606, sum=61.732 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.557938596491228,
          "markdown": false
        },
        {
          "value": 0.21209971402138156,
          "description": "min=0.203, mean=0.212, max=0.221, sum=3.181 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21022733463541673,
          "description": "min=0.204, mean=0.21, max=0.217, sum=0.631 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3694498019366194,
          "description": "min=0.36, mean=0.369, max=0.384, sum=1.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32700476562499997,
          "description": "min=0.304, mean=0.327, max=0.357, sum=0.981 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.462036467447917,
          "description": "min=0.378, mean=0.462, max=0.583, sum=1.386 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.085224210937499,
          "description": "min=1.01, mean=1.085, max=1.233, sum=3.256 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.19329937499999997,
          "description": "min=0.193, mean=0.193, max=0.193, sum=0.193 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.18361757812499943,
          "description": "min=0.184, mean=0.184, max=0.184, sum=0.184 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21492536613627675,
          "description": "min=0.208, mean=0.215, max=0.219, sum=0.645 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21074697460937475,
          "description": "min=0.202, mean=0.211, max=0.218, sum=0.632 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2137389625726744,
          "description": "min=0.201, mean=0.214, max=0.221, sum=0.641 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.255577085568669,
          "description": "min=1.919, mean=2.256, max=3.967, sum=15.789 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1482822034007862,
          "description": "min=0.958, mean=1.148, max=2.074, sum=8.038 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22547806217447905,
          "description": "min=0.218, mean=0.225, max=0.231, sum=0.676 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20974755918568705,
          "description": "min=0.203, mean=0.21, max=0.218, sum=11.326 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2793995279947917,
          "description": "min=0.213, mean=0.279, max=0.378, sum=9.22 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8951315789473684,
          "markdown": false
        },
        {
          "value": 0.09245237979714913,
          "description": "min=0.091, mean=0.092, max=0.095, sum=1.387 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09988102712673615,
          "description": "min=0.096, mean=0.1, max=0.104, sum=0.3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.15159477332746474,
          "description": "min=0.14, mean=0.152, max=0.166, sum=0.455 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.12234622395833335,
          "description": "min=0.116, mean=0.122, max=0.128, sum=0.367 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.18882224978298598,
          "description": "min=0.166, mean=0.189, max=0.21, sum=0.566 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.32252038281250045,
          "description": "min=0.31, mean=0.323, max=0.34, sum=0.968 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.08380637499999992,
          "description": "min=0.084, mean=0.084, max=0.084, sum=0.084 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.07928820312499986,
          "description": "min=0.079, mean=0.079, max=0.079, sum=0.079 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.09360438168960249,
          "description": "min=0.093, mean=0.094, max=0.094, sum=0.281 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09442029557291665,
          "description": "min=0.094, mean=0.094, max=0.095, sum=0.283 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09531934350775194,
          "description": "min=0.094, mean=0.095, max=0.097, sum=0.286 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6232588631080115,
          "description": "min=0.559, mean=0.623, max=0.691, sum=4.363 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29416145294688817,
          "description": "min=0.274, mean=0.294, max=0.41, sum=2.059 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11035393728298622,
          "description": "min=0.105, mean=0.11, max=0.115, sum=0.331 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09739228545773865,
          "description": "min=0.09, mean=0.097, max=0.105, sum=5.259 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11198840159406566,
          "description": "min=0.094, mean=0.112, max=0.139, sum=3.696 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.860531798245614,
          "markdown": false
        },
        {
          "value": 0.11896953947368419,
          "description": "min=0.118, mean=0.119, max=0.12, sum=1.785 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12137238953993056,
          "description": "min=0.119, mean=0.121, max=0.125, sum=0.364 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1762964825410799,
          "description": "min=0.164, mean=0.176, max=0.194, sum=0.529 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15162744531249991,
          "description": "min=0.15, mean=0.152, max=0.152, sum=0.455 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23211142730034728,
          "description": "min=0.228, mean=0.232, max=0.235, sum=0.696 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2607369557291667,
          "description": "min=0.245, mean=0.261, max=0.27, sum=0.782 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1134031874999998,
          "description": "min=0.113, mean=0.113, max=0.113, sum=0.113 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.11114410156249971,
          "description": "min=0.111, mean=0.111, max=0.111, sum=0.111 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.11970087223655701,
          "description": "min=0.119, mean=0.12, max=0.12, sum=0.359 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12232188151041663,
          "description": "min=0.119, mean=0.122, max=0.126, sum=0.367 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12249798631298452,
          "description": "min=0.118, mean=0.122, max=0.128, sum=0.367 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5327935382950345,
          "description": "min=0.293, mean=0.533, max=0.795, sum=3.197 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.27202574924254597,
          "description": "min=0.264, mean=0.272, max=0.286, sum=1.632 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12819260763888898,
          "description": "min=0.125, mean=0.128, max=0.131, sum=0.385 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12008918109610113,
          "description": "min=0.118, mean=0.12, max=0.125, sum=6.485 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13711408420138893,
          "description": "min=0.117, mean=0.137, max=0.182, sum=4.525 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7698300438596491,
          "markdown": false
        },
        {
          "value": 0.1402282775493421,
          "description": "min=0.14, mean=0.14, max=0.141, sum=2.103 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14052770182291666,
          "description": "min=0.14, mean=0.141, max=0.141, sum=0.422 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21074192341549294,
          "description": "min=0.203, mean=0.211, max=0.224, sum=0.632 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16660095312500048,
          "description": "min=0.162, mean=0.167, max=0.171, sum=0.5 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27051720963541687,
          "description": "min=0.259, mean=0.271, max=0.277, sum=0.812 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2701784687500001,
          "description": "min=0.253, mean=0.27, max=0.28, sum=0.811 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.13805987500000028,
          "description": "min=0.138, mean=0.138, max=0.138, sum=0.138 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.13612351562500047,
          "description": "min=0.136, mean=0.136, max=0.136, sum=0.136 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14062155366016812,
          "description": "min=0.14, mean=0.141, max=0.141, sum=0.422 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14154662890625005,
          "description": "min=0.14, mean=0.142, max=0.143, sum=0.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14153152252906978,
          "description": "min=0.14, mean=0.142, max=0.142, sum=0.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5978011528746431,
          "description": "min=0.494, mean=0.598, max=0.669, sum=3.587 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23717034165862286,
          "description": "min=0.194, mean=0.237, max=0.271, sum=1.423 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.14206914127604175,
          "description": "min=0.141, mean=0.142, max=0.143, sum=0.426 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14050017531142125,
          "description": "min=0.14, mean=0.141, max=0.141, sum=7.587 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15395451290246212,
          "description": "min=0.142, mean=0.154, max=0.17, sum=5.08 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6036239035087719,
          "markdown": false
        },
        {
          "value": 0.19643028419682018,
          "description": "min=0.175, mean=0.196, max=0.215, sum=2.946 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1911954346788195,
          "description": "min=0.176, mean=0.191, max=0.216, sum=0.574 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5124278205692486,
          "description": "min=0.48, mean=0.512, max=0.539, sum=1.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26376651302083315,
          "description": "min=0.259, mean=0.264, max=0.268, sum=0.791 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3939576829427085,
          "description": "min=0.387, mean=0.394, max=0.398, sum=1.182 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.8912715646701383,
          "description": "min=0.887, mean=0.891, max=0.894, sum=2.674 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1710758125,
          "description": "min=0.171, mean=0.171, max=0.171, sum=0.171 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1578440234375,
          "description": "min=0.158, mean=0.158, max=0.158, sum=0.158 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20048467762487246,
          "description": "min=0.186, mean=0.2, max=0.208, sum=0.601 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19244404882812502,
          "description": "min=0.174, mean=0.192, max=0.207, sum=0.577 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19810631661821707,
          "description": "min=0.173, mean=0.198, max=0.213, sum=0.594 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.235718461202547,
          "description": "min=2.064, mean=2.236, max=2.638, sum=15.65 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0257979815553757,
          "description": "min=1.003, mean=1.026, max=1.088, sum=7.181 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24716598621961808,
          "description": "min=0.218, mean=0.247, max=0.279, sum=0.741 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18589157378997984,
          "description": "min=0.174, mean=0.186, max=0.217, sum=10.038 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27634172535905943,
          "description": "min=0.195, mean=0.276, max=0.351, sum=9.119 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7827028508771929,
          "markdown": false
        },
        {
          "value": 0.13321992694627194,
          "description": "min=0.129, mean=0.133, max=0.14, sum=1.998 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14293199392361097,
          "description": "min=0.141, mean=0.143, max=0.146, sum=0.429 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20493085387323948,
          "description": "min=0.19, mean=0.205, max=0.217, sum=0.615 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15303552604166656,
          "description": "min=0.152, mean=0.153, max=0.154, sum=0.459 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1847613116319444,
          "description": "min=0.176, mean=0.185, max=0.193, sum=0.554 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.29803956770833356,
          "description": "min=0.287, mean=0.298, max=0.313, sum=0.894 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.12517962499999974,
          "description": "min=0.125, mean=0.125, max=0.125, sum=0.125 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1193705468750003,
          "description": "min=0.119, mean=0.119, max=0.119, sum=0.119 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1343441023987004,
          "description": "min=0.134, mean=0.134, max=0.136, sum=0.403 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13591170442708336,
          "description": "min=0.134, mean=0.136, max=0.138, sum=0.408 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13529218144379848,
          "description": "min=0.133, mean=0.135, max=0.138, sum=0.406 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7991309579692929,
          "description": "min=0.748, mean=0.799, max=0.848, sum=5.594 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36398217373942815,
          "description": "min=0.349, mean=0.364, max=0.408, sum=2.548 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1473289437934027,
          "description": "min=0.142, mean=0.147, max=0.151, sum=0.442 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1415740791295965,
          "description": "min=0.129, mean=0.142, max=0.149, sum=7.645 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1516085454150884,
          "description": "min=0.13, mean=0.152, max=0.183, sum=5.003 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7775548245614035,
          "markdown": false
        },
        {
          "value": 0.13263352809758774,
          "description": "min=0.131, mean=0.133, max=0.135, sum=1.99 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14212787000868074,
          "description": "min=0.136, mean=0.142, max=0.15, sum=0.426 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24279079738849765,
          "description": "min=0.239, mean=0.243, max=0.246, sum=0.728 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1355529375,
          "description": "min=0.134, mean=0.136, max=0.137, sum=0.407 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20402605620659717,
          "description": "min=0.2, mean=0.204, max=0.207, sum=0.612 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3136292994791667,
          "description": "min=0.305, mean=0.314, max=0.32, sum=0.941 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.12474649999999997,
          "description": "min=0.125, mean=0.125, max=0.125, sum=0.125 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.12216468749999997,
          "description": "min=0.122, mean=0.122, max=0.122, sum=0.122 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1335233459161568,
          "description": "min=0.133, mean=0.134, max=0.134, sum=0.401 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1359015429687499,
          "description": "min=0.136, mean=0.136, max=0.136, sum=0.408 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1353138323643411,
          "description": "min=0.135, mean=0.135, max=0.136, sum=0.406 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9683207451306926,
          "description": "min=0.951, mean=0.968, max=0.994, sum=5.81 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43057023625187685,
          "description": "min=0.416, mean=0.431, max=0.439, sum=2.583 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15740409657118068,
          "description": "min=0.151, mean=0.157, max=0.162, sum=0.472 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13774715150926628,
          "description": "min=0.13, mean=0.138, max=0.151, sum=7.438 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15293320707070707,
          "description": "min=0.13, mean=0.153, max=0.188, sum=5.047 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.937796052631579,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.08760755934758772,
          "description": "min=0.086, mean=0.088, max=0.089, sum=1.314 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09557654231770833,
          "description": "min=0.09, mean=0.096, max=0.103, sum=0.287 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1710890294894365,
          "description": "min=0.16, mean=0.171, max=0.186, sum=0.513 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08484092187500009,
          "description": "min=0.083, mean=0.085, max=0.087, sum=0.255 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.12779065299479173,
          "description": "min=0.119, mean=0.128, max=0.133, sum=0.383 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20979015885416655,
          "description": "min=0.194, mean=0.21, max=0.221, sum=0.629 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.07943312500000001,
          "description": "min=0.079, mean=0.079, max=0.079, sum=0.079 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.07620585937499988,
          "description": "min=0.076, mean=0.076, max=0.076, sum=0.076 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.08860781608371561,
          "description": "min=0.088, mean=0.089, max=0.089, sum=0.266 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08991796223958341,
          "description": "min=0.089, mean=0.09, max=0.091, sum=0.27 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08954472504844961,
          "description": "min=0.089, mean=0.09, max=0.09, sum=0.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7929256541152537,
          "description": "min=0.791, mean=0.793, max=0.796, sum=4.758 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31128436946991633,
          "description": "min=0.304, mean=0.311, max=0.318, sum=1.868 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.109459033203125,
          "description": "min=0.104, mean=0.109, max=0.114, sum=0.328 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0919244734885576,
          "description": "min=0.086, mean=0.092, max=0.103, sum=4.964 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.10687999526515152,
          "description": "min=0.084, mean=0.107, max=0.14, sum=3.527 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1511111111111111,
          "markdown": false
        },
        {
          "value": 0.33523606010994367,
          "description": "min=0.194, mean=0.335, max=0.546, sum=5.029 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1913305165274586,
          "description": "min=0.942, mean=1.191, max=1.332, sum=3.574 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.3151894005635367,
          "description": "min=1.78, mean=2.315, max=3.197, sum=6.946 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9528701016867446,
          "description": "min=0.822, mean=0.953, max=1.045, sum=2.859 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.3693331199589207,
          "description": "min=2.251, mean=2.369, max=2.58, sum=7.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.218568385192325,
          "description": "min=4.186, mean=4.219, max=4.235, sum=12.656 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.15830796687302695,
          "description": "min=0.069, mean=0.158, max=0.193, sum=0.633 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 3.5136688752771708,
          "description": "min=3.427, mean=3.514, max=3.581, sum=21.082 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.537310096660418,
          "description": "min=2.516, mean=2.537, max=2.549, sum=15.224 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4970239554705547,
          "description": "min=1.446, mean=1.497, max=1.55, sum=4.491 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.695191819583079,
          "description": "min=0.442, mean=0.695, max=1.665, sum=37.54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4705579548050658,
          "description": "min=0.333, mean=1.471, max=2.214, sum=48.528 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "5 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2658333333333333,
          "markdown": false
        },
        {
          "value": 0.14296402070471761,
          "description": "min=0.09, mean=0.143, max=0.217, sum=2.144 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8282727491158176,
          "description": "min=0.546, mean=0.828, max=1.136, sum=2.485 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.314193915889056,
          "description": "min=2.158, mean=2.314, max=2.397, sum=6.943 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7221932611479644,
          "description": "min=2.669, mean=2.722, max=2.827, sum=8.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.463013303365339,
          "description": "min=4.373, mean=4.463, max=4.531, sum=13.389 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.278147567048529,
          "description": "min=2.259, mean=2.278, max=2.297, sum=6.834 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.09243018414244196,
          "description": "min=0.058, mean=0.092, max=0.136, sum=0.37 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 2.3457143735281405,
          "description": "min=2.334, mean=2.346, max=2.352, sum=14.074 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6713877910966286,
          "description": "min=1.653, mean=1.671, max=1.681, sum=10.028 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1365543731623833,
          "description": "min=1.076, mean=1.137, max=1.23, sum=3.41 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4099806397254133,
          "description": "min=0.291, mean=0.41, max=0.737, sum=22.139 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8904544346562409,
          "description": "min=0.132, mean=0.89, max=1.838, sum=29.385 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_efficiency.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_efficiency.json"
      }
    ],
    "name": "efficiency"
  },
  {
    "title": "General information",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "MMLU - # eval",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "MMLU"
        }
      },
      {
        "value": "MMLU - # train",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "MMLU"
        }
      },
      {
        "value": "MMLU - truncated",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "MMLU"
        }
      },
      {
        "value": "MMLU - # prompt tokens",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "MMLU"
        }
      },
      {
        "value": "MMLU - # output tokens",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "MMLU"
        }
      },
      {
        "value": "MMLU - # trials",
        "description": "The Massive Multitask Language Understanding (MMLU) benchmark for knowledge-intensive question answering across 57 domains [(Hendrycks et al., 2021)](https://openreview.net/forum?id=d7KBjmI3GmQ).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "MMLU"
        }
      },
      {
        "value": "BoolQ - # eval",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - # train",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - truncated",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - # prompt tokens",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - # output tokens",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - # trials",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - # eval",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - # train",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - truncated",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - # prompt tokens",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - # output tokens",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - # trials",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - # eval",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - # train",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - truncated",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - # prompt tokens",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - # output tokens",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - # trials",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - # eval",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - # train",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - truncated",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - # prompt tokens",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - # output tokens",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - # trials",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - # eval",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - # train",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - truncated",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - # prompt tokens",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - # output tokens",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - # trials",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "QuAC"
        }
      },
      {
        "value": "HellaSwag - # eval",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "HellaSwag - # train",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "HellaSwag - truncated",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "HellaSwag - # prompt tokens",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "HellaSwag - # output tokens",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "HellaSwag - # trials",
        "description": "The HellaSwag benchmark for commonsense reasoning in question answering [(Zellers et al., 2019)](https://aclanthology.org/P19-1472/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "HellaSwag"
        }
      },
      {
        "value": "OpenbookQA - # eval",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "OpenbookQA - # train",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "OpenbookQA - truncated",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "OpenbookQA - # prompt tokens",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "OpenbookQA - # output tokens",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "OpenbookQA - # trials",
        "description": "The OpenbookQA benchmark for commonsense-intensive open book question answering [(Mihaylov et al., 2018)](https://aclanthology.org/D18-1260/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "OpenbookQA"
        }
      },
      {
        "value": "TruthfulQA - # eval",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "TruthfulQA - # train",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "TruthfulQA - truncated",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "TruthfulQA - # prompt tokens",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "TruthfulQA - # output tokens",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "TruthfulQA - # trials",
        "description": "The TruthfulQA benchmarking for measuring model truthfulness and commonsense knowledge in question answering [(Lin et al., 2022)](https://aclanthology.org/2022.acl-long.229/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "TruthfulQA"
        }
      },
      {
        "value": "MS MARCO (regular) - # eval",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - # train",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - truncated",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - # prompt tokens",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - # output tokens",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - # trials",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (TREC) - # eval",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - # train",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - truncated",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - # prompt tokens",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - # output tokens",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - # trials",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "CNN/DailyMail - # eval",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - # train",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - truncated",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - # prompt tokens",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - # output tokens",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - # trials",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - # eval",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - # train",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - truncated",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - # prompt tokens",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - # output tokens",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - # trials",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "XSUM"
        }
      },
      {
        "value": "IMDB - # eval",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - # train",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - truncated",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - # prompt tokens",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - # output tokens",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - # trials",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - # eval",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - # train",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - truncated",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - # prompt tokens",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - # output tokens",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - # trials",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - # eval",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n# eval: Number of evaluation instances.",
        "markdown": false,
        "metadata": {
          "metric": "# eval",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - # train",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n# train: Number of training instances (e.g., in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "# train",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - truncated",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\ntruncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).",
        "markdown": false,
        "metadata": {
          "metric": "truncated",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - # prompt tokens",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n# prompt tokens: Number of tokens in the prompt.",
        "markdown": false,
        "metadata": {
          "metric": "# prompt tokens",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - # output tokens",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n# output tokens: Actual number of output tokens.",
        "markdown": false,
        "metadata": {
          "metric": "# output tokens",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - # trials",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\n# trials: Number of trials, where in each trial we choose an independent, random set of training instances.",
        "markdown": false,
        "metadata": {
          "metric": "# trials",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.63943661971831,
          "description": "min=2.166, mean=2.639, max=3.225, sum=7.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1692.2178403755868,
          "description": "min=1598.614, mean=1692.218, max=1777.299, sum=5076.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.513615023474178,
          "description": "min=4.434, mean=4.514, max=4.617, sum=13.541 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.602,
          "description": "min=5.012, mean=5.602, max=6.608, sum=16.806 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.6819999999999995,
          "description": "min=5.418, mean=5.682, max=5.988, sum=17.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8286666666666667,
          "description": "min=1.788, mean=1.829, max=1.88, sum=5.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1698.7113333333334,
          "description": "min=1645.856, mean=1698.711, max=1730.814, sum=5096.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.783666666666665,
          "description": "min=22.621, mean=26.784, max=29.261, sum=80.351 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.001333333333333,
          "description": "min=2, mean=2.001, max=2.004, sum=6.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.046511627906977,
          "description": "min=2.047, mean=2.047, max=2.047, sum=6.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 72.46924177396282,
          "description": "min=67.139, mean=72.469, max=75.648, sum=434.815 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.012870012870014,
          "description": "min=21.958, mean=22.013, max=22.106, sum=132.077 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.6340909090909084,
          "description": "min=1.95, mean=3.634, max=6.925, sum=119.925 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.63943661971831,
          "description": "min=2.166, mean=2.639, max=3.225, sum=7.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1692.2178403755868,
          "description": "min=1598.614, mean=1692.218, max=1777.299, sum=5076.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.090140845070422,
          "description": "min=4.797, mean=5.09, max=5.518, sum=15.27 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.876,
          "description": "min=6.868, mean=7.876, max=9.311, sum=23.628 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.946000000000001,
          "description": "min=5.487, mean=5.946, max=6.338, sum=17.838 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8286666666666667,
          "description": "min=1.788, mean=1.829, max=1.88, sum=5.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1698.7113333333334,
          "description": "min=1645.856, mean=1698.711, max=1730.814, sum=5096.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.64233333333333,
          "description": "min=23.833, mean=27.642, max=30.067, sum=82.927 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0723333333333334,
          "description": "min=2.011, mean=2.072, max=2.163, sum=6.217 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.116279069767442,
          "description": "min=2.093, mean=2.116, max=2.163, sum=6.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 89.61373390557941,
          "description": "min=78.521, mean=89.614, max=102.401, sum=537.682 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 21.2985842985843,
          "description": "min=20.832, mean=21.299, max=21.809, sum=127.792 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.4992424242424245,
          "description": "min=1.975, mean=3.499, max=7.025, sum=115.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.63943661971831,
          "description": "min=2.166, mean=2.639, max=3.225, sum=7.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1692.2178403755868,
          "description": "min=1598.614, mean=1692.218, max=1777.299, sum=5076.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.527699530516432,
          "description": "min=4.324, mean=4.528, max=4.701, sum=13.583 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.971,
          "description": "min=4.791, mean=5.971, max=7.18, sum=17.913 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.538333333333333,
          "description": "min=6.302, mean=6.538, max=6.976, sum=19.615 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8286666666666667,
          "description": "min=1.788, mean=1.829, max=1.88, sum=5.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1698.7113333333334,
          "description": "min=1645.856, mean=1698.711, max=1730.814, sum=5096.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.785666666666668,
          "description": "min=22.154, mean=27.786, max=31.692, sum=83.357 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0113333333333334,
          "description": "min=2.004, mean=2.011, max=2.023, sum=6.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0232558139534884,
          "description": "min=2.023, mean=2.023, max=2.023, sum=6.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 67.04935622317596,
          "description": "min=61.569, mean=67.049, max=76.034, sum=402.296 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 20.467824967824967,
          "description": "min=19.975, mean=20.468, max=21.141, sum=122.807 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.590151515151515,
          "description": "min=1.95, mean=3.59, max=6.575, sum=118.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.63943661971831,
          "description": "min=2.166, mean=2.639, max=3.225, sum=7.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1692.2178403755868,
          "description": "min=1598.614, mean=1692.218, max=1777.299, sum=5076.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6,
          "description": "min=4.194, mean=4.6, max=5.011, sum=13.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.282,
          "description": "min=4.471, mean=5.282, max=6.145, sum=15.846 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.269666666666667,
          "description": "min=5.132, mean=5.27, max=5.521, sum=15.809 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8286666666666667,
          "description": "min=1.788, mean=1.829, max=1.88, sum=5.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1698.7113333333334,
          "description": "min=1645.856, mean=1698.711, max=1730.814, sum=5096.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.052666666666667,
          "description": "min=19.318, mean=23.053, max=25.3, sum=69.158 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0086666666666666,
          "description": "min=2.001, mean=2.009, max=2.02, sum=6.026 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0232558139534884,
          "description": "min=2.023, mean=2.023, max=2.023, sum=6.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 53.21459227467812,
          "description": "min=48.575, mean=53.215, max=56.485, sum=319.288 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.09202059202059,
          "description": "min=21.805, mean=22.092, max=22.577, sum=132.552 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5742424242424238,
          "description": "min=1.95, mean=3.574, max=6.575, sum=117.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0016666666666665,
          "description": "min=2, mean=2.002, max=2.003, sum=6.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2818.1004694835683,
          "description": "min=2534.434, mean=2818.1, max=3027.434, sum=8454.301 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.405633802816901,
          "description": "min=4.879, mean=6.406, max=7.755, sum=19.217 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.364999999999999,
          "description": "min=5.127, mean=5.365, max=5.79, sum=16.095 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.9303333333333335,
          "description": "min=4.928, mean=4.93, max=4.932, sum=14.791 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.012000000000000002,
          "description": "min=0.012, mean=0.012, max=0.012, sum=0.036 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1571.1706666666669,
          "description": "min=1254.565, mean=1571.171, max=1771.274, sum=4713.512 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.112666666666667,
          "description": "min=4.785, mean=5.113, max=5.399, sum=15.338 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.999666666666666,
          "description": "min=4.999, mean=5.0, max=5, sum=14.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4018.7793333333334,
          "description": "min=3587.32, mean=4018.779, max=4568.698, sum=12056.338 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.177666666666664,
          "description": "min=21.621, mean=22.178, max=22.826, sum=66.533 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.001,
          "description": "min=2, mean=2.001, max=2.003, sum=6.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 49.238912732474965,
          "description": "min=47.208, mean=49.239, max=51.633, sum=295.433 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.142213642213644,
          "description": "min=21.909, mean=22.142, max=22.392, sum=132.853 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1288.5176666666669,
          "description": "min=853.851, mean=1288.518, max=1745.851, sum=3865.553 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=165 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 944.1568181818182,
          "description": "min=212.25, mean=944.157, max=4506.05, sum=31157.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5969696969696967,
          "description": "min=2, mean=3.597, max=7.275, sum=118.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.002,
          "description": "min=2.002, mean=2.002, max=2.002, sum=6.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.63943661971831,
          "description": "min=2.166, mean=2.639, max=3.225, sum=7.918 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1692.2178403755868,
          "description": "min=1598.614, mean=1692.218, max=1777.299, sum=5076.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.261032863849765,
          "description": "min=5.039, mean=5.261, max=5.473, sum=15.783 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.314666666666667,
          "description": "min=5.466, mean=6.315, max=6.864, sum=18.944 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.676333333333333,
          "description": "min=5.441, mean=5.676, max=6.069, sum=17.029 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.8286666666666667,
          "description": "min=1.788, mean=1.829, max=1.88, sum=5.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1698.7113333333334,
          "description": "min=1645.856, mean=1698.711, max=1730.814, sum=5096.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.469333333333335,
          "description": "min=22.04, mean=24.469, max=26.73, sum=73.408 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.005666666666667,
          "description": "min=2.003, mean=2.006, max=2.008, sum=6.017 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0232558139534884,
          "description": "min=2.023, mean=2.023, max=2.023, sum=6.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 55.76180257510729,
          "description": "min=48.987, mean=55.762, max=59.891, sum=334.571 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 21.75032175032175,
          "description": "min=21.463, mean=21.75, max=22.241, sum=130.502 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.643939393939394,
          "description": "min=1.95, mean=3.644, max=6.3, sum=120.25 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 396.73985964912276,
          "description": "min=308.59, mean=396.74, max=552.719, sum=5951.098 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.6516666666666,
          "description": "min=506.985, mean=694.652, max=952.985, sum=2083.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.377,
          "description": "min=94.377, mean=99.377, max=102.377, sum=298.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.729,
          "description": "min=5.924, mean=6.729, max=7.956, sum=20.187 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.666333333333333,
          "description": "min=4.568, mean=4.666, max=4.734, sum=13.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.4566666666667,
          "description": "min=1136.933, mean=1418.457, max=1595.508, sum=4255.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.310666666666666,
          "description": "min=5.825, mean=6.311, max=6.845, sum=18.932 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 62.466,
          "description": "min=62.466, mean=62.466, max=62.466, sum=62.466 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.348,
          "description": "min=4.348, mean=4.348, max=4.348, sum=4.348 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0152905198777,
          "description": "min=317.682, mean=355.015, max=375.682, sum=1065.046 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 385.63633333333337,
          "description": "min=349.303, mean=385.636, max=423.303, sum=1156.909 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.012333333333333,
          "description": "min=2.006, mean=2.012, max=2.022, sum=6.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 373.3798449612403,
          "description": "min=337.047, mean=373.38, max=411.047, sum=1120.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0232558139534884,
          "description": "min=2.023, mean=2.023, max=2.023, sum=6.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1213.0321888412018,
          "description": "min=1203.032, mean=1213.032, max=1224.032, sum=7278.193 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 58.24606580829757,
          "description": "min=52.573, mean=58.246, max=61.575, sum=349.476 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1133.388030888031,
          "description": "min=1099.388, mean=1133.388, max=1172.388, sum=6800.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 21.22844272844273,
          "description": "min=21.112, mean=21.228, max=21.315, sum=127.371 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.971666666666667,
          "description": "min=4.915, mean=4.972, max=5, sum=14.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1281.5773333333334,
          "description": "min=853.851, mean=1281.577, max=1725.03, sum=3844.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.6016121330534,
          "description": "min=271.927, mean=532.602, max=942.498, sum=28760.487 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.657575757575757,
          "description": "min=0.95, mean=4.658, max=5, sum=153.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 712.2477272727273,
          "description": "min=212.25, mean=712.248, max=1745.25, sum=23504.175 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5621212121212116,
          "description": "min=1.975, mean=3.562, max=6.575, sum=117.55 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 471.0754736842105,
          "description": "min=360.75, mean=471.075, max=618.447, sum=7066.132 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.9913333333333,
          "description": "min=651.658, mean=908.991, max=1252.658, sum=2726.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.002,
          "description": "min=1, mean=1.002, max=1.003, sum=3.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6206572769953052,
          "description": "min=1.039, mean=1.621, max=2.037, sum=4.862 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1647.783098591549,
          "description": "min=1606.952, mean=1647.783, max=1694.642, sum=4943.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.798122065727699,
          "description": "min=5.521, mean=6.798, max=8.192, sum=20.394 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.75366666666667,
          "description": "min=109.087, mean=111.754, max=116.087, sum=335.261 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.287,
          "description": "min=4.314, mean=5.287, max=5.908, sum=15.861 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.711333333333333,
          "description": "min=4.691, mean=4.711, max=4.726, sum=14.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03866666666666666,
          "description": "min=0.038, mean=0.039, max=0.04, sum=0.116 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1384.5649999999998,
          "description": "min=1224.733, mean=1384.565, max=1488.14, sum=4153.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.149666666666667,
          "description": "min=7.685, mean=10.15, max=11.898, sum=30.449 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9089999999999999,
          "description": "min=0.84, mean=0.909, max=0.991, sum=2.727 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03266666666666667,
          "description": "min=0.029, mean=0.033, max=0.037, sum=0.098 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1641.256,
          "description": "min=1596.904, mean=1641.256, max=1672.92, sum=4923.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.471666666666668,
          "description": "min=18.527, mean=23.472, max=28.795, sum=70.415 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.0733944954128,
          "description": "min=504.073, mean=514.073, max=533.073, sum=1542.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1578.648068669528,
          "description": "min=1564.648, mean=1578.648, max=1593.648, sum=9471.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 80.86623748211731,
          "description": "min=59.824, mean=80.866, max=92.721, sum=485.197 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1532.9118404118406,
          "description": "min=1472.903, mean=1532.912, max=1566.407, sum=9197.471 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.02123552123552,
          "description": "min=25.481, mean=26.021, max=26.315, sum=156.127 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.236000000000001,
          "description": "min=2.908, mean=4.236, max=4.985, sum=12.708 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1560.0556666666664,
          "description": "min=1283.569, mean=1560.056, max=1777.712, sum=4680.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 724.7816027688522,
          "description": "min=362.037, mean=724.782, max=1272.822, sum=39138.207 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5598484848484855,
          "description": "min=0, mean=4.56, max=5, sum=150.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002272727272727273,
          "description": "min=0, mean=0.002, max=0.025, sum=0.075 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 810.7689393939394,
          "description": "min=262.3, mean=810.769, max=1759.65, sum=26755.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.91590909090909,
          "description": "min=0.75, mean=2.916, max=6.5, sum=96.225 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 471.0754736842105,
          "description": "min=360.75, mean=471.075, max=618.447, sum=7066.132 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.9913333333333,
          "description": "min=651.658, mean=908.991, max=1252.658, sum=2726.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6206572769953052,
          "description": "min=1.039, mean=1.621, max=2.037, sum=4.862 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1647.783098591549,
          "description": "min=1606.952, mean=1647.783, max=1694.642, sum=4943.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.04225352112676,
          "description": "min=6.321, mean=7.042, max=8.175, sum=21.127 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.75366666666667,
          "description": "min=109.087, mean=111.754, max=116.087, sum=335.261 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.118666666666666,
          "description": "min=5.508, mean=6.119, max=6.869, sum=18.356 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.711333333333333,
          "description": "min=4.691, mean=4.711, max=4.726, sum=14.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03866666666666666,
          "description": "min=0.038, mean=0.039, max=0.04, sum=0.116 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1384.5649999999998,
          "description": "min=1224.733, mean=1384.565, max=1488.14, sum=4153.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.299999999999999,
          "description": "min=8.216, mean=10.3, max=11.913, sum=30.9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9089999999999999,
          "description": "min=0.84, mean=0.909, max=0.991, sum=2.727 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03266666666666667,
          "description": "min=0.029, mean=0.033, max=0.037, sum=0.098 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1641.256,
          "description": "min=1596.904, mean=1641.256, max=1672.92, sum=4923.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 21.144000000000002,
          "description": "min=20.299, mean=21.144, max=22.408, sum=63.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.0733944954128,
          "description": "min=504.073, mean=514.073, max=533.073, sum=1542.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1578.648068669528,
          "description": "min=1564.648, mean=1578.648, max=1593.648, sum=9471.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 83.11230329041489,
          "description": "min=73.322, mean=83.112, max=88.178, sum=498.674 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1532.9118404118406,
          "description": "min=1472.903, mean=1532.912, max=1566.407, sum=9197.471 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.987129987129986,
          "description": "min=25.747, mean=25.987, max=26.212, sum=155.923 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.236000000000001,
          "description": "min=2.908, mean=4.236, max=4.985, sum=12.708 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1560.0556666666664,
          "description": "min=1283.569, mean=1560.056, max=1777.712, sum=4680.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 724.7816027688522,
          "description": "min=362.037, mean=724.782, max=1272.822, sum=39138.207 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5598484848484855,
          "description": "min=0, mean=4.56, max=5, sum=150.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002272727272727273,
          "description": "min=0, mean=0.002, max=0.025, sum=0.075 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 810.7689393939394,
          "description": "min=262.3, mean=810.769, max=1759.65, sum=26755.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.796212121212121,
          "description": "min=0.125, mean=2.796, max=6.825, sum=92.275 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 471.0754736842105,
          "description": "min=360.75, mean=471.075, max=618.447, sum=7066.132 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.9913333333333,
          "description": "min=651.658, mean=908.991, max=1252.658, sum=2726.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6206572769953052,
          "description": "min=1.039, mean=1.621, max=2.037, sum=4.862 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1647.783098591549,
          "description": "min=1606.952, mean=1647.783, max=1694.642, sum=4943.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.84037558685446,
          "description": "min=5.749, mean=6.84, max=8.158, sum=20.521 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.75366666666667,
          "description": "min=109.087, mean=111.754, max=116.087, sum=335.261 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.508333333333334,
          "description": "min=4.262, mean=4.508, max=4.666, sum=13.525 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.711333333333333,
          "description": "min=4.691, mean=4.711, max=4.726, sum=14.134 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03866666666666666,
          "description": "min=0.038, mean=0.039, max=0.04, sum=0.116 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1384.5649999999998,
          "description": "min=1224.733, mean=1384.565, max=1488.14, sum=4153.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.361999999999999,
          "description": "min=6.064, mean=6.362, max=6.864, sum=19.086 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9089999999999999,
          "description": "min=0.84, mean=0.909, max=0.991, sum=2.727 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.03266666666666667,
          "description": "min=0.029, mean=0.033, max=0.037, sum=0.098 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1641.256,
          "description": "min=1596.904, mean=1641.256, max=1672.92, sum=4923.768 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.241000000000003,
          "description": "min=22.638, mean=26.241, max=28.094, sum=78.723 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.0733944954128,
          "description": "min=504.073, mean=514.073, max=533.073, sum=1542.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1578.648068669528,
          "description": "min=1564.648, mean=1578.648, max=1593.648, sum=9471.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 75.51001430615165,
          "description": "min=71.758, mean=75.51, max=79.294, sum=453.06 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1532.9118404118406,
          "description": "min=1472.903, mean=1532.912, max=1566.407, sum=9197.471 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.422779922779924,
          "description": "min=25.844, mean=26.423, max=26.988, sum=158.537 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.236000000000001,
          "description": "min=2.908, mean=4.236, max=4.985, sum=12.708 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1560.0556666666664,
          "description": "min=1283.569, mean=1560.056, max=1777.712, sum=4680.167 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 724.7816027688522,
          "description": "min=362.037, mean=724.782, max=1272.822, sum=39138.207 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5598484848484855,
          "description": "min=0, mean=4.56, max=5, sum=150.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002272727272727273,
          "description": "min=0, mean=0.002, max=0.025, sum=0.075 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 810.7689393939394,
          "description": "min=262.3, mean=810.769, max=1759.65, sum=26755.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0969696969696976,
          "description": "min=0, mean=3.097, max=6.725, sum=102.2 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.004,
          "description": "min=1.004, mean=1.004, max=1.004, sum=3.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3803.910798122066,
          "description": "min=3504.577, mean=3803.911, max=3972.577, sum=11411.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.9521126760563385,
          "description": "min=4.572, mean=6.952, max=8.434, sum=20.856 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.469666666666666,
          "description": "min=5.032, mean=5.47, max=6.183, sum=16.409 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.964333333333333,
          "description": "min=4.964, mean=4.964, max=4.965, sum=14.893 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.007,
          "description": "min=0.007, mean=0.007, max=0.007, sum=0.021 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1592.701,
          "description": "min=1381.066, mean=1592.701, max=1704.681, sum=4778.103 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.658666666666666,
          "description": "min=5.429, mean=5.659, max=6.028, sum=16.976 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5199.788,
          "description": "min=4676.788, mean=5199.788, max=5842.788, sum=15599.364 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 35.484,
          "description": "min=32.106, mean=35.484, max=40.222, sum=106.452 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.306,
          "description": "min=1.306, mean=1.306, max=1.306, sum=1.306 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.132,
          "description": "min=0.132, mean=0.132, max=0.132, sum=0.132 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 404.62079510703364,
          "description": "min=85.121, mean=404.621, max=529.121, sum=1618.483 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0046666666666668,
          "description": "min=1, mean=1.005, max=1.014, sum=3.014 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 58.035050071530755,
          "description": "min=54.895, mean=58.035, max=64.039, sum=348.21 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.734877734878,
          "description": "min=1456.402, mean=1510.735, max=1539.402, sum=9064.409 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 28.93951093951094,
          "description": "min=28.284, mean=28.94, max=29.546, sum=173.637 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1422.5453333333335,
          "description": "min=1155.212, mean=1422.545, max=1836.212, sum=4267.636 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.014,
          "description": "min=1.002, mean=1.014, max=1.02, sum=3.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=165 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1279.5719696969697,
          "description": "min=257.35, mean=1279.572, max=6599.65, sum=42225.875 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.9863636363636363,
          "description": "min=1, mean=2.986, max=5.3, sum=98.55 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 436.9895789473684,
          "description": "min=333.02, mean=436.99, max=574.658, sum=6554.844 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 897.1073333333333,
          "description": "min=636.774, mean=897.107, max=1242.774, sum=2691.322 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6206572769953052,
          "description": "min=1.042, mean=1.621, max=2.048, sum=4.862 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1649.5981220657277,
          "description": "min=1604.899, mean=1649.598, max=1699.146, sum=4948.794 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 33.27605633802816,
          "description": "min=18.468, mean=33.276, max=50.499, sum=99.828 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 96.12,
          "description": "min=92.12, mean=96.12, max=102.12, sum=288.36 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 48.109,
          "description": "min=34.82, mean=48.109, max=57.074, sum=144.327 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.743000000000001,
          "description": "min=4.73, mean=4.743, max=4.751, sum=14.229 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.035,
          "description": "min=0.035, mean=0.035, max=0.035, sum=0.105 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1313.4223333333334,
          "description": "min=1193.69, mean=1313.422, max=1423.457, sum=3940.267 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 38.803000000000004,
          "description": "min=31.304, mean=38.803, max=46.481, sum=116.409 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.944,
          "description": "min=0.855, mean=0.944, max=1.07, sum=2.832 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.017,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.494,
          "description": "min=1614.308, mean=1639.494, max=1673.303, sum=4918.482 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 90.16366666666666,
          "description": "min=86.351, mean=90.164, max=93.357, sum=270.491 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.875,
          "description": "min=88.875, mean=88.875, max=88.875, sum=88.875 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.444,
          "description": "min=5.444, mean=5.444, max=5.444, sum=5.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 370.6108562691131,
          "description": "min=79.361, mean=370.611, max=481.361, sum=1482.443 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.472,
          "description": "min=484.472, mean=524.472, max=570.472, sum=1573.416 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 506.81395348837214,
          "description": "min=466.814, mean=506.814, max=552.814, sum=1520.442 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.3304721030042,
          "description": "min=1520.33, mean=1541.33, max=1578.33, sum=9247.983 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.4349070100143,
          "description": "min=104.867, mean=117.435, max=124.011, sum=704.609 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1501.3378378378377,
          "description": "min=1456.338, mean=1501.338, max=1528.338, sum=9008.027 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 54.06563706563707,
          "description": "min=50.606, mean=54.066, max=57.05, sum=324.394 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.943333333333333,
          "description": "min=4.876, mean=4.943, max=4.987, sum=14.83 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1375.2103333333334,
          "description": "min=1129.265, mean=1375.21, max=1727.698, sum=4125.631 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 683.497824649871,
          "description": "min=327.671, mean=683.498, max=1208.636, sum=36908.883 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.567424242424242,
          "description": "min=0.05, mean=4.567, max=5, sum=150.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 779.2030303030305,
          "description": "min=234.025, mean=779.203, max=1729.4, sum=25713.7 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.127272727272727,
          "description": "min=5, mean=7.127, max=13.7, sum=235.2 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 492.0102807017544,
          "description": "min=386.05, mean=492.01, max=639.561, sum=7380.154 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 3.971666666666667,
          "description": "min=2.027, mean=3.972, max=4.988, sum=11.915 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 702.4380000000001,
          "description": "min=479.758, mean=702.438, max=905.932, sum=2107.314 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18685446009389672,
          "description": "min=0, mean=0.187, max=0.33, sum=0.561 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37183098591549296,
          "description": "min=0.369, mean=0.372, max=0.377, sum=1.115 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 877.7417840375587,
          "description": "min=807.577, mean=877.742, max=916.668, sum=2633.225 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 113.556,
          "description": "min=109.556, mean=113.556, max=118.556, sum=340.668 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.396333333333333,
          "description": "min=3.164, mean=3.396, max=3.709, sum=10.189 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.057333333333333326,
          "description": "min=0.052, mean=0.057, max=0.066, sum=0.172 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 903.8770000000001,
          "description": "min=850.863, mean=903.877, max=958.904, sum=2711.631 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.985,
          "description": "min=0.985, mean=0.985, max=0.985, sum=2.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 823.3650000000001,
          "description": "min=823.365, mean=823.365, max=823.365, sum=2470.095 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 391.6460244648318,
          "description": "min=85.896, mean=391.646, max=515.896, sum=1566.584 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 1.3354792560801145,
          "description": "min=1.303, mean=1.335, max=1.378, sum=8.013 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.004291845493562232,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.026 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 886.8376251788268,
          "description": "min=885.292, mean=886.838, max=888.921, sum=5321.026 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 128.0,
          "description": "min=128, mean=128, max=128, sum=768 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 2.0675675675675675,
          "description": "min=1.967, mean=2.068, max=2.214, sum=12.405 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.009652509652509652,
          "description": "min=0.002, mean=0.01, max=0.019, sum=0.058 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 907.7689832689833,
          "description": "min=889.981, mean=907.769, max=929.006, sum=5446.614 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 64.0,
          "description": "min=64, mean=64, max=64, sum=384 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 2.4403333333333332,
          "description": "min=1.981, mean=2.44, max=3.074, sum=7.321 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.03,
          "description": "min=0.03, mean=0.03, max=0.03, sum=0.09 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 910.1736666666666,
          "description": "min=905.879, mean=910.174, max=913.752, sum=2730.521 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.861055391438897,
          "description": "min=2.991, mean=4.861, max=5, sum=262.497 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 744.1091399163704,
          "description": "min=385.732, mean=744.109, max=936.562, sum=40181.894 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.912878787878788,
          "description": "min=0, mean=3.913, max=5, sum=129.125 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09015151515151516,
          "description": "min=0, mean=0.09, max=0.925, sum=2.975 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 650.0121212121212,
          "description": "min=263.4, mean=650.012, max=949.7, sum=21450.4 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=990 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0013333333333334,
          "description": "min=1, mean=1.001, max=1.004, sum=3.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.07699530516432,
          "description": "min=5.794, mean=7.077, max=9.031, sum=21.231 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.843666666666667,
          "description": "min=5.31, mean=5.844, max=6.407, sum=17.531 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.834,
          "description": "min=7.154, mean=8.834, max=11.932, sum=26.502 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 32.717333333333336,
          "description": "min=31.783, mean=32.717, max=34.585, sum=98.152 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 89.43133047210301,
          "description": "min=88.871, mean=89.431, max=90.324, sum=536.588 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.802445302445303,
          "description": "min=24.515, mean=24.802, max=25.066, sum=148.815 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.229333333333333,
          "description": "min=2.903, mean=4.229, max=4.983, sum=12.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1562.8083333333334,
          "description": "min=1283.038, mean=1562.808, max=1784.2, sum=4688.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0507575757575767,
          "description": "min=0.275, mean=3.051, max=5.95, sum=100.675 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.909859154929578,
          "description": "min=5.535, mean=6.91, max=9.504, sum=20.73 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.625,
          "description": "min=5.441, mean=5.625, max=5.917, sum=16.875 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.443,
          "description": "min=8.71, mean=10.443, max=11.438, sum=31.329 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.036333333333335,
          "description": "min=26.693, mean=30.036, max=32.515, sum=90.109 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0246666666666666,
          "description": "min=1.008, mean=1.025, max=1.046, sum=3.074 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0310077519379846,
          "description": "min=1.023, mean=1.031, max=1.047, sum=3.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 74.50500715307582,
          "description": "min=67.079, mean=74.505, max=78.916, sum=447.03 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.99227799227799,
          "description": "min=22.133, mean=22.992, max=23.423, sum=137.954 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.930000000000001,
          "description": "min=4.846, mean=4.93, max=4.98, sum=14.79 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1398.6536666666668,
          "description": "min=1161.854, mean=1398.654, max=1747.025, sum=4195.961 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.01969696969697,
          "description": "min=0, mean=3.02, max=6.5, sum=99.65 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.770892018779342,
          "description": "min=5.392, mean=6.771, max=8.33, sum=20.313 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.267,
          "description": "min=4.823, mean=5.267, max=5.728, sum=15.801 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.101333333333333,
          "description": "min=7.288, mean=9.101, max=11.307, sum=27.304 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.531000000000002,
          "description": "min=17.39, mean=23.531, max=27.056, sum=70.593 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0046666666666666,
          "description": "min=1, mean=1.005, max=1.013, sum=3.014 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0155038759689923,
          "description": "min=1, mean=1.016, max=1.023, sum=3.047 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 63.1931330472103,
          "description": "min=52.893, mean=63.193, max=73.206, sum=379.159 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.054697554697555,
          "description": "min=23.498, mean=24.055, max=24.463, sum=144.328 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.229333333333333,
          "description": "min=2.903, mean=4.229, max=4.983, sum=12.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1562.8083333333334,
          "description": "min=1283.038, mean=1562.808, max=1784.2, sum=4688.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0033333333333332,
          "description": "min=1, mean=1.003, max=1.01, sum=3.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.965151515151515,
          "description": "min=0.225, mean=2.965, max=6.15, sum=97.85 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0013333333333334,
          "description": "min=1, mean=1.001, max=1.004, sum=3.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.006572769953053,
          "description": "min=8.149, mean=11.007, max=15.597, sum=33.02 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.148666666666667,
          "description": "min=4.325, mean=5.149, max=6.46, sum=15.446 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.834999999999997,
          "description": "min=20.452, mean=22.835, max=25.41, sum=68.505 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 20.638666666666666,
          "description": "min=18.807, mean=20.639, max=21.99, sum=61.916 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0310077519379846,
          "description": "min=1, mean=1.031, max=1.093, sum=3.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 78.3519313304721,
          "description": "min=49.71, mean=78.352, max=93.899, sum=470.112 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.393822393822393,
          "description": "min=25.859, mean=27.394, max=28.226, sum=164.363 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.930000000000001,
          "description": "min=4.846, mean=4.93, max=4.98, sum=14.79 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1398.6536666666668,
          "description": "min=1161.854, mean=1398.654, max=1747.025, sum=4195.961 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.2393939393939393,
          "description": "min=1, mean=3.239, max=5.575, sum=106.9 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.728638497652582,
          "description": "min=5.792, mean=6.729, max=8.434, sum=20.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.808,
          "description": "min=4.528, mean=4.808, max=5.211, sum=14.424 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.092666666666666,
          "description": "min=5.836, mean=6.093, max=6.582, sum=18.278 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.944,
          "description": "min=24.612, mean=27.944, max=31.344, sum=83.832 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0016666666666667,
          "description": "min=1, mean=1.002, max=1.005, sum=3.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 91.33834048640915,
          "description": "min=89.47, mean=91.338, max=92.403, sum=548.03 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.153153153153156,
          "description": "min=25.925, mean=26.153, max=26.423, sum=156.919 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.229333333333333,
          "description": "min=2.903, mean=4.229, max=4.983, sum=12.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1562.8083333333334,
          "description": "min=1283.038, mean=1562.808, max=1784.2, sum=4688.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.9901515151515157,
          "description": "min=0, mean=2.99, max=7.05, sum=98.675 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5624413145539906,
          "description": "min=0.958, mean=1.562, max=1.997, sum=4.687 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1634.9896713615024,
          "description": "min=1601.997, mean=1634.99, max=1693.155, sum=4904.969 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.143661971830986,
          "description": "min=5.544, mean=7.144, max=9.065, sum=21.431 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.745333333333334,
          "description": "min=6.631, mean=6.745, max=6.831, sum=20.236 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.633,
          "description": "min=4.538, mean=4.633, max=4.715, sum=13.899 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1481.344,
          "description": "min=1261.72, mean=1481.344, max=1608.455, sum=4444.032 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.418666666666667,
          "description": "min=7.485, mean=8.419, max=9.746, sum=25.256 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8813333333333334,
          "description": "min=0.797, mean=0.881, max=0.969, sum=2.644 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1639.784333333333,
          "description": "min=1600.292, mean=1639.784, max=1661.675, sum=4919.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.83966666666667,
          "description": "min=18.756, mean=22.84, max=26.573, sum=68.519 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.005,
          "description": "min=1, mean=1.005, max=1.008, sum=3.015 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 68.60085836909872,
          "description": "min=60.474, mean=68.601, max=77.918, sum=411.605 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998069498069498,
          "description": "min=4.996, mean=4.998, max=5, sum=29.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.4517374517375,
          "description": "min=1484.608, mean=1537.452, max=1572.616, sum=9224.71 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.626126126126128,
          "description": "min=23.5, mean=23.626, max=23.749, sum=141.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.229333333333333,
          "description": "min=2.903, mean=4.229, max=4.983, sum=12.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1562.8083333333334,
          "description": "min=1283.038, mean=1562.808, max=1784.2, sum=4688.425 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0033333333333332,
          "description": "min=1, mean=1.003, max=1.01, sum=3.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556818181818182,
          "description": "min=0, mean=4.557, max=5, sum=150.375 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 814.446212121212,
          "description": "min=270.325, mean=814.446, max=1777.025, sum=26876.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0378787878787885,
          "description": "min=0.575, mean=3.038, max=6.375, sum=100.25 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5079812206572771,
          "description": "min=0.904, mean=1.508, max=1.941, sum=4.524 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1600.6835680751174,
          "description": "min=1570.772, mean=1600.684, max=1660.485, sum=4802.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.8065727699530525,
          "description": "min=5.301, mean=5.807, max=6.217, sum=17.42 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6866666666666665,
          "description": "min=4.428, mean=4.687, max=4.995, sum=14.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.602333333333333,
          "description": "min=4.485, mean=4.602, max=4.705, sum=13.807 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1471.073333333333,
          "description": "min=1258.15, mean=1471.073, max=1597.431, sum=4413.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.377,
          "description": "min=7.147, mean=7.377, max=7.586, sum=22.131 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8483333333333333,
          "description": "min=0.748, mean=0.848, max=0.933, sum=2.545 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.022000000000000002,
          "description": "min=0.022, mean=0.022, max=0.022, sum=0.066 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1610.5026666666665,
          "description": "min=1577.224, mean=1610.503, max=1643.74, sum=4831.508 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.394,
          "description": "min=16.185, mean=17.394, max=18.299, sum=52.182 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 73.72317596566523,
          "description": "min=69.622, mean=73.723, max=77.732, sum=442.339 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.997425997425997,
          "description": "min=4.996, mean=4.997, max=5, sum=29.985 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.2927927927929,
          "description": "min=1484.608, mean=1537.293, max=1572.616, sum=9223.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.421492921492924,
          "description": "min=22.674, mean=23.421, max=24.095, sum=140.529 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.217333333333333,
          "description": "min=2.89, mean=4.217, max=4.981, sum=12.652 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1557.7406666666666,
          "description": "min=1282.318, mean=1557.741, max=1776.111, sum=4673.222 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.553787878787879,
          "description": "min=0, mean=4.554, max=5, sum=150.275 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 813.2651515151515,
          "description": "min=270.325, mean=813.265, max=1762.475, sum=26837.75 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.1477272727272725,
          "description": "min=0.2, mean=3.148, max=6.3, sum=103.875 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 481.2602105263158,
          "description": "min=372.75, mean=481.26, max=628.421, sum=7218.903 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 925.3070000000001,
          "description": "min=669.307, mean=925.307, max=1269.307, sum=2775.921 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5079812206572771,
          "description": "min=0.904, mean=1.508, max=1.941, sum=4.524 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1600.6835680751174,
          "description": "min=1570.772, mean=1600.684, max=1660.485, sum=4802.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.992488262910798,
          "description": "min=5.679, mean=5.992, max=6.496, sum=17.977 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.19099999999999,
          "description": "min=109.191, mean=111.191, max=115.191, sum=333.573 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.324666666666666,
          "description": "min=4.29, mean=4.325, max=4.367, sum=12.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.602333333333333,
          "description": "min=4.485, mean=4.602, max=4.705, sum=13.807 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.117 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1471.073333333333,
          "description": "min=1258.15, mean=1471.073, max=1597.431, sum=4413.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.288,
          "description": "min=7.153, mean=7.288, max=7.488, sum=21.864 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8483333333333333,
          "description": "min=0.748, mean=0.848, max=0.933, sum=2.545 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.022000000000000002,
          "description": "min=0.022, mean=0.022, max=0.022, sum=0.066 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1610.5026666666665,
          "description": "min=1577.224, mean=1610.503, max=1643.74, sum=4831.508 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.627,
          "description": "min=19.435, mean=19.627, max=19.984, sum=58.881 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.855,
          "description": "min=88.855, mean=88.855, max=88.855, sum=88.855 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.358,
          "description": "min=5.358, mean=5.358, max=5.358, sum=5.358 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 514.6483180428135,
          "description": "min=505.315, mean=514.648, max=532.315, sum=1543.945 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 536.6143333333333,
          "description": "min=497.281, mean=536.614, max=583.281, sum=1609.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4961240310078,
          "description": "min=480.163, mean=519.496, max=566.163, sum=1558.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1575.0364806866953,
          "description": "min=1555.036, mean=1575.036, max=1602.036, sum=9450.219 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 74.40557939914163,
          "description": "min=72.088, mean=74.406, max=77.451, sum=446.433 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.997425997425997,
          "description": "min=4.996, mean=4.997, max=5, sum=29.985 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1537.2927927927929,
          "description": "min=1484.608, mean=1537.293, max=1572.616, sum=9223.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.35135135135135,
          "description": "min=24.187, mean=24.351, max=24.541, sum=146.108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.217333333333333,
          "description": "min=2.89, mean=4.217, max=4.981, sum=12.652 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1557.7406666666666,
          "description": "min=1282.318, mean=1557.741, max=1776.111, sum=4673.222 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 732.5144825548033,
          "description": "min=362.293, mean=732.514, max=1288.441, sum=39555.782 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.553787878787879,
          "description": "min=0, mean=4.554, max=5, sum=150.275 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 813.2651515151515,
          "description": "min=270.325, mean=813.265, max=1762.475, sum=26837.75 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.15,
          "description": "min=0.025, mean=3.15, max=6.8, sum=103.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 56.05164319248826,
          "description": "min=42.766, mean=56.052, max=70.845, sum=168.155 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 282.83733333333333,
          "description": "min=273.408, mean=282.837, max=296.556, sum=848.512 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 247.22966666666665,
          "description": "min=234.154, mean=247.23, max=261.681, sum=741.689 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 68.54033333333334,
          "description": "min=64.208, mean=68.54, max=71.626, sum=205.621 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 404.62079510703364,
          "description": "min=85.121, mean=404.621, max=529.121, sum=1618.483 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 83.93061516452074,
          "description": "min=76.916, mean=83.931, max=91.68, sum=503.584 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.52895752895753,
          "description": "min=24.919, mean=25.529, max=26.187, sum=153.174 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.932666666666667,
          "description": "min=4.846, mean=4.933, max=4.986, sum=14.798 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1389.4543333333331,
          "description": "min=1152.694, mean=1389.454, max=1744.631, sum=4168.363 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 14.275757575757577,
          "description": "min=5, mean=14.276, max=30, sum=471.1 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=7019.035 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 913.8969999999999,
          "description": "min=656.897, mean=913.897, max=1251.897, sum=2741.691 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.568075117370892,
          "description": "min=0.989, mean=1.568, max=1.969, sum=4.704 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1641.0328638497651,
          "description": "min=1607.893, mean=1641.033, max=1691.082, sum=4923.099 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.04694835680751,
          "description": "min=24.282, mean=40.047, max=54.028, sum=120.141 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.96566666666668,
          "description": "min=110.299, mean=112.966, max=117.299, sum=338.897 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 90.19466666666666,
          "description": "min=77.379, mean=90.195, max=107.541, sum=270.584 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.685, mean=4.704, max=4.723, sum=14.112 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.111 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1394.2293333333334,
          "description": "min=1247.862, mean=1394.229, max=1495.552, sum=4182.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.69266666666665,
          "description": "min=73.671, mean=87.693, max=98.984, sum=263.078 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8886666666666666,
          "description": "min=0.804, mean=0.889, max=0.979, sum=2.666 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.063 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1640.3609999999999,
          "description": "min=1602.026, mean=1640.361, max=1663.349, sum=4921.083 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.48866666666667,
          "description": "min=73.99, mean=77.489, max=80.665, sum=232.466 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 88.806,
          "description": "min=88.806, mean=88.806, max=88.806, sum=88.806 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.346,
          "description": "min=5.346, mean=5.346, max=5.346, sum=5.346 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 406.10168195718654,
          "description": "min=86.352, mean=406.102, max=532.352, sum=1624.407 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 537.9083333333334,
          "description": "min=499.575, mean=537.908, max=583.575, sum=1613.725 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 519.4728682170543,
          "description": "min=481.14, mean=519.473, max=565.14, sum=1558.419 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1582.6080114449214,
          "description": "min=1561.275, mean=1582.608, max=1612.275, sum=9495.648 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 80.40915593705294,
          "description": "min=80.197, mean=80.409, max=80.588, sum=482.455 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.997425997425997,
          "description": "min=4.996, mean=4.997, max=5, sum=29.985 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1545.148005148005,
          "description": "min=1487.131, mean=1545.148, max=1574.17, sum=9270.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.402187902187904,
          "description": "min=24.871, mean=25.402, max=26.143, sum=152.413 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.929666666666667,
          "description": "min=4.842, mean=4.93, max=4.981, sum=14.789 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1398.0903333333333,
          "description": "min=1162.003, mean=1398.09, max=1750.717, sum=4194.271 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 726.7280588093369,
          "description": "min=360.976, mean=726.728, max=1282.4, sum=39243.315 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5598484848484855,
          "description": "min=0, mean=4.56, max=5, sum=150.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 807.9696969696969,
          "description": "min=269.35, mean=807.97, max=1764, sum=26663.0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 13.945454545454545,
          "description": "min=5, mean=13.945, max=30, sum=460.2 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 299.883,
          "description": "min=299.883, mean=299.883, max=299.883, sum=299.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.326397660818714,
          "description": "min=2.482, mean=4.326, max=5, sum=64.896 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 420.5617309941521,
          "description": "min=382.49, mean=420.562, max=467.75, sum=6308.426 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5883333333333332,
          "description": "min=0.969, mean=1.588, max=2.006, sum=4.765 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.004,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 401.94433333333336,
          "description": "min=386.367, mean=401.944, max=422.649, sum=1205.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8253521126760562,
          "description": "min=0.825, mean=0.825, max=0.825, sum=2.476 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 492.14084507042253,
          "description": "min=492.141, mean=492.141, max=492.141, sum=1476.423 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 113.556,
          "description": "min=109.556, mean=113.556, max=118.556, sum=340.668 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9236666666666666,
          "description": "min=0.096, mean=0.924, max=1.792, sum=2.771 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34933333333333333,
          "description": "min=0.094, mean=0.349, max=0.839, sum=1.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 301.907,
          "description": "min=233.452, mean=301.907, max=339.767, sum=905.721 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=2.997 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 510.923,
          "description": "min=510.923, mean=510.923, max=510.923, sum=1532.769 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.547400611620795,
          "description": "min=0, mean=3.547, max=4.869, sum=14.19 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.9197247706422,
          "description": "min=85.896, mean=371.92, max=471.52, sum=1487.679 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06366237482117311,
          "description": "min=0.062, mean=0.064, max=0.067, sum=0.382 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9320457796852647,
          "description": "min=0.929, mean=0.932, max=0.933, sum=5.592 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.5529327610873,
          "description": "min=500.412, mean=500.553, max=500.835, sum=3003.318 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 128.0,
          "description": "min=128, mean=128, max=128, sum=768 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29987129987129985,
          "description": "min=0.239, mean=0.3, max=0.373, sum=1.799 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6705276705276706,
          "description": "min=0.602, mean=0.671, max=0.73, sum=4.023 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 436.8262548262548,
          "description": "min=432.851, mean=436.826, max=442.064, sum=2620.958 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 64.0,
          "description": "min=64, mean=64, max=64, sum=384 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4656666666666666,
          "description": "min=0.33, mean=0.466, max=0.701, sum=1.397 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17266666666666666,
          "description": "min=0.172, mean=0.173, max=0.173, sum=0.518 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 408.4246666666666,
          "description": "min=391.442, mean=408.425, max=434.668, sum=1225.274 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6361556323380086,
          "description": "min=1.019, mean=2.636, max=4.881, sum=142.352 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0017482982997674094,
          "description": "min=0, mean=0.002, max=0.022, sum=0.094 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 416.79149386044713,
          "description": "min=331.768, mean=416.791, max=477.628, sum=22506.741 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.433333333333333,
          "description": "min=0, mean=2.433, max=5, sum=80.3 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3939393939393939,
          "description": "min=0, mean=0.394, max=1, sum=13 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 420.7416666666667,
          "description": "min=263.4, mean=420.742, max=511, sum=13884.475 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=990 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.316222222222222,
          "description": "min=2.465, mean=4.316, max=5, sum=64.743 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 423.39457309941525,
          "description": "min=385.228, mean=423.395, max=467.79, sum=6350.919 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5696666666666668,
          "description": "min=0.953, mean=1.57, max=1.978, sum=4.709 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.004,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 402.2846666666667,
          "description": "min=386.826, mean=402.285, max=424.449, sum=1206.854 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8338028169014086,
          "description": "min=0.834, mean=0.834, max=0.834, sum=2.501 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 492.87605633802815,
          "description": "min=492.876, mean=492.876, max=492.876, sum=1478.628 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.556,
          "description": "min=113.556, mean=117.556, max=122.556, sum=352.668 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9183333333333333,
          "description": "min=0.083, mean=0.918, max=1.789, sum=2.755 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3546666666666667,
          "description": "min=0.097, mean=0.355, max=0.852, sum=1.064 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 303.61899999999997,
          "description": "min=231.47, mean=303.619, max=343.479, sum=910.857 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=900 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=2.997 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 510.93799999999993,
          "description": "min=510.938, mean=510.938, max=510.938, sum=1532.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=300 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5126146788990824,
          "description": "min=0, mean=3.513, max=4.838, sum=14.05 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 372.66781345565744,
          "description": "min=89.896, mean=372.668, max=473.333, sum=1490.671 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.060801144492131615,
          "description": "min=0.06, mean=0.061, max=0.062, sum=0.365 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9349070100143061,
          "description": "min=0.933, mean=0.935, max=0.936, sum=5.609 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.8290414878398,
          "description": "min=500.788, mean=500.829, max=500.912, sum=3004.974 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 128.0,
          "description": "min=128, mean=128, max=128, sum=768 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29343629343629346,
          "description": "min=0.234, mean=0.293, max=0.361, sum=1.761 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.676962676962677,
          "description": "min=0.614, mean=0.677, max=0.736, sum=4.062 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 437.96975546975546,
          "description": "min=433.917, mean=437.97, max=442.292, sum=2627.819 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 64.0,
          "description": "min=64, mean=64, max=64, sum=384 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.449,
          "description": "min=0.309, mean=0.449, max=0.689, sum=1.347 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17566666666666664,
          "description": "min=0.175, mean=0.176, max=0.176, sum=0.527 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 407.0976666666666,
          "description": "min=388.254, mean=407.098, max=435.686, sum=1221.293 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.608459470057463,
          "description": "min=1.01, mean=2.608, max=4.878, sum=140.857 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0025500084787325617,
          "description": "min=0, mean=0.003, max=0.032, sum=0.138 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 416.89557696196465,
          "description": "min=335.768, mean=416.896, max=479.235, sum=22512.361 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.433333333333333,
          "description": "min=0, mean=2.433, max=5, sum=80.3 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3939393939393939,
          "description": "min=0, mean=0.394, max=1, sum=13 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 423.53712121212124,
          "description": "min=267.4, mean=423.537, max=511, sum=13976.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=990 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.781220657277,
          "description": "min=27.152, mean=40.781, max=56.166, sum=122.344 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 278.01966666666664,
          "description": "min=272.695, mean=278.02, max=287.118, sum=834.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 194.67133333333334,
          "description": "min=168.53, mean=194.671, max=213.115, sum=584.014 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.83566666666667,
          "description": "min=75.972, mean=77.836, max=79.528, sum=233.507 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 404.62079510703364,
          "description": "min=85.121, mean=404.621, max=529.121, sum=1618.483 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 73.53290414878398,
          "description": "min=72.006, mean=73.533, max=75.564, sum=441.197 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.22908622908623,
          "description": "min=26.037, mean=26.229, max=26.481, sum=157.375 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.932666666666667,
          "description": "min=4.846, mean=4.933, max=4.986, sum=14.798 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1389.4543333333331,
          "description": "min=1152.694, mean=1389.454, max=1744.631, sum=4168.363 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.056818181818182,
          "description": "min=5, mean=9.057, max=18.95, sum=298.875 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 50.90422535211267,
          "description": "min=39.707, mean=50.904, max=65.363, sum=152.713 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 153.23066666666668,
          "description": "min=128.956, mean=153.231, max=173.545, sum=459.692 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 211.80499999999998,
          "description": "min=168.231, mean=211.805, max=244.906, sum=635.415 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 91.90933333333334,
          "description": "min=89.614, mean=91.909, max=95.996, sum=275.728 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2,
          "description": "min=0.2, mean=0.2, max=0.2, sum=0.2 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 404.62079510703364,
          "description": "min=85.121, mean=404.621, max=529.121, sum=1618.483 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.9277539341917,
          "description": "min=72.955, mean=77.928, max=83.685, sum=467.567 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.361647361647357,
          "description": "min=23.931, mean=24.362, max=24.873, sum=146.17 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.932666666666667,
          "description": "min=4.846, mean=4.933, max=4.986, sum=14.798 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1389.4543333333331,
          "description": "min=1152.694, mean=1389.454, max=1744.631, sum=4168.363 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.712121212121207,
          "description": "min=5, mean=18.712, max=30, sum=617.5 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.794,
          "description": "min=99.794, mean=99.794, max=99.794, sum=99.794 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 29.961363636363636,
          "description": "min=29.575, mean=29.961, max=30, sum=329.575 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.882,
          "description": "min=99.882, mean=99.882, max=99.882, sum=99.882 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 29.361363636363638,
          "description": "min=22.975, mean=29.361, max=30, sum=322.975 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.987,
          "description": "min=99.987, mean=99.987, max=99.987, sum=99.987 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.987,
          "description": "min=0.987, mean=0.987, max=0.987, sum=0.987 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.997,
          "description": "min=0.997, mean=0.997, max=0.997, sum=0.997 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9818181818181819,
          "description": "min=0.8, mean=0.982, max=1, sum=10.8 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.296,
          "description": "min=1.296, mean=1.296, max=1.296, sum=1.296 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.414084507042253,
          "description": "min=4.414, mean=4.414, max=4.414, sum=4.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3673.2676056338028,
          "description": "min=3673.268, mean=3673.268, max=3673.268, sum=3673.268 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.998,
          "description": "min=0.998, mean=0.998, max=0.998, sum=0.998 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.831,
          "description": "min=4.831, mean=4.831, max=4.831, sum=4.831 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.026,
          "description": "min=0.026, mean=0.026, max=0.026, sum=0.026 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2289.409,
          "description": "min=2289.409, mean=2289.409, max=2289.409, sum=2289.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.955,
          "description": "min=0.955, mean=0.955, max=0.955, sum=0.955 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.204,
          "description": "min=3.204, mean=3.204, max=3.204, sum=3.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3617.038,
          "description": "min=3617.038, mean=3617.038, max=3617.038, sum=3617.038 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2897.409,
          "description": "min=2897.409, mean=2897.409, max=2897.409, sum=2897.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.779545454545455,
          "description": "min=2.575, mean=4.78, max=5, sum=52.575 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1153.8522727272727,
          "description": "min=303.675, mean=1153.852, max=3623.9, sum=12692.375 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.414084507042253,
          "description": "min=4.414, mean=4.414, max=4.414, sum=4.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3673.2676056338028,
          "description": "min=3673.268, mean=3673.268, max=3673.268, sum=3673.268 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.831,
          "description": "min=4.831, mean=4.831, max=4.831, sum=4.831 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.026,
          "description": "min=0.026, mean=0.026, max=0.026, sum=0.026 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2289.409,
          "description": "min=2289.409, mean=2289.409, max=2289.409, sum=2289.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.984,
          "description": "min=0.984, mean=0.984, max=0.984, sum=0.984 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.204,
          "description": "min=3.204, mean=3.204, max=3.204, sum=3.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3617.038,
          "description": "min=3617.038, mean=3617.038, max=3617.038, sum=3617.038 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2897.409,
          "description": "min=2897.409, mean=2897.409, max=2897.409, sum=2897.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6915388744093813,
          "description": "min=1, mean=2.692, max=5, sum=48.448 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.779545454545455,
          "description": "min=2.575, mean=4.78, max=5, sum=52.575 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1153.8522727272727,
          "description": "min=303.675, mean=1153.852, max=3623.9, sum=12692.375 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.414084507042253,
          "description": "min=4.414, mean=4.414, max=4.414, sum=4.414 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3673.2676056338028,
          "description": "min=3673.268, mean=3673.268, max=3673.268, sum=3673.268 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.831,
          "description": "min=4.831, mean=4.831, max=4.831, sum=4.831 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.026,
          "description": "min=0.026, mean=0.026, max=0.026, sum=0.026 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2289.409,
          "description": "min=2289.409, mean=2289.409, max=2289.409, sum=2289.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.998,
          "description": "min=0.998, mean=0.998, max=0.998, sum=0.998 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.204,
          "description": "min=3.204, mean=3.204, max=3.204, sum=3.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3617.038,
          "description": "min=3617.038, mean=3617.038, max=3617.038, sum=3617.038 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2897.409,
          "description": "min=2897.409, mean=2897.409, max=2897.409, sum=2897.409 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.779545454545455,
          "description": "min=2.575, mean=4.78, max=5, sum=52.575 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1153.8522727272727,
          "description": "min=303.675, mean=1153.852, max=3623.9, sum=12692.375 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.883,
          "description": "min=4.883, mean=4.883, max=4.883, sum=4.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.005633802816902,
          "description": "min=26.006, mean=26.006, max=26.006, sum=26.006 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 84.53,
          "description": "min=84.53, mean=84.53, max=84.53, sum=84.53 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 122.525,
          "description": "min=122.525, mean=122.525, max=122.525, sum=122.525 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.323,
          "description": "min=77.323, mean=77.323, max=77.323, sum=77.323 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.966,
          "description": "min=4.966, mean=4.966, max=4.966, sum=4.966 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.2159316386124255,
          "description": "min=2.746, mean=4.216, max=4.89, sum=75.887 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.468181818181815,
          "description": "min=3.7, mean=19.468, max=30, sum=214.15 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.412,
          "description": "min=4.412, mean=4.412, max=4.412, sum=4.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.28732394366197,
          "description": "min=19.287, mean=19.287, max=19.287, sum=19.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 296.95,
          "description": "min=296.95, mean=296.95, max=296.95, sum=296.95 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 286.175,
          "description": "min=286.175, mean=286.175, max=286.175, sum=286.175 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.25,
          "description": "min=77.25, mean=77.25, max=77.25, sum=77.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.258,
          "description": "min=3.258, mean=3.258, max=3.258, sum=3.258 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.980000522687608,
          "description": "min=4.854, mean=4.98, max=5, sum=89.64 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.4,
          "description": "min=5.8, mean=24.4, max=30, sum=268.4 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 522.5470877192982,
          "description": "min=397.65, mean=522.547, max=684.675, sum=2612.735 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1439.447,
          "description": "min=1439.447, mean=1439.447, max=1439.447, sum=1439.447 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.996,
          "description": "min=4.996, mean=4.996, max=4.996, sum=4.996 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4366197183098592,
          "description": "min=1.437, mean=1.437, max=1.437, sum=1.437 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1541.1154929577465,
          "description": "min=1541.115, mean=1541.115, max=1541.115, sum=1541.115 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 67.57464788732395,
          "description": "min=67.575, mean=67.575, max=67.575, sum=67.575 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 137.383,
          "description": "min=137.383, mean=137.383, max=137.383, sum=137.383 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 299.508,
          "description": "min=299.508, mean=299.508, max=299.508, sum=299.508 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.722,
          "description": "min=3.722, mean=3.722, max=3.722, sum=3.722 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.049,
          "description": "min=0.049, mean=0.049, max=0.049, sum=0.049 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1407.178,
          "description": "min=1407.178, mean=1407.178, max=1407.178, sum=1407.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 266.895,
          "description": "min=266.895, mean=266.895, max=266.895, sum=266.895 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.507,
          "description": "min=0.507, mean=0.507, max=0.507, sum=0.507 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06,
          "description": "min=0.06, mean=0.06, max=0.06, sum=0.06 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1498.657,
          "description": "min=1498.657, mean=1498.657, max=1498.657, sum=1498.657 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 77.743,
          "description": "min=77.743, mean=77.743, max=77.743, sum=77.743 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 524.6024464831804,
          "description": "min=524.602, mean=524.602, max=524.602, sum=524.602 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.781,
          "description": "min=2.781, mean=2.781, max=2.781, sum=2.781 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1751.213,
          "description": "min=1751.213, mean=1751.213, max=1751.213, sum=1751.213 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.32,
          "description": "min=3.32, mean=3.32, max=3.32, sum=3.32 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 855.2410378605821,
          "description": "min=404.732, mean=855.241, max=1417.567, sum=15394.339 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.589879611958418,
          "description": "min=2, mean=2.59, max=4.159, sum=46.618 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.552272727272727,
          "description": "min=0.45, mean=4.552, max=5, sum=50.075 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 954.1113636363635,
          "description": "min=303.675, mean=954.111, max=1882.1, sum=10495.225 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.399999999999999,
          "description": "min=5.3, mean=15.4, max=30, sum=169.4 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1418.259,
          "description": "min=1418.259, mean=1418.259, max=1418.259, sum=1418.259 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.574647887323944,
          "description": "min=4.575, mean=4.575, max=4.575, sum=4.575 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3627.7154929577464,
          "description": "min=3627.715, mean=3627.715, max=3627.715, sum=3627.715 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.832,
          "description": "min=4.832, mean=4.832, max=4.832, sum=4.832 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.026,
          "description": "min=0.026, mean=0.026, max=0.026, sum=0.026 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2268.728,
          "description": "min=2268.728, mean=2268.728, max=2268.728, sum=2268.728 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.987,
          "description": "min=0.987, mean=0.987, max=0.987, sum=0.987 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.44,
          "description": "min=3.44, mean=3.44, max=3.44, sum=3.44 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3680.143,
          "description": "min=3680.143, mean=3680.143, max=3680.143, sum=3680.143 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2811.31,
          "description": "min=2811.31, mean=2811.31, max=2811.31, sum=2811.31 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 831.9036212109548,
          "description": "min=390.28, mean=831.904, max=1394.234, sum=14974.265 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.788636363636363,
          "description": "min=2.675, mean=4.789, max=5, sum=52.675 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 328.5954545454546,
          "description": "min=0, mean=328.595, max=3614.55, sum=3614.55 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6460093896713615,
          "description": "min=1.051, mean=1.646, max=2.085, sum=4.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1651.8478873239437,
          "description": "min=1600.366, mean=1651.848, max=1705.003, sum=4955.544 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.982159624413145,
          "description": "min=5.113, mean=5.982, max=7.265, sum=17.946 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.569,
          "description": "min=3.8, mean=4.569, max=5.632, sum=13.707 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.690666666666666,
          "description": "min=4.647, mean=4.691, max=4.723, sum=14.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.3276666666668,
          "description": "min=1231.056, mean=1419.328, max=1523.222, sum=4257.983 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.015000000000001,
          "description": "min=5.953, mean=6.015, max=6.134, sum=18.045 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9436666666666667,
          "description": "min=0.845, mean=0.944, max=1.084, sum=2.831 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.436,
          "description": "min=1624.371, mean=1644.436, max=1670.589, sum=4933.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 29.95566666666667,
          "description": "min=25.915, mean=29.956, max=32.756, sum=89.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0113333333333334,
          "description": "min=1.004, mean=1.011, max=1.02, sum=3.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0155038759689923,
          "description": "min=1, mean=1.016, max=1.023, sum=3.047 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 66.9041487839771,
          "description": "min=64.44, mean=66.904, max=70.5, sum=401.425 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.501287001287,
          "description": "min=27.172, mean=27.501, max=27.815, sum=165.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.9319999999999995,
          "description": "min=4.845, mean=4.932, max=4.985, sum=14.796 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1389.1833333333332,
          "description": "min=1152.524, mean=1389.183, max=1743.988, sum=4167.55 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.022727272727273,
          "description": "min=0.15, mean=3.023, max=6.625, sum=99.75 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6460093896713615,
          "description": "min=1.051, mean=1.646, max=2.085, sum=4.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1651.8478873239437,
          "description": "min=1600.366, mean=1651.848, max=1705.003, sum=4955.544 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.498591549295774,
          "description": "min=5.189, mean=6.499, max=7.989, sum=19.496 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.6000000000000005,
          "description": "min=5.189, mean=5.6, max=5.896, sum=16.8 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.690666666666666,
          "description": "min=4.647, mean=4.691, max=4.723, sum=14.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.3276666666668,
          "description": "min=1231.056, mean=1419.328, max=1523.222, sum=4257.983 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.369,
          "description": "min=7.244, mean=8.369, max=10.389, sum=25.107 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9436666666666667,
          "description": "min=0.845, mean=0.944, max=1.084, sum=2.831 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.436,
          "description": "min=1624.371, mean=1644.436, max=1670.589, sum=4933.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.574333333333332,
          "description": "min=17.622, mean=19.574, max=21.058, sum=58.723 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0666666666666667,
          "description": "min=1.028, mean=1.067, max=1.136, sum=3.2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0465116279069768,
          "description": "min=1.047, mean=1.047, max=1.047, sum=3.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 83.55579399141631,
          "description": "min=70.732, mean=83.556, max=100.29, sum=501.335 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.578507078507084,
          "description": "min=23.276, mean=23.579, max=24.127, sum=141.471 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.9319999999999995,
          "description": "min=4.845, mean=4.932, max=4.985, sum=14.796 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1389.1833333333332,
          "description": "min=1152.524, mean=1389.183, max=1743.988, sum=4167.55 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7598484848484848,
          "description": "min=0.15, mean=2.76, max=6.175, sum=91.075 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.708920187793427,
          "description": "min=5.338, mean=5.709, max=6.197, sum=17.127 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.360666666666667,
          "description": "min=4.601, mean=5.361, max=6.345, sum=16.082 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 8.992333333333333,
          "description": "min=6.369, mean=8.992, max=12.931, sum=26.977 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 29.572333333333333,
          "description": "min=27.082, mean=29.572, max=34.534, sum=88.717 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=3262 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.285714285714286,
          "description": "min=0, mean=4.286, max=5, sum=30 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1411.8715511955854,
          "description": "min=583.586, mean=1411.872, max=1567.586, sum=9883.101 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 68.76026977314531,
          "description": "min=57.459, mean=68.76, max=126.343, sum=481.322 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3626 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.284611141753999,
          "description": "min=0, mean=4.285, max=5, sum=29.992 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1350.1301709873137,
          "description": "min=388.402, mean=1350.13, max=1538.921, sum=9450.911 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 31.87699944842802,
          "description": "min=25.444, mean=31.877, max=63.193, sum=223.139 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9999957802714455,
          "description": "min=0.998, mean=1.0, max=1.001, sum=54.0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.056060606060606,
          "description": "min=0.3, mean=3.056, max=6.575, sum=100.85 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.606572769953051,
          "description": "min=4.775, mean=6.607, max=8.732, sum=19.82 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 6.3133333333333335,
          "description": "min=5.376, mean=6.313, max=7.104, sum=18.94 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 12.580666666666668,
          "description": "min=9.89, mean=12.581, max=15.337, sum=37.742 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 31.034000000000002,
          "description": "min=29.104, mean=31.034, max=33.548, sum=93.102 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.112,
          "description": "min=1.035, mean=1.112, max=1.183, sum=3.336 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.248062015503876,
          "description": "min=1.093, mean=1.248, max=1.488, sum=3.744 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=3262 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.285714285714286,
          "description": "min=0, mean=4.286, max=5, sum=30 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1411.8715511955854,
          "description": "min=583.586, mean=1411.872, max=1567.586, sum=9883.101 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 74.60637645616187,
          "description": "min=65.127, mean=74.606, max=84.073, sum=522.245 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3626 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.284611141753999,
          "description": "min=0, mean=4.285, max=5, sum=29.992 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1350.1301709873137,
          "description": "min=388.402, mean=1350.13, max=1538.921, sum=9450.911 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 27.75675675675676,
          "description": "min=24.405, mean=27.757, max=46.521, sum=194.297 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.8666666666666667,
          "description": "min=0.025, mean=2.867, max=6.375, sum=94.6 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.83474178403756,
          "description": "min=6.659, mean=8.835, max=11.769, sum=26.504 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 7.257666666666666,
          "description": "min=6.994, mean=7.258, max=7.401, sum=21.773 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 18.539,
          "description": "min=18.158, mean=18.539, max=18.902, sum=55.617 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 22.91633333333333,
          "description": "min=20.236, mean=22.916, max=24.512, sum=68.749 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5373333333333334,
          "description": "min=1.128, mean=1.537, max=2.075, sum=4.612 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.4961240310077522,
          "description": "min=1, mean=1.496, max=2.302, sum=4.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 68.43991416309014,
          "description": "min=28.479, mean=68.44, max=112.258, sum=410.639 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.051480051480052,
          "description": "min=23.645, mean=25.051, max=27.259, sum=150.309 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5106060606060603,
          "description": "min=1, mean=3.511, max=10.6, sum=115.85 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.004,
          "description": "min=1, mean=1.004, max=1.008, sum=3.012 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.381220657276996,
          "description": "min=11.13, mean=12.381, max=14.623, sum=37.144 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.656333333333333,
          "description": "min=4.865, mean=5.656, max=6.378, sum=16.969 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 22.436000000000003,
          "description": "min=20.643, mean=22.436, max=23.53, sum=67.308 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 22.281333333333333,
          "description": "min=19.431, mean=22.281, max=23.851, sum=66.844 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.2186666666666666,
          "description": "min=1.059, mean=1.219, max=1.379, sum=3.656 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1705426356589146,
          "description": "min=1.093, mean=1.171, max=1.209, sum=3.512 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 76.95779685264664,
          "description": "min=59.695, mean=76.958, max=88.815, sum=461.747 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.878378378378375,
          "description": "min=9.643, mean=16.878, max=22.542, sum=101.27 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.125,
          "description": "min=1.275, mean=3.125, max=5.85, sum=103.125 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0433333333333332,
          "description": "min=1.036, mean=1.043, max=1.058, sum=3.13 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.532394366197183,
          "description": "min=4.259, mean=4.532, max=4.955, sum=13.597 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3579.092957746479,
          "description": "min=3479.563, mean=3579.093, max=3633.659, sum=10737.279 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.16431924882629,
          "description": "min=8.231, mean=9.164, max=9.732, sum=27.493 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 7.963666666666666,
          "description": "min=7.074, mean=7.964, max=8.442, sum=23.891 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.883333333333334,
          "description": "min=4.874, mean=4.883, max=4.891, sum=14.65 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1520.977,
          "description": "min=1315.257, mean=1520.977, max=1629.945, sum=4562.931 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 6.9366666666666665,
          "description": "min=6.8, mean=6.937, max=7.011, sum=20.81 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.438333333333333,
          "description": "min=2.978, mean=3.438, max=3.878, sum=10.315 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3249.907333333333,
          "description": "min=2819.048, mean=3249.907, max=3487.39, sum=9749.722 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 27.198666666666668,
          "description": "min=25.946, mean=27.199, max=28.821, sum=81.596 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 64.31473533619457,
          "description": "min=60.524, mean=64.315, max=67.878, sum=385.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.734877734878,
          "description": "min=1456.402, mean=1510.735, max=1539.402, sum=9064.409 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 35.293436293436294,
          "description": "min=34.797, mean=35.293, max=36.073, sum=211.761 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1897.4636666666665,
          "description": "min=1282.797, mean=1897.464, max=2572.797, sum=5692.391 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0001279344975371,
          "description": "min=1, mean=1.0, max=1.007, sum=54.007 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.751515151515152,
          "description": "min=2.025, mean=4.752, max=5, sum=156.8 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1033.4651515151515,
          "description": "min=257.35, mean=1033.465, max=3591.4, sum=34104.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.1371212121212113,
          "description": "min=1, mean=3.137, max=6.7, sum=103.525 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.013,
          "description": "min=1.009, mean=1.013, max=1.018, sum=3.039 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.532394366197183,
          "description": "min=4.259, mean=4.532, max=4.955, sum=13.597 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3579.092957746479,
          "description": "min=3479.563, mean=3579.093, max=3633.659, sum=10737.279 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.378403755868544,
          "description": "min=6.158, mean=7.378, max=8.448, sum=22.135 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.9536666666666664,
          "description": "min=3.783, mean=3.954, max=4.116, sum=11.861 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.883333333333334,
          "description": "min=4.874, mean=4.883, max=4.891, sum=14.65 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.02,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.06 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1520.977,
          "description": "min=1315.257, mean=1520.977, max=1629.945, sum=4562.931 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 6.652333333333334,
          "description": "min=6.586, mean=6.652, max=6.739, sum=19.957 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.438333333333333,
          "description": "min=2.978, mean=3.438, max=3.878, sum=10.315 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3249.907333333333,
          "description": "min=2819.048, mean=3249.907, max=3487.39, sum=9749.722 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 20.98633333333333,
          "description": "min=20.711, mean=20.986, max=21.534, sum=62.959 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.014,
          "description": "min=1.006, mean=1.014, max=1.024, sum=3.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9922480620155039,
          "description": "min=0.977, mean=0.992, max=1, sum=2.977 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=3262 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.285714285714286,
          "description": "min=0, mean=4.286, max=5, sum=30 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1411.8715511955854,
          "description": "min=583.586, mean=1411.872, max=1567.586, sum=9883.101 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 70.37032495401594,
          "description": "min=64.197, mean=70.37, max=85.644, sum=492.592 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3626 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.285714285714286,
          "description": "min=0, mean=4.286, max=5, sum=30 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1350.4015444015445,
          "description": "min=388.402, mean=1350.402, max=1539.402, sum=9452.811 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 28.673745173745175,
          "description": "min=27.776, mean=28.674, max=31.952, sum=200.716 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1897.4636666666665,
          "description": "min=1282.797, mean=1897.464, max=2572.797, sum=5692.391 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9996666666666667,
          "description": "min=0.999, mean=1.0, max=1, sum=2.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9973133394349212,
          "description": "min=0.967, mean=0.997, max=1, sum=53.855 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.751515151515152,
          "description": "min=2.025, mean=4.752, max=5, sum=156.8 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1033.4651515151515,
          "description": "min=257.35, mean=1033.465, max=3591.4, sum=34104.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0568181818181817,
          "description": "min=0.875, mean=3.057, max=6.85, sum=100.875 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.007,
          "description": "min=1.004, mean=1.007, max=1.012, sum=3.021 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.970892018779344,
          "description": "min=6.645, mean=8.971, max=10.738, sum=26.913 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.641,
          "description": "min=4.507, mean=4.641, max=4.737, sum=13.923 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 6.633666666666667,
          "description": "min=5.931, mean=6.634, max=7.52, sum=19.901 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 22.197666666666663,
          "description": "min=20.676, mean=22.198, max=24.409, sum=66.593 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0306666666666666,
          "description": "min=1.005, mean=1.031, max=1.08, sum=3.092 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0775193798449612,
          "description": "min=1, mean=1.078, max=1.209, sum=3.233 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=3262 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.285714285714286,
          "description": "min=0, mean=4.286, max=5, sum=30 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1411.8715511955854,
          "description": "min=583.586, mean=1411.872, max=1567.586, sum=9883.101 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 94.31422440220724,
          "description": "min=86.798, mean=94.314, max=101.208, sum=660.2 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3626 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.284611141753999,
          "description": "min=0, mean=4.285, max=5, sum=29.992 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1350.1301709873137,
          "description": "min=388.402, mean=1350.13, max=1538.921, sum=9450.911 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 32.3450082735797,
          "description": "min=29.917, mean=32.345, max=40.357, sum=226.415 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7142857142857144,
          "description": "min=1, mean=2.714, max=3, sum=19 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9986666666666667,
          "description": "min=0.998, mean=0.999, max=1, sum=2.996 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9791789992573504,
          "description": "min=0.905, mean=0.979, max=1, sum=52.876 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.750757575757576,
          "description": "min=0, mean=2.751, max=5.95, sum=90.775 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.004,
          "description": "min=1, mean=1.004, max=1.008, sum=3.012 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.829107981220657,
          "description": "min=12.048, mean=12.829, max=13.307, sum=38.487 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 2.016,
          "description": "min=1.708, mean=2.016, max=2.304, sum=6.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 7.772333333333333,
          "description": "min=7.676, mean=7.772, max=7.9, sum=23.317 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 22.965666666666667,
          "description": "min=21.715, mean=22.966, max=24.001, sum=68.897 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.2116666666666667,
          "description": "min=1.142, mean=1.212, max=1.282, sum=3.635 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1317829457364341,
          "description": "min=0.977, mean=1.132, max=1.326, sum=3.395 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 116.85765379113019,
          "description": "min=114.333, mean=116.858, max=120.519, sum=701.146 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.16473616473616,
          "description": "min=38.037, mean=40.165, max=41.259, sum=240.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0010000000000001,
          "description": "min=1, mean=1.001, max=1.003, sum=3.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7742424242424244,
          "description": "min=0.85, mean=2.774, max=5.875, sum=91.55 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.003,
          "description": "min=0.995, mean=1.003, max=1.009, sum=3.009 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6469483568075116,
          "description": "min=1.051, mean=1.647, max=2.085, sum=4.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1652.3774647887324,
          "description": "min=1601.955, mean=1652.377, max=1705.003, sum=4957.132 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.755868544600938,
          "description": "min=9.054, mean=10.756, max=13.293, sum=32.268 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0399999999999998,
          "description": "min=0.729, mean=1.04, max=1.418, sum=3.12 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 4.691333333333334,
          "description": "min=4.647, mean=4.691, max=4.724, sum=14.074 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1419.5736666666664,
          "description": "min=1231.212, mean=1419.574, max=1523.257, sum=4258.721 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.933,
          "description": "min=1.801, mean=3.933, max=5.648, sum=11.799 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.9443333333333334,
          "description": "min=0.845, mean=0.944, max=1.086, sum=2.833 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1644.8306666666667,
          "description": "min=1625.523, mean=1644.831, max=1670.605, sum=4934.492 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 17.273666666666667,
          "description": "min=14.536, mean=17.274, max=19.327, sum=51.821 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 87.888,
          "description": "min=87.888, mean=87.888, max=87.888, sum=87.888 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 500.0,
          "description": "min=500, mean=500, max=500, sum=500 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 5.27,
          "description": "min=5.27, mean=5.27, max=5.27, sum=5.27 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 532.5653333333333,
          "description": "min=495.232, mean=532.565, max=577.232, sum=1597.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.123,
          "description": "min=1.014, mean=1.123, max=1.303, sum=3.369 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.0,
          "description": "min=43, mean=43, max=43, sum=129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 515.8217054263565,
          "description": "min=478.488, mean=515.822, max=560.488, sum=1547.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1007751937984496,
          "description": "min=0.953, mean=1.101, max=1.326, sum=3.302 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=9299.515 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 114.93776824034335,
          "description": "min=114.727, mean=114.938, max=115.313, sum=689.627 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=29.992 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=9062.51 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 34.805662805662806,
          "description": "min=33.533, mean=34.806, max=36.037, sum=208.834 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.013,
          "description": "min=1.006, mean=1.013, max=1.021, sum=3.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=54 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.996969696969697,
          "description": "min=0.15, mean=2.997, max=6.925, sum=98.9 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 460.71996491228066,
          "description": "min=366.44, mean=460.72, max=607.43, sum=2303.6 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.012,
          "description": "min=1, mean=1.012, max=1.06, sum=5.06 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1220.329,
          "description": "min=1220.329, mean=1220.329, max=1220.329, sum=1220.329 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.932,
          "description": "min=1.932, mean=1.932, max=1.932, sum=1.932 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.966197183098592,
          "description": "min=4.966, mean=4.966, max=4.966, sum=4.966 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3443.349295774648,
          "description": "min=3443.349, mean=3443.349, max=3443.349, sum=3443.349 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.185915492957747,
          "description": "min=11.186, mean=11.186, max=11.186, sum=11.186 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.127,
          "description": "min=112.127, mean=112.127, max=112.127, sum=112.127 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.241,
          "description": "min=16.241, mean=16.241, max=16.241, sum=16.241 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.887,
          "description": "min=4.887, mean=4.887, max=4.887, sum=4.887 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.019,
          "description": "min=0.019, mean=0.019, max=0.019, sum=0.019 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1590.821,
          "description": "min=1590.821, mean=1590.821, max=1590.821, sum=1590.821 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.998,
          "description": "min=12.998, mean=12.998, max=12.998, sum=12.998 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.871,
          "description": "min=3.871, mean=3.871, max=3.871, sum=3.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3461.981,
          "description": "min=3461.981, mean=3461.981, max=3461.981, sum=3461.981 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.136,
          "description": "min=23.136, mean=23.136, max=23.136, sum=23.136 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 464.434250764526,
          "description": "min=464.434, mean=464.434, max=464.434, sum=464.434 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.047400611620795,
          "description": "min=1.047, mean=1.047, max=1.047, sum=1.047 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2543.665,
          "description": "min=2543.665, mean=2543.665, max=2543.665, sum=2543.665 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.006,
          "description": "min=1.006, mean=1.006, max=1.006, sum=1.006 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 733.3618295565135,
          "description": "min=333.915, mean=733.362, max=1226.723, sum=13200.513 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0225713328901465,
          "description": "min=1, mean=1.023, max=1.103, sum=18.406 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.818181818181818,
          "description": "min=3, mean=4.818, max=5, sum=53 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1002.2386363636365,
          "description": "min=252.275, mean=1002.239, max=3545.1, sum=11024.625 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.9818181818181815,
          "description": "min=1.325, mean=2.982, max=5, sum=32.8 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 460.71996491228066,
          "description": "min=366.44, mean=460.72, max=607.43, sum=2303.6 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.3714035087719298,
          "description": "min=1.19, mean=1.371, max=1.61, sum=6.857 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1220.329,
          "description": "min=1220.329, mean=1220.329, max=1220.329, sum=1220.329 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.057,
          "description": "min=1.057, mean=1.057, max=1.057, sum=1.057 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.966197183098592,
          "description": "min=4.966, mean=4.966, max=4.966, sum=4.966 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3443.349295774648,
          "description": "min=3443.349, mean=3443.349, max=3443.349, sum=3443.349 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.194366197183099,
          "description": "min=12.194, mean=12.194, max=12.194, sum=12.194 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.127,
          "description": "min=112.127, mean=112.127, max=112.127, sum=112.127 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.876,
          "description": "min=18.876, mean=18.876, max=18.876, sum=18.876 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.887,
          "description": "min=4.887, mean=4.887, max=4.887, sum=4.887 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.019,
          "description": "min=0.019, mean=0.019, max=0.019, sum=0.019 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1590.821,
          "description": "min=1590.821, mean=1590.821, max=1590.821, sum=1590.821 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.901,
          "description": "min=11.901, mean=11.901, max=11.901, sum=11.901 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.871,
          "description": "min=3.871, mean=3.871, max=3.871, sum=3.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3461.981,
          "description": "min=3461.981, mean=3461.981, max=3461.981, sum=3461.981 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.691,
          "description": "min=25.691, mean=25.691, max=25.691, sum=25.691 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 464.434250764526,
          "description": "min=464.434, mean=464.434, max=464.434, sum=464.434 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.5168195718654434,
          "description": "min=1.517, mean=1.517, max=1.517, sum=1.517 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2543.665,
          "description": "min=2543.665, mean=2543.665, max=2543.665, sum=2543.665 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 733.3618295565135,
          "description": "min=333.915, mean=733.362, max=1226.723, sum=13200.513 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0013947024944874,
          "description": "min=1, mean=1.001, max=1.01, sum=18.025 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.818181818181818,
          "description": "min=3, mean=4.818, max=5, sum=53 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1002.2386363636365,
          "description": "min=252.275, mean=1002.239, max=3545.1, sum=11024.625 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.9545454545454546,
          "description": "min=1.275, mean=2.955, max=5.05, sum=32.5 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 299.738,
          "description": "min=299.738, mean=299.738, max=299.738, sum=299.738 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 300.0,
          "description": "min=300, mean=300, max=300, sum=300 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 100.0,
          "description": "min=100, mean=100, max=100, sum=100 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.0,
          "description": "min=30, mean=30, max=30, sum=330 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.993,
          "description": "min=0.993, mean=0.993, max=0.993, sum=0.993 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.997,
          "description": "min=0.997, mean=0.997, max=0.997, sum=0.997 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.975,
          "description": "min=0.725, mean=0.975, max=1, sum=10.725 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 467.935649122807,
          "description": "min=358.76, mean=467.936, max=612.798, sum=2339.678 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1251.897,
          "description": "min=1251.897, mean=1251.897, max=1251.897, sum=1251.897 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9690140845070423,
          "description": "min=1.969, mean=1.969, max=1.969, sum=1.969 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1691.081690140845,
          "description": "min=1691.082, mean=1691.082, max=1691.082, sum=1691.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 117.299,
          "description": "min=117.299, mean=117.299, max=117.299, sum=117.299 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704,
          "description": "min=4.704, mean=4.704, max=4.704, sum=4.704 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.037,
          "description": "min=0.037, mean=0.037, max=0.037, sum=0.037 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1495.552,
          "description": "min=1495.552, mean=1495.552, max=1495.552, sum=1495.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.994,
          "description": "min=0.994, mean=0.994, max=0.994, sum=0.994 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.883,
          "description": "min=0.883, mean=0.883, max=0.883, sum=0.883 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.021,
          "description": "min=0.021, mean=0.021, max=0.021, sum=0.021 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1655.708,
          "description": "min=1655.708, mean=1655.708, max=1655.708, sum=1655.708 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.998,
          "description": "min=0.998, mean=0.998, max=0.998, sum=0.998 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 505.35168195718654,
          "description": "min=505.352, mean=505.352, max=505.352, sum=505.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.911,
          "description": "min=2.911, mean=2.911, max=2.911, sum=2.911 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1619.568,
          "description": "min=1619.568, mean=1619.568, max=1619.568, sum=1619.568 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 771.6539847352628,
          "description": "min=360.976, mean=771.654, max=1282.4, sum=13889.772 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6045454545454545,
          "description": "min=0.7, mean=4.605, max=5, sum=50.65 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 869.6909090909089,
          "description": "min=280.35, mean=869.691, max=1756.575, sum=9566.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.12014035087725,
          "description": "min=389.6, mean=500.12, max=664.281, sum=2500.601 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1284.629,
          "description": "min=1284.629, mean=1284.629, max=1284.629, sum=1284.629 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0253521126760563,
          "description": "min=2.025, mean=2.025, max=2.025, sum=2.025 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1694.081690140845,
          "description": "min=1694.082, mean=1694.082, max=1694.082, sum=1694.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 124.246,
          "description": "min=124.246, mean=124.246, max=124.246, sum=124.246 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.599,
          "description": "min=4.599, mean=4.599, max=4.599, sum=4.599 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.039 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1587.334,
          "description": "min=1587.334, mean=1587.334, max=1587.334, sum=1587.334 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.994,
          "description": "min=0.994, mean=0.994, max=0.994, sum=0.994 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.862,
          "description": "min=0.862, mean=0.862, max=0.862, sum=0.862 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031,
          "description": "min=0.031, mean=0.031, max=0.031, sum=0.031 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1667.28,
          "description": "min=1667.28, mean=1667.28, max=1667.28, sum=1667.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.995,
          "description": "min=0.995, mean=0.995, max=0.995, sum=0.995 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 507.50305810397555,
          "description": "min=507.503, mean=507.503, max=507.503, sum=507.503 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.871,
          "description": "min=2.871, mean=2.871, max=2.871, sum=2.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1666.079,
          "description": "min=1666.079, mean=1666.079, max=1666.079, sum=1666.079 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 782.7590374602355,
          "description": "min=367.585, mean=782.759, max=1312.924, sum=14089.663 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6000000000000005,
          "description": "min=0.7, mean=4.6, max=5, sum=50.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 877.4636363636364,
          "description": "min=289.025, mean=877.464, max=1772.5, sum=9652.1 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.975,
          "description": "min=0.725, mean=0.975, max=1, sum=10.725 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.12014035087725,
          "description": "min=389.6, mean=500.12, max=664.281, sum=2500.601 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1284.629,
          "description": "min=1284.629, mean=1284.629, max=1284.629, sum=1284.629 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0253521126760563,
          "description": "min=2.025, mean=2.025, max=2.025, sum=2.025 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1694.081690140845,
          "description": "min=1694.082, mean=1694.082, max=1694.082, sum=1694.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 124.246,
          "description": "min=124.246, mean=124.246, max=124.246, sum=124.246 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.599,
          "description": "min=4.599, mean=4.599, max=4.599, sum=4.599 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.039 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1587.334,
          "description": "min=1587.334, mean=1587.334, max=1587.334, sum=1587.334 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.984,
          "description": "min=0.984, mean=0.984, max=0.984, sum=0.984 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.862,
          "description": "min=0.862, mean=0.862, max=0.862, sum=0.862 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031,
          "description": "min=0.031, mean=0.031, max=0.031, sum=0.031 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1667.28,
          "description": "min=1667.28, mean=1667.28, max=1667.28, sum=1667.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.997,
          "description": "min=0.997, mean=0.997, max=0.997, sum=0.997 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 507.50305810397555,
          "description": "min=507.503, mean=507.503, max=507.503, sum=507.503 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.871,
          "description": "min=2.871, mean=2.871, max=2.871, sum=2.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1666.079,
          "description": "min=1666.079, mean=1666.079, max=1666.079, sum=1666.079 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 782.7590374602355,
          "description": "min=367.585, mean=782.759, max=1312.924, sum=14089.663 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6000000000000005,
          "description": "min=0.7, mean=4.6, max=5, sum=50.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 877.4636363636364,
          "description": "min=289.025, mean=877.464, max=1772.5, sum=9652.1 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9954545454545454,
          "description": "min=0.95, mean=0.995, max=1, sum=10.95 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.12014035087725,
          "description": "min=389.6, mean=500.12, max=664.281, sum=2500.601 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1284.629,
          "description": "min=1284.629, mean=1284.629, max=1284.629, sum=1284.629 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0253521126760563,
          "description": "min=2.025, mean=2.025, max=2.025, sum=2.025 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1694.081690140845,
          "description": "min=1694.082, mean=1694.082, max=1694.082, sum=1694.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 124.246,
          "description": "min=124.246, mean=124.246, max=124.246, sum=124.246 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.599,
          "description": "min=4.599, mean=4.599, max=4.599, sum=4.599 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.039 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1587.334,
          "description": "min=1587.334, mean=1587.334, max=1587.334, sum=1587.334 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.995,
          "description": "min=0.995, mean=0.995, max=0.995, sum=0.995 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.862,
          "description": "min=0.862, mean=0.862, max=0.862, sum=0.862 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031,
          "description": "min=0.031, mean=0.031, max=0.031, sum=0.031 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1667.28,
          "description": "min=1667.28, mean=1667.28, max=1667.28, sum=1667.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 507.50305810397555,
          "description": "min=507.503, mean=507.503, max=507.503, sum=507.503 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.871,
          "description": "min=2.871, mean=2.871, max=2.871, sum=2.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1666.079,
          "description": "min=1666.079, mean=1666.079, max=1666.079, sum=1666.079 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 782.7590374602355,
          "description": "min=367.585, mean=782.759, max=1312.924, sum=14089.663 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6000000000000005,
          "description": "min=0.7, mean=4.6, max=5, sum=50.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 877.4636363636364,
          "description": "min=289.025, mean=877.464, max=1772.5, sum=9652.1 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9727272727272727,
          "description": "min=0.7, mean=0.973, max=1, sum=10.7 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=514 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=25 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 500.12014035087725,
          "description": "min=389.6, mean=500.12, max=664.281, sum=2500.601 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=5 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1284.629,
          "description": "min=1284.629, mean=1284.629, max=1284.629, sum=1284.629 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=355 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0253521126760563,
          "description": "min=2.025, mean=2.025, max=2.025, sum=2.025 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1694.081690140845,
          "description": "min=1694.082, mean=1694.082, max=1694.082, sum=1694.082 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 124.246,
          "description": "min=124.246, mean=124.246, max=124.246, sum=124.246 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.599,
          "description": "min=4.599, mean=4.599, max=4.599, sum=4.599 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.039,
          "description": "min=0.039, mean=0.039, max=0.039, sum=0.039 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1587.334,
          "description": "min=1587.334, mean=1587.334, max=1587.334, sum=1587.334 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.995,
          "description": "min=0.995, mean=0.995, max=0.995, sum=0.995 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.862,
          "description": "min=0.862, mean=0.862, max=0.862, sum=0.862 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031,
          "description": "min=0.031, mean=0.031, max=0.031, sum=0.031 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1667.28,
          "description": "min=1667.28, mean=1667.28, max=1667.28, sum=1667.28 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.999,
          "description": "min=0.999, mean=0.999, max=0.999, sum=0.999 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=654 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 507.50305810397555,
          "description": "min=507.503, mean=507.503, max=507.503, sum=507.503 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=1000 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.871,
          "description": "min=2.871, mean=2.871, max=2.871, sum=2.871 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1666.079,
          "description": "min=1666.079, mean=1666.079, max=1666.079, sum=1666.079 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=1 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=6688 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=90 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 782.7590374602355,
          "description": "min=367.585, mean=782.759, max=1312.924, sum=14089.663 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=18 (18)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=440 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.6000000000000005,
          "description": "min=0.7, mean=4.6, max=5, sum=50.6 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 877.4636363636364,
          "description": "min=289.025, mean=877.464, max=1772.5, sum=9652.1 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.984090909090909,
          "description": "min=0.825, mean=0.984, max=1, sum=10.825 (11)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=11 (11)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 460.63743859649117,
          "description": "min=354.52, mean=460.637, max=611.877, sum=6909.562 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 931.4243333333333,
          "description": "min=679.091, mean=931.424, max=1276.091, sum=2794.273 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6751173708920186,
          "description": "min=1.101, mean=1.675, max=2.11, sum=5.025 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1658.8112676056337,
          "description": "min=1597.372, mean=1658.811, max=1711.876, sum=4976.434 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.938967136150234,
          "description": "min=6.008, mean=9.939, max=17.439, sum=29.817 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 122.99133333333333,
          "description": "min=121.658, mean=122.991, max=125.658, sum=368.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.706666666666667,
          "description": "min=6.22, mean=6.707, max=7.262, sum=20.12 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.630666666666667,
          "description": "min=4.505, mean=4.631, max=4.705, sum=13.892 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04666666666666667,
          "description": "min=0.042, mean=0.047, max=0.056, sum=0.14 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1502.676666666667,
          "description": "min=1340.319, mean=1502.677, max=1625.084, sum=4508.03 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 21.064333333333334,
          "description": "min=19.342, mean=21.064, max=23.914, sum=63.193 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.874,
          "description": "min=0.823, mean=0.874, max=0.929, sum=2.622 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13366666666666668,
          "description": "min=0.094, mean=0.134, max=0.177, sum=0.401 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1651.9716666666666,
          "description": "min=1621.422, mean=1651.972, max=1668.212, sum=4955.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 73.56533333333333,
          "description": "min=65.116, mean=73.565, max=88.524, sum=220.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 389.0359327217125,
          "description": "min=80.786, mean=389.036, max=521.786, sum=1556.144 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1657.1244635193134,
          "description": "min=1644.124, mean=1657.124, max=1680.124, sum=9942.747 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 82.99713876967097,
          "description": "min=74.479, mean=82.997, max=91.644, sum=497.983 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.9961389961389955,
          "description": "min=4.994, mean=4.996, max=4.998, sum=29.977 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1567.3120978120978,
          "description": "min=1516.483, mean=1567.312, max=1610.471, sum=9403.873 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.73680823680824,
          "description": "min=25.458, mean=25.737, max=26.021, sum=154.421 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.923333333333333,
          "description": "min=4.832, mean=4.923, max=4.979, sum=14.77 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1412.2849999999999,
          "description": "min=1182.719, mean=1412.285, max=1755.875, sum=4236.855 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 694.3901297399493,
          "description": "min=342, mean=694.39, max=1246.337, sum=37497.067 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.0,
          "description": "min=2, mean=2, max=2, sum=108 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5628787878787875,
          "description": "min=0, mean=4.563, max=5, sum=150.575 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06969696969696969,
          "description": "min=0, mean=0.07, max=1, sum=2.3 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 803.3181818181819,
          "description": "min=244.45, mean=803.318, max=1757.15, sum=26509.5 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.886363636363637,
          "description": "min=2.6, mean=4.886, max=11.6, sum=161.25 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.6460093896713615,
          "description": "min=1.051, mean=1.646, max=2.085, sum=4.938 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1651.8478873239437,
          "description": "min=1600.366, mean=1651.848, max=1705.003, sum=4955.544 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.347417840375587,
          "description": "min=1.93, mean=5.347, max=7.079, sum=16.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.246666666666667,
          "description": "min=3.935, mean=4.247, max=4.675, sum=12.74 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.690666666666666,
          "description": "min=4.647, mean=4.691, max=4.723, sum=14.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.036,
          "description": "min=0.036, mean=0.036, max=0.036, sum=0.108 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1419.3276666666668,
          "description": "min=1231.056, mean=1419.328, max=1523.222, sum=4257.983 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.656666666666666,
          "description": "min=6.778, mean=7.657, max=8.266, sum=22.97 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9436666666666667,
          "description": "min=0.845, mean=0.944, max=1.084, sum=2.831 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.436,
          "description": "min=1624.371, mean=1644.436, max=1670.589, sum=4933.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.969000000000005,
          "description": "min=18.652, mean=22.969, max=26.445, sum=68.907 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.998980632008155,
          "description": "min=0.998, mean=0.999, max=1, sum=2.997 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=1398 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=4649.758 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 83.96494992846924,
          "description": "min=74.511, mean=83.965, max=95.704, sum=251.895 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=1554 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.998712998712999,
          "description": "min=4.998, mean=4.999, max=5, sum=14.996 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.4182754182755,
          "description": "min=1456.402, mean=1510.418, max=1538.921, sum=4531.255 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.631917631917634,
          "description": "min=26.207, mean=26.632, max=27.241, sum=79.896 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.242,
          "description": "min=2.916, mean=4.242, max=4.986, sum=12.726 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1553.363,
          "description": "min=1277.729, mean=1553.363, max=1768.607, sum=4660.089 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9973333333333333,
          "description": "min=0.995, mean=0.997, max=0.999, sum=2.992 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9053814074087929,
          "description": "min=0, mean=0.905, max=1, sum=48.891 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.556060606060607,
          "description": "min=0, mean=4.556, max=5, sum=150.35 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 812.937878787879,
          "description": "min=257.35, mean=812.938, max=1773.675, sum=26826.95 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.9674242424242423,
          "description": "min=1, mean=2.967, max=6.15, sum=97.925 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 472.2740350877193,
          "description": "min=371.38, mean=472.274, max=624.07, sum=7084.111 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 908.4063333333334,
          "description": "min=660.073, mean=908.406, max=1242.073, sum=2725.219 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.007,
          "description": "min=1.005, mean=1.007, max=1.01, sum=3.021 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3803.910798122066,
          "description": "min=3504.577, mean=3803.911, max=3972.577, sum=11411.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.272300469483568,
          "description": "min=5.375, mean=6.272, max=7.29, sum=18.817 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 112.254,
          "description": "min=110.254, mean=112.254, max=116.254, sum=336.762 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.1903333333333332,
          "description": "min=3.166, mean=3.19, max=3.231, sum=9.571 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5199.788,
          "description": "min=4676.788, mean=5199.788, max=5842.788, sum=15599.364 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.580666666666662,
          "description": "min=25.906, mean=26.581, max=27.052, sum=79.742 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=1962 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 511.12079510703364,
          "description": "min=501.121, mean=511.121, max=529.121, sum=1533.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9490316004077473,
          "description": "min=0.908, mean=0.949, max=0.982, sum=2.847 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=1398 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1549.9191702432045,
          "description": "min=1531.586, mean=1549.919, max=1567.586, sum=4649.758 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.630185979971387,
          "description": "min=0, mean=17.63, max=52.891, sum=52.891 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=1554 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1510.734877734878,
          "description": "min=1456.402, mean=1510.735, max=1539.402, sum=4532.205 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.248391248391247,
          "description": "min=25.077, mean=25.248, max=25.463, sum=75.745 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1897.4636666666665,
          "description": "min=1282.797, mean=1897.464, max=2572.797, sum=5692.391 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9386666666666665,
          "description": "min=1.928, mean=1.939, max=1.95, sum=5.816 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 722.6354931173206,
          "description": "min=356.537, mean=722.635, max=1267.519, sum=39022.317 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.011187107057192404,
          "description": "min=0, mean=0.011, max=0.504, sum=0.604 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=165 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1279.5719696969697,
          "description": "min=257.35, mean=1279.572, max=6599.65, sum=42225.875 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.06969696969697,
          "description": "min=0, mean=3.07, max=6.825, sum=101.3 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": 102.8,
          "description": "min=100, mean=102.8, max=114, sum=1542 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=75 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 453.38266666666664,
          "description": "min=354.96, mean=453.383, max=580.833, sum=6800.74 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=15 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=45 (15)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 899.0056666666666,
          "description": "min=649.339, mean=899.006, max=1233.339, sum=2697.017 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 355.0,
          "description": "min=355, mean=355, max=355, sum=1065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.603755868544601,
          "description": "min=1.028, mean=1.604, max=2.008, sum=4.811 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1644.8779342723003,
          "description": "min=1603.569, mean=1644.878, max=1690.352, sum=4934.634 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 96.01784037558686,
          "description": "min=94.115, mean=96.018, max=98.566, sum=288.054 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 111.53433333333332,
          "description": "min=108.201, mean=111.534, max=117.201, sum=334.603 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 299.51500000000004,
          "description": "min=298.545, mean=299.515, max=300, sum=898.545 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.702333333333333,
          "description": "min=4.669, mean=4.702, max=4.738, sum=14.107 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.038,
          "description": "min=0.038, mean=0.038, max=0.038, sum=0.114 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1409.2403333333332,
          "description": "min=1218.159, mean=1409.24, max=1510.891, sum=4227.721 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 291.57166666666666,
          "description": "min=289.149, mean=291.572, max=293.886, sum=874.715 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.951,
          "description": "min=0.841, mean=0.951, max=1.111, sum=2.853 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016,
          "description": "min=0.016, mean=0.016, max=0.016, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1646.7293333333334,
          "description": "min=1630.348, mean=1646.729, max=1667.958, sum=4940.188 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 99.146,
          "description": "min=99.146, mean=99.146, max=99.146, sum=297.438 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 654.0,
          "description": "min=654, mean=654, max=654, sum=2616 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.75,
          "description": "min=0, mean=3.75, max=5, sum=15 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 405.41360856269114,
          "description": "min=85.664, mean=405.414, max=531.664, sum=1621.654 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=4 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.5,
          "description": "min=1, mean=2.5, max=3, sum=10 (4)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 466.0,
          "description": "min=466, mean=466, max=466, sum=2796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1544.7653791130188,
          "description": "min=1536.099, mean=1544.765, max=1562.099, sum=9268.592 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 102.40701001430614,
          "description": "min=90.71, mean=102.407, max=108.32, sum=614.442 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 518.0,
          "description": "min=518, mean=518, max=518, sum=3108 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=30 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1507.497425997426,
          "description": "min=1452.164, mean=1507.497, max=1536.164, sum=9044.985 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 49.4009009009009,
          "description": "min=46.541, mean=49.401, max=51.544, sum=296.405 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=18 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1000.0,
          "description": "min=1000, mean=1000, max=1000, sum=3000 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.929333333333333,
          "description": "min=4.845, mean=4.929, max=4.982, sum=14.788 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1402.2759999999998,
          "description": "min=1161.789, mean=1402.276, max=1747.837, sum=4206.828 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=15 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 371.55555555555554,
          "description": "min=74, mean=371.556, max=683, sum=20064 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 729.6713289334527,
          "description": "min=365, mean=729.671, max=1285.924, sum=39402.252 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.0,
          "description": "min=5, mean=5, max=5, sum=270 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=162 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 40.0,
          "description": "min=40, mean=40, max=40, sum=1320 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5621212121212125,
          "description": "min=0, mean=4.562, max=5, sum=150.55 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 784.9613636363637,
          "description": "min=255.875, mean=784.961, max=1758.075, sum=25903.725 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 13.615151515151515,
          "description": "min=5, mean=13.615, max=30, sum=449.3 (33)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0,
          "description": "min=3, mean=3, max=3, sum=99 (33)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_general_information.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_general_information.json"
      }
    ],
    "name": "general_information"
  },
  {
    "title": "Bias",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "BoolQ - Stereotypes (race)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - Stereotypes (gender)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - Representation (race)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "BoolQ - Representation (gender)",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - Stereotypes (race)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - Stereotypes (gender)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - Representation (race)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NarrativeQA - Representation (gender)",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Stereotypes (race)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Stereotypes (gender)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Representation (race)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Representation (gender)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Stereotypes (race)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Stereotypes (gender)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Representation (race)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Representation (gender)",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - Stereotypes (race)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - Stereotypes (gender)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - Representation (race)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "QuAC - Representation (gender)",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "QuAC"
        }
      },
      {
        "value": "MS MARCO (regular) - Stereotypes (race)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - Stereotypes (gender)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - Representation (race)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (regular) - Representation (gender)",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Stereotypes (race)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Stereotypes (gender)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Representation (race)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Representation (gender)",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "CNN/DailyMail - Stereotypes (race)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Stereotypes (gender)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Representation (race)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Representation (gender)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - Stereotypes (race)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Stereotypes (gender)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Representation (race)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Representation (gender)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "IMDB - Stereotypes (race)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - Stereotypes (gender)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - Representation (race)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "IMDB - Representation (gender)",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - Stereotypes (race)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - Stereotypes (gender)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - Representation (race)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "CivilComments - Representation (gender)",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - Stereotypes (race)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nStereotypical associations (race, profession): Measures uneven association of racial groups (Asian, Hispanic, White) with target professions. This measurement is based on cooccurence statistics between the racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (race)",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - Stereotypes (gender)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nStereotypical associations (gender, profession): Measures uneven association of gender groups (male, female) with target professions. This measurement is based on cooccurence statistics between the gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)) and the target professions (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Stereotypes (gender)",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - Representation (race)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nDemographic representation (race): Measures uneven representation of racial groups (Asian, Hispanic, White). This measurement is based on disparities in the frequency statistics across racially-associated names (word list from [Garg et al., 2018](https://www.pnas.org/doi/10.1073/pnas.1720347115); race associations based on US Census statistics).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (race)",
          "run_group": "RAFT"
        }
      },
      {
        "value": "RAFT - Representation (gender)",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nDemographic representation (gender): Measures uneven representation of gender groups (male, female). This measurement is based on disparities in the frequency statistics across gender terms (word list from [Bolukbasi et al., 2016](https://papers.nips.cc/paper/2016/hash/a486cd07e4ac3d270571622f4f316ec5-Abstract.html)).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Representation (gender)",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5485082680240319,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4375,
          "description": "min=0.375, mean=0.438, max=0.5, sum=0.875 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21357560568086884,
          "description": "min=0.196, mean=0.214, max=0.225, sum=0.641 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3331804837187507,
          "description": "min=0.255, mean=0.333, max=0.386, sum=1.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17500000000000002,
          "description": "min=0.125, mean=0.175, max=0.2, sum=0.525 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4601449275362319,
          "description": "min=0.38, mean=0.46, max=0.5, sum=1.38 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47760288745821544,
          "description": "min=0.451, mean=0.478, max=0.506, sum=1.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04050846488217801,
          "description": "min=0.011, mean=0.041, max=0.063, sum=0.122 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6038019374416433,
          "description": "min=0.594, mean=0.604, max=0.613, sum=1.811 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4200049682548366,
          "description": "min=0.417, mean=0.42, max=0.425, sum=1.26 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3293434102054505,
          "description": "min=0.287, mean=0.329, max=0.362, sum=0.988 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2415041378322658,
          "description": "min=0.231, mean=0.242, max=0.257, sum=0.725 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6302246589223909,
          "description": "min=0.62, mean=0.63, max=0.647, sum=3.781 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.385603383216647,
          "description": "min=0.382, mean=0.386, max=0.393, sum=2.314 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3250193306482005,
          "description": "min=0.288, mean=0.325, max=0.362, sum=1.95 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13141527227323743,
          "description": "min=0.13, mean=0.131, max=0.132, sum=0.788 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4724007038712921,
          "description": "min=0.46, mean=0.472, max=0.483, sum=2.834 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47956989247311826,
          "description": "min=0.467, mean=0.48, max=0.505, sum=2.877 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18604199883585584,
          "description": "min=0.154, mean=0.186, max=0.216, sum=1.116 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5487461676083087,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20304247377415918,
          "description": "min=0.17, mean=0.203, max=0.223, sum=0.609 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4047619047619048,
          "description": "min=0.214, mean=0.405, max=0.5, sum=1.214 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36169748540882557,
          "description": "min=0.302, mean=0.362, max=0.45, sum=1.085 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21556767868437698,
          "description": "min=0.088, mean=0.216, max=0.371, sum=0.647 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39383347574877653,
          "description": "min=0.327, mean=0.394, max=0.457, sum=1.182 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10941198128319474,
          "description": "min=0.106, mean=0.109, max=0.113, sum=0.328 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6472747525379104,
          "description": "min=0.632, mean=0.647, max=0.667, sum=1.942 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42785601825865643,
          "description": "min=0.407, mean=0.428, max=0.446, sum=1.284 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2998485806834953,
          "description": "min=0.226, mean=0.3, max=0.351, sum=0.9 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24941347459181362,
          "description": "min=0.235, mean=0.249, max=0.271, sum=0.748 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6318145834093977,
          "description": "min=0.602, mean=0.632, max=0.648, sum=3.791 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3914278177516011,
          "description": "min=0.385, mean=0.391, max=0.396, sum=2.349 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3019033965877131,
          "description": "min=0.257, mean=0.302, max=0.354, sum=1.811 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14183552076259287,
          "description": "min=0.135, mean=0.142, max=0.152, sum=0.851 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42449478248089356,
          "description": "min=0.397, mean=0.424, max=0.451, sum=2.547 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4255855855855855,
          "description": "min=0.387, mean=0.426, max=0.467, sum=2.554 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1717873516720604,
          "description": "min=0.151, mean=0.172, max=0.189, sum=1.031 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5580147362700336,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1636261091893518,
          "description": "min=0.15, mean=0.164, max=0.18, sum=0.491 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5214747518446415,
          "description": "min=0.473, mean=0.521, max=0.556, sum=1.564 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.033333333333333326,
          "description": "min=0, mean=0.033, max=0.1, sum=0.1 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3461538461538461,
          "description": "min=0.346, mean=0.346, max=0.346, sum=1.038 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48764942579375564,
          "description": "min=0.45, mean=0.488, max=0.521, sum=1.463 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11339991677070331,
          "description": "min=0.111, mean=0.113, max=0.118, sum=0.34 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5996635891593876,
          "description": "min=0.58, mean=0.6, max=0.639, sum=1.799 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42780085419627883,
          "description": "min=0.415, mean=0.428, max=0.44, sum=1.283 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3397817992618246,
          "description": "min=0.298, mean=0.34, max=0.378, sum=1.019 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24231770708576347,
          "description": "min=0.237, mean=0.242, max=0.25, sum=0.727 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6334968330766649,
          "description": "min=0.608, mean=0.633, max=0.647, sum=3.801 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39959768497778553,
          "description": "min=0.39, mean=0.4, max=0.407, sum=2.398 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3506178570090534,
          "description": "min=0.263, mean=0.351, max=0.399, sum=2.104 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1303299541894603,
          "description": "min=0.115, mean=0.13, max=0.14, sum=0.782 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.44203142536475876,
          "description": "min=0.417, mean=0.442, max=0.485, sum=2.652 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5566296694116243,
          "description": "min=0.439, mean=0.557, max=0.667, sum=3.34 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17086307216738958,
          "description": "min=0.149, mean=0.171, max=0.211, sum=1.025 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5919924787763542,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3,
          "description": "min=0.25, mean=0.3, max=0.4, sum=0.9 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1787801116945903,
          "description": "min=0.156, mean=0.179, max=0.205, sum=0.536 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3923268084547134,
          "description": "min=0.288, mean=0.392, max=0.491, sum=1.177 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17397232083140401,
          "description": "min=0.026, mean=0.174, max=0.318, sum=0.522 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.1, mean=0.167, max=0.3, sum=0.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48822694742885336,
          "description": "min=0.478, mean=0.488, max=0.498, sum=1.465 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38112988257848074,
          "description": "min=0.369, mean=0.381, max=0.394, sum=1.143 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6279609279609281,
          "description": "min=0.583, mean=0.628, max=0.66, sum=1.884 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41081218336807646,
          "description": "min=0.396, mean=0.411, max=0.426, sum=1.232 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3270316371542728,
          "description": "min=0.302, mean=0.327, max=0.359, sum=0.981 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22518777152451866,
          "description": "min=0.198, mean=0.225, max=0.241, sum=0.676 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.615138154027043,
          "description": "min=0.605, mean=0.615, max=0.633, sum=3.691 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4014349780782224,
          "description": "min=0.39, mean=0.401, max=0.416, sum=2.409 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2933799533799534,
          "description": "min=0.278, mean=0.293, max=0.321, sum=1.76 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09929925405618005,
          "description": "min=0.077, mean=0.099, max=0.123, sum=0.596 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.46523352396514167,
          "description": "min=0.45, mean=0.465, max=0.474, sum=2.791 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5222388805597201,
          "description": "min=0.494, mean=0.522, max=0.536, sum=3.133 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21406383130768433,
          "description": "min=0.201, mean=0.214, max=0.224, sum=1.284 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5968189835436076,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4298611111111111,
          "description": "min=0.385, mean=0.43, max=0.5, sum=1.29 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.333, mean=0.5, max=0.667, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18345814920903128,
          "description": "min=0.171, mean=0.183, max=0.192, sum=0.55 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3756261756261756,
          "description": "min=0.352, mean=0.376, max=0.405, sum=1.127 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09502719502719503,
          "description": "min=0.033, mean=0.095, max=0.136, sum=0.285 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41250000000000003,
          "description": "min=0.3, mean=0.413, max=0.5, sum=1.238 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5414311179017061,
          "description": "min=0.514, mean=0.541, max=0.561, sum=1.624 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10706952566601687,
          "description": "min=0.06, mean=0.107, max=0.132, sum=0.321 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6416361416361417,
          "description": "min=0.615, mean=0.642, max=0.667, sum=1.925 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45448951168627727,
          "description": "min=0.425, mean=0.454, max=0.476, sum=1.363 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35949126363389555,
          "description": "min=0.342, mean=0.359, max=0.375, sum=1.078 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23190752816365634,
          "description": "min=0.22, mean=0.232, max=0.241, sum=0.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6082305358040653,
          "description": "min=0.593, mean=0.608, max=0.618, sum=3.649 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4111171483483329,
          "description": "min=0.396, mean=0.411, max=0.434, sum=2.467 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25438070908615346,
          "description": "min=0.177, mean=0.254, max=0.301, sum=1.526 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08290586755395449,
          "description": "min=0.064, mean=0.083, max=0.119, sum=0.497 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4660306771417882,
          "description": "min=0.451, mean=0.466, max=0.478, sum=2.796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39943255885284873,
          "description": "min=0.362, mean=0.399, max=0.429, sum=2.397 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20538608377971754,
          "description": "min=0.189, mean=0.205, max=0.224, sum=1.232 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.561885097395068,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4481481481481482,
          "description": "min=0.4, mean=0.448, max=0.5, sum=1.344 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19550967146595563,
          "description": "min=0.185, mean=0.196, max=0.205, sum=0.587 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5067443890625439,
          "description": "min=0.431, mean=0.507, max=0.569, sum=1.52 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1755244755244755,
          "description": "min=0.1, mean=0.176, max=0.273, sum=0.527 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46507125832968527,
          "description": "min=0.431, mean=0.465, max=0.498, sum=1.395 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02952187967385538,
          "description": "min=0.005, mean=0.03, max=0.053, sum=0.089 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6395502645502645,
          "description": "min=0.625, mean=0.64, max=0.651, sum=1.919 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4224807266199369,
          "description": "min=0.389, mean=0.422, max=0.455, sum=1.267 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22977891012599364,
          "description": "min=0.183, mean=0.23, max=0.263, sum=0.689 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22430144583085757,
          "description": "min=0.223, mean=0.224, max=0.225, sum=0.673 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6361416361416362,
          "description": "min=0.619, mean=0.636, max=0.667, sum=3.817 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4017992121362035,
          "description": "min=0.386, mean=0.402, max=0.424, sum=2.411 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3586894722560466,
          "description": "min=0.338, mean=0.359, max=0.379, sum=2.152 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11681135928174619,
          "description": "min=0.099, mean=0.117, max=0.128, sum=0.701 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4559853927203065,
          "description": "min=0.445, mean=0.456, max=0.463, sum=2.736 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4664089053990878,
          "description": "min=0.362, mean=0.466, max=0.532, sum=2.798 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2066101848280066,
          "description": "min=0.192, mean=0.207, max=0.233, sum=1.24 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4461156665667944,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5313654482080615,
          "description": "min=0.502, mean=0.531, max=0.563, sum=1.594 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07925407925407925,
          "description": "min=0, mean=0.079, max=0.192, sum=0.238 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43333333333333335,
          "description": "min=0.3, mean=0.433, max=0.5, sum=1.3 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5041929581337629,
          "description": "min=0.441, mean=0.504, max=0.574, sum=1.513 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20273109243697482,
          "description": "min=0.186, mean=0.203, max=0.225, sum=0.608 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6474734228728262,
          "description": "min=0.612, mean=0.647, max=0.667, sum=3.885 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.405313769914252,
          "description": "min=0.365, mean=0.405, max=0.442, sum=2.432 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24474724360307878,
          "description": "min=0.175, mean=0.245, max=0.377, sum=1.468 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13266873135824753,
          "description": "min=0.103, mean=0.133, max=0.149, sum=0.796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.46417690732206857,
          "description": "min=0.433, mean=0.464, max=0.492, sum=2.785 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5802469135802469,
          "description": "min=0.407, mean=0.58, max=0.667, sum=3.481 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2200902099970423,
          "description": "min=0.209, mean=0.22, max=0.234, sum=1.321 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5516493320513314,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4375901875901876,
          "description": "min=0.396, mean=0.438, max=0.5, sum=1.313 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555557,
          "description": "min=0.333, mean=0.556, max=0.667, sum=1.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1718450326045263,
          "description": "min=0.152, mean=0.172, max=0.197, sum=0.516 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4166666666666667,
          "description": "min=0.25, mean=0.417, max=0.5, sum=1.25 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43278417840114286,
          "description": "min=0.339, mean=0.433, max=0.5, sum=1.298 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16214742091319934,
          "description": "min=0.081, mean=0.162, max=0.239, sum=0.486 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.432010582010582,
          "description": "min=0.3, mean=0.432, max=0.5, sum=1.296 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45656911106888937,
          "description": "min=0.429, mean=0.457, max=0.498, sum=1.37 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3202891068062547,
          "description": "min=0.272, mean=0.32, max=0.416, sum=0.961 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6581196581196581,
          "description": "min=0.641, mean=0.658, max=0.667, sum=1.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41695983406755,
          "description": "min=0.401, mean=0.417, max=0.432, sum=1.251 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3200297021845843,
          "description": "min=0.258, mean=0.32, max=0.377, sum=0.96 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20338227449992274,
          "description": "min=0.193, mean=0.203, max=0.212, sum=0.61 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.629159058053613,
          "description": "min=0.607, mean=0.629, max=0.667, sum=3.775 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40834546858679427,
          "description": "min=0.388, mean=0.408, max=0.443, sum=2.45 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2874529064836184,
          "description": "min=0.211, mean=0.287, max=0.333, sum=1.725 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16396073067980207,
          "description": "min=0.138, mean=0.164, max=0.192, sum=0.984 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4424845269672855,
          "description": "min=0.429, mean=0.442, max=0.453, sum=2.655 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16492426719539477,
          "description": "min=0.153, mean=0.165, max=0.183, sum=0.99 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.629471974916769,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4159611992945326,
          "description": "min=0.4, mean=0.416, max=0.44, sum=1.248 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555557,
          "description": "min=0.333, mean=0.556, max=0.667, sum=1.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19931611685099856,
          "description": "min=0.186, mean=0.199, max=0.207, sum=0.598 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4597701149425288,
          "description": "min=0.379, mean=0.46, max=0.5, sum=1.379 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43455385345385017,
          "description": "min=0.414, mean=0.435, max=0.447, sum=1.304 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2230769230769231,
          "description": "min=0.15, mean=0.223, max=0.269, sum=0.669 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41111111111111115,
          "description": "min=0.4, mean=0.411, max=0.433, sum=1.233 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44143286168772855,
          "description": "min=0.421, mean=0.441, max=0.477, sum=1.324 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.04515740195666192,
          "description": "min=0.022, mean=0.045, max=0.082, sum=0.135 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6124061124061125,
          "description": "min=0.59, mean=0.612, max=0.636, sum=1.837 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40276421801932005,
          "description": "min=0.382, mean=0.403, max=0.421, sum=1.208 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23980711859954595,
          "description": "min=0.202, mean=0.24, max=0.259, sum=0.719 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20029662396768255,
          "description": "min=0.194, mean=0.2, max=0.205, sum=0.601 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6084787955510622,
          "description": "min=0.58, mean=0.608, max=0.637, sum=3.651 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3911797965697547,
          "description": "min=0.382, mean=0.391, max=0.398, sum=2.347 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27361254875467617,
          "description": "min=0.254, mean=0.274, max=0.288, sum=1.642 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15142644383010628,
          "description": "min=0.128, mean=0.151, max=0.191, sum=0.909 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.450224364113253,
          "description": "min=0.449, mean=0.45, max=0.451, sum=2.701 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5469576096753798,
          "description": "min=0.532, mean=0.547, max=0.565, sum=3.282 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2138886962661304,
          "description": "min=0.212, mean=0.214, max=0.217, sum=1.283 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5709490829944818,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46527777777777773,
          "description": "min=0.396, mean=0.465, max=0.5, sum=1.396 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23804020866547204,
          "description": "min=0.216, mean=0.238, max=0.256, sum=0.714 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.445882557030098,
          "description": "min=0.338, mean=0.446, max=0.5, sum=1.338 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48022397745392514,
          "description": "min=0.467, mean=0.48, max=0.498, sum=1.441 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12466386554621849,
          "description": "min=0.02, mean=0.125, max=0.265, sum=0.374 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444445,
          "description": "min=0.4, mean=0.444, max=0.5, sum=1.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43982889050590296,
          "description": "min=0.401, mean=0.44, max=0.506, sum=1.319 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2201426024955437,
          "description": "min=0.205, mean=0.22, max=0.25, sum=0.66 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5980796023899473,
          "description": "min=0.571, mean=0.598, max=0.615, sum=1.794 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41214192227908586,
          "description": "min=0.408, mean=0.412, max=0.415, sum=1.236 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3046567170277752,
          "description": "min=0.269, mean=0.305, max=0.351, sum=0.914 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23187441800624423,
          "description": "min=0.227, mean=0.232, max=0.235, sum=0.696 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6303974395279242,
          "description": "min=0.621, mean=0.63, max=0.646, sum=3.782 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4010246477666291,
          "description": "min=0.39, mean=0.401, max=0.412, sum=2.406 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2910346586068148,
          "description": "min=0.281, mean=0.291, max=0.297, sum=1.746 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1303630037220396,
          "description": "min=0.114, mean=0.13, max=0.148, sum=0.782 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4390946502057613,
          "description": "min=0.42, mean=0.439, max=0.456, sum=2.635 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5439341780805197,
          "description": "min=0.532, mean=0.544, max=0.556, sum=3.264 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2063342186388344,
          "description": "min=0.201, mean=0.206, max=0.21, sum=1.238 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5930298633071189,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38950617283950617,
          "description": "min=0.333, mean=0.39, max=0.419, sum=1.169 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20792828096614854,
          "description": "min=0.19, mean=0.208, max=0.218, sum=0.624 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38616369646117926,
          "description": "min=0.358, mean=0.386, max=0.439, sum=1.158 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1475748194014448,
          "description": "min=0, mean=0.148, max=0.237, sum=0.443 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4288888888888889,
          "description": "min=0.367, mean=0.429, max=0.5, sum=1.287 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48032222577096423,
          "description": "min=0.459, mean=0.48, max=0.498, sum=1.441 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.043024227234753555,
          "description": "min=0.024, mean=0.043, max=0.079, sum=0.129 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6088490550046614,
          "description": "min=0.604, mean=0.609, max=0.614, sum=1.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4190730790466706,
          "description": "min=0.405, mean=0.419, max=0.441, sum=1.257 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32117266495855845,
          "description": "min=0.283, mean=0.321, max=0.341, sum=0.964 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24753349327018945,
          "description": "min=0.246, mean=0.248, max=0.249, sum=0.743 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6157343144185249,
          "description": "min=0.6, mean=0.616, max=0.642, sum=3.694 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41239374128525014,
          "description": "min=0.4, mean=0.412, max=0.426, sum=2.474 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2523476523476524,
          "description": "min=0.241, mean=0.252, max=0.26, sum=1.514 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09258312556525572,
          "description": "min=0.075, mean=0.093, max=0.102, sum=0.555 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.43949621664675426,
          "description": "min=0.415, mean=0.439, max=0.454, sum=2.637 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.54094360657117,
          "description": "min=0.497, mean=0.541, max=0.59, sum=3.246 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20735056882648284,
          "description": "min=0.189, mean=0.207, max=0.22, sum=1.244 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5459762982621468,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.354945620223398,
          "description": "min=0.333, mean=0.355, max=0.389, sum=1.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16472050143449737,
          "description": "min=0.118, mean=0.165, max=0.241, sum=0.494 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4180133480204756,
          "description": "min=0.303, mean=0.418, max=0.519, sum=1.254 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08994708994708996,
          "description": "min=0.056, mean=0.09, max=0.143, sum=0.27 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42619047619047623,
          "description": "min=0.352, mean=0.426, max=0.5, sum=0.852 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.499333679443982,
          "description": "min=0.454, mean=0.499, max=0.546, sum=1.498 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13470779383719764,
          "description": "min=0.11, mean=0.135, max=0.177, sum=0.404 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6313294548588666,
          "description": "min=0.604, mean=0.631, max=0.647, sum=1.894 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3963840842187811,
          "description": "min=0.388, mean=0.396, max=0.408, sum=1.189 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3645250034421991,
          "description": "min=0.35, mean=0.365, max=0.381, sum=1.094 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2440549375970967,
          "description": "min=0.235, mean=0.244, max=0.26, sum=0.732 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6581699346405229,
          "description": "min=0.641, mean=0.658, max=0.667, sum=3.949 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3851952735514946,
          "description": "min=0.372, mean=0.385, max=0.405, sum=2.311 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31373280163525924,
          "description": "min=0.291, mean=0.314, max=0.352, sum=1.882 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14536660393941517,
          "description": "min=0.119, mean=0.145, max=0.16, sum=0.872 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46699346405228753,
          "description": "min=0.45, mean=0.467, max=0.5, sum=2.802 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3092501368363437,
          "description": "min=0.238, mean=0.309, max=0.356, sum=1.856 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.17201180425265794,
          "description": "min=0.109, mean=0.172, max=0.212, sum=1.032 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6045183982683983,
          "markdown": false
        },
        {
          "description": "(0)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "(0)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "(0)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.25,
          "description": "min=0, mean=0.25, max=0.5, sum=0.5 (2)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3389834657156105,
          "description": "min=0.332, mean=0.339, max=0.343, sum=1.017 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1046501526237907,
          "description": "min=0.093, mean=0.105, max=0.113, sum=0.314 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46155024509803927,
          "description": "min=0.385, mean=0.462, max=0.5, sum=1.385 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6131917464492584,
          "description": "min=0.552, mean=0.613, max=0.657, sum=1.84 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17673498741459906,
          "description": "min=0.028, mean=0.177, max=0.252, sum=0.53 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32890264223378113,
          "description": "min=0.209, mean=0.329, max=0.473, sum=0.987 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.38814814814814813,
          "description": "min=0.289, mean=0.388, max=0.456, sum=1.164 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4620750643944221,
          "description": "min=0.394, mean=0.462, max=0.563, sum=1.386 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09087407629591253,
          "description": "min=0.044, mean=0.091, max=0.176, sum=0.273 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42797040922040913,
          "description": "min=0.428, mean=0.428, max=0.428, sum=1.284 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4358974358974359,
          "description": "min=0.436, mean=0.436, max=0.436, sum=1.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2905073649754501,
          "description": "min=0.291, mean=0.291, max=0.291, sum=0.872 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.5936999598322023,
          "description": "min=0.562, mean=0.594, max=0.631, sum=3.562 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.4028700462262689,
          "description": "min=0.391, mean=0.403, max=0.421, sum=2.417 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.2769263317991031,
          "description": "min=0.27, mean=0.277, max=0.282, sum=1.662 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.09311410441258088,
          "description": "min=0.047, mean=0.093, max=0.138, sum=0.559 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.4438297255067441,
          "description": "min=0.43, mean=0.444, max=0.463, sum=2.663 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.45673778645470176,
          "description": "min=0.286, mean=0.457, max=0.617, sum=2.74 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.2699471127776433,
          "description": "min=0.215, mean=0.27, max=0.328, sum=1.62 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4585978835978836,
          "description": "min=0.3, mean=0.459, max=0.5, sum=5.503 (12)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12500000000000003,
          "description": "min=0.125, mean=0.125, max=0.125, sum=0.375 (3)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5983741692925366,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4541666666666666,
          "description": "min=0.396, mean=0.454, max=0.5, sum=1.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555557,
          "description": "min=0.333, mean=0.556, max=0.667, sum=1.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20801619481196945,
          "description": "min=0.204, mean=0.208, max=0.215, sum=0.624 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4304995528213292,
          "description": "min=0.382, mean=0.43, max=0.498, sum=1.291 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09357753357753357,
          "description": "min=0.024, mean=0.094, max=0.18, sum=0.281 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38769841269841265,
          "description": "min=0.332, mean=0.388, max=0.488, sum=1.163 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40861462430089884,
          "description": "min=0.373, mean=0.409, max=0.446, sum=1.226 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.051062717190300304,
          "description": "min=0.026, mean=0.051, max=0.066, sum=0.153 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5815402704291595,
          "description": "min=0.556, mean=0.582, max=0.6, sum=1.745 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4381760996205441,
          "description": "min=0.43, mean=0.438, max=0.449, sum=1.315 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3443830841027822,
          "description": "min=0.333, mean=0.344, max=0.355, sum=1.033 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23033600244512342,
          "description": "min=0.223, mean=0.23, max=0.237, sum=0.691 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6255738197534654,
          "description": "min=0.616, mean=0.626, max=0.635, sum=3.753 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38662344919565644,
          "description": "min=0.377, mean=0.387, max=0.397, sum=2.32 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30129162776221596,
          "description": "min=0.244, mean=0.301, max=0.358, sum=1.808 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.116591581511673,
          "description": "min=0.104, mean=0.117, max=0.128, sum=0.7 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4633319142897687,
          "description": "min=0.456, mean=0.463, max=0.468, sum=2.78 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6216216216216217,
          "description": "min=0.532, mean=0.622, max=0.667, sum=3.73 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2051781150126976,
          "description": "min=0.184, mean=0.205, max=0.224, sum=1.231 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5413536579003514,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4726495726495727,
          "description": "min=0.418, mean=0.473, max=0.5, sum=1.418 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20233455199447267,
          "description": "min=0.193, mean=0.202, max=0.211, sum=0.607 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.25, mean=0.333, max=0.5, sum=1 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34034751045060324,
          "description": "min=0.244, mean=0.34, max=0.429, sum=1.021 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23326210826210825,
          "description": "min=0.208, mean=0.233, max=0.269, sum=0.7 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38999999999999996,
          "description": "min=0.37, mean=0.39, max=0.4, sum=1.17 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45706182643221777,
          "description": "min=0.447, mean=0.457, max=0.467, sum=1.371 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17447005829358772,
          "description": "min=0.125, mean=0.174, max=0.251, sum=0.523 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4407422751666938,
          "description": "min=0.43, mean=0.441, max=0.46, sum=1.322 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3382593663469334,
          "description": "min=0.306, mean=0.338, max=0.358, sum=1.015 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23804653081585347,
          "description": "min=0.234, mean=0.238, max=0.243, sum=0.714 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6260369618341756,
          "description": "min=0.58, mean=0.626, max=0.659, sum=3.756 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40149048314255253,
          "description": "min=0.371, mean=0.401, max=0.431, sum=2.409 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23843844144516976,
          "description": "min=0.185, mean=0.238, max=0.295, sum=1.431 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1341289455316015,
          "description": "min=0.115, mean=0.134, max=0.153, sum=0.805 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4655148596176822,
          "description": "min=0.456, mean=0.466, max=0.484, sum=2.793 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15743560442588508,
          "description": "min=0.139, mean=0.157, max=0.172, sum=0.945 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4663309072932103,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42718253968253966,
          "description": "min=0.394, mean=0.427, max=0.45, sum=1.282 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5686274509803922,
          "description": "min=0.373, mean=0.569, max=0.667, sum=1.706 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17371956530315583,
          "description": "min=0.152, mean=0.174, max=0.195, sum=0.521 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4410100926954859,
          "description": "min=0.419, mean=0.441, max=0.476, sum=1.323 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2511387163561077,
          "description": "min=0.214, mean=0.251, max=0.3, sum=0.753 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3541666666666667,
          "description": "min=0.292, mean=0.354, max=0.417, sum=0.708 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3247724272114516,
          "description": "min=0.289, mean=0.325, max=0.385, sum=0.974 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.23429326676087917,
          "description": "min=0.202, mean=0.234, max=0.285, sum=0.703 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41249828370040936,
          "description": "min=0.383, mean=0.412, max=0.431, sum=1.237 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35746080227329485,
          "description": "min=0.303, mean=0.357, max=0.392, sum=1.072 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2618392019722732,
          "description": "min=0.233, mean=0.262, max=0.276, sum=0.786 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6592592592592593,
          "description": "min=0.644, mean=0.659, max=0.667, sum=3.956 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44008624507065996,
          "description": "min=0.402, mean=0.44, max=0.476, sum=2.641 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30422478269658376,
          "description": "min=0.285, mean=0.304, max=0.333, sum=1.825 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17278322431241475,
          "description": "min=0.127, mean=0.173, max=0.229, sum=1.037 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.46086088123125163,
          "description": "min=0.447, mean=0.461, max=0.481, sum=2.765 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4982964658021866,
          "description": "min=0.449, mean=0.498, max=0.579, sum=2.99 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18582940251572325,
          "description": "min=0.167, mean=0.186, max=0.198, sum=1.115 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.45155563090416306,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4184126984126984,
          "description": "min=0.411, mean=0.418, max=0.429, sum=1.255 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555556,
          "description": "min=0.333, mean=0.556, max=0.667, sum=1.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20205501924662395,
          "description": "min=0.186, mean=0.202, max=0.217, sum=0.606 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41471861471861476,
          "description": "min=0.238, mean=0.415, max=0.539, sum=1.244 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2341269841269841,
          "description": "min=0.167, mean=0.234, max=0.286, sum=0.702 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48499285130718955,
          "description": "min=0.48, mean=0.485, max=0.494, sum=1.455 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43543086336382425,
          "description": "min=0.382, mean=0.435, max=0.467, sum=1.306 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2653339127915399,
          "description": "min=0.234, mean=0.265, max=0.3, sum=0.796 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45823351891324243,
          "description": "min=0.447, mean=0.458, max=0.468, sum=1.375 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.34075560523096593,
          "description": "min=0.329, mean=0.341, max=0.364, sum=1.022 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2847879707506289,
          "description": "min=0.277, mean=0.285, max=0.299, sum=0.854 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6475615887380594,
          "description": "min=0.625, mean=0.648, max=0.667, sum=3.885 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4203329386778049,
          "description": "min=0.405, mean=0.42, max=0.449, sum=2.522 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14468337947687135,
          "description": "min=0.099, mean=0.145, max=0.201, sum=0.868 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.18171396544569016,
          "description": "min=0.163, mean=0.182, max=0.21, sum=1.09 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.43004930254930257,
          "description": "min=0.399, mean=0.43, max=0.493, sum=2.58 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555556,
          "description": "min=0.542, mean=0.556, max=0.583, sum=3.333 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2457025240044108,
          "description": "min=0.224, mean=0.246, max=0.283, sum=1.474 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.601504827172334,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47222222222222227,
          "description": "min=0.417, mean=0.472, max=0.5, sum=1.417 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19158509798903886,
          "description": "min=0.184, mean=0.192, max=0.197, sum=0.575 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444444,
          "description": "min=0.333, mean=0.444, max=0.5, sum=1.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4804079441760602,
          "description": "min=0.407, mean=0.48, max=0.556, sum=1.441 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24693627450980396,
          "description": "min=0.147, mean=0.247, max=0.385, sum=0.741 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2324074074074074,
          "description": "min=0.186, mean=0.232, max=0.278, sum=0.697 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4744480248239647,
          "description": "min=0.467, mean=0.474, max=0.483, sum=1.423 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11298873219533077,
          "description": "min=0.092, mean=0.113, max=0.135, sum=0.339 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.570980870980871,
          "description": "min=0.543, mean=0.571, max=0.589, sum=1.713 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3948930748680999,
          "description": "min=0.371, mean=0.395, max=0.426, sum=1.185 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3038684617631986,
          "description": "min=0.253, mean=0.304, max=0.331, sum=0.912 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2330910766304025,
          "description": "min=0.211, mean=0.233, max=0.263, sum=0.699 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.606957921303154,
          "description": "min=0.579, mean=0.607, max=0.649, sum=3.642 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3833873353199473,
          "description": "min=0.362, mean=0.383, max=0.409, sum=2.3 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26620678930063096,
          "description": "min=0.223, mean=0.266, max=0.328, sum=1.597 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1326032519141558,
          "description": "min=0.128, mean=0.133, max=0.14, sum=0.796 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.45401696819707577,
          "description": "min=0.447, mean=0.454, max=0.463, sum=2.724 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5371029656743943,
          "description": "min=0.515, mean=0.537, max=0.565, sum=3.223 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2176913745770286,
          "description": "min=0.204, mean=0.218, max=0.236, sum=1.306 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5558769690348637,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44097222222222215,
          "description": "min=0.417, mean=0.441, max=0.469, sum=1.323 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18104985015382555,
          "description": "min=0.15, mean=0.181, max=0.213, sum=0.543 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44969278033794163,
          "description": "min=0.357, mean=0.45, max=0.5, sum=1.349 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4511619362542481,
          "description": "min=0.382, mean=0.451, max=0.504, sum=1.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3140619884317363,
          "description": "min=0.173, mean=0.314, max=0.386, sum=0.942 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30777777777777776,
          "description": "min=0.233, mean=0.308, max=0.35, sum=0.923 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4519283176992704,
          "description": "min=0.421, mean=0.452, max=0.476, sum=1.356 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06120328473269649,
          "description": "min=0.056, mean=0.061, max=0.069, sum=0.184 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6507936507936508,
          "description": "min=0.619, mean=0.651, max=0.667, sum=1.952 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4407764298624513,
          "description": "min=0.436, mean=0.441, max=0.444, sum=1.322 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35330965547213355,
          "description": "min=0.345, mean=0.353, max=0.359, sum=1.06 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2510004319407244,
          "description": "min=0.248, mean=0.251, max=0.255, sum=0.753 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6118203882651768,
          "description": "min=0.604, mean=0.612, max=0.618, sum=3.671 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.408087030039703,
          "description": "min=0.401, mean=0.408, max=0.419, sum=2.449 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2867291116025263,
          "description": "min=0.257, mean=0.287, max=0.318, sum=1.72 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14067727789435583,
          "description": "min=0.117, mean=0.141, max=0.159, sum=0.844 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.43605987410335234,
          "description": "min=0.424, mean=0.436, max=0.453, sum=2.616 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.393188854489164,
          "description": "min=0.373, mean=0.393, max=0.404, sum=2.359 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.194128141174599,
          "description": "min=0.181, mean=0.194, max=0.206, sum=1.165 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.43551719208606965,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48765432098765427,
          "description": "min=0.463, mean=0.488, max=0.5, sum=1.463 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14398558425056623,
          "description": "min=0.126, mean=0.144, max=0.169, sum=0.432 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46474105132386057,
          "description": "min=0.421, mean=0.465, max=0.506, sum=1.394 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18333333333333335,
          "description": "min=0.1, mean=0.183, max=0.3, sum=0.55 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48677896291115386,
          "description": "min=0.473, mean=0.487, max=0.509, sum=1.46 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3560153609831029,
          "description": "min=0.348, mean=0.356, max=0.363, sum=1.068 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47144607843137254,
          "description": "min=0.469, mean=0.471, max=0.475, sum=1.414 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35619490458200137,
          "description": "min=0.312, mean=0.356, max=0.423, sum=1.069 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2476420794142787,
          "description": "min=0.236, mean=0.248, max=0.259, sum=0.743 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6029930306246096,
          "description": "min=0.594, mean=0.603, max=0.609, sum=3.618 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40820094830714143,
          "description": "min=0.384, mean=0.408, max=0.421, sum=2.449 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2588148950314076,
          "description": "min=0.245, mean=0.259, max=0.269, sum=1.553 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1206019792299876,
          "description": "min=0.116, mean=0.121, max=0.127, sum=0.724 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.45422077922077925,
          "description": "min=0.445, mean=0.454, max=0.467, sum=2.725 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5051915503043323,
          "description": "min=0.483, mean=0.505, max=0.524, sum=3.031 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2150586429483566,
          "description": "min=0.198, mean=0.215, max=0.235, sum=1.29 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5758163753811841,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.404320987654321,
          "description": "min=0.361, mean=0.404, max=0.444, sum=1.213 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1778748183802931,
          "description": "min=0.174, mean=0.178, max=0.181, sum=0.534 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5517958743765196,
          "description": "min=0.487, mean=0.552, max=0.634, sum=1.655 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12914332399626519,
          "description": "min=0.063, mean=0.129, max=0.206, sum=0.387 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48194444444444445,
          "description": "min=0.479, mean=0.482, max=0.483, sum=1.446 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5791309646902151,
          "description": "min=0.577, mean=0.579, max=0.582, sum=1.737 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05047080979284368,
          "description": "min=0.025, mean=0.05, max=0.067, sum=0.151 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5961199294532628,
          "description": "min=0.593, mean=0.596, max=0.603, sum=1.788 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4696816360952984,
          "description": "min=0.459, mean=0.47, max=0.484, sum=1.409 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.316297459154602,
          "description": "min=0.299, mean=0.316, max=0.333, sum=0.949 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23168423828159934,
          "description": "min=0.219, mean=0.232, max=0.245, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6121656731068496,
          "description": "min=0.587, mean=0.612, max=0.629, sum=3.673 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39642600089657387,
          "description": "min=0.391, mean=0.396, max=0.407, sum=2.379 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28558037967512334,
          "description": "min=0.238, mean=0.286, max=0.343, sum=1.713 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08955985269326716,
          "description": "min=0.088, mean=0.09, max=0.093, sum=0.537 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4574302134646962,
          "description": "min=0.433, mean=0.457, max=0.476, sum=2.745 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5217473884140551,
          "description": "min=0.481, mean=0.522, max=0.556, sum=3.13 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1810207108427353,
          "description": "min=0.18, mean=0.181, max=0.182, sum=1.086 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4572430192172563,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4510416666666666,
          "description": "min=0.416, mean=0.451, max=0.5, sum=1.353 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21710889248239795,
          "description": "min=0.204, mean=0.217, max=0.229, sum=0.651 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49013920663848926,
          "description": "min=0.373, mean=0.49, max=0.553, sum=1.47 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19214285714285717,
          "description": "min=0.071, mean=0.192, max=0.38, sum=0.576 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5236086934551658,
          "description": "min=0.484, mean=0.524, max=0.561, sum=1.571 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3167977414801371,
          "description": "min=0.289, mean=0.317, max=0.333, sum=0.95 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6126959460292795,
          "description": "min=0.568, mean=0.613, max=0.641, sum=1.838 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4301368170697724,
          "description": "min=0.41, mean=0.43, max=0.447, sum=1.29 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2658629278217009,
          "description": "min=0.232, mean=0.266, max=0.294, sum=0.798 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2300432286449244,
          "description": "min=0.211, mean=0.23, max=0.241, sum=0.69 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6299677400199846,
          "description": "min=0.602, mean=0.63, max=0.655, sum=3.78 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40247728320483095,
          "description": "min=0.398, mean=0.402, max=0.41, sum=2.415 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2931668421996429,
          "description": "min=0.23, mean=0.293, max=0.359, sum=1.759 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14576217898261626,
          "description": "min=0.131, mean=0.146, max=0.169, sum=0.875 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.43535525321239604,
          "description": "min=0.393, mean=0.435, max=0.466, sum=2.612 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5133548156104547,
          "description": "min=0.467, mean=0.513, max=0.565, sum=3.08 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1646512031093765,
          "description": "min=0.141, mean=0.165, max=0.179, sum=0.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.333, mean=0.5, max=0.667, sum=1 (2)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.46836548983528487,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44861111111111107,
          "description": "min=0.396, mean=0.449, max=0.5, sum=1.346 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18579713036394171,
          "description": "min=0.159, mean=0.186, max=0.206, sum=0.557 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3621399176954732,
          "description": "min=0.309, mean=0.362, max=0.444, sum=1.086 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31784137078254726,
          "description": "min=0.233, mean=0.318, max=0.382, sum=0.954 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5695499220251695,
          "description": "min=0.538, mean=0.57, max=0.59, sum=1.709 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09428104575163399,
          "description": "min=0, mean=0.094, max=0.241, sum=0.283 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6257674787086551,
          "description": "min=0.606, mean=0.626, max=0.639, sum=1.877 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4481503328194676,
          "description": "min=0.436, mean=0.448, max=0.455, sum=1.344 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3344046827039365,
          "description": "min=0.319, mean=0.334, max=0.354, sum=1.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26793463346025864,
          "description": "min=0.258, mean=0.268, max=0.282, sum=0.804 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6162431158667614,
          "description": "min=0.612, mean=0.616, max=0.62, sum=3.697 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4099353286102709,
          "description": "min=0.386, mean=0.41, max=0.431, sum=2.46 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.288716873622534,
          "description": "min=0.182, mean=0.289, max=0.35, sum=1.732 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14933277507884896,
          "description": "min=0.127, mean=0.149, max=0.168, sum=0.896 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4490600226000671,
          "description": "min=0.449, mean=0.449, max=0.449, sum=2.694 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5263835263835264,
          "description": "min=0.483, mean=0.526, max=0.565, sum=3.158 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16191706040214252,
          "description": "min=0.132, mean=0.162, max=0.184, sum=0.972 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5099743679983342,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444444,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20434782608695648,
          "description": "min=0.204, mean=0.204, max=0.204, sum=0.204 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31182795698924726,
          "description": "min=0.312, mean=0.312, max=0.312, sum=0.312 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1875,
          "description": "min=0.188, mean=0.188, max=0.188, sum=0.188 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38690476190476186,
          "description": "min=0.387, mean=0.387, max=0.387, sum=0.387 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42222222222222217,
          "description": "min=0.422, mean=0.422, max=0.422, sum=0.422 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1590909090909091,
          "description": "min=0.159, mean=0.159, max=0.159, sum=0.159 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6349206349206349,
          "description": "min=0.635, mean=0.635, max=0.635, sum=0.635 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41639199007620065,
          "description": "min=0.416, mean=0.416, max=0.416, sum=0.416 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3687074829931972,
          "description": "min=0.369, mean=0.369, max=0.369, sum=0.369 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4331466568182155,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2152777777777778,
          "description": "min=0.215, mean=0.215, max=0.215, sum=0.215 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40682414698162733,
          "description": "min=0.407, mean=0.407, max=0.407, sum=0.407 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1216216216216216,
          "description": "min=0.122, mean=0.122, max=0.122, sum=0.122 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4047619047619048,
          "description": "min=0.405, mean=0.405, max=0.405, sum=0.405 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4666666666666667,
          "description": "min=0.467, mean=0.467, max=0.467, sum=0.467 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27551020408163257,
          "description": "min=0.276, mean=0.276, max=0.276, sum=0.276 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6406926406926409,
          "description": "min=0.641, mean=0.641, max=0.641, sum=0.641 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4150793650793651,
          "description": "min=0.415, mean=0.415, max=0.415, sum=0.415 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3137254901960784,
          "description": "min=0.314, mean=0.314, max=0.314, sum=0.314 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25965665236051505,
          "description": "min=0.26, mean=0.26, max=0.26, sum=0.26 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4887674914954327,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.375,
          "description": "min=0.125, mean=0.375, max=0.5, sum=1.125 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4081829027907459,
          "description": "min=0.408, mean=0.408, max=0.408, sum=1.225 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36666666666666664,
          "description": "min=0.367, mean=0.367, max=0.367, sum=1.1 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15620542082738947,
          "description": "min=0.156, mean=0.156, max=0.156, sum=0.469 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5332530194915516,
          "description": "min=0.529, mean=0.533, max=0.535, sum=1.6 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10251322751322754,
          "description": "min=0.071, mean=0.103, max=0.125, sum=0.308 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4166666666666666,
          "description": "min=0.389, mean=0.417, max=0.472, sum=1.25 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5163891020108681,
          "description": "min=0.483, mean=0.516, max=0.552, sum=1.549 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24276995305164317,
          "description": "min=0.218, mean=0.243, max=0.26, sum=0.728 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6495726495726497,
          "description": "min=0.65, mean=0.65, max=0.65, sum=1.949 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4400900674211062,
          "description": "min=0.44, mean=0.44, max=0.44, sum=1.32 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39717891610987377,
          "description": "min=0.397, mean=0.397, max=0.397, sum=1.192 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25702629193109705,
          "description": "min=0.257, mean=0.257, max=0.257, sum=0.771 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.631578947368421,
          "description": "min=0.632, mean=0.632, max=0.632, sum=3.789 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4515726043503821,
          "description": "min=0.452, mean=0.452, max=0.452, sum=2.709 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26356589147286824,
          "description": "min=0.264, mean=0.264, max=0.264, sum=1.581 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11890102842483792,
          "description": "min=0.119, mean=0.119, max=0.12, sum=0.713 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2.667 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=3 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3582634859230604,
          "description": "min=0.333, mean=0.358, max=0.394, sum=2.15 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2219358310118288,
          "description": "min=0.214, mean=0.222, max=0.231, sum=1.332 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5601766236691538,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23015873015873015,
          "description": "min=0.167, mean=0.23, max=0.357, sum=0.69 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3368016513369257,
          "description": "min=0.337, mean=0.337, max=0.337, sum=1.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3419913419913419,
          "description": "min=0.342, mean=0.342, max=0.342, sum=1.026 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15399534522885955,
          "description": "min=0.154, mean=0.154, max=0.154, sum=0.462 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3874074074074074,
          "description": "min=0.333, mean=0.387, max=0.44, sum=1.162 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5194689485314483,
          "description": "min=0.444, mean=0.519, max=0.562, sum=1.558 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1829490113242974,
          "description": "min=0.079, mean=0.183, max=0.239, sum=0.549 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44858553791887124,
          "description": "min=0.41, mean=0.449, max=0.5, sum=1.346 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5381999649472214,
          "description": "min=0.451, mean=0.538, max=0.595, sum=1.615 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11064384639781977,
          "description": "min=0.069, mean=0.111, max=0.136, sum=0.332 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6143486267149368,
          "description": "min=0.614, mean=0.614, max=0.614, sum=1.843 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40228575253954807,
          "description": "min=0.402, mean=0.402, max=0.402, sum=1.207 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3169129720853858,
          "description": "min=0.317, mean=0.317, max=0.317, sum=0.951 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2525635309852876,
          "description": "min=0.253, mean=0.253, max=0.253, sum=0.758 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4018787714810442,
          "description": "min=0.402, mean=0.402, max=0.402, sum=2.411 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3605442176870748,
          "description": "min=0.361, mean=0.361, max=0.361, sum=2.163 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1882129277566539,
          "description": "min=0.188, mean=0.188, max=0.188, sum=1.129 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.45478395061728394,
          "description": "min=0.45, mean=0.455, max=0.463, sum=2.729 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5241150528821762,
          "description": "min=0.489, mean=0.524, max=0.556, sum=3.145 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.251389993488347,
          "description": "min=0.236, mean=0.251, max=0.262, sum=1.508 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07894736842105265,
          "description": "min=0.079, mean=0.079, max=0.079, sum=0.237 (3)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.58013310485115,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49074074074074076,
          "description": "min=0.472, mean=0.491, max=0.5, sum=1.472 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23182834585691858,
          "description": "min=0.213, mean=0.232, max=0.257, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32684426229508196,
          "description": "min=0.279, mean=0.327, max=0.375, sum=0.654 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5211641167340236,
          "description": "min=0.48, mean=0.521, max=0.562, sum=1.563 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0811320308714203,
          "description": "min=0.029, mean=0.081, max=0.119, sum=0.243 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4388888888888889,
          "description": "min=0.433, mean=0.439, max=0.45, sum=1.317 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4612918002748511,
          "description": "min=0.423, mean=0.461, max=0.48, sum=1.384 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.324702218997521,
          "description": "min=0.318, mean=0.325, max=0.332, sum=0.974 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5910808767951625,
          "description": "min=0.561, mean=0.591, max=0.614, sum=1.773 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38627685600159944,
          "description": "min=0.376, mean=0.386, max=0.399, sum=1.159 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2433558772540988,
          "description": "min=0.167, mean=0.243, max=0.304, sum=0.73 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2069846056271054,
          "description": "min=0.195, mean=0.207, max=0.218, sum=0.621 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.5912557147615382,
          "description": "min=0.584, mean=0.591, max=0.602, sum=3.548 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.406575836707982,
          "description": "min=0.389, mean=0.407, max=0.423, sum=2.439 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29422007838910086,
          "description": "min=0.258, mean=0.294, max=0.328, sum=1.765 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1233558384477443,
          "description": "min=0.109, mean=0.123, max=0.15, sum=0.74 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.44948914431673054,
          "description": "min=0.444, mean=0.449, max=0.459, sum=2.697 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45310942412391686,
          "description": "min=0.429, mean=0.453, max=0.481, sum=2.719 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21820243248814677,
          "description": "min=0.188, mean=0.218, max=0.235, sum=1.309 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6312224376358433,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41597222222222224,
          "description": "min=0.406, mean=0.416, max=0.425, sum=1.248 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5555555555555556,
          "description": "min=0.333, mean=0.556, max=0.667, sum=1.667 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1911771437726737,
          "description": "min=0.164, mean=0.191, max=0.207, sum=0.574 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27777777777777773,
          "description": "min=0, mean=0.278, max=0.5, sum=0.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.481339792158324,
          "description": "min=0.467, mean=0.481, max=0.491, sum=1.444 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.156341189674523,
          "description": "min=0.106, mean=0.156, max=0.233, sum=0.469 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33841269841269833,
          "description": "min=0.287, mean=0.338, max=0.395, sum=1.015 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42701178032188486,
          "description": "min=0.4, mean=0.427, max=0.48, sum=1.281 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11888541157186479,
          "description": "min=0.116, mean=0.119, max=0.124, sum=0.357 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5915343915343915,
          "description": "min=0.556, mean=0.592, max=0.619, sum=1.775 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41297615039041286,
          "description": "min=0.398, mean=0.413, max=0.424, sum=1.239 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27205505897640186,
          "description": "min=0.228, mean=0.272, max=0.324, sum=0.816 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2445248639131045,
          "description": "min=0.239, mean=0.245, max=0.252, sum=0.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6094903870639165,
          "description": "min=0.589, mean=0.609, max=0.627, sum=3.657 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40393077624581836,
          "description": "min=0.396, mean=0.404, max=0.412, sum=2.424 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33739205476866063,
          "description": "min=0.287, mean=0.337, max=0.37, sum=2.024 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12773227690338504,
          "description": "min=0.121, mean=0.128, max=0.139, sum=0.766 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.46873713991769544,
          "description": "min=0.453, mean=0.469, max=0.478, sum=2.812 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.46156957217464706,
          "description": "min=0.356, mean=0.462, max=0.532, sum=2.769 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18640980232047377,
          "description": "min=0.168, mean=0.186, max=0.201, sum=1.118 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5501935339738984,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444444,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17785234899328858,
          "description": "min=0.178, mean=0.178, max=0.178, sum=0.178 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3739837398373984,
          "description": "min=0.374, mean=0.374, max=0.374, sum=0.374 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11111111111111116,
          "description": "min=0.111, mean=0.111, max=0.111, sum=0.111 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3,
          "description": "min=0.3, mean=0.3, max=0.3, sum=0.3 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5061728395061729,
          "description": "min=0.506, mean=0.506, max=0.506, sum=0.506 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3604651162790698,
          "description": "min=0.36, mean=0.36, max=0.36, sum=0.36 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5714285714285715,
          "description": "min=0.571, mean=0.571, max=0.571, sum=0.571 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42791413680110835,
          "description": "min=0.428, mean=0.428, max=0.428, sum=0.428 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28395061728395066,
          "description": "min=0.284, mean=0.284, max=0.284, sum=0.284 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2594070695553022,
          "description": "min=0.259, mean=0.259, max=0.259, sum=0.259 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5777177774710669,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4166666666666667,
          "description": "min=0.417, mean=0.417, max=0.417, sum=0.417 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22357723577235772,
          "description": "min=0.224, mean=0.224, max=0.224, sum=0.224 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43775100401606426,
          "description": "min=0.438, mean=0.438, max=0.438, sum=0.438 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08333333333333334,
          "description": "min=0.083, mean=0.083, max=0.083, sum=0.083 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6047619047619048,
          "description": "min=0.605, mean=0.605, max=0.605, sum=0.605 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44425076013311304,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2761904761904762,
          "description": "min=0.276, mean=0.276, max=0.276, sum=0.276 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22388059701492535,
          "description": "min=0.224, mean=0.224, max=0.224, sum=0.224 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5955016826844834,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4,
          "description": "min=0.4, mean=0.4, max=0.4, sum=0.4 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2142857142857143,
          "description": "min=0.214, mean=0.214, max=0.214, sum=0.214 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32753623188405795,
          "description": "min=0.328, mean=0.328, max=0.328, sum=0.328 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33333333333333337,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09999999999999998,
          "description": "min=0.1, mean=0.1, max=0.1, sum=0.1 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3900709219858156,
          "description": "min=0.39, mean=0.39, max=0.39, sum=0.39 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2567567567567568,
          "description": "min=0.257, mean=0.257, max=0.257, sum=0.257 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5714285714285715,
          "description": "min=0.571, mean=0.571, max=0.571, sum=0.571 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43576827288346653,
          "description": "min=0.436, mean=0.436, max=0.436, sum=0.436 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22891566265060237,
          "description": "min=0.229, mean=0.229, max=0.229, sum=0.229 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.22215709261430247,
          "description": "min=0.222, mean=0.222, max=0.222, sum=0.222 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4059399223461723,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1981132075471698,
          "description": "min=0.198, mean=0.198, max=0.198, sum=0.198 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35238095238095235,
          "description": "min=0.352, mean=0.352, max=0.352, sum=0.352 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30000000000000004,
          "description": "min=0.3, mean=0.3, max=0.3, sum=0.3 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4358974358974359,
          "description": "min=0.436, mean=0.436, max=0.436, sum=0.436 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3928571428571429,
          "description": "min=0.393, mean=0.393, max=0.393, sum=0.393 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6210526315789473,
          "description": "min=0.621, mean=0.621, max=0.621, sum=0.621 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3944670750705233,
          "description": "min=0.394, mean=0.394, max=0.394, sum=0.394 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3804713804713804,
          "description": "min=0.38, mean=0.38, max=0.38, sum=0.38 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24335260115606938,
          "description": "min=0.243, mean=0.243, max=0.243, sum=0.243 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4576728062932413,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20348837209302328,
          "description": "min=0.203, mean=0.203, max=0.203, sum=0.203 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38095238095238093,
          "description": "min=0.381, mean=0.381, max=0.381, sum=0.381 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18181818181818182,
          "description": "min=0.182, mean=0.182, max=0.182, sum=0.182 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5770114942528735,
          "description": "min=0.577, mean=0.577, max=0.577, sum=0.577 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48630136986301375,
          "description": "min=0.486, mean=0.486, max=0.486, sum=0.486 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5833333333333334,
          "description": "min=0.583, mean=0.583, max=0.583, sum=0.583 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4264652792029702,
          "description": "min=0.426, mean=0.426, max=0.426, sum=0.426 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2831541218637993,
          "description": "min=0.283, mean=0.283, max=0.283, sum=0.283 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23093681917211328,
          "description": "min=0.231, mean=0.231, max=0.231, sum=0.231 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.46948265409803874,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4166666666666667,
          "description": "min=0.417, mean=0.417, max=0.417, sum=0.417 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21830985915492954,
          "description": "min=0.218, mean=0.218, max=0.218, sum=0.218 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5205992509363295,
          "description": "min=0.521, mean=0.521, max=0.521, sum=0.521 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15000000000000002,
          "description": "min=0.15, mean=0.15, max=0.15, sum=0.15 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4666666666666667,
          "description": "min=0.467, mean=0.467, max=0.467, sum=0.467 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3571428571428571,
          "description": "min=0.357, mean=0.357, max=0.357, sum=0.357 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5485347985347986,
          "description": "min=0.549, mean=0.549, max=0.549, sum=0.549 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.39214643381310055,
          "description": "min=0.392, mean=0.392, max=0.392, sum=0.392 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3248945147679325,
          "description": "min=0.325, mean=0.325, max=0.325, sum=0.325 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24197860962566847,
          "description": "min=0.242, mean=0.242, max=0.242, sum=0.242 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5375895851224799,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18695652173913044,
          "description": "min=0.187, mean=0.187, max=0.187, sum=0.187 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5238095238095237,
          "description": "min=0.524, mean=0.524, max=0.524, sum=0.524 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3125,
          "description": "min=0.312, mean=0.312, max=0.312, sum=0.312 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5655430711610487,
          "description": "min=0.566, mean=0.566, max=0.566, sum=0.566 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1842105263157895,
          "description": "min=0.184, mean=0.184, max=0.184, sum=0.184 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6111111111111112,
          "description": "min=0.611, mean=0.611, max=0.611, sum=0.611 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4025455927051672,
          "description": "min=0.403, mean=0.403, max=0.403, sum=0.403 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27183271832718325,
          "description": "min=0.272, mean=0.272, max=0.272, sum=0.272 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23913043478260873,
          "description": "min=0.239, mean=0.239, max=0.239, sum=0.239 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4865162612605669,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41025641025641024,
          "description": "min=0.41, mean=0.41, max=0.41, sum=0.41 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19627507163323785,
          "description": "min=0.196, mean=0.196, max=0.196, sum=0.196 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45588235294117646,
          "description": "min=0.456, mean=0.456, max=0.456, sum=0.456 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4117647058823529,
          "description": "min=0.412, mean=0.412, max=0.412, sum=0.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.053571428571428575,
          "description": "min=0.054, mean=0.054, max=0.054, sum=0.054 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4185185185185185,
          "description": "min=0.419, mean=0.419, max=0.419, sum=0.419 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4540682414698163,
          "description": "min=0.454, mean=0.454, max=0.454, sum=0.454 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31481481481481477,
          "description": "min=0.315, mean=0.315, max=0.315, sum=0.315 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6363636363636365,
          "description": "min=0.636, mean=0.636, max=0.636, sum=0.636 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4349771051252814,
          "description": "min=0.435, mean=0.435, max=0.435, sum=0.435 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23589743589743586,
          "description": "min=0.236, mean=0.236, max=0.236, sum=0.236 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2813953488372093,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5093893164757827,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3794642857142857,
          "description": "min=0.379, mean=0.379, max=0.379, sum=0.379 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.37254901960784315,
          "description": "min=0.373, mean=0.373, max=0.373, sum=0.373 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18604651162790695,
          "description": "min=0.186, mean=0.186, max=0.186, sum=0.186 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5497835497835497,
          "description": "min=0.55, mean=0.55, max=0.55, sum=0.55 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32352941176470584,
          "description": "min=0.324, mean=0.324, max=0.324, sum=0.324 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5205992509363295,
          "description": "min=0.521, mean=0.521, max=0.521, sum=0.521 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45833333333333326,
          "description": "min=0.458, mean=0.458, max=0.458, sum=0.458 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6333333333333334,
          "description": "min=0.633, mean=0.633, max=0.633, sum=0.633 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41569852337396196,
          "description": "min=0.416, mean=0.416, max=0.416, sum=0.416 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27653213751868466,
          "description": "min=0.277, mean=0.277, max=0.277, sum=0.277 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2550295857988165,
          "description": "min=0.255, mean=0.255, max=0.255, sum=0.255 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5333173629091996,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41666666666666663,
          "description": "min=0.417, mean=0.417, max=0.417, sum=0.417 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1806282722513089,
          "description": "min=0.181, mean=0.181, max=0.181, sum=0.181 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.363914373088685,
          "description": "min=0.364, mean=0.364, max=0.364, sum=0.364 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13157894736842105,
          "description": "min=0.132, mean=0.132, max=0.132, sum=0.132 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4838709677419355,
          "description": "min=0.484, mean=0.484, max=0.484, sum=0.484 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29310344827586204,
          "description": "min=0.293, mean=0.293, max=0.293, sum=0.293 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6296296296296295,
          "description": "min=0.63, mean=0.63, max=0.63, sum=0.63 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4083074125172457,
          "description": "min=0.408, mean=0.408, max=0.408, sum=0.408 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28888888888888886,
          "description": "min=0.289, mean=0.289, max=0.289, sum=0.289 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2418952618453865,
          "description": "min=0.242, mean=0.242, max=0.242, sum=0.242 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5247457047269077,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1730769230769231,
          "description": "min=0.173, mean=0.173, max=0.173, sum=0.173 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25,
          "description": "min=0.25, mean=0.25, max=0.25, sum=0.25 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28746177370030584,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.06521739130434784,
          "description": "min=0.065, mean=0.065, max=0.065, sum=0.065 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4385964912280702,
          "description": "min=0.439, mean=0.439, max=0.439, sum=0.439 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48000000000000004,
          "description": "min=0.48, mean=0.48, max=0.48, sum=0.48 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6213450292397661,
          "description": "min=0.621, mean=0.621, max=0.621, sum=0.621 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4119047619047619,
          "description": "min=0.412, mean=0.412, max=0.412, sum=0.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27356321839080466,
          "description": "min=0.274, mean=0.274, max=0.274, sum=0.274 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2479564032697547,
          "description": "min=0.248, mean=0.248, max=0.248, sum=0.248 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5308990441173578,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3952991452991453,
          "description": "min=0.375, mean=0.395, max=0.436, sum=1.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22112892189926373,
          "description": "min=0.204, mean=0.221, max=0.239, sum=0.663 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.342063492063492,
          "description": "min=0.25, mean=0.342, max=0.443, sum=1.026 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5587121212121212,
          "description": "min=0.53, mean=0.559, max=0.573, sum=1.676 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2891147156537034,
          "description": "min=0.206, mean=0.289, max=0.419, sum=0.867 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27656250000000004,
          "description": "min=0.191, mean=0.277, max=0.345, sum=0.83 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4693006584979578,
          "description": "min=0.457, mean=0.469, max=0.484, sum=1.408 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2587447378492154,
          "description": "min=0.254, mean=0.259, max=0.261, sum=0.776 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5794166151309009,
          "description": "min=0.56, mean=0.579, max=0.599, sum=1.738 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43504680341335694,
          "description": "min=0.428, mean=0.435, max=0.448, sum=1.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33315102716024375,
          "description": "min=0.282, mean=0.333, max=0.369, sum=0.999 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2499075403684782,
          "description": "min=0.24, mean=0.25, max=0.259, sum=0.75 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6288257738993034,
          "description": "min=0.601, mean=0.629, max=0.647, sum=3.773 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3980717194410541,
          "description": "min=0.377, mean=0.398, max=0.411, sum=2.388 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22651255675216078,
          "description": "min=0.135, mean=0.227, max=0.309, sum=1.359 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12013592572007394,
          "description": "min=0.114, mean=0.12, max=0.124, sum=0.721 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4493607590885817,
          "description": "min=0.443, mean=0.449, max=0.459, sum=2.696 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4857302118171683,
          "description": "min=0.362, mean=0.486, max=0.567, sum=2.914 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2037662889603199,
          "description": "min=0.195, mean=0.204, max=0.217, sum=1.223 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.43656162406269206,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47625,
          "description": "min=0.46, mean=0.476, max=0.5, sum=1.429 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21227319042207152,
          "description": "min=0.203, mean=0.212, max=0.221, sum=0.637 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4981481481481482,
          "description": "min=0.494, mean=0.498, max=0.5, sum=1.494 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47890062007709067,
          "description": "min=0.32, mean=0.479, max=0.588, sum=1.437 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2737208807573663,
          "description": "min=0.179, mean=0.274, max=0.437, sum=0.821 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.167, mean=0.333, max=0.417, sum=1.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4460824634464231,
          "description": "min=0.399, mean=0.446, max=0.489, sum=1.338 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22804989848201077,
          "description": "min=0.115, mean=0.228, max=0.345, sum=0.684 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6181852538995397,
          "description": "min=0.598, mean=0.618, max=0.639, sum=1.855 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47198334521620583,
          "description": "min=0.451, mean=0.472, max=0.486, sum=1.416 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35120217651448443,
          "description": "min=0.32, mean=0.351, max=0.412, sum=1.054 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23164076323994623,
          "description": "min=0.213, mean=0.232, max=0.259, sum=0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6163696620441931,
          "description": "min=0.605, mean=0.616, max=0.623, sum=3.698 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4036032258152607,
          "description": "min=0.387, mean=0.404, max=0.42, sum=2.422 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32584352768289004,
          "description": "min=0.306, mean=0.326, max=0.352, sum=1.955 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1463963556163381,
          "description": "min=0.125, mean=0.146, max=0.173, sum=0.878 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.46245791245791246,
          "description": "min=0.451, mean=0.462, max=0.473, sum=2.775 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4888826343934703,
          "description": "min=0.373, mean=0.489, max=0.579, sum=2.933 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18150391082886233,
          "description": "min=0.136, mean=0.182, max=0.23, sum=1.089 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.44460142486244675,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44285714285714284,
          "description": "min=0.4, mean=0.443, max=0.5, sum=1.329 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2075773756101625,
          "description": "min=0.199, mean=0.208, max=0.221, sum=0.623 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4472502805836139,
          "description": "min=0.342, mean=0.447, max=0.5, sum=1.342 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.382401229992038,
          "description": "min=0.286, mean=0.382, max=0.439, sum=1.147 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24726062467997953,
          "description": "min=0.032, mean=0.247, max=0.4, sum=0.742 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3654871847728991,
          "description": "min=0.293, mean=0.365, max=0.412, sum=1.096 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4346811201445348,
          "description": "min=0.422, mean=0.435, max=0.447, sum=1.304 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24420285420364105,
          "description": "min=0.222, mean=0.244, max=0.271, sum=0.733 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6495628554452085,
          "description": "min=0.636, mean=0.65, max=0.667, sum=1.949 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4451588893133011,
          "description": "min=0.435, mean=0.445, max=0.455, sum=1.335 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.366690749431994,
          "description": "min=0.354, mean=0.367, max=0.375, sum=1.1 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25124249915688174,
          "description": "min=0.244, mean=0.251, max=0.256, sum=0.754 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.618631744195654,
          "description": "min=0.579, mean=0.619, max=0.641, sum=4.33 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4005751850408633,
          "description": "min=0.373, mean=0.401, max=0.418, sum=2.804 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3007554818500092,
          "description": "min=0.235, mean=0.301, max=0.378, sum=2.105 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12511140031093898,
          "description": "min=0.111, mean=0.125, max=0.16, sum=0.876 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.667 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44436594684493835,
          "description": "min=0.427, mean=0.444, max=0.469, sum=3.111 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5639808220453382,
          "description": "min=0.473, mean=0.564, max=0.667, sum=3.948 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.21723674492179154,
          "description": "min=0.189, mean=0.217, max=0.251, sum=1.521 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.36598228279277495,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45462962962962966,
          "description": "min=0.431, mean=0.455, max=0.5, sum=1.364 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2292955082742317,
          "description": "min=0.209, mean=0.229, max=0.267, sum=0.688 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4150858887700994,
          "description": "min=0.291, mean=0.415, max=0.509, sum=1.245 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.20272601794340928,
          "description": "min=0.119, mean=0.203, max=0.25, sum=0.608 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.469047619047619,
          "description": "min=0.407, mean=0.469, max=0.5, sum=1.407 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4528357579590976,
          "description": "min=0.441, mean=0.453, max=0.467, sum=1.359 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3786428074398272,
          "description": "min=0.361, mean=0.379, max=0.397, sum=1.136 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6454545454545455,
          "description": "min=0.633, mean=0.645, max=0.667, sum=1.936 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4390862600512319,
          "description": "min=0.426, mean=0.439, max=0.452, sum=1.317 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24599483204134365,
          "description": "min=0.2, mean=0.246, max=0.271, sum=0.738 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23109052551695608,
          "description": "min=0.226, mean=0.231, max=0.234, sum=0.693 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6416796928441896,
          "description": "min=0.619, mean=0.642, max=0.667, sum=4.492 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40861926379951435,
          "description": "min=0.383, mean=0.409, max=0.43, sum=2.86 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29545894187058713,
          "description": "min=0.238, mean=0.295, max=0.417, sum=2.068 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.12851266312443646,
          "description": "min=0.109, mean=0.129, max=0.144, sum=0.9 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=3.333 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44897893078382667,
          "description": "min=0.409, mean=0.449, max=0.488, sum=3.143 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5994124922696351,
          "description": "min=0.446, mean=0.599, max=0.667, sum=4.196 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20496360887910145,
          "description": "min=0.169, mean=0.205, max=0.268, sum=1.435 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.47969140134405086,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44511511879932936,
          "description": "min=0.404, mean=0.445, max=0.5, sum=1.335 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1912053369170701,
          "description": "min=0.142, mean=0.191, max=0.246, sum=0.574 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6236303630363037,
          "description": "min=0.578, mean=0.624, max=0.667, sum=1.871 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.015466015466015476,
          "description": "min=0, mean=0.015, max=0.038, sum=0.046 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.47855712855712856,
          "description": "min=0.445, mean=0.479, max=0.5, sum=1.436 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.44113329919781535,
          "description": "min=0.422, mean=0.441, max=0.46, sum=1.323 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.34872771165606054,
          "description": "min=0.257, mean=0.349, max=0.419, sum=1.046 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6587301587301589,
          "description": "min=0.643, mean=0.659, max=0.667, sum=1.976 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4452529926214137,
          "description": "min=0.434, mean=0.445, max=0.452, sum=1.336 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.33878845629358273,
          "description": "min=0.311, mean=0.339, max=0.382, sum=1.016 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25817229310554,
          "description": "min=0.251, mean=0.258, max=0.264, sum=0.775 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.5683358120009704,
          "description": "min=0.5, mean=0.568, max=0.611, sum=3.41 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4181282755076701,
          "description": "min=0.403, mean=0.418, max=0.435, sum=2.509 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32700197854837026,
          "description": "min=0.321, mean=0.327, max=0.333, sum=1.962 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14643429372740835,
          "description": "min=0.131, mean=0.146, max=0.165, sum=0.879 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.42004149135109864,
          "description": "min=0.389, mean=0.42, max=0.46, sum=2.52 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4583333333333333,
          "description": "min=0.417, mean=0.458, max=0.542, sum=2.75 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14837887499687488,
          "description": "min=0.105, mean=0.148, max=0.182, sum=0.89 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (2)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4272126112641924,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44422611988401467,
          "description": "min=0.415, mean=0.444, max=0.464, sum=1.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13244266197852694,
          "description": "min=0.074, mean=0.132, max=0.198, sum=0.397 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2838533114395183,
          "description": "min=0.067, mean=0.284, max=0.429, sum=0.852 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2809020267563887,
          "description": "min=0.167, mean=0.281, max=0.404, sum=0.843 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4955194805194805,
          "description": "min=0.487, mean=0.496, max=0.5, sum=1.487 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.46622237638437936,
          "description": "min=0.401, mean=0.466, max=0.574, sum=1.399 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.33253136409012896,
          "description": "min=0.308, mean=0.333, max=0.361, sum=0.998 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4515937058073862,
          "description": "min=0.437, mean=0.452, max=0.465, sum=1.355 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3407089337701805,
          "description": "min=0.269, mean=0.341, max=0.377, sum=1.022 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2091296383711505,
          "description": "min=0.195, mean=0.209, max=0.237, sum=0.627 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6280987623495909,
          "description": "min=0.598, mean=0.628, max=0.667, sum=3.769 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4025937932369326,
          "description": "min=0.361, mean=0.403, max=0.447, sum=2.416 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2969968830498775,
          "description": "min=0.275, mean=0.297, max=0.329, sum=1.782 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13397007527013516,
          "description": "min=0.109, mean=0.134, max=0.15, sum=0.804 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4122685185185186,
          "description": "min=0.383, mean=0.412, max=0.438, sum=2.474 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5583333333333335,
          "description": "min=0.467, mean=0.558, max=0.667, sum=3.35 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22244262246907046,
          "description": "min=0.158, mean=0.222, max=0.264, sum=1.335 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4087317179294733,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44232989232989234,
          "description": "min=0.424, mean=0.442, max=0.464, sum=1.327 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17722658310007708,
          "description": "min=0.169, mean=0.177, max=0.187, sum=0.532 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4841269841269842,
          "description": "min=0.452, mean=0.484, max=0.5, sum=1.452 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.34749417249417247,
          "description": "min=0.292, mean=0.347, max=0.43, sum=1.042 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27037037037037037,
          "description": "min=0.167, mean=0.27, max=0.367, sum=0.811 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4428170082518513,
          "description": "min=0.429, mean=0.443, max=0.454, sum=1.328 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.407051282051282,
          "description": "min=0.375, mean=0.407, max=0.423, sum=1.221 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5816498316498318,
          "description": "min=0.556, mean=0.582, max=0.606, sum=1.745 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4283515137656795,
          "description": "min=0.427, mean=0.428, max=0.43, sum=1.285 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.368660072841299,
          "description": "min=0.321, mean=0.369, max=0.395, sum=1.106 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2573013036656095,
          "description": "min=0.244, mean=0.257, max=0.27, sum=0.772 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6464418252138059,
          "description": "min=0.643, mean=0.646, max=0.652, sum=3.879 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41359496216384023,
          "description": "min=0.404, mean=0.414, max=0.427, sum=2.482 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2735791651454302,
          "description": "min=0.245, mean=0.274, max=0.29, sum=1.641 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08299026507382476,
          "description": "min=0.074, mean=0.083, max=0.099, sum=0.498 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44896203413444785,
          "description": "min=0.413, mean=0.449, max=0.482, sum=2.694 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.533635827356637,
          "description": "min=0.518, mean=0.534, max=0.545, sum=3.202 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23788037651548422,
          "description": "min=0.234, mean=0.238, max=0.242, sum=1.427 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.502171676177358,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39479717813051146,
          "description": "min=0.363, mean=0.395, max=0.417, sum=1.184 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18948121770702417,
          "description": "min=0.17, mean=0.189, max=0.21, sum=0.568 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.44795321637426905,
          "description": "min=0.439, mean=0.448, max=0.467, sum=1.344 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.1294903926482874,
          "description": "min=0.079, mean=0.129, max=0.167, sum=0.388 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.40666666666666673,
          "description": "min=0.4, mean=0.407, max=0.42, sum=1.22 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.48653132655730696,
          "description": "min=0.474, mean=0.487, max=0.505, sum=1.46 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.40059748427672953,
          "description": "min=0.375, mean=0.401, max=0.44, sum=1.202 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5793650793650794,
          "description": "min=0.567, mean=0.579, max=0.6, sum=1.738 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4526990667248227,
          "description": "min=0.443, mean=0.453, max=0.461, sum=1.358 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2701590708612791,
          "description": "min=0.256, mean=0.27, max=0.28, sum=0.81 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2545671124587146,
          "description": "min=0.245, mean=0.255, max=0.265, sum=0.764 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6249837439576494,
          "description": "min=0.603, mean=0.625, max=0.667, sum=4.375 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4080224162158765,
          "description": "min=0.388, mean=0.408, max=0.42, sum=2.856 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.293047968208597,
          "description": "min=0.238, mean=0.293, max=0.347, sum=2.051 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1073937839039085,
          "description": "min=0.07, mean=0.107, max=0.138, sum=0.752 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.667 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45745150585486727,
          "description": "min=0.441, mean=0.457, max=0.48, sum=3.202 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.48149813295367977,
          "description": "min=0.376, mean=0.481, max=0.556, sum=3.37 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2388259605365298,
          "description": "min=0.19, mean=0.239, max=0.257, sum=1.672 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.49509040746991073,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44628176056747487,
          "description": "min=0.436, mean=0.446, max=0.453, sum=1.339 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6091954022988506,
          "description": "min=0.494, mean=0.609, max=0.667, sum=1.828 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1896444305777106,
          "description": "min=0.161, mean=0.19, max=0.207, sum=0.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5657407407407408,
          "description": "min=0.542, mean=0.566, max=0.6, sum=1.697 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.23840048840048841,
          "description": "min=0.119, mean=0.238, max=0.346, sum=0.715 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.43333333333333335,
          "description": "min=0.3, mean=0.433, max=0.5, sum=1.3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.44097026888062185,
          "description": "min=0.405, mean=0.441, max=0.467, sum=1.323 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.15754640839386602,
          "description": "min=0.144, mean=0.158, max=0.179, sum=0.473 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6308641975308643,
          "description": "min=0.593, mean=0.631, max=0.667, sum=1.893 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4556780038650607,
          "description": "min=0.438, mean=0.456, max=0.473, sum=1.367 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.27410775768984724,
          "description": "min=0.244, mean=0.274, max=0.294, sum=0.822 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24189395211611728,
          "description": "min=0.231, mean=0.242, max=0.26, sum=0.726 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.609875949224765,
          "description": "min=0.566, mean=0.61, max=0.637, sum=4.269 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38654992671117155,
          "description": "min=0.366, mean=0.387, max=0.406, sum=2.706 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.30088570849440416,
          "description": "min=0.282, mean=0.301, max=0.322, sum=2.106 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11810804679822585,
          "description": "min=0.1, mean=0.118, max=0.133, sum=0.827 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.667 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4418823146165695,
          "description": "min=0.419, mean=0.442, max=0.466, sum=3.093 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5395129666982432,
          "description": "min=0.473, mean=0.54, max=0.584, sum=3.777 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1937219794503278,
          "description": "min=0.172, mean=0.194, max=0.228, sum=1.356 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5333126239886427,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40286362942612947,
          "description": "min=0.382, mean=0.403, max=0.433, sum=1.209 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13153743304740043,
          "description": "min=0.089, mean=0.132, max=0.178, sum=0.395 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3167919799498747,
          "description": "min=0.238, mean=0.317, max=0.467, sum=0.95 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.14484126984126985,
          "description": "min=0.125, mean=0.145, max=0.167, sum=0.435 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.3331168831168831,
          "description": "min=0.286, mean=0.333, max=0.364, sum=0.999 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4025813878698122,
          "description": "min=0.35, mean=0.403, max=0.457, sum=1.208 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.2427837942788109,
          "description": "min=0.221, mean=0.243, max=0.273, sum=0.728 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6171143671143672,
          "description": "min=0.593, mean=0.617, max=0.643, sum=1.851 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.43511418044370825,
          "description": "min=0.425, mean=0.435, max=0.449, sum=1.305 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.36134886795921545,
          "description": "min=0.342, mean=0.361, max=0.388, sum=1.084 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.25974518866516266,
          "description": "min=0.255, mean=0.26, max=0.268, sum=0.779 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6261965622126104,
          "description": "min=0.623, mean=0.626, max=0.63, sum=3.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3853218330657557,
          "description": "min=0.369, mean=0.385, max=0.401, sum=2.312 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38877532854423413,
          "description": "min=0.366, mean=0.389, max=0.408, sum=2.333 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14657801266351475,
          "description": "min=0.142, mean=0.147, max=0.152, sum=0.879 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.44339662209590786,
          "description": "min=0.42, mean=0.443, max=0.467, sum=2.66 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5206745206745207,
          "description": "min=0.436, mean=0.521, max=0.667, sum=3.124 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20364463830300386,
          "description": "min=0.178, mean=0.204, max=0.222, sum=1.222 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4261942744755245,
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40317130936696155,
          "description": "min=0.382, mean=0.403, max=0.438, sum=1.21 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20287726757892108,
          "description": "min=0.151, mean=0.203, max=0.252, sum=0.609 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "(0)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1 (2)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6333333333333334,
          "description": "min=0.567, mean=0.633, max=0.667, sum=1.9 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.21717171717171715,
          "description": "min=0.1, mean=0.217, max=0.318, sum=0.652 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.6527777777777778,
          "description": "min=0.625, mean=0.653, max=0.667, sum=1.958 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.4333686045042254,
          "description": "min=0.415, mean=0.433, max=0.448, sum=1.3 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.34482454482454483,
          "description": "min=0.308, mean=0.345, max=0.387, sum=1.034 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.24387920564334062,
          "description": "min=0.223, mean=0.244, max=0.269, sum=0.732 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.6033209686988849,
          "description": "min=0.585, mean=0.603, max=0.618, sum=3.62 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.376337569695528,
          "description": "min=0.366, mean=0.376, max=0.394, sum=2.258 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3273411562788524,
          "description": "min=0.32, mean=0.327, max=0.336, sum=1.964 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13502681064518518,
          "description": "min=0.118, mean=0.135, max=0.151, sum=0.81 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4030736615819075,
          "description": "min=0.387, mean=0.403, max=0.414, sum=2.418 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5965455454885051,
          "description": "min=0.547, mean=0.597, max=0.623, sum=3.579 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19037429957632912,
          "description": "min=0.087, mean=0.19, max=0.25, sum=1.142 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5128923320135726,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4789473684210526,
          "description": "min=0.479, mean=0.479, max=0.479, sum=0.479 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33333333333333337,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.21590909090909088,
          "description": "min=0.216, mean=0.216, max=0.216, sum=0.216 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.35333333333333333,
          "description": "min=0.353, mean=0.353, max=0.353, sum=0.353 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3643410852713178,
          "description": "min=0.364, mean=0.364, max=0.364, sum=0.364 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16666666666666669,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4083885209713024,
          "description": "min=0.408, mean=0.408, max=0.408, sum=0.408 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23584905660377362,
          "description": "min=0.236, mean=0.236, max=0.236, sum=0.236 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.638888888888889,
          "description": "min=0.639, mean=0.639, max=0.639, sum=0.639 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40322916666666675,
          "description": "min=0.403, mean=0.403, max=0.403, sum=0.403 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43589743589743585,
          "description": "min=0.436, mean=0.436, max=0.436, sum=0.436 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22941176470588232,
          "description": "min=0.229, mean=0.229, max=0.229, sum=0.229 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5232317557148765,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45454545454545453,
          "description": "min=0.455, mean=0.455, max=0.455, sum=0.455 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42857142857142855,
          "description": "min=0.429, mean=0.429, max=0.429, sum=0.429 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16860465116279072,
          "description": "min=0.169, mean=0.169, max=0.169, sum=0.169 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38211382113821135,
          "description": "min=0.382, mean=0.382, max=0.382, sum=0.382 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.10377358490566038,
          "description": "min=0.104, mean=0.104, max=0.104, sum=0.104 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41463414634146334,
          "description": "min=0.415, mean=0.415, max=0.415, sum=0.415 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23333333333333336,
          "description": "min=0.233, mean=0.233, max=0.233, sum=0.233 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5889724310776943,
          "description": "min=0.589, mean=0.589, max=0.589, sum=0.589 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4030096483037659,
          "description": "min=0.403, mean=0.403, max=0.403, sum=0.403 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3782051282051282,
          "description": "min=0.378, mean=0.378, max=0.378, sum=0.378 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22334293948126804,
          "description": "min=0.223, mean=0.223, max=0.223, sum=0.223 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4599624127215427,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4629629629629629,
          "description": "min=0.463, mean=0.463, max=0.463, sum=0.463 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16666666666666666,
          "description": "min=0.167, mean=0.167, max=0.167, sum=0.167 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4597701149425287,
          "description": "min=0.46, mean=0.46, max=0.46, sum=0.46 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18181818181818182,
          "description": "min=0.182, mean=0.182, max=0.182, sum=0.182 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4642857142857143,
          "description": "min=0.464, mean=0.464, max=0.464, sum=0.464 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45299145299145294,
          "description": "min=0.453, mean=0.453, max=0.453, sum=0.453 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24223602484472045,
          "description": "min=0.242, mean=0.242, max=0.242, sum=0.242 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.575,
          "description": "min=0.575, mean=0.575, max=0.575, sum=0.575 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38936550778656037,
          "description": "min=0.389, mean=0.389, max=0.389, sum=0.389 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3003300330033003,
          "description": "min=0.3, mean=0.3, max=0.3, sum=0.3 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.268640350877193,
          "description": "min=0.269, mean=0.269, max=0.269, sum=0.269 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.18974591969523494,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18354430379746836,
          "description": "min=0.184, mean=0.184, max=0.184, sum=0.184 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4666666666666666,
          "description": "min=0.467, mean=0.467, max=0.467, sum=0.467 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2777777777777778,
          "description": "min=0.278, mean=0.278, max=0.278, sum=0.278 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5660749506903353,
          "description": "min=0.566, mean=0.566, max=0.566, sum=0.566 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32352941176470584,
          "description": "min=0.324, mean=0.324, max=0.324, sum=0.324 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4393162393162393,
          "description": "min=0.439, mean=0.439, max=0.439, sum=0.439 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33993399339933994,
          "description": "min=0.34, mean=0.34, max=0.34, sum=0.34 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28532608695652173,
          "description": "min=0.285, mean=0.285, max=0.285, sum=0.285 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.41358382155085455,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4375,
          "description": "min=0.438, mean=0.438, max=0.438, sum=0.438 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17123287671232879,
          "description": "min=0.171, mean=0.171, max=0.171, sum=0.171 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.49783549783549785,
          "description": "min=0.498, mean=0.498, max=0.498, sum=0.498 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2894736842105263,
          "description": "min=0.289, mean=0.289, max=0.289, sum=0.289 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4081597222222222,
          "description": "min=0.408, mean=0.408, max=0.408, sum=0.408 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4124293785310734,
          "description": "min=0.412, mean=0.412, max=0.412, sum=0.412 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25630252100840334,
          "description": "min=0.256, mean=0.256, max=0.256, sum=0.256 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38163008049881736,
          "description": "min=0.382, mean=0.382, max=0.382, sum=0.382 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.3802816901408451,
          "description": "min=0.38, mean=0.38, max=0.38, sum=0.38 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24864864864864863,
          "description": "min=0.249, mean=0.249, max=0.249, sum=0.249 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.33794748465968927,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19318181818181815,
          "description": "min=0.193, mean=0.193, max=0.193, sum=0.193 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4061624649859944,
          "description": "min=0.406, mean=0.406, max=0.406, sum=0.406 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5238095238095237,
          "description": "min=0.524, mean=0.524, max=0.524, sum=0.524 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28125,
          "description": "min=0.281, mean=0.281, max=0.281, sum=0.281 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6296296296296297,
          "description": "min=0.63, mean=0.63, max=0.63, sum=0.63 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4446840232318048,
          "description": "min=0.445, mean=0.445, max=0.445, sum=0.445 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33333333333333337,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24226804123711343,
          "description": "min=0.242, mean=0.242, max=0.242, sum=0.242 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2946998974900761,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2377049180327869,
          "description": "min=0.238, mean=0.238, max=0.238, sum=0.238 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08823529411764708,
          "description": "min=0.088, mean=0.088, max=0.088, sum=0.088 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5268817204301075,
          "description": "min=0.527, mean=0.527, max=0.527, sum=0.527 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17999999999999997,
          "description": "min=0.18, mean=0.18, max=0.18, sum=0.18 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4133540372670807,
          "description": "min=0.413, mean=0.413, max=0.413, sum=0.413 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4433656957928802,
          "description": "min=0.443, mean=0.443, max=0.443, sum=0.443 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27914110429447847,
          "description": "min=0.279, mean=0.279, max=0.279, sum=0.279 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3616994955593857,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.22357723577235772,
          "description": "min=0.224, mean=0.224, max=0.224, sum=0.224 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5416666666666667,
          "description": "min=0.542, mean=0.542, max=0.542, sum=0.542 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.09090909090909088,
          "description": "min=0.091, mean=0.091, max=0.091, sum=0.091 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4931129476584022,
          "description": "min=0.493, mean=0.493, max=0.493, sum=0.493 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2857142857142857,
          "description": "min=0.286, mean=0.286, max=0.286, sum=0.286 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42553763440860215,
          "description": "min=0.426, mean=0.426, max=0.426, sum=0.426 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4074074074074074,
          "description": "min=0.407, mean=0.407, max=0.407, sum=0.407 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23239436619718312,
          "description": "min=0.232, mean=0.232, max=0.232, sum=0.232 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.35594420480554084,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444444,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2046979865771812,
          "description": "min=0.205, mean=0.205, max=0.205, sum=0.205 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38888888888888884,
          "description": "min=0.389, mean=0.389, max=0.389, sum=0.389 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.47619047619047616,
          "description": "min=0.476, mean=0.476, max=0.476, sum=0.476 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.14,
          "description": "min=0.14, mean=0.14, max=0.14, sum=0.14 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3333333333333333,
          "description": "min=0.333, mean=0.333, max=0.333, sum=0.333 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5528942115768464,
          "description": "min=0.553, mean=0.553, max=0.553, sum=0.553 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2745098039215687,
          "description": "min=0.275, mean=0.275, max=0.275, sum=0.275 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45680272108843534,
          "description": "min=0.457, mean=0.457, max=0.457, sum=0.457 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4022988505747127,
          "description": "min=0.402, mean=0.402, max=0.402, sum=0.402 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24695863746958635,
          "description": "min=0.247, mean=0.247, max=0.247, sum=0.247 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.514714004225644,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444444,
          "description": "min=0.444, mean=0.444, max=0.444, sum=0.444 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1870229007633588,
          "description": "min=0.187, mean=0.187, max=0.187, sum=0.187 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2716049382716049,
          "description": "min=0.272, mean=0.272, max=0.272, sum=0.272 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07142857142857142,
          "description": "min=0.071, mean=0.071, max=0.071, sum=0.071 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4257907542579076,
          "description": "min=0.426, mean=0.426, max=0.426, sum=0.426 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0684931506849315,
          "description": "min=0.068, mean=0.068, max=0.068, sum=0.068 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.625,
          "description": "min=0.625, mean=0.625, max=0.625, sum=0.625 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4561372269705603,
          "description": "min=0.456, mean=0.456, max=0.456, sum=0.456 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26241134751773054,
          "description": "min=0.262, mean=0.262, max=0.262, sum=0.262 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.25052854122621565,
          "description": "min=0.251, mean=0.251, max=0.251, sum=0.251 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.48586479674272687,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39814814814814814,
          "description": "min=0.398, mean=0.398, max=0.398, sum=0.398 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19148936170212763,
          "description": "min=0.191, mean=0.191, max=0.191, sum=0.191 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2556237218813906,
          "description": "min=0.256, mean=0.256, max=0.256, sum=0.256 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.10714285714285715,
          "description": "min=0.107, mean=0.107, max=0.107, sum=0.107 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4428571428571429,
          "description": "min=0.443, mean=0.443, max=0.443, sum=0.443 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38245614035087716,
          "description": "min=0.382, mean=0.382, max=0.382, sum=0.382 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13157894736842105,
          "description": "min=0.132, mean=0.132, max=0.132, sum=0.132 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4681547619047619,
          "description": "min=0.468, mean=0.468, max=0.468, sum=0.468 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42342342342342343,
          "description": "min=0.423, mean=0.423, max=0.423, sum=0.423 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.141304347826087,
          "description": "min=0.141, mean=0.141, max=0.141, sum=0.141 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4307003912490803,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33194444444444443,
          "description": "min=0.332, mean=0.332, max=0.332, sum=0.332 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4666666666666667,
          "description": "min=0.467, mean=0.467, max=0.467, sum=0.467 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17464114832535887,
          "description": "min=0.175, mean=0.175, max=0.175, sum=0.175 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.41463414634146334,
          "description": "min=0.415, mean=0.415, max=0.415, sum=0.415 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15517241379310343,
          "description": "min=0.155, mean=0.155, max=0.155, sum=0.155 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42000000000000004,
          "description": "min=0.42, mean=0.42, max=0.42, sum=0.42 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5516224188790559,
          "description": "min=0.552, mean=0.552, max=0.552, sum=0.552 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19491525423728814,
          "description": "min=0.195, mean=0.195, max=0.195, sum=0.195 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4182641806722689,
          "description": "min=0.418, mean=0.418, max=0.418, sum=0.418 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4756554307116105,
          "description": "min=0.476, mean=0.476, max=0.476, sum=0.476 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2142857142857143,
          "description": "min=0.214, mean=0.214, max=0.214, sum=0.214 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.45074793034678545,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3717948717948718,
          "description": "min=0.365, mean=0.372, max=0.375, sum=1.115 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1896318370894642,
          "description": "min=0.168, mean=0.19, max=0.215, sum=0.569 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2689924681892553,
          "description": "min=0.121, mean=0.269, max=0.393, sum=0.807 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05911680911680913,
          "description": "min=0.038, mean=0.059, max=0.083, sum=0.177 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.584615044473471,
          "description": "min=0.571, mean=0.585, max=0.598, sum=1.754 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.07328275644065117,
          "description": "min=0.068, mean=0.073, max=0.079, sum=0.22 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6201234839116704,
          "description": "min=0.604, mean=0.62, max=0.642, sum=1.86 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43137624831417937,
          "description": "min=0.411, mean=0.431, max=0.451, sum=1.294 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40815960651383004,
          "description": "min=0.372, mean=0.408, max=0.45, sum=1.224 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2675064821442643,
          "description": "min=0.259, mean=0.268, max=0.282, sum=0.803 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.61056496482126,
          "description": "min=0.601, mean=0.611, max=0.623, sum=3.663 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3944955327838351,
          "description": "min=0.377, mean=0.394, max=0.409, sum=2.367 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2901527051306585,
          "description": "min=0.276, mean=0.29, max=0.305, sum=1.741 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13850777854837878,
          "description": "min=0.134, mean=0.139, max=0.147, sum=0.831 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4.0 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4473352072310406,
          "description": "min=0.399, mean=0.447, max=0.477, sum=2.684 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5447683118463776,
          "description": "min=0.519, mean=0.545, max=0.579, sum=3.269 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2071945417372382,
          "description": "min=0.202, mean=0.207, max=0.211, sum=1.243 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.47136458620459815,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.44516594516594515,
          "description": "min=0.381, mean=0.445, max=0.5, sum=1.335 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4444444444444445,
          "description": "min=0.333, mean=0.444, max=0.667, sum=1.333 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1960646593836042,
          "description": "min=0.164, mean=0.196, max=0.241, sum=0.588 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=0.667 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=1.5 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5252747252747252,
          "description": "min=0.498, mean=0.525, max=0.55, sum=1.576 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.13375350140056022,
          "description": "min=0.088, mean=0.134, max=0.206, sum=0.401 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39206349206349206,
          "description": "min=0.3, mean=0.392, max=0.443, sum=1.176 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4899991188650981,
          "description": "min=0.45, mean=0.49, max=0.533, sum=1.47 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3838592033738646,
          "description": "min=0.327, mean=0.384, max=0.422, sum=1.152 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5815018315018315,
          "description": "min=0.571, mean=0.582, max=0.59, sum=1.745 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43052581120508293,
          "description": "min=0.413, mean=0.431, max=0.463, sum=1.292 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.33749135321526574,
          "description": "min=0.317, mean=0.337, max=0.368, sum=1.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2355073330063574,
          "description": "min=0.224, mean=0.236, max=0.243, sum=0.707 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.638095238095238,
          "description": "min=0.619, mean=0.638, max=0.651, sum=1.914 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3705770935558364,
          "description": "min=0.344, mean=0.371, max=0.398, sum=1.112 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.2575629817009127,
          "description": "min=0.199, mean=0.258, max=0.288, sum=0.773 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11691353772442492,
          "description": "min=0.108, mean=0.117, max=0.129, sum=0.351 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.45852730200556285,
          "description": "min=0.436, mean=0.459, max=0.489, sum=1.376 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5901750807411186,
          "description": "min=0.532, mean=0.59, max=0.667, sum=1.771 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18720575071822934,
          "description": "min=0.17, mean=0.187, max=0.207, sum=0.562 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5458006056443556,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666667,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39814814814814814,
          "description": "min=0.396, mean=0.398, max=0.403, sum=1.194 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.15935305534542177,
          "description": "min=0.149, mean=0.159, max=0.181, sum=0.478 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.31352905160694455,
          "description": "min=0.245, mean=0.314, max=0.378, sum=0.941 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.26566951566951563,
          "description": "min=0.25, mean=0.266, max=0.278, sum=0.797 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6419753086419754,
          "description": "min=0.63, mean=0.642, max=0.667, sum=1.926 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39526937310090554,
          "description": "min=0.364, mean=0.395, max=0.447, sum=1.186 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.29267512260888473,
          "description": "min=0.286, mean=0.293, max=0.298, sum=0.878 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.23492413534960777,
          "description": "min=0.221, mean=0.235, max=0.248, sum=0.705 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6219394640447272,
          "description": "min=0.622, mean=0.622, max=0.622, sum=0.622 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.42094867293009713,
          "description": "min=0.421, mean=0.421, max=0.421, sum=0.421 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27642276422764234,
          "description": "min=0.276, mean=0.276, max=0.276, sum=0.276 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11422708618331054,
          "description": "min=0.114, mean=0.114, max=0.114, sum=0.114 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666669,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2.0 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43769157088122607,
          "description": "min=0.434, mean=0.438, max=0.444, sum=1.313 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4393992219104699,
          "description": "min=0.383, mean=0.439, max=0.494, sum=1.318 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2054618848004968,
          "description": "min=0.202, mean=0.205, max=0.208, sum=0.616 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.37929404953000706,
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.449065994913171,
          "description": "min=0.434, mean=0.449, max=0.478, sum=1.347 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5676937441643325,
          "description": "min=0.429, mean=0.568, max=0.667, sum=1.703 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17681914997964296,
          "description": "min=0.127, mean=0.177, max=0.216, sum=0.53 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4776758409785933,
          "description": "min=0.433, mean=0.478, max=0.5, sum=1.433 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3274145329078469,
          "description": "min=0.324, mean=0.327, max=0.33, sum=0.982 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.16816448651008897,
          "description": "min=0.014, mean=0.168, max=0.277, sum=0.504 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.38473904949347787,
          "description": "min=0.204, mean=0.385, max=0.523, sum=1.154 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.17544176986611967,
          "description": "min=0.102, mean=0.175, max=0.25, sum=0.526 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4543925551127126,
          "description": "min=0.44, mean=0.454, max=0.465, sum=1.363 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4653480174056855,
          "description": "min=0.312, mean=0.465, max=0.582, sum=1.396 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3431307584494557,
          "description": "min=0.335, mean=0.343, max=0.358, sum=1.029 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4196869049681346,
          "description": "min=0.406, mean=0.42, max=0.438, sum=2.518 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5875706214689266,
          "description": "min=0.429, mean=0.588, max=0.667, sum=3.525 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.20635612913269732,
          "description": "min=0.171, mean=0.206, max=0.237, sum=1.238 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=4 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.4419820754826329,
          "description": "min=0.434, mean=0.442, max=0.456, sum=2.652 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5014430014430014,
          "description": "min=0.333, mean=0.501, max=0.595, sum=3.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.24754799603959324,
          "description": "min=0.209, mean=0.248, max=0.286, sum=1.485 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "description": "(0)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5,
          "description": "min=0.5, mean=0.5, max=0.5, sum=0.5 (1)",
          "style": {},
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_bias.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_bias.json"
      }
    ],
    "name": "bias"
  },
  {
    "title": "Toxicity",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "BoolQ - Toxic fraction",
        "description": "The BoolQ benchmark for binary (yes/no) question answering [(Clark et al., 2019)](https://aclanthology.org/N19-1300/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "BoolQ"
        }
      },
      {
        "value": "NarrativeQA - Toxic fraction",
        "description": "The NarrativeQA benchmark for reading comprehension over narratives [(Ko\u010disk\u00fd et al., 2017)](https://aclanthology.org/Q18-1023/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "NarrativeQA"
        }
      },
      {
        "value": "NaturalQuestions (closed-book) - Toxic fraction",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input does not include the Wikipedia page with the answer.\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "NaturalQuestions (closed-book)"
        }
      },
      {
        "value": "NaturalQuestions (open-book) - Toxic fraction",
        "description": "The NaturalQuestions [(Kwiatkowski et al., 2019)](https://aclanthology.org/Q19-1026/) benchmark for question answering based on naturally-occurring queries through Google Search. The input includes the Wikipedia page with the answer.\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "NaturalQuestions (open-book)"
        }
      },
      {
        "value": "QuAC - Toxic fraction",
        "description": "The QuAC benchmark for question answering in the context of dialogues [(Choi et al., 2018)](https://aclanthology.org/D18-1241/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "QuAC"
        }
      },
      {
        "value": "MS MARCO (regular) - Toxic fraction",
        "description": "The MS MARCO benchmark's regular track for passage retrieval in information retrieval [(https://microsoft.github.io/msmarco/)](https://microsoft.github.io/msmarco/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "MS MARCO (regular)"
        }
      },
      {
        "value": "MS MARCO (TREC) - Toxic fraction",
        "description": "The MS MARCO benchmark's deep learning TREC track for passage retrieval in information retrieval [(https://trec.nist.gov)](https://microsoft.github.io/msmarco/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "MS MARCO (TREC)"
        }
      },
      {
        "value": "CNN/DailyMail - Toxic fraction",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - Toxic fraction",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "XSUM"
        }
      },
      {
        "value": "IMDB - Toxic fraction",
        "description": "The IMDB benchmark for sentiment analysis in movie review [(Maas et al., 2011)](https://aclanthology.org/P11-1015/).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "IMDB"
        }
      },
      {
        "value": "CivilComments - Toxic fraction",
        "description": "The CivilComments benchmark for toxicity detection [(Borkan et al., 2019)](https://arxiv.org/pdf/1903.04561.pdf).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "CivilComments"
        }
      },
      {
        "value": "RAFT - Toxic fraction",
        "description": "The Real-world annotated few-shot (RAFT) meta-benchmark of 11 real-world text classification tasks [(Alex et al., 2021)](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/ca46c1b9512a7a8315fa3c5a946e8265-Abstract-round2.html).\n\nToxic fraction: Fraction of model outputs that are toxic (based on the PerspectiveAPI toxicity classifier).",
        "markdown": false,
        "lower_is_better": true,
        "metadata": {
          "metric": "Toxic fraction",
          "run_group": "RAFT"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6042735042735042,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.014, mean=0.014, max=0.014, sum=0.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0030000000000000005,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.009 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.002145922746781116,
          "description": "min=0, mean=0.002, max=0.004, sum=0.013 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6599416016082683,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.013145539906103287,
          "description": "min=0.011, mean=0.013, max=0.014, sum=0.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.008 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.004, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6300489633822968,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.008, mean=0.014, max=0.017, sum=0.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.004,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.012 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5063399563399563,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.008, mean=0.014, max=0.017, sum=0.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0033333333333333335,
          "description": "min=0.003, mean=0.003, max=0.004, sum=0.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.004291845493562232,
          "description": "min=0.002, mean=0.004, max=0.006, sum=0.026 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.002, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5064102564102564,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.016901408450704227,
          "description": "min=0.014, mean=0.017, max=0.02, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0032175032175032173,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.019 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3875874125874126,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.019718309859154928,
          "description": "min=0.017, mean=0.02, max=0.023, sum=0.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0030000000000000005,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.009 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.002861230329041488,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.017 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4555798368298368,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5035063701730368,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0215962441314554,
          "description": "min=0.02, mean=0.022, max=0.025, sum=0.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0, mean=0.001, max=0.003, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7191265524598858,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.016901408450704227,
          "description": "min=0.014, mean=0.017, max=0.02, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5562049062049063,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.01596244131455399,
          "description": "min=0.011, mean=0.016, max=0.02, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.002, mean=0.002, max=0.003, sum=0.007 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.002, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.648748165414832,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.013145539906103287,
          "description": "min=0.011, mean=0.013, max=0.014, sum=0.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0038610038610038615,
          "description": "min=0.002, mean=0.004, max=0.006, sum=0.023 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5959534292867626,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.012206572769953052,
          "description": "min=0.011, mean=0.012, max=0.014, sum=0.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3965229215229215,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.02347417840375587,
          "description": "min=0.023, mean=0.023, max=0.025, sum=0.07 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0004596436870303355,
          "description": "min=0, mean=0.0, max=0.008, sum=0.025 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5744286577619911,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.020657276995305163,
          "description": "min=0.011, mean=0.021, max=0.028, sum=0.062 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.002145922746781116,
          "description": "min=0, mean=0.002, max=0.004, sum=0.013 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.48450623450623453,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.016901408450704227,
          "description": "min=0.014, mean=0.017, max=0.02, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0033333333333333335,
          "description": "min=0.003, mean=0.003, max=0.004, sum=0.01 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.002, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5508257174923842,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.01971830985915493,
          "description": "min=0.014, mean=0.02, max=0.025, sum=0.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.002, mean=0.002, max=0.003, sum=0.007 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.412334270667604,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.027230046948356807,
          "description": "min=0.025, mean=0.027, max=0.031, sum=0.082 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.002, mean=0.003, max=0.003, sum=0.008 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.001, mean=0.003, max=0.004, sum=0.008 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5642015392015391,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.013145539906103287,
          "description": "min=0.008, mean=0.013, max=0.02, sum=0.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.007 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6328714495381162,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.008, mean=0.011, max=0.014, sum=0.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0, mean=0.002, max=0.003, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6688037271370605,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.010328638497652582,
          "description": "min=0.008, mean=0.01, max=0.014, sum=0.031 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6738178488178488,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.011, mean=0.014, max=0.017, sum=0.042 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.24521373688040354,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.020657276995305163,
          "description": "min=0.017, mean=0.021, max=0.025, sum=0.062 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0036666666666666666,
          "description": "min=0.001, mean=0.004, max=0.005, sum=0.011 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.002145922746781116,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.013 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 2.7763895829862844e-05,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (54)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.36547434047434046,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0215962441314554,
          "description": "min=0.017, mean=0.022, max=0.025, sum=0.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.002, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.512004662004662,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.014, mean=0.014, max=0.014, sum=0.014 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.38444055944055944,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.022535211267605635,
          "description": "min=0.023, mean=0.023, max=0.023, sum=0.023 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5758109174775842,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2902378485711819,
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.016901408450704224,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.006000000000000001,
          "description": "min=0.006, mean=0.006, max=0.006, sum=0.018 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.008583690987124463,
          "description": "min=0.009, mean=0.009, max=0.009, sum=0.052 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.43513523513523517,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.018779342723004692,
          "description": "min=0.017, mean=0.019, max=0.023, sum=0.056 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.003, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.002, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3347556764223431,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0215962441314554,
          "description": "min=0.02, mean=0.022, max=0.025, sum=0.065 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002574002574002574,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.015 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7582167832167832,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.005633802816901409,
          "description": "min=0.006, mean=0.006, max=0.006, sum=0.006 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6102564102564103,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6467365967365968,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.011 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.004,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.004 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5910839160839161,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8121794871794872,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.011 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4142191142191142,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.014, mean=0.014, max=0.014, sum=0.014 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.004,
          "description": "min=0.004, mean=0.004, max=0.004, sum=0.004 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.643006993006993,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6546037296037296,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.005633802816901409,
          "description": "min=0.006, mean=0.006, max=0.006, sum=0.006 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8238927738927739,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5758158508158508,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4297202797202797,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3298371381704715,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.012206572769953052,
          "description": "min=0.011, mean=0.012, max=0.014, sum=0.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.002, mean=0.003, max=0.003, sum=0.008 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.002861230329041488,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.017 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002574002574002574,
          "description": "min=0, mean=0.003, max=0.004, sum=0.015 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4445961445961446,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.011267605633802816,
          "description": "min=0.008, mean=0.011, max=0.014, sum=0.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.002, mean=0.002, max=0.003, sum=0.007 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.42202673869340535,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.012206572769953052,
          "description": "min=0.008, mean=0.012, max=0.014, sum=0.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.002, sum=0.002 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0015328019619865114,
          "description": "min=0, mean=0.002, max=0.002, sum=0.011 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0027578599007170436,
          "description": "min=0, mean=0.003, max=0.015, sum=0.019 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4175808759142092,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.016901408450704224,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.003, sum=0.005 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.002, mean=0.003, max=0.003, sum=0.008 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0006131207847946045,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0005515719801434088,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5128371628371629,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.01596244131455399,
          "description": "min=0.011, mean=0.016, max=0.023, sum=0.048 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.002, sum=0.002 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.30052416719083386,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.030046948356807508,
          "description": "min=0.025, mean=0.03, max=0.037, sum=0.09 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.001, mean=0.002, max=0.004, sum=0.007 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0026666666666666666,
          "description": "min=0.002, mean=0.003, max=0.004, sum=0.008 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4974399057732391,
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.013145539906103287,
          "description": "min=0.011, mean=0.013, max=0.014, sum=0.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.004, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4088448588448588,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.013145539906103286,
          "description": "min=0.008, mean=0.013, max=0.017, sum=0.039 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0023333333333333335,
          "description": "min=0.002, mean=0.002, max=0.003, sum=0.007 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0016547159404302263,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4050529717196384,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.015023474178403754,
          "description": "min=0.014, mean=0.015, max=0.017, sum=0.045 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0013333333333333333,
          "description": "min=0.001, mean=0.001, max=0.002, sum=0.004 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (7)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0016547159404302263,
          "description": "min=0, mean=0.002, max=0.004, sum=0.012 (7)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5020704604037938,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.009389671361502348,
          "description": "min=0.003, mean=0.009, max=0.02, sum=0.028 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001287001287001287,
          "description": "min=0, mean=0.001, max=0.002, sum=0.008 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0007575757575757576,
          "description": "min=0, mean=0.001, max=0.025, sum=0.025 (33)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5531715198381865,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.005633802816901408,
          "description": "min=0.003, mean=0.006, max=0.008, sum=0.017 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray",
            "font-weight": "bold"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "value": 0.0003333333333333333,
          "description": "min=0, mean=0.0, max=0.001, sum=0.001 (3)\n\u26a0 Brown et al. perform an analysis of the contamination for GPT-3 and its known derivatives. For these datasets, they find that 1% - 6% of the datasets' test instances are contaminated based on N-gram overlap, and model performance does not substantially change for these datasets. See Table C.1 on page 45 of https://arxiv.org/pdf/2005.14165.pdf.",
          "style": {
            "color": "gray"
          },
          "markdown": false,
          "contamination_level": "weak"
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.8050116550116551,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.011 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7166083916083916,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.011 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7068181818181818,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.008450704225352112,
          "description": "min=0.008, mean=0.008, max=0.008, sum=0.008 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6051282051282051,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.014, mean=0.014, max=0.014, sum=0.014 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1998834498834499,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.014084507042253521,
          "description": "min=0.014, mean=0.014, max=0.014, sum=0.014 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.005,
          "description": "min=0.005, mean=0.005, max=0.005, sum=0.005 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29364801864801865,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.02535211267605634,
          "description": "min=0.025, mean=0.025, max=0.025, sum=0.025 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.44918414918414923,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.01971830985915493,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.02 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.2453962703962704,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.016901408450704224,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.017 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.003,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.003 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5821678321678322,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.016901408450704224,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.017 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29545454545454547,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.016901408450704224,
          "description": "min=0.017, mean=0.017, max=0.017, sum=0.017 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.001 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4706876456876457,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.01971830985915493,
          "description": "min=0.02, mean=0.02, max=0.02, sum=0.02 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.44994172494172496,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.011, mean=0.011, max=0.011, sum=0.011 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.002,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.002 (1)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3347137430470764,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.012206572769953052,
          "description": "min=0.011, mean=0.012, max=0.014, sum=0.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0016666666666666668,
          "description": "min=0.001, mean=0.002, max=0.002, sum=0.005 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.001, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.001430615164520744,
          "description": "min=0, mean=0.001, max=0.004, sum=0.009 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5811383061383062,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.01220657276995305,
          "description": "min=0.003, mean=0.012, max=0.017, sum=0.037 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0006666666666666666,
          "description": "min=0, mean=0.001, max=0.002, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.002145922746781116,
          "description": "min=0, mean=0.002, max=0.006, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0006435006435006435,
          "description": "min=0, mean=0.001, max=0.002, sum=0.002 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.462995337995338,
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.011267605633802818,
          "description": "min=0.008, mean=0.011, max=0.014, sum=0.034 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0.001, mean=0.001, max=0.001, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.002, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0019305019305019308,
          "description": "min=0.002, mean=0.002, max=0.002, sum=0.006 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "9 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "11 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.24189051689051688,
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.016901408450704227,
          "description": "min=0.014, mean=0.017, max=0.02, sum=0.051 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.008,
          "description": "min=0.007, mean=0.008, max=0.009, sum=0.024 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0030000000000000005,
          "description": "min=0.003, mean=0.003, max=0.003, sum=0.009 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.001,
          "description": "min=0, mean=0.001, max=0.003, sum=0.003 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "value": 0.000715307582260372,
          "description": "min=0, mean=0.001, max=0.002, sum=0.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (54)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.0,
          "description": "min=0, mean=0, max=0, sum=0 (33)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_toxicity.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_toxicity.json"
      }
    ],
    "name": "toxicity"
  },
  {
    "title": "Summarization metrics",
    "header": [
      {
        "value": "Model/adapter",
        "markdown": false,
        "metadata": {}
      },
      {
        "value": "Mean win rate",
        "description": "How many models this model outperform on average (over columns).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {}
      },
      {
        "value": "CNN/DailyMail - SummaC",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nSummaC: Faithfulness scores based on the SummaC method of [Laban et al. (2022)](https://aclanthology.org/2022.tacl-1.10/).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "SummaC",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - QAFactEval",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nQAFactEval: Faithfulness scores based on the SummaC method of [Laban et al. (2022)](https://aclanthology.org/2022.tacl-1.10/).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "QAFactEval",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - BERTScore (F1)",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nBERTScore (F1): Average BERTScore F1 [(Zhang et al., 2020)](https://openreview.net/pdf?id=SkeHuCVFDr) between model generation and reference summary.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "BERTScore (F1)",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Coverage",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nCoverage: Extent to which the model-generated summaries are extractive fragments from the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Coverage",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Density",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nDensity: Extent to which the model-generated summaries are extractive summaries based on the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Density",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - Compression",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nCompression: Extent to which the model-generated summaries are compressed relative to the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Compression",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - HumanEval-faithfulness",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nHumanEval-faithfulness: Human evaluation score for faithfulness.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-faithfulness",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - HumanEval-relevance",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nHumanEval-relevance: Human evaluation score for relevance.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-relevance",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "CNN/DailyMail - HumanEval-coherence",
        "description": "The CNN/DailyMail benchmark for text summarization ([Hermann et al., 2015](https://papers.nips.cc/paper/2015/hash/afdec7005cc9f14302cd0474fd0f3c96-Abstract.html); [Nallapati et al.,2016](https://aclanthology.org/K16-1028/)).\n\nHumanEval-coherence: Human evaluation score for coherence.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-coherence",
          "run_group": "CNN/DailyMail"
        }
      },
      {
        "value": "XSUM - SummaC",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nSummaC: Faithfulness scores based on the SummaC method of [Laban et al. (2022)](https://aclanthology.org/2022.tacl-1.10/).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "SummaC",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - QAFactEval",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nQAFactEval: Faithfulness scores based on the SummaC method of [Laban et al. (2022)](https://aclanthology.org/2022.tacl-1.10/).",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "QAFactEval",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - BERTScore (F1)",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nBERTScore (F1): Average BERTScore F1 [(Zhang et al., 2020)](https://openreview.net/pdf?id=SkeHuCVFDr) between model generation and reference summary.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "BERTScore (F1)",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Coverage",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nCoverage: Extent to which the model-generated summaries are extractive fragments from the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Coverage",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Density",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nDensity: Extent to which the model-generated summaries are extractive summaries based on the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Density",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - Compression",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nCompression: Extent to which the model-generated summaries are compressed relative to the source document [(Grusky et al., 2018)](https://aclanthology.org/N18-1065/).",
        "markdown": false,
        "metadata": {
          "metric": "Compression",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - HumanEval-faithfulness",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nHumanEval-faithfulness: Human evaluation score for faithfulness.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-faithfulness",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - HumanEval-relevance",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nHumanEval-relevance: Human evaluation score for relevance.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-relevance",
          "run_group": "XSUM"
        }
      },
      {
        "value": "XSUM - HumanEval-coherence",
        "description": "The XSUM benchmark for text summarization of BBC news articles [(Narayan et al., 2018)](https://aclanthology.org/D18-1206/).\n\nHumanEval-coherence: Human evaluation score for coherence.",
        "markdown": false,
        "lower_is_better": false,
        "metadata": {
          "metric": "HumanEval-coherence",
          "run_group": "XSUM"
        }
      }
    ],
    "rows": [
      [
        {
          "value": "J1-Jumbo v1 (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5867794486215538,
          "markdown": false
        },
        {
          "value": 0.5151288171631818,
          "description": "min=0.491, mean=0.515, max=0.544, sum=1.545 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.696964335081241,
          "description": "min=4.661, mean=4.697, max=4.725, sum=28.182 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.27790265116917295,
          "description": "min=0.264, mean=0.278, max=0.301, sum=0.834 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.97598626364496,
          "description": "min=0.965, mean=0.976, max=0.984, sum=5.856 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 53.929605831357485,
          "description": "min=40.605, mean=53.93, max=67.411, sum=323.578 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.579310239916042,
          "description": "min=8.981, mean=9.579, max=10.219, sum=57.476 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2868511554050323,
          "description": "min=-0.294, mean=-0.287, max=-0.282, sum=-0.861 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.1818935586249126,
          "description": "min=2.48, mean=3.182, max=3.598, sum=19.091 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.43511885902101227,
          "description": "min=0.432, mean=0.435, max=0.438, sum=1.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7840584721092689,
          "description": "min=0.775, mean=0.784, max=0.792, sum=4.704 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6298709619480816,
          "description": "min=2.514, mean=2.63, max=2.802, sum=15.779 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.861740741647864,
          "description": "min=16.767, mean=16.862, max=16.987, sum=101.17 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Large v1 (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6502297410192147,
          "markdown": false
        },
        {
          "value": 0.5121705493530246,
          "description": "min=0.488, mean=0.512, max=0.535, sum=1.537 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.715823146970394,
          "description": "min=4.664, mean=4.716, max=4.749, sum=28.295 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2482954175661162,
          "description": "min=0.229, mean=0.248, max=0.272, sum=0.745 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9768840440430324,
          "description": "min=0.971, mean=0.977, max=0.985, sum=5.861 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 71.65405587945487,
          "description": "min=55.528, mean=71.654, max=97.831, sum=429.924 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.631709472598792,
          "description": "min=5.872, mean=7.632, max=9.373, sum=45.79 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.23866760351278402,
          "description": "min=-0.26, mean=-0.239, max=-0.222, sum=-0.716 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.674546888395078,
          "description": "min=3.354, mean=3.675, max=4.009, sum=22.047 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40004604044843806,
          "description": "min=0.393, mean=0.4, max=0.405, sum=1.2 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8084128334077892,
          "description": "min=0.804, mean=0.808, max=0.813, sum=4.85 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.7567632334705046,
          "description": "min=3.618, mean=3.757, max=3.939, sum=22.541 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.133322572088453,
          "description": "min=17.523, mean=18.133, max=18.761, sum=108.8 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v1 (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6689640768588138,
          "markdown": false
        },
        {
          "value": 0.5391092885196874,
          "description": "min=0.514, mean=0.539, max=0.586, sum=1.617 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.809910581145076,
          "description": "min=4.706, mean=4.81, max=4.896, sum=28.859 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.2747429286177279,
          "description": "min=0.247, mean=0.275, max=0.302, sum=0.824 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9733042514029583,
          "description": "min=0.966, mean=0.973, max=0.984, sum=5.84 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 41.02711755812993,
          "description": "min=31.118, mean=41.027, max=60.066, sum=246.163 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.887609814491976,
          "description": "min=8.092, mean=9.888, max=11.258, sum=59.326 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2715132814883572,
          "description": "min=-0.282, mean=-0.272, max=-0.264, sum=-0.815 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.446713620425662,
          "description": "min=3.221, mean=3.447, max=3.575, sum=20.68 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4288941077256343,
          "description": "min=0.424, mean=0.429, max=0.434, sum=1.287 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7826042118856411,
          "description": "min=0.78, mean=0.783, max=0.785, sum=4.696 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6397086455700927,
          "description": "min=2.514, mean=2.64, max=2.767, sum=15.838 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.011567725134377,
          "description": "min=18.382, mean=19.012, max=19.445, sum=114.069 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "J1-Grande v2 beta (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6776315789473685,
          "markdown": false
        },
        {
          "value": 0.5516800688123055,
          "description": "min=0.533, mean=0.552, max=0.585, sum=1.655 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.2904019284209938,
          "description": "min=0.273, mean=0.29, max=0.308, sum=0.871 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9729724626233943,
          "description": "min=0.965, mean=0.973, max=0.983, sum=5.838 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.0317341420422,
          "description": "min=18.643, mean=24.032, max=31.138, sum=144.19 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.65941362001026,
          "description": "min=10.389, mean=11.659, max=13.368, sum=69.956 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2817185772994412,
          "description": "min=-0.298, mean=-0.282, max=-0.27, sum=-0.845 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4538733417652499,
          "description": "min=0.45, mean=0.454, max=0.458, sum=1.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7856975370843048,
          "description": "min=0.782, mean=0.786, max=0.79, sum=4.714 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.815909720295231,
          "description": "min=2.624, mean=2.816, max=3.113, sum=16.895 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.856596376166145,
          "description": "min=16.323, mean=16.857, max=17.149, sum=101.14 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Jumbo (178B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6447368421052632,
          "markdown": false
        },
        {
          "value": 0.48944984939262354,
          "description": "min=0.442, mean=0.489, max=0.543, sum=1.468 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.31320318480412634,
          "description": "min=0.299, mean=0.313, max=0.33, sum=0.94 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9574608785885589,
          "description": "min=0.952, mean=0.957, max=0.964, sum=5.745 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.31737957113954,
          "description": "min=12.535, mean=15.317, max=20.424, sum=91.904 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.30449736723726,
          "description": "min=11.81, mean=12.304, max=13.072, sum=73.827 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.31997175372142944,
          "description": "min=-0.325, mean=-0.32, max=-0.314, sum=-0.96 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4894925021585029,
          "description": "min=0.484, mean=0.489, max=0.493, sum=1.468 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.7549647155240389,
          "description": "min=0.75, mean=0.755, max=0.761, sum=4.53 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.144865535443147,
          "description": "min=1.852, mean=2.145, max=2.331, sum=12.869 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.58922760069323,
          "description": "min=16.369, mean=16.589, max=16.81, sum=99.535 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Grande (17B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6710526315789473,
          "markdown": false
        },
        {
          "value": 0.5032610058862116,
          "description": "min=0.469, mean=0.503, max=0.535, sum=1.51 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.2987736324577836,
          "description": "min=0.281, mean=0.299, max=0.308, sum=0.896 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9600651009447835,
          "description": "min=0.953, mean=0.96, max=0.965, sum=5.76 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.304503793993888,
          "description": "min=14.681, mean=22.305, max=27.564, sum=133.827 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.39877050033896,
          "description": "min=10.404, mean=11.399, max=13.033, sum=68.393 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2893415716573027,
          "description": "min=-0.31, mean=-0.289, max=-0.268, sum=-0.868 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.474663326872436,
          "description": "min=0.47, mean=0.475, max=0.48, sum=1.424 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7660021617230298,
          "description": "min=0.761, mean=0.766, max=0.771, sum=4.596 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.359653576011524,
          "description": "min=2.196, mean=2.36, max=2.464, sum=14.158 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.044545661784866,
          "description": "min=16.605, mean=17.045, max=17.3, sum=102.267 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Jurassic-2 Large (7.5B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5723684210526315,
          "markdown": false
        },
        {
          "value": 0.49606841741715785,
          "description": "min=0.465, mean=0.496, max=0.548, sum=1.488 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.27057214623114106,
          "description": "min=0.242, mean=0.271, max=0.304, sum=0.812 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9630886941006946,
          "description": "min=0.952, mean=0.963, max=0.98, sum=5.779 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.250963083991945,
          "description": "min=15.279, mean=25.251, max=36.976, sum=151.506 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.503115138085485,
          "description": "min=9.923, mean=11.503, max=13.28, sum=69.019 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.27758991887056994,
          "description": "min=-0.306, mean=-0.278, max=-0.26, sum=-0.833 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.44989833153156206,
          "description": "min=0.449, mean=0.45, max=0.451, sum=1.35 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7823704015893701,
          "description": "min=0.781, mean=0.782, max=0.783, sum=4.694 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6589249165198687,
          "description": "min=2.345, mean=2.659, max=2.826, sum=15.954 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.02961749079778,
          "description": "min=17.896, mean=18.03, max=18.26, sum=108.178 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Base (13B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.42105263157894735,
          "markdown": false
        },
        {
          "value": 0.3197354449182434,
          "description": "min=-0.076, mean=0.32, max=0.527, sum=0.959 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.18776450739321585,
          "description": "min=0.045, mean=0.188, max=0.278, sum=0.563 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8340516341645151,
          "description": "min=0.543, mean=0.834, max=0.982, sum=5.004 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 35.66281771790173,
          "description": "min=15.163, mean=35.663, max=51.192, sum=213.977 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.346357628862261,
          "description": "min=8.191, mean=9.346, max=11.345, sum=56.078 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2129847266550281,
          "description": "min=-0.217, mean=-0.213, max=-0.206, sum=-0.639 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.3944890669761573,
          "description": "min=0.391, mean=0.394, max=0.396, sum=1.183 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8336902125268334,
          "description": "min=0.828, mean=0.834, max=0.838, sum=5.002 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.392991783737345,
          "description": "min=4.128, mean=4.393, max=4.529, sum=26.358 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.535051923934834,
          "description": "min=17.248, mean=17.535, max=17.956, sum=105.21 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Extended (30B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5657894736842105,
          "markdown": false
        },
        {
          "value": 0.4809362133230566,
          "description": "min=0.309, mean=0.481, max=0.569, sum=1.443 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.25521962437955664,
          "description": "min=0.202, mean=0.255, max=0.288, sum=0.766 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9253891304300669,
          "description": "min=0.8, mean=0.925, max=0.989, sum=5.552 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 41.61911540769457,
          "description": "min=34.945, mean=41.619, max=45.552, sum=249.715 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.039273431117751,
          "description": "min=8.478, mean=9.039, max=9.909, sum=54.236 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.22500232932190178,
          "description": "min=-0.233, mean=-0.225, max=-0.212, sum=-0.675 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4230439766625391,
          "description": "min=0.419, mean=0.423, max=0.427, sum=1.269 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8184154242425056,
          "description": "min=0.817, mean=0.818, max=0.819, sum=4.91 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.507010978728374,
          "description": "min=3.392, mean=3.507, max=3.668, sum=21.042 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.376290660463752,
          "description": "min=17.136, mean=17.376, max=17.524, sum=104.258 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Luminous Supreme (70B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7171052631578947,
          "markdown": false
        },
        {
          "value": 0.5518853318256234,
          "description": "min=0.423, mean=0.552, max=0.624, sum=1.656 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.28049037475726807,
          "description": "min=0.236, mean=0.28, max=0.304, sum=0.841 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9393220183960566,
          "description": "min=0.846, mean=0.939, max=0.988, sum=5.636 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 33.625141882714196,
          "description": "min=31.874, mean=33.625, max=34.739, sum=201.751 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.29781469578472,
          "description": "min=8.884, mean=9.298, max=9.552, sum=55.787 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2409771191414105,
          "description": "min=-0.251, mean=-0.241, max=-0.231, sum=-0.723 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.44350630738930513,
          "description": "min=0.442, mean=0.444, max=0.446, sum=1.331 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8068883614050096,
          "description": "min=0.799, mean=0.807, max=0.816, sum=4.841 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.080091964253596,
          "description": "min=2.852, mean=3.08, max=3.225, sum=18.481 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.97049624677277,
          "description": "min=16.326, mean=16.97, max=17.573, sum=101.823 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Anthropic-LM v4-s3 (52B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5306599832915623,
          "markdown": false
        },
        {
          "value": 0.4923968635744633,
          "description": "min=0.473, mean=0.492, max=0.515, sum=1.477 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.691904356057608,
          "description": "min=4.385, mean=4.692, max=4.898, sum=28.151 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.32642089401655566,
          "description": "min=0.315, mean=0.326, max=0.342, sum=0.979 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9602766718208816,
          "description": "min=0.953, mean=0.96, max=0.968, sum=5.762 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.831883037736205,
          "description": "min=9.043, mean=10.832, max=14.179, sum=64.991 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.889831050263881,
          "description": "min=10.561, mean=11.89, max=12.628, sum=71.339 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6666666666666666,
          "description": "min=0.667, mean=0.667, max=0.667, sum=1.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.0,
          "description": "min=4, mean=4, max=4, sum=8 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6666666666666665,
          "description": "min=2.667, mean=2.667, max=2.667, sum=5.333 (2)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.2708329675740717,
          "description": "min=-0.278, mean=-0.271, max=-0.263, sum=-0.812 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0656965498353155,
          "description": "min=2.934, mean=3.066, max=3.179, sum=18.394 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4370376831136327,
          "description": "min=0.434, mean=0.437, max=0.441, sum=1.311 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8082245669950062,
          "description": "min=0.806, mean=0.808, max=0.811, sum=4.849 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6910357109145138,
          "description": "min=2.656, mean=2.691, max=2.726, sum=16.146 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.182390855675616,
          "description": "min=14.828, mean=15.182, max=15.567, sum=91.094 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7777777777777777,
          "description": "min=0.667, mean=0.778, max=0.889, sum=4.667 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.398148148148148,
          "description": "min=4.333, mean=4.398, max=4.444, sum=26.389 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.898148148148149,
          "description": "min=4.889, mean=4.898, max=4.917, sum=29.389 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        }
      ],
      [
        {
          "value": "BLOOM (176B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29074770258980787,
          "markdown": false
        },
        {
          "value": -0.01977462275373982,
          "description": "min=-0.129, mean=-0.02, max=0.115, sum=-0.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.66471171081461,
          "description": "min=4.63, mean=4.665, max=4.719, sum=27.988 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08008308750782954,
          "description": "min=0.005, mean=0.08, max=0.184, sum=0.24 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7099913231813372,
          "description": "min=0.618, mean=0.71, max=0.826, sum=4.26 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 32.0134921906249,
          "description": "min=20.964, mean=32.013, max=45.756, sum=192.081 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.2523388558949184,
          "description": "min=4.623, mean=5.252, max=6.434, sum=31.514 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.3496571157539257,
          "description": "min=-0.365, mean=-0.35, max=-0.335, sum=-1.049 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.77785601273731,
          "description": "min=4.196, mean=4.778, max=5.107, sum=28.667 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.05904374779925766,
          "description": "min=0.025, mean=0.059, max=0.095, sum=0.177 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5151319646119767,
          "description": "min=0.48, mean=0.515, max=0.553, sum=3.091 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.764128575895107,
          "description": "min=1.41, mean=1.764, max=2.014, sum=10.585 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.933804533381347,
          "description": "min=7.741, mean=8.934, max=10.222, sum=53.603 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "T0pp (11B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "value": -0.04384894228805586,
          "description": "min=-0.052, mean=-0.044, max=-0.031, sum=-0.132 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.1550916195946839,
          "description": "min=0.151, mean=0.155, max=0.163, sum=0.465 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.841192270385719,
          "description": "min=0.836, mean=0.841, max=0.845, sum=5.047 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 8.588383920302716,
          "description": "min=8.147, mean=8.588, max=8.816, sum=51.53 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 8.27387938295926,
          "description": "min=8.169, mean=8.274, max=8.416, sum=49.643 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.3004745337800477,
          "description": "min=-0.331, mean=-0.3, max=-0.268, sum=-0.901 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.09723521885401472,
          "description": "min=0.083, mean=0.097, max=0.111, sum=0.292 (3)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 0.5789418979978066,
          "description": "min=0.543, mean=0.579, max=0.605, sum=3.474 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 1.6841663389066148,
          "description": "min=1.492, mean=1.684, max=1.861, sum=10.105 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "value": 11.17756803869132,
          "description": "min=10.341, mean=11.178, max=11.672, sum=67.065 (6)\n\u2620 T0++ is explicitly trained on these datasets, i.e. data from the same distribution as the test set. See Table 5 on page 24 of https://arxiv.org/pdf/2110.08207.pdf.",
          "style": {
            "color": "lightgray"
          },
          "markdown": false,
          "contamination_level": "strong"
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20220609 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.546345029239766,
          "markdown": false
        },
        {
          "value": 0.46891720389173397,
          "description": "min=0.393, mean=0.469, max=0.516, sum=1.407 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.683468662049275,
          "description": "min=4.621, mean=4.683, max=4.752, sum=28.101 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2639259716833397,
          "description": "min=0.257, mean=0.264, max=0.275, sum=0.792 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.945166441130516,
          "description": "min=0.897, mean=0.945, max=0.971, sum=5.671 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 49.713109703758754,
          "description": "min=43.963, mean=49.713, max=55.846, sum=298.279 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.071669466217989,
          "description": "min=8.816, mean=9.072, max=9.547, sum=54.43 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9925925925925926,
          "description": "min=0.978, mean=0.993, max=1, sum=5.956 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.5394335511982575,
          "description": "min=4.422, mean=4.539, max=4.667, sum=27.237 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.6903205726735138,
          "description": "min=3.556, mean=3.69, max=3.81, sum=22.142 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.252571659198599,
          "description": "min=-0.265, mean=-0.253, max=-0.236, sum=-0.758 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.981288283366219,
          "description": "min=2.761, mean=2.981, max=3.213, sum=17.888 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4335328367301425,
          "description": "min=0.431, mean=0.434, max=0.438, sum=1.301 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7995514803953769,
          "description": "min=0.794, mean=0.8, max=0.803, sum=4.797 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.945005615644467,
          "description": "min=2.71, mean=2.945, max=3.142, sum=17.67 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.422086618359014,
          "description": "min=18.323, mean=18.422, max=18.574, sum=110.533 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6612578878025103,
          "description": "min=0.638, mean=0.661, max=0.697, sum=3.968 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.238517902133463,
          "description": "min=4.212, mean=4.239, max=4.275, sum=25.431 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.825335737235052,
          "description": "min=4.773, mean=4.825, max=4.877, sum=28.952 (6)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere large v20220720 (13.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5760442773600668,
          "markdown": false
        },
        {
          "value": 0.4997740334832678,
          "description": "min=0.447, mean=0.5, max=0.543, sum=1.499 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.763415476947068,
          "description": "min=4.715, mean=4.763, max=4.822, sum=28.58 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2457600895432969,
          "description": "min=0.227, mean=0.246, max=0.263, sum=0.737 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9463649022058865,
          "description": "min=0.903, mean=0.946, max=0.975, sum=5.678 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 37.73347863579329,
          "description": "min=30.364, mean=37.733, max=45.984, sum=226.401 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.269948645908789,
          "description": "min=9.977, mean=11.27, max=13.424, sum=67.62 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.18902428828304493,
          "description": "min=-0.196, mean=-0.189, max=-0.185, sum=-0.567 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.889265592037019,
          "description": "min=2.852, mean=2.889, max=2.928, sum=17.336 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3984961779205311,
          "description": "min=0.394, mean=0.398, max=0.403, sum=1.195 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8227568594164721,
          "description": "min=0.82, mean=0.823, max=0.825, sum=4.937 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5988000456323377,
          "description": "min=3.497, mean=3.599, max=3.746, sum=21.593 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 20.711693139962097,
          "description": "min=20.099, mean=20.712, max=21.78, sum=124.27 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20220720 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4311194653299916,
          "markdown": false
        },
        {
          "value": 0.22880441457511005,
          "description": "min=-0.174, mean=0.229, max=0.443, sum=0.686 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.663724611238682,
          "description": "min=4.552, mean=4.664, max=4.795, sum=27.982 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.11522739683384077,
          "description": "min=0.008, mean=0.115, max=0.197, sum=0.346 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7988868167525552,
          "description": "min=0.482, mean=0.799, max=0.965, sum=4.793 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 22.17629615230217,
          "description": "min=9.34, mean=22.176, max=32.926, sum=133.058 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 13.15437099106955,
          "description": "min=11.915, mean=13.154, max=15.457, sum=78.926 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.1589340320425144,
          "description": "min=-0.17, mean=-0.159, max=-0.142, sum=-0.477 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.2227135293221596,
          "description": "min=3.197, mean=3.223, max=3.258, sum=19.336 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.36729036225155814,
          "description": "min=0.364, mean=0.367, max=0.371, sum=1.102 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8472154184001573,
          "description": "min=0.84, mean=0.847, max=0.855, sum=5.083 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.7541975208526,
          "description": "min=4.485, mean=4.754, max=4.928, sum=28.525 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.748450478665102,
          "description": "min=19.527, mean=19.748, max=20.169, sum=118.491 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere small v20220720 (410M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.29156223893065997,
          "markdown": false
        },
        {
          "value": 0.053643734154981075,
          "description": "min=-0.077, mean=0.054, max=0.168, sum=0.161 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6384596103973283,
          "description": "min=0.051, mean=2.638, max=4.057, sum=15.831 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.025643326292308758,
          "description": "min=-0.069, mean=0.026, max=0.075, sum=0.077 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7441391663831297,
          "description": "min=0.532, mean=0.744, max=0.913, sum=4.465 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 25.237906513316556,
          "description": "min=11.632, mean=25.238, max=33.415, sum=151.427 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 13.243377373187593,
          "description": "min=9.053, mean=13.243, max=20.787, sum=79.46 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.02834827232857105,
          "description": "min=0.0, mean=0.028, max=0.073, sum=0.085 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 3.0938511325795113,
          "description": "min=2.873, mean=3.094, max=3.373, sum=18.563 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.1951040609680371,
          "description": "min=0.173, mean=0.195, max=0.221, sum=0.585 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8630576414302875,
          "description": "min=0.853, mean=0.863, max=0.87, sum=5.178 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.556911526268395,
          "description": "min=9.489, mean=10.557, max=12.063, sum=63.341 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.55096225657148,
          "description": "min=16.738, mean=17.551, max=18.157, sum=105.306 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere xlarge v20221108 (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.7039473684210527,
          "markdown": false
        },
        {
          "value": 0.5141110990456594,
          "description": "min=0.469, mean=0.514, max=0.552, sum=1.542 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.2858638938260981,
          "description": "min=0.281, mean=0.286, max=0.295, sum=0.858 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9705641483765838,
          "description": "min=0.946, mean=0.971, max=0.984, sum=5.823 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 44.771778103334206,
          "description": "min=41.158, mean=44.772, max=50.734, sum=268.631 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.02592370223569,
          "description": "min=7.733, mean=8.026, max=8.278, sum=48.156 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.25799066096812756,
          "description": "min=-0.28, mean=-0.258, max=-0.245, sum=-0.774 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.45133514557325344,
          "description": "min=0.447, mean=0.451, max=0.454, sum=1.354 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7978456468638059,
          "description": "min=0.79, mean=0.798, max=0.803, sum=4.787 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.008801536227543,
          "description": "min=2.823, mean=3.009, max=3.208, sum=18.053 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.187984260626735,
          "description": "min=17.074, mean=17.188, max=17.359, sum=103.128 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere medium v20221108 (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.506578947368421,
          "markdown": false
        },
        {
          "value": 0.35895859214347764,
          "description": "min=0.231, mean=0.359, max=0.443, sum=1.077 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.21796490870344257,
          "description": "min=0.195, mean=0.218, max=0.246, sum=0.654 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8985701854042452,
          "description": "min=0.801, mean=0.899, max=0.957, sum=5.391 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 24.343863209587038,
          "description": "min=16.696, mean=24.344, max=33.085, sum=146.063 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.420494637224708,
          "description": "min=9.239, mean=11.42, max=13.421, sum=68.523 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.17113255308913036,
          "description": "min=-0.192, mean=-0.171, max=-0.149, sum=-0.513 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.38412741233326225,
          "description": "min=0.382, mean=0.384, max=0.388, sum=1.152 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8418943137133965,
          "description": "min=0.842, mean=0.842, max=0.842, sum=5.051 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.8148335440941747,
          "description": "min=3.715, mean=3.815, max=3.914, sum=22.889 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.7034371773279,
          "description": "min=19.45, mean=19.703, max=19.907, sum=118.221 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (6.1B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5789473684210527,
          "markdown": false
        },
        {
          "value": 0.3306993242099164,
          "description": "min=0.318, mean=0.331, max=0.342, sum=0.992 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.29605955170271475,
          "description": "min=0.289, mean=0.296, max=0.305, sum=0.888 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9746996636764317,
          "description": "min=0.974, mean=0.975, max=0.975, sum=5.848 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 31.707488870766706,
          "description": "min=28.678, mean=31.707, max=36.132, sum=190.245 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.688415513712991,
          "description": "min=9.108, mean=9.688, max=10.161, sum=58.13 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.23871033593647883,
          "description": "min=-0.244, mean=-0.239, max=-0.235, sum=-0.716 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4181413420706151,
          "description": "min=0.417, mean=0.418, max=0.42, sum=1.254 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8238944118657666,
          "description": "min=0.823, mean=0.824, max=0.826, sum=4.943 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.7930375453507623,
          "description": "min=2.687, mean=2.793, max=2.942, sum=16.758 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.016669951894464,
          "description": "min=17.475, mean=18.017, max=18.57, sum=108.1 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Cohere Command beta (52.4B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6776315789473684,
          "markdown": false
        },
        {
          "value": 0.4149051333035736,
          "description": "min=0.366, mean=0.415, max=0.441, sum=1.245 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.31834420143428105,
          "description": "min=0.316, mean=0.318, max=0.322, sum=0.955 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9790462109521986,
          "description": "min=0.976, mean=0.979, max=0.982, sum=5.874 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 32.164866076836944,
          "description": "min=28.96, mean=32.165, max=35.676, sum=192.989 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.156293880030324,
          "description": "min=8.594, mean=9.156, max=9.657, sum=54.938 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.27140173856816235,
          "description": "min=-0.285, mean=-0.271, max=-0.262, sum=-0.814 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4587225678869484,
          "description": "min=0.455, mean=0.459, max=0.462, sum=1.376 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7930169105851288,
          "description": "min=0.788, mean=0.793, max=0.797, sum=4.758 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.54760656490819,
          "description": "min=2.417, mean=2.548, max=2.678, sum=15.286 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.93675136805864,
          "description": "min=16.704, mean=16.937, max=17.065, sum=101.621 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-J (6B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5489557226399332,
          "markdown": false
        },
        {
          "value": 0.20780144742590156,
          "description": "min=0.172, mean=0.208, max=0.236, sum=0.623 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.704313539792442,
          "description": "min=4.648, mean=4.704, max=4.739, sum=28.226 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2466254745716148,
          "description": "min=0.241, mean=0.247, max=0.25, sum=0.74 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9475541325972495,
          "description": "min=0.902, mean=0.948, max=0.97, sum=5.685 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 48.283839374824815,
          "description": "min=41.364, mean=48.284, max=57.69, sum=289.703 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.864391531990323,
          "description": "min=8.117, mean=9.864, max=11.439, sum=59.186 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.1976111372976741,
          "description": "min=-0.229, mean=-0.198, max=-0.176, sum=-0.593 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.8128682530109397,
          "description": "min=3.59, mean=3.813, max=4.142, sum=22.877 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3808147712365148,
          "description": "min=0.379, mean=0.381, max=0.384, sum=1.142 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8286466360730634,
          "description": "min=0.824, mean=0.829, max=0.831, sum=4.972 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.042629935538992,
          "description": "min=3.796, mean=4.043, max=4.434, sum=24.256 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.941696288315352,
          "description": "min=17.57, mean=17.942, max=18.398, sum=107.65 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "GPT-NeoX (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4456349206349206,
          "markdown": false
        },
        {
          "value": 0.16465107490254738,
          "description": "min=-0.009, mean=0.165, max=0.255, sum=0.494 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.689614935266213,
          "description": "min=4.591, mean=4.69, max=4.763, sum=28.138 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2255769362361307,
          "description": "min=0.175, mean=0.226, max=0.262, sum=0.677 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.910005755446767,
          "description": "min=0.786, mean=0.91, max=0.973, sum=5.46 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 37.14890205441478,
          "description": "min=35.834, mean=37.149, max=38.818, sum=222.893 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.676104726319009,
          "description": "min=9.164, mean=9.676, max=9.978, sum=58.057 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2082928215061222,
          "description": "min=-0.22, mean=-0.208, max=-0.2, sum=-0.625 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.302964744932122,
          "description": "min=3.048, mean=3.303, max=3.621, sum=19.818 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.39129907447599627,
          "description": "min=0.385, mean=0.391, max=0.395, sum=1.174 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8247285888112758,
          "description": "min=0.822, mean=0.825, max=0.83, sum=4.948 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.3710531876366,
          "description": "min=3.228, mean=3.371, max=3.613, sum=20.226 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.23798025069092,
          "description": "min=17.631, mean=18.238, max=18.621, sum=109.428 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (6.9B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Pythia (12B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "T5 (11B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.1118421052631579,
          "markdown": false
        },
        {
          "value": -0.12151602946968616,
          "description": "min=-0.125, mean=-0.122, max=-0.117, sum=-0.365 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.16977369097758946,
          "description": "min=-0.173, mean=-0.17, max=-0.165, sum=-0.509 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5547542182286073,
          "description": "min=0.55, mean=0.555, max=0.56, sum=3.329 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.698337926712314,
          "description": "min=2.69, mean=2.698, max=2.706, sum=16.19 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 19.248383205041776,
          "description": "min=19.085, mean=19.248, max=19.44, sum=115.49 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2584302846171323,
          "description": "min=-0.267, mean=-0.258, max=-0.244, sum=-0.775 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.3147063674770794,
          "description": "min=-0.379, mean=-0.315, max=-0.276, sum=-0.944 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3554524422801694,
          "description": "min=0.324, mean=0.355, max=0.372, sum=2.133 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.831154946558878,
          "description": "min=0.763, mean=0.831, max=0.866, sum=4.987 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.543527805806836,
          "description": "min=16.29, mean=16.544, max=16.714, sum=99.261 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "UL2 (20B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.11842105263157894,
          "markdown": false
        },
        {
          "value": -0.2698551726198464,
          "description": "min=-0.27, mean=-0.27, max=-0.27, sum=-0.81 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.12078049146748136,
          "description": "min=-0.122, mean=-0.121, max=-0.12, sum=-0.362 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7197585278365729,
          "description": "min=0.72, mean=0.72, max=0.72, sum=4.319 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.044183333839311,
          "description": "min=5.044, mean=5.044, max=5.044, sum=30.265 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.186281356409094,
          "description": "min=7.173, mean=7.186, max=7.2, sum=43.118 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2753430534988641,
          "description": "min=-0.28, mean=-0.275, max=-0.272, sum=-0.826 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.07156637071699196,
          "description": "min=0.028, mean=0.072, max=0.121, sum=0.215 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6426528869383965,
          "description": "min=0.617, mean=0.643, max=0.671, sum=3.856 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.2083925287601787,
          "description": "min=3.058, mean=3.208, max=3.428, sum=19.25 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.853257861418139,
          "description": "min=7.31, mean=7.853, max=8.427, sum=47.12 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5927318295739348,
          "markdown": false
        },
        {
          "value": 0.20179927196685032,
          "description": "min=0.094, mean=0.202, max=0.259, sum=0.605 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.67041236939807,
          "description": "min=4.642, mean=4.67, max=4.721, sum=28.022 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2755570292220846,
          "description": "min=0.234, mean=0.276, max=0.301, sum=0.827 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9331599358896452,
          "description": "min=0.855, mean=0.933, max=0.973, sum=5.599 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 31.306505459997258,
          "description": "min=28.251, mean=31.307, max=33.584, sum=187.839 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.800322939057557,
          "description": "min=9.442, mean=9.8, max=10.068, sum=58.802 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0,
          "description": "min=1, mean=1, max=1, sum=6 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 4.377777777777777,
          "description": "min=4.333, mean=4.378, max=4.467, sum=26.267 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.233333333333333,
          "description": "min=2.833, mean=3.233, max=3.867, sum=19.4 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.25337265715073337,
          "description": "min=-0.271, mean=-0.253, max=-0.224, sum=-0.76 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.5231601957035803,
          "description": "min=3.343, mean=3.523, max=3.7, sum=21.139 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.45990517032509515,
          "description": "min=0.458, mean=0.46, max=0.461, sum=1.38 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7933759020774565,
          "description": "min=0.792, mean=0.793, max=0.795, sum=4.76 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.732196710488823,
          "description": "min=2.672, mean=2.732, max=2.852, sum=16.393 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.79220871639349,
          "description": "min=16.442, mean=16.792, max=17.056, sum=100.753 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7981481481481479,
          "description": "min=0.583, mean=0.798, max=0.944, sum=4.789 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.300000000000001,
          "description": "min=4.167, mean=4.3, max=4.4, sum=25.8 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.890740740740742,
          "description": "min=4.867, mean=4.891, max=4.917, sum=29.344 (6)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "OPT (66B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5785714285714286,
          "markdown": false
        },
        {
          "value": 0.19745183659958473,
          "description": "min=0.064, mean=0.197, max=0.291, sum=0.592 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.735075808555843,
          "description": "min=4.708, mean=4.735, max=4.771, sum=28.41 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2564336767010044,
          "description": "min=0.206, mean=0.256, max=0.287, sum=0.769 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9202647711974157,
          "description": "min=0.829, mean=0.92, max=0.97, sum=5.522 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 41.59545904426739,
          "description": "min=34.301, mean=41.595, max=46.027, sum=249.573 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.759458553538733,
          "description": "min=8.796, mean=9.759, max=10.302, sum=58.557 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.18875486064192462,
          "description": "min=-0.208, mean=-0.189, max=-0.166, sum=-0.566 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.3243234460347995,
          "description": "min=3.146, mean=3.324, max=3.669, sum=19.946 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4169695047035986,
          "description": "min=0.416, mean=0.417, max=0.419, sum=1.251 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8172878337570123,
          "description": "min=0.815, mean=0.817, max=0.819, sum=4.904 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.898863398596404,
          "description": "min=3.708, mean=3.899, max=4.102, sum=23.393 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.413782867028814,
          "description": "min=18.005, mean=18.414, max=18.872, sum=110.483 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "LLaMA (65B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Llama 2 (70B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Alpaca (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Vicuna v1.3 (13B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Mistral v0.1 (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (530B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.756578947368421,
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.5727510890981916,
          "description": "min=0.553, mean=0.573, max=0.595, sum=1.718 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.3157002201673737,
          "description": "min=0.296, mean=0.316, max=0.326, sum=0.947 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9770276969879915,
          "description": "min=0.975, mean=0.977, max=0.981, sum=5.862 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.967920888770376,
          "description": "min=25.944, mean=26.968, max=27.893, sum=161.808 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.317434111699901,
          "description": "min=9.708, mean=10.317, max=10.928, sum=61.905 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.2807751739040458,
          "description": "min=-0.297, mean=-0.281, max=-0.266, sum=-0.842 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.4734549353569219,
          "description": "min=0.472, mean=0.473, max=0.476, sum=1.42 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7735373951395458,
          "description": "min=0.772, mean=0.774, max=0.777, sum=4.641 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.321577703631062,
          "description": "min=2.174, mean=2.322, max=2.471, sum=13.929 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.775903485860036,
          "description": "min=15.596, mean=15.776, max=15.931, sum=94.655 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "TNLG v2 (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.611842105263158,
          "markdown": false
        },
        {
          "value": 0.4933195613927493,
          "description": "min=0.487, mean=0.493, max=0.501, sum=1.48 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.2815425075266347,
          "description": "min=0.278, mean=0.282, max=0.284, sum=0.845 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9761546866038108,
          "description": "min=0.973, mean=0.976, max=0.981, sum=5.857 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 48.951173188846475,
          "description": "min=38.053, mean=48.951, max=68.464, sum=293.707 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.59754128304669,
          "description": "min=7.327, mean=9.598, max=11.919, sum=57.585 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.20340532606019324,
          "description": "min=-0.217, mean=-0.203, max=-0.192, sum=-0.61 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.3853545238949662,
          "description": "min=0.38, mean=0.385, max=0.394, sum=1.156 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.792833262373014,
          "description": "min=0.786, mean=0.793, max=0.801, sum=4.757 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.2859287054515427,
          "description": "min=3.215, mean=3.286, max=3.34, sum=19.716 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 18.428451341381788,
          "description": "min=17.984, mean=18.428, max=18.968, sum=110.571 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "davinci (175B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.3600250626566416,
          "markdown": false
        },
        {
          "value": 0.321074205166444,
          "description": "min=-0.08, mean=0.321, max=0.532, sum=1.284 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.062076530805548,
          "description": "min=2.929, mean=4.062, max=4.888, sum=28.435 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.18232803102041212,
          "description": "min=0.023, mean=0.182, max=0.25, sum=0.729 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.87307141297806,
          "description": "min=0.72, mean=0.873, max=0.944, sum=6.111 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.913710646412884,
          "description": "min=15.056, mean=17.914, max=20.184, sum=125.396 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.842721706219109,
          "description": "min=4.761, mean=9.843, max=11.282, sum=68.899 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9526666666666668,
          "description": "min=0.763, mean=0.953, max=1, sum=4.763 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.500666666666667,
          "description": "min=3.503, mean=4.501, max=5, sum=22.503 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.862666666666667,
          "description": "min=2.647, mean=3.863, max=4.667, sum=19.313 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.2669066513504126,
          "description": "min=-0.317, mean=-0.267, max=-0.218, sum=-1.068 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.337582859954366,
          "description": "min=1.878, mean=2.338, max=2.635, sum=16.363 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3179425085241978,
          "description": "min=0.063, mean=0.318, max=0.423, sum=1.272 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7506856271565006,
          "description": "min=0.698, mean=0.751, max=0.774, sum=5.255 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.3513024292310853,
          "description": "min=2.081, mean=3.351, max=10.076, sum=23.459 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 14.079969364330754,
          "description": "min=7.668, mean=14.08, max=15.293, sum=98.56 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8290476190476191,
          "description": "min=0.5, mean=0.829, max=1, sum=5.803 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.074761904761905,
          "description": "min=2.833, mean=4.075, max=5, sum=28.523 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.397619047619048,
          "description": "min=2.167, mean=3.398, max=5, sum=23.783 (7)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "curie (6.7B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.32471804511278196,
          "markdown": false
        },
        {
          "value": 0.3538436304603978,
          "description": "min=-0.108, mean=0.354, max=0.557, sum=1.415 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.20445410382703,
          "description": "min=1.248, mean=4.204, max=4.78, sum=29.431 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.08867060792677807,
          "description": "min=-0.343, mean=0.089, max=0.264, sum=0.355 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8901263761958778,
          "description": "min=0.425, mean=0.89, max=0.973, sum=6.231 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 23.471817181725523,
          "description": "min=11.471, mean=23.472, max=34.455, sum=164.303 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.494670330829432,
          "description": "min=5.037, mean=9.495, max=12.229, sum=66.463 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2866666666666666,
          "description": "min=0.287, mean=0.287, max=0.287, sum=0.287 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.9333333333333333,
          "description": "min=1.933, mean=1.933, max=1.933, sum=1.933 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.7666666666666666,
          "description": "min=1.767, mean=1.767, max=1.767, sum=1.767 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.14346265436541167,
          "description": "min=-0.237, mean=-0.143, max=0.073, sum=-0.574 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.9220091164391953,
          "description": "min=2.914, mean=3.922, max=4.204, sum=27.454 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.312644368874429,
          "description": "min=0.091, mean=0.313, max=0.388, sum=1.251 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8152742026902194,
          "description": "min=0.795, mean=0.815, max=0.823, sum=5.707 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.569907111767537,
          "description": "min=2.849, mean=5.57, max=19.82, sum=38.989 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 17.01754099745573,
          "description": "min=10.146, mean=17.018, max=18.474, sum=119.123 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9244444444444445,
          "description": "min=0.773, mean=0.924, max=1, sum=2.773 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.573333333333333,
          "description": "min=3.387, mean=3.573, max=3.667, sum=10.72 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.165555555555556,
          "description": "min=3.163, mean=4.166, max=4.667, sum=12.497 (3)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "babbage (1.3B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.19609440267335004,
          "markdown": false
        },
        {
          "value": 0.19395910509097278,
          "description": "min=-0.024, mean=0.194, max=0.404, sum=0.582 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.206720080183251,
          "description": "min=1.208, mean=3.207, max=4.672, sum=19.24 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.12942978993545518,
          "description": "min=-0.533, mean=-0.129, max=0.256, sum=-0.388 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6061106279492011,
          "description": "min=0.243, mean=0.606, max=0.942, sum=3.637 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 43.533595505945534,
          "description": "min=7.213, mean=43.534, max=84.961, sum=261.202 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.733051993966683,
          "description": "min=5.569, mean=6.733, max=8.376, sum=40.398 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.18805348402642733,
          "description": "min=-0.221, mean=-0.188, max=-0.16, sum=-0.564 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.19517962440346606,
          "description": "min=0.003, mean=0.195, max=0.546, sum=1.171 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.01972435572139075,
          "description": "min=-0.047, mean=0.02, max=0.139, sum=0.059 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.6037080043294082,
          "description": "min=0.538, mean=0.604, max=0.715, sum=3.622 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.385950410054523,
          "description": "min=3.597, mean=4.386, max=5.935, sum=26.316 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.71557516895029,
          "description": "min=10.355, mean=11.716, max=13.636, sum=70.293 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "ada (350M)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.23114035087719298,
          "markdown": false
        },
        {
          "value": 0.1685268875223913,
          "description": "min=0.007, mean=0.169, max=0.28, sum=0.506 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.742251717543341,
          "description": "min=3.028, mean=3.742, max=4.119, sum=22.454 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.02646359689379031,
          "description": "min=-0.233, mean=0.026, max=0.191, sum=0.079 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7733298424406031,
          "description": "min=0.551, mean=0.773, max=0.886, sum=4.64 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 36.59619529550019,
          "description": "min=18.265, mean=36.596, max=52.461, sum=219.577 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.070019676025145,
          "description": "min=9.827, mean=12.07, max=15.425, sum=72.42 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.11515867019712234,
          "description": "min=-0.151, mean=-0.115, max=-0.086, sum=-0.345 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.009336465575789038,
          "description": "min=0, mean=0.009, max=0.028, sum=0.056 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.23174258205917408,
          "description": "min=-0.509, mean=-0.232, max=-0.002, sum=-0.695 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.40704982952261465,
          "description": "min=0.208, mean=0.407, max=0.566, sum=2.442 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.652801659570502,
          "description": "min=1.129, mean=2.653, max=3.54, sum=15.917 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.022940864769765,
          "description": "min=4.395, mean=8.023, max=11.123, sum=48.138 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-003",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.5263157894736842,
          "markdown": false
        },
        {
          "value": 0.35893042891379157,
          "description": "min=0.33, mean=0.359, max=0.403, sum=1.077 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.3420449797279243,
          "description": "min=0.336, mean=0.342, max=0.347, sum=1.026 (3)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.9556982855176755,
          "description": "min=0.953, mean=0.956, max=0.959, sum=5.734 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.544859402012935,
          "description": "min=7.169, mean=7.545, max=7.928, sum=45.269 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.389062386727216,
          "description": "min=8.736, mean=9.389, max=10.065, sum=56.334 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.3005772048135215,
          "description": "min=-0.313, mean=-0.301, max=-0.289, sum=-0.902 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.411029433026404,
          "description": "min=0.406, mean=0.411, max=0.414, sum=1.233 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8221014569634312,
          "description": "min=0.814, mean=0.822, max=0.829, sum=4.933 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.6298820148802573,
          "description": "min=2.461, mean=2.63, max=2.752, sum=15.779 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 10.931690583444237,
          "description": "min=10.736, mean=10.932, max=11.034, sum=65.59 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "text-davinci-002",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6410087719298245,
          "markdown": false
        },
        {
          "value": 0.35298687802144607,
          "description": "min=0.136, mean=0.353, max=0.455, sum=1.412 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.635409033816104,
          "description": "min=4.04, mean=4.635, max=4.834, sum=32.448 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3206946902747002,
          "description": "min=0.303, mean=0.321, max=0.333, sum=1.283 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9464923911138073,
          "description": "min=0.904, mean=0.946, max=0.957, sum=6.625 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.994591776988235,
          "description": "min=13.275, mean=15.995, max=17.016, sum=111.962 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.818392473408851,
          "description": "min=7.152, mean=8.818, max=9.675, sum=61.729 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9990476190476191,
          "description": "min=0.993, mean=0.999, max=1, sum=6.993 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.434920634920635,
          "description": "min=4.333, mean=4.435, max=4.6, sum=31.044 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.3711111111111105,
          "description": "min=4, mean=4.371, max=5, sum=30.598 (7)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": -0.2728636190391109,
          "description": "min=-0.288, mean=-0.273, max=-0.257, sum=-1.091 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.0071326818732076,
          "description": "min=2.795, mean=3.007, max=3.207, sum=21.05 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.4296202005928721,
          "description": "min=0.366, mean=0.43, max=0.459, sum=1.718 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8005553389114972,
          "description": "min=0.789, mean=0.801, max=0.833, sum=5.604 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.8724523474356,
          "description": "min=2.471, mean=2.872, max=4.654, sum=20.107 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 14.069713395015288,
          "description": "min=13.554, mean=14.07, max=14.306, sum=98.488 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.848692365835223,
          "description": "min=0.762, mean=0.849, max=0.963, sum=5.941 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.40989417989418,
          "description": "min=4.277, mean=4.41, max=4.63, sum=30.869 (7)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 4.684981103552532,
          "description": "min=4.403, mean=4.685, max=4.815, sum=32.795 (7)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-curie-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6165831244778613,
          "markdown": false
        },
        {
          "value": 0.2913458656100147,
          "description": "min=0.156, mean=0.291, max=0.356, sum=1.165 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.616429547159027,
          "description": "min=4.214, mean=4.616, max=4.743, sum=32.315 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3055441003363248,
          "description": "min=0.299, mean=0.306, max=0.314, sum=1.222 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9607616041668255,
          "description": "min=0.935, mean=0.961, max=0.97, sum=6.725 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 26.09992906850249,
          "description": "min=17.105, mean=26.1, max=29.982, sum=182.7 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.829258437977153,
          "description": "min=6.155, mean=6.829, max=7.635, sum=47.805 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9666666666666669,
          "description": "min=0.967, mean=0.967, max=0.967, sum=0.967 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.586666666666667,
          "description": "min=4.587, mean=4.587, max=4.587, sum=4.587 (1)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 4.243333333333334,
          "description": "min=4.243, mean=4.243, max=4.243, sum=4.243 (1)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.18531544589014434,
          "description": "min=-0.241, mean=-0.185, max=-0.057, sum=-0.741 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.458996653634986,
          "description": "min=3.199, mean=3.459, max=3.799, sum=24.213 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.3536865086232682,
          "description": "min=0.308, mean=0.354, max=0.372, sum=1.415 (4)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.838839539634714,
          "description": "min=0.823, mean=0.839, max=0.903, sum=5.872 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.008473483028278,
          "description": "min=3.005, mean=4.008, max=8.274, sum=28.059 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 12.979988031884476,
          "description": "min=11.556, mean=12.98, max=13.601, sum=90.86 (7)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9913333333333334,
          "description": "min=0.957, mean=0.991, max=1, sum=4.957 (5)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 4.068,
          "description": "min=4, mean=4.068, max=4.34, sum=20.34 (5)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.3213333333333335,
          "description": "min=4.273, mean=4.321, max=4.333, sum=21.607 (5)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "text-babbage-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.6459690893901421,
          "markdown": false
        },
        {
          "value": 0.3784199534784201,
          "description": "min=0.347, mean=0.378, max=0.402, sum=1.135 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.676089387380419,
          "description": "min=4.659, mean=4.676, max=4.708, sum=28.057 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28169928727191773,
          "description": "min=0.277, mean=0.282, max=0.285, sum=0.845 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9716251936961523,
          "description": "min=0.969, mean=0.972, max=0.973, sum=5.83 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 45.94847550953912,
          "description": "min=41.642, mean=45.948, max=53.738, sum=275.691 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.290663826380655,
          "description": "min=5.013, mean=5.291, max=5.576, sum=31.744 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.05681849002633572,
          "description": "min=-0.078, mean=-0.057, max=-0.044, sum=-0.17 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.330178153632894,
          "description": "min=4.256, mean=4.33, max=4.381, sum=25.981 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.28149043918051486,
          "description": "min=0.277, mean=0.281, max=0.286, sum=0.844 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8853480945766184,
          "description": "min=0.873, mean=0.885, max=0.893, sum=5.312 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.487450287350649,
          "description": "min=7.239, mean=8.487, max=9.133, sum=50.925 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 11.856076449493486,
          "description": "min=11.1, mean=11.856, max=12.376, sum=71.136 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "text-ada-001",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.48596491228070177,
          "markdown": false
        },
        {
          "value": 0.22335669413101697,
          "description": "min=0.202, mean=0.223, max=0.237, sum=0.67 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.3694626717468696,
          "description": "min=2.69, mean=3.369, max=3.833, sum=20.217 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.2468463296383967,
          "description": "min=0.244, mean=0.247, max=0.25, sum=0.741 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9289690481394134,
          "description": "min=0.923, mean=0.929, max=0.933, sum=5.574 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 31.424005422737114,
          "description": "min=28.745, mean=31.424, max=35.767, sum=188.544 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 5.461465024583634,
          "description": "min=5.334, mean=5.461, max=5.548, sum=32.769 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.10168572979799827,
          "description": "min=-0.132, mean=-0.102, max=-0.078, sum=-0.305 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.92859074878104,
          "description": "min=4.849, mean=4.929, max=5.055, sum=29.572 (6)",
          "style": {
            "font-weight": "bold"
          },
          "markdown": false
        },
        {
          "value": 0.24476258912195994,
          "description": "min=0.237, mean=0.245, max=0.254, sum=0.734 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8466942307223615,
          "description": "min=0.834, mean=0.847, max=0.866, sum=5.08 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.625570347216255,
          "description": "min=7.289, mean=7.626, max=8.299, sum=45.753 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 13.080494860928995,
          "description": "min=12.7, mean=13.08, max=13.496, sum=78.483 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0301",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "gpt-3.5-turbo-0613",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct-v1 (3B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Base (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "RedPajama-INCITE-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "MPT-Instruct (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (7B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "Falcon-Instruct (40B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        },
        {
          "description": "No matching runs",
          "markdown": false
        }
      ],
      [
        {
          "value": "GLM (130B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.4714285714285714,
          "markdown": false
        },
        {
          "value": 0.5663194802454004,
          "description": "min=0.537, mean=0.566, max=0.591, sum=1.699 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.287517514648812,
          "description": "min=0.266, mean=0.288, max=0.312, sum=0.863 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9724896258431271,
          "description": "min=0.96, mean=0.972, max=0.987, sum=5.835 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 30.259024131398863,
          "description": "min=24.014, mean=30.259, max=37.594, sum=181.554 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 8.68711944818053,
          "description": "min=7.643, mean=8.687, max=9.754, sum=52.123 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.9629629629629629,
          "description": "min=0.889, mean=0.963, max=1, sum=5.778 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.166666666666667,
          "description": "min=3.889, mean=4.167, max=4.5, sum=25 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.4629629629629632,
          "description": "min=3.111, mean=3.463, max=3.833, sum=20.778 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": -0.20556503322082545,
          "description": "min=-0.225, mean=-0.206, max=-0.183, sum=-0.617 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.42745522151316395,
          "description": "min=0.427, mean=0.427, max=0.428, sum=1.282 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.8174518357071618,
          "description": "min=0.813, mean=0.817, max=0.82, sum=4.905 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.040514978645572,
          "description": "min=3.819, mean=4.041, max=4.367, sum=24.243 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 16.25000448561988,
          "description": "min=16.122, mean=16.25, max=16.375, sum=97.5 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.7626984126984127,
          "description": "min=0.583, mean=0.763, max=0.905, sum=4.576 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.842857142857143,
          "description": "min=3.333, mean=3.843, max=4.1, sum=23.057 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 4.249999999999999,
          "description": "min=3.417, mean=4.25, max=4.667, sum=25.5 (6)",
          "style": {},
          "markdown": false
        }
      ],
      [
        {
          "value": "InstructPalmyra (30B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.9716859203819838,
          "description": "min=0.961, mean=0.972, max=0.979, sum=2.915 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 28.97014469233496,
          "description": "min=22.383, mean=28.97, max=38.633, sum=86.91 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 7.901010404629208,
          "description": "min=6.723, mean=7.901, max=9.103, sum=23.703 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.8437121246995759,
          "description": "min=0.836, mean=0.844, max=0.853, sum=2.531 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.4410181202034944,
          "description": "min=3.292, mean=3.441, max=3.518, sum=10.323 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 15.707173220790708,
          "description": "min=15.467, mean=15.707, max=15.837, sum=47.122 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "Palmyra X (43B)",
          "description": "",
          "markdown": false
        },
        {
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.29078580039209107,
          "description": "min=0, mean=0.291, max=0.872, sum=0.872 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.34978873721003,
          "description": "min=0, mean=2.35, max=7.049, sum=7.049 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 3.116859693035,
          "description": "min=0, mean=3.117, max=9.351, sum=9.351 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": 0.7746217499327193,
          "description": "min=0.77, mean=0.775, max=0.778, sum=2.324 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 2.4662768763204443,
          "description": "min=2.38, mean=2.466, max=2.546, sum=7.399 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 14.25194669426599,
          "description": "min=14.242, mean=14.252, max=14.266, sum=42.756 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "1 matching runs, but no matching metrics",
          "markdown": false
        }
      ],
      [
        {
          "value": "YaLM (100B)",
          "description": "",
          "markdown": false
        },
        {
          "value": 0.04536340852130326,
          "markdown": false
        },
        {
          "value": -0.3217409663792838,
          "description": "min=-0.35, mean=-0.322, max=-0.296, sum=-0.965 (3)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.14496527560996572,
          "description": "min=-0.154, mean=-0.145, max=-0.127, sum=-0.435 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5414806522156069,
          "description": "min=0.406, mean=0.541, max=0.615, sum=3.249 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0902141864760964,
          "description": "min=0.681, mean=1.09, max=1.303, sum=6.541 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 6.935882429972025,
          "description": "min=6.289, mean=6.936, max=8.148, sum=41.615 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "value": -0.3466731809697447,
          "description": "min=-0.352, mean=-0.347, max=-0.344, sum=-1.04 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.1763058409064706,
          "description": "min=0.856, mean=1.176, max=1.555, sum=7.058 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.031129963643441894,
          "description": "min=0.007, mean=0.031, max=0.057, sum=0.093 (3)",
          "style": {},
          "markdown": false
        },
        {
          "value": 0.5674251187038739,
          "description": "min=0.557, mean=0.567, max=0.574, sum=3.405 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 1.0413571284332044,
          "description": "min=1.005, mean=1.041, max=1.081, sum=6.248 (6)",
          "style": {},
          "markdown": false
        },
        {
          "value": 9.951019350255967,
          "description": "min=9.397, mean=9.951, max=10.96, sum=59.706 (6)",
          "style": {},
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        },
        {
          "description": "2 matching runs, but no matching metrics",
          "markdown": false
        }
      ]
    ],
    "links": [
      {
        "text": "LaTeX",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/latex/core_scenarios_summarization_metrics.tex"
      },
      {
        "text": "JSON",
        "href": "/nlp/scr4/nlp/crfm/yifanmai/helm-release/benchmark_output/releases/v0.4.0/groups/json/core_scenarios_summarization_metrics.json"
      }
    ],
    "name": "summarization_metrics"
  }
]