{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "80xnUmoI7fBX"
   },
   "source": [
    "##### Copyright 2020 The TensorFlow Authors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "cellView": "form",
    "execution": {
     "iopub.execute_input": "2023-10-17T12:22:53.951563Z",
     "iopub.status.busy": "2023-10-17T12:22:53.951033Z",
     "iopub.status.idle": "2023-10-17T12:22:53.954589Z",
     "shell.execute_reply": "2023-10-17T12:22:53.954021Z"
    },
    "id": "8nvTnfs6Q692"
   },
   "outputs": [],
   "source": [
    "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
    "# you may not use this file except in compliance with the License.\n",
    "# You may obtain a copy of the License at\n",
    "#\n",
    "# https://www.apache.org/licenses/LICENSE-2.0\n",
    "#\n",
    "# Unless required by applicable law or agreed to in writing, software\n",
    "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
    "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
    "# See the License for the specific language governing permissions and\n",
    "# limitations under the License."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WmfcMK5P5C1G"
   },
   "source": [
    "# Introduction to the TensorFlow Models NLP library"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cH-oJ8R6AHMK"
   },
   "source": [
    "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://www.tensorflow.org/tfmodels/nlp\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/models/blob/master/docs/nlp/index.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://github.com/tensorflow/models/blob/master/docs/nlp/index.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a href=\"https://storage.googleapis.com/tensorflow_docs/models/docs/nlp/index.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
    "  </td>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0H_EFIhq4-MJ"
   },
   "source": [
    "## Learning objectives\n",
    "\n",
    "In this Colab notebook, you will learn how to build transformer-based models for common NLP tasks including pretraining, span labelling and classification using the building blocks from [NLP modeling library](https://github.com/tensorflow/models/tree/master/official/nlp/modeling)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2N97-dps_nUk"
   },
   "source": [
    "## Install and import"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "459ygAVl_rg0"
   },
   "source": [
    "### Install the TensorFlow Model Garden pip package\n",
    "\n",
    "*  `tf-models-official` is the stable Model Garden package. Note that it may not include the latest changes in the `tensorflow_models` github repo. To include latest changes, you may install `tf-models-nightly`,\n",
    "which is the nightly Model Garden package created daily automatically.\n",
    "*  `pip` will install all models and dependencies automatically."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:22:53.958613Z",
     "iopub.status.busy": "2023-10-17T12:22:53.958071Z",
     "iopub.status.idle": "2023-10-17T12:23:04.140390Z",
     "shell.execute_reply": "2023-10-17T12:23:04.139373Z"
    },
    "id": "Y-qGkdh6_sZc"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting tf-models-official\r\n",
      "  Using cached tf_models_official-2.14.2-py2.py3-none-any.whl.metadata (1.4 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting Cython (from tf-models-official)\r\n",
      "  Using cached Cython-3.0.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.2 kB)\r\n",
      "Requirement already satisfied: Pillow in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (10.1.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting gin-config (from tf-models-official)\r\n",
      "  Using cached gin_config-0.5.0-py3-none-any.whl (61 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting google-api-python-client>=1.6.7 (from tf-models-official)\r\n",
      "  Using cached google_api_python_client-2.103.0-py2.py3-none-any.whl.metadata (6.6 kB)\r\n",
      "Collecting immutabledict (from tf-models-official)\r\n",
      "  Using cached immutabledict-3.0.0-py3-none-any.whl.metadata (3.1 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting kaggle>=1.3.9 (from tf-models-official)\r\n",
      "  Using cached kaggle-1.5.16-py3-none-any.whl\r\n",
      "Requirement already satisfied: matplotlib in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (3.8.0)\r\n",
      "Requirement already satisfied: numpy>=1.20 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (1.26.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting oauth2client (from tf-models-official)\r\n",
      "  Using cached oauth2client-4.1.3-py2.py3-none-any.whl (98 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting opencv-python-headless (from tf-models-official)\r\n",
      "  Using cached opencv_python_headless-4.8.1.78-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pandas>=0.22.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (2.1.1)\r\n",
      "Requirement already satisfied: psutil>=5.4.3 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (5.9.6)\r\n",
      "Collecting py-cpuinfo>=3.3.0 (from tf-models-official)\r\n",
      "  Using cached py_cpuinfo-9.0.0-py3-none-any.whl (22 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting pycocotools (from tf-models-official)\r\n",
      "  Using cached pycocotools-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.1 kB)\r\n",
      "Requirement already satisfied: pyyaml>=6.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (6.0.1)\r\n",
      "Collecting sacrebleu (from tf-models-official)\r\n",
      "  Using cached sacrebleu-2.3.1-py3-none-any.whl (118 kB)\r\n",
      "Requirement already satisfied: scipy>=0.19.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (1.11.3)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting sentencepiece (from tf-models-official)\r\n",
      "  Using cached sentencepiece-0.1.99-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\r\n",
      "Collecting seqeval (from tf-models-official)\r\n",
      "  Using cached seqeval-1.2.2-py3-none-any.whl\r\n",
      "Requirement already satisfied: six in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (1.16.0)\r\n",
      "Requirement already satisfied: tensorflow-datasets in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (4.9.3)\r\n",
      "Requirement already satisfied: tensorflow-hub>=0.6.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (0.15.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting tensorflow-model-optimization>=0.4.1 (from tf-models-official)\r\n",
      "  Using cached tensorflow_model_optimization-0.7.5-py2.py3-none-any.whl.metadata (914 bytes)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting tensorflow-text~=2.14.0 (from tf-models-official)\r\n",
      "  Using cached tensorflow_text-2.14.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.9 kB)\r\n",
      "Requirement already satisfied: tensorflow~=2.14.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tf-models-official) (2.14.0)\r\n",
      "Collecting tf-slim>=1.1.0 (from tf-models-official)\r\n",
      "  Using cached tf_slim-1.1.0-py2.py3-none-any.whl (352 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting httplib2<1.dev0,>=0.15.0 (from google-api-python-client>=1.6.7->tf-models-official)\r\n",
      "  Using cached httplib2-0.22.0-py3-none-any.whl (96 kB)\r\n",
      "Requirement already satisfied: google-auth<3.0.0.dev0,>=1.19.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from google-api-python-client>=1.6.7->tf-models-official) (2.23.3)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting google-auth-httplib2>=0.1.0 (from google-api-python-client>=1.6.7->tf-models-official)\r\n",
      "  Using cached google_auth_httplib2-0.1.1-py2.py3-none-any.whl.metadata (2.1 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5 (from google-api-python-client>=1.6.7->tf-models-official)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  Using cached google_api_core-2.12.0-py3-none-any.whl.metadata (2.7 kB)\r\n",
      "Collecting uritemplate<5,>=3.0.1 (from google-api-python-client>=1.6.7->tf-models-official)\r\n",
      "  Using cached uritemplate-4.1.1-py2.py3-none-any.whl (10 kB)\r\n",
      "Requirement already satisfied: certifi in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (2023.7.22)\r\n",
      "Requirement already satisfied: python-dateutil in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (2.8.2)\r\n",
      "Requirement already satisfied: requests in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (2.31.0)\r\n",
      "Requirement already satisfied: tqdm in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (4.66.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting python-slugify (from kaggle>=1.3.9->tf-models-official)\r\n",
      "  Using cached python_slugify-8.0.1-py2.py3-none-any.whl (9.7 kB)\r\n",
      "Requirement already satisfied: urllib3 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (2.0.6)\r\n",
      "Requirement already satisfied: bleach in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from kaggle>=1.3.9->tf-models-official) (6.1.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pytz>=2020.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from pandas>=0.22.0->tf-models-official) (2023.3.post1)\r\n",
      "Requirement already satisfied: tzdata>=2022.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from pandas>=0.22.0->tf-models-official) (2023.3)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: absl-py>=1.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (1.4.0)\r\n",
      "Requirement already satisfied: astunparse>=1.6.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (1.6.3)\r\n",
      "Requirement already satisfied: flatbuffers>=23.5.26 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (23.5.26)\r\n",
      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (0.5.4)\r\n",
      "Requirement already satisfied: google-pasta>=0.1.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (0.2.0)\r\n",
      "Requirement already satisfied: h5py>=2.9.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (3.10.0)\r\n",
      "Requirement already satisfied: libclang>=13.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (16.0.6)\r\n",
      "Requirement already satisfied: ml-dtypes==0.2.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (0.2.0)\r\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (3.3.0)\r\n",
      "Requirement already satisfied: packaging in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (23.2)\r\n",
      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (3.20.3)\r\n",
      "Requirement already satisfied: setuptools in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (68.2.2)\r\n",
      "Requirement already satisfied: termcolor>=1.1.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (2.3.0)\r\n",
      "Requirement already satisfied: typing-extensions>=3.6.6 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (4.8.0)\r\n",
      "Requirement already satisfied: wrapt<1.15,>=1.11.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (1.14.1)\r\n",
      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (0.34.0)\r\n",
      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (1.59.0)\r\n",
      "Requirement already satisfied: tensorboard<2.15,>=2.14 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (2.14.1)\r\n",
      "Requirement already satisfied: tensorflow-estimator<2.15,>=2.14.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (2.14.0)\r\n",
      "Requirement already satisfied: keras<2.15,>=2.14.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow~=2.14.0->tf-models-official) (2.14.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: dm-tree~=0.1.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-model-optimization>=0.4.1->tf-models-official) (0.1.8)\r\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (1.1.1)\r\n",
      "Requirement already satisfied: cycler>=0.10 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (0.12.1)\r\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (4.43.1)\r\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (1.4.5)\r\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (3.1.1)\r\n",
      "Requirement already satisfied: importlib-resources>=3.2.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from matplotlib->tf-models-official) (6.1.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pyasn1>=0.1.7 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from oauth2client->tf-models-official) (0.5.0)\r\n",
      "Requirement already satisfied: pyasn1-modules>=0.0.5 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from oauth2client->tf-models-official) (0.3.0)\r\n",
      "Requirement already satisfied: rsa>=3.1.4 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from oauth2client->tf-models-official) (4.9)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting portalocker (from sacrebleu->tf-models-official)\r\n",
      "  Using cached portalocker-2.8.2-py3-none-any.whl.metadata (8.5 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting regex (from sacrebleu->tf-models-official)\r\n",
      "  Using cached regex-2023.10.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting tabulate>=0.8.9 (from sacrebleu->tf-models-official)\r\n",
      "  Using cached tabulate-0.9.0-py3-none-any.whl (35 kB)\r\n",
      "Collecting colorama (from sacrebleu->tf-models-official)\r\n",
      "  Using cached colorama-0.4.6-py2.py3-none-any.whl (25 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting lxml (from sacrebleu->tf-models-official)\r\n",
      "  Using cached lxml-4.9.3-cp39-cp39-manylinux_2_28_x86_64.whl.metadata (3.8 kB)\r\n",
      "Requirement already satisfied: scikit-learn>=0.21.3 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from seqeval->tf-models-official) (1.3.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: array-record in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-datasets->tf-models-official) (0.4.1)\r\n",
      "Requirement already satisfied: click in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-datasets->tf-models-official) (8.1.7)\r\n",
      "Requirement already satisfied: etils>=0.9.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from etils[enp,epath,etree]>=0.9.0->tensorflow-datasets->tf-models-official) (1.5.1)\r\n",
      "Requirement already satisfied: promise in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-datasets->tf-models-official) (2.3)\r\n",
      "Requirement already satisfied: tensorflow-metadata in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-datasets->tf-models-official) (1.14.0)\r\n",
      "Requirement already satisfied: toml in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorflow-datasets->tf-models-official) (0.10.2)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: wheel<1.0,>=0.23.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from astunparse>=1.6.0->tensorflow~=2.14.0->tf-models-official) (0.41.2)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: fsspec in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from etils[enp,epath,etree]>=0.9.0->tensorflow-datasets->tf-models-official) (2023.9.2)\r\n",
      "Requirement already satisfied: zipp in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from etils[enp,epath,etree]>=0.9.0->tensorflow-datasets->tf-models-official) (3.17.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: googleapis-common-protos<2.0.dev0,>=1.56.2 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0.dev0,>=1.31.5->google-api-python-client>=1.6.7->tf-models-official) (1.61.0)\r\n",
      "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from google-auth<3.0.0.dev0,>=1.19.0->google-api-python-client>=1.6.7->tf-models-official) (5.3.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: charset-normalizer<4,>=2 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from requests->kaggle>=1.3.9->tf-models-official) (3.3.0)\r\n",
      "Requirement already satisfied: idna<4,>=2.5 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from requests->kaggle>=1.3.9->tf-models-official) (3.4)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: joblib>=1.1.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from scikit-learn>=0.21.3->seqeval->tf-models-official) (1.3.2)\r\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from scikit-learn>=0.21.3->seqeval->tf-models-official) (3.2.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (1.0.0)\r\n",
      "Requirement already satisfied: markdown>=2.6.8 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (3.5)\r\n",
      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (0.7.1)\r\n",
      "Requirement already satisfied: werkzeug>=1.0.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (3.0.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: webencodings in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from bleach->kaggle>=1.3.9->tf-models-official) (0.5.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting text-unidecode>=1.3 (from python-slugify->kaggle>=1.3.9->tf-models-official)\r\n",
      "  Using cached text_unidecode-1.3-py2.py3-none-any.whl (78 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: requests-oauthlib>=0.7.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (1.3.1)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: importlib-metadata>=4.4 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from markdown>=2.6.8->tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (6.8.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: MarkupSafe>=2.1.1 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from werkzeug>=1.0.1->tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (2.1.3)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: oauthlib>=3.0.0 in /tmpfs/src/tf_docs_env/lib/python3.9/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard<2.15,>=2.14->tensorflow~=2.14.0->tf-models-official) (3.2.2)\r\n",
      "Using cached tf_models_official-2.14.2-py2.py3-none-any.whl (2.7 MB)\r\n",
      "Using cached google_api_python_client-2.103.0-py2.py3-none-any.whl (12.6 MB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cached tensorflow_model_optimization-0.7.5-py2.py3-none-any.whl (241 kB)\r\n",
      "Using cached tensorflow_text-2.14.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.5 MB)\r\n",
      "Using cached Cython-3.0.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\r\n",
      "Using cached immutabledict-3.0.0-py3-none-any.whl (4.0 kB)\r\n",
      "Using cached opencv_python_headless-4.8.1.78-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (49.1 MB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cached pycocotools-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (435 kB)\r\n",
      "Using cached google_api_core-2.12.0-py3-none-any.whl (121 kB)\r\n",
      "Using cached google_auth_httplib2-0.1.1-py2.py3-none-any.whl (9.3 kB)\r\n",
      "Using cached lxml-4.9.3-cp39-cp39-manylinux_2_28_x86_64.whl (8.0 MB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cached portalocker-2.8.2-py3-none-any.whl (17 kB)\r\n",
      "Using cached regex-2023.10.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Installing collected packages: text-unidecode, sentencepiece, py-cpuinfo, gin-config, uritemplate, tf-slim, tensorflow-model-optimization, tabulate, regex, python-slugify, portalocker, opencv-python-headless, lxml, immutabledict, httplib2, Cython, colorama, sacrebleu, oauth2client, kaggle, seqeval, pycocotools, google-auth-httplib2, google-api-core, google-api-python-client, tensorflow-text, tf-models-official\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully installed Cython-3.0.3 colorama-0.4.6 gin-config-0.5.0 google-api-core-2.12.0 google-api-python-client-2.103.0 google-auth-httplib2-0.1.1 httplib2-0.22.0 immutabledict-3.0.0 kaggle-1.5.16 lxml-4.9.3 oauth2client-4.1.3 opencv-python-headless-4.8.1.78 portalocker-2.8.2 py-cpuinfo-9.0.0 pycocotools-2.0.7 python-slugify-8.0.1 regex-2023.10.3 sacrebleu-2.3.1 sentencepiece-0.1.99 seqeval-1.2.2 tabulate-0.9.0 tensorflow-model-optimization-0.7.5 tensorflow-text-2.14.0 text-unidecode-1.3 tf-models-official-2.14.2 tf-slim-1.1.0 uritemplate-4.1.1\r\n",
      "\u001b[33mWARNING: There was an error checking the latest version of pip.\u001b[0m\u001b[33m\r\n",
      "\u001b[0m"
     ]
    }
   ],
   "source": [
    "!pip install tf-models-official"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "e4huSSwyAG_5"
   },
   "source": [
    "### Import Tensorflow and other libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:04.144503Z",
     "iopub.status.busy": "2023-10-17T12:23:04.144235Z",
     "iopub.status.idle": "2023-10-17T12:23:08.677875Z",
     "shell.execute_reply": "2023-10-17T12:23:08.676839Z"
    },
    "id": "jqYXqtjBAJd9"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-10-17 12:23:04.557393: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
      "2023-10-17 12:23:04.557445: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
      "2023-10-17 12:23:04.557482: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "\n",
    "from tensorflow_models import nlp"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "djBQWjvy-60Y"
   },
   "source": [
    "## BERT pretraining model\n",
    "\n",
    "BERT ([Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805)) introduced the method of pre-training language representations on a large text corpus and then using that model for downstream NLP tasks.\n",
    "\n",
    "In this section, we will learn how to build a model to pretrain BERT on the masked language modeling task and next sentence prediction task. For simplicity, we only show the minimum example and use dummy data."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MKuHVlsCHmiq"
   },
   "source": [
    "### Build a `BertPretrainer` model wrapping `BertEncoder`\n",
    "\n",
    "The `nlp.networks.BertEncoder` class implements the Transformer-based encoder as described in [BERT paper](https://arxiv.org/abs/1810.04805). It includes the embedding lookups and transformer layers (`nlp.layers.TransformerEncoderBlock`), but not the masked language model or classification task networks.\n",
    "\n",
    "The `nlp.models.BertPretrainer` class allows a user to pass in a transformer stack, and instantiates the masked language model and classification networks that are used to create the training objectives."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:08.682541Z",
     "iopub.status.busy": "2023-10-17T12:23:08.682076Z",
     "iopub.status.idle": "2023-10-17T12:23:10.449811Z",
     "shell.execute_reply": "2023-10-17T12:23:10.449124Z"
    },
    "id": "EXkcXz-9BwB3"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-10-17 12:23:09.241708: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2211] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
      "Skipping registering GPU devices...\n"
     ]
    }
   ],
   "source": [
    "# Build a small transformer network.\n",
    "vocab_size = 100\n",
    "network = nlp.networks.BertEncoder(\n",
    "    vocab_size=vocab_size, \n",
    "    # The number of TransformerEncoderBlock layers\n",
    "    num_layers=3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0NH5irV5KTMS"
   },
   "source": [
    "Inspecting the encoder, we see it contains few embedding layers, stacked `nlp.layers.TransformerEncoderBlock` layers and are connected to three input layers:\n",
    "\n",
    "`input_word_ids`, `input_type_ids` and `input_mask`.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:10.453824Z",
     "iopub.status.busy": "2023-10-17T12:23:10.453561Z",
     "iopub.status.idle": "2023-10-17T12:23:10.582274Z",
     "shell.execute_reply": "2023-10-17T12:23:10.581302Z"
    },
    "id": "lZNoZkBrIoff"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.keras.utils.plot_model(network, show_shapes=True, expand_nested=True, dpi=48)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:10.586352Z",
     "iopub.status.busy": "2023-10-17T12:23:10.586056Z",
     "iopub.status.idle": "2023-10-17T12:23:11.025871Z",
     "shell.execute_reply": "2023-10-17T12:23:11.025197Z"
    },
    "id": "o7eFOZXiIl-b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/official/nlp/modeling/models/bert_pretrainer.py:112: Classification.__init__ (from official.nlp.modeling.networks.classification) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Classification as a network is deprecated. Please use the layers.ClassificationHead instead.\n"
     ]
    }
   ],
   "source": [
    "# Create a BERT pretrainer with the created network.\n",
    "num_token_predictions = 8\n",
    "bert_pretrainer = nlp.models.BertPretrainer(\n",
    "    network, num_classes=2, num_token_predictions=num_token_predictions, output='predictions')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "d5h5HT7gNHx_"
   },
   "source": [
    "Inspecting the `bert_pretrainer`, we see it wraps the `encoder` with additional `MaskedLM` and `nlp.layers.ClassificationHead` heads."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:11.029511Z",
     "iopub.status.busy": "2023-10-17T12:23:11.029276Z",
     "iopub.status.idle": "2023-10-17T12:23:11.185272Z",
     "shell.execute_reply": "2023-10-17T12:23:11.184372Z"
    },
    "id": "2tcNfm03IBF7"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.keras.utils.plot_model(bert_pretrainer, show_shapes=True, expand_nested=True, dpi=48)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:11.189820Z",
     "iopub.status.busy": "2023-10-17T12:23:11.189559Z",
     "iopub.status.idle": "2023-10-17T12:23:11.332943Z",
     "shell.execute_reply": "2023-10-17T12:23:11.332240Z"
    },
    "id": "F2oHrXGUIS0M"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "lm_output: shape=(2, 8, 100), dtype=tf.float32\n",
      "sentence_output: shape=(2, 2), dtype=tf.float32\n"
     ]
    }
   ],
   "source": [
    "# We can feed some dummy data to get masked language model and sentence output.\n",
    "sequence_length = 16\n",
    "batch_size = 2\n",
    "\n",
    "word_id_data = np.random.randint(vocab_size, size=(batch_size, sequence_length))\n",
    "mask_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "type_id_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "masked_lm_positions_data = np.random.randint(2, size=(batch_size, num_token_predictions))\n",
    "\n",
    "outputs = bert_pretrainer(\n",
    "    [word_id_data, mask_data, type_id_data, masked_lm_positions_data])\n",
    "lm_output = outputs[\"masked_lm\"]\n",
    "sentence_output = outputs[\"classification\"]\n",
    "print(f'lm_output: shape={lm_output.shape}, dtype={lm_output.dtype!r}')\n",
    "print(f'sentence_output: shape={sentence_output.shape}, dtype={sentence_output.dtype!r}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bnx3UCHniCS5"
   },
   "source": [
    "### Compute loss\n",
    "Next, we can use `lm_output` and `sentence_output` to compute `loss`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:11.336520Z",
     "iopub.status.busy": "2023-10-17T12:23:11.336050Z",
     "iopub.status.idle": "2023-10-17T12:23:11.354224Z",
     "shell.execute_reply": "2023-10-17T12:23:11.353589Z"
    },
    "id": "k30H4Q86f52x"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tf.Tensor(5.2983174, shape=(), dtype=float32)\n"
     ]
    }
   ],
   "source": [
    "masked_lm_ids_data = np.random.randint(vocab_size, size=(batch_size, num_token_predictions))\n",
    "masked_lm_weights_data = np.random.randint(2, size=(batch_size, num_token_predictions))\n",
    "next_sentence_labels_data = np.random.randint(2, size=(batch_size))\n",
    "\n",
    "mlm_loss = nlp.losses.weighted_sparse_categorical_crossentropy_loss(\n",
    "    labels=masked_lm_ids_data,\n",
    "    predictions=lm_output,\n",
    "    weights=masked_lm_weights_data)\n",
    "sentence_loss = nlp.losses.weighted_sparse_categorical_crossentropy_loss(\n",
    "    labels=next_sentence_labels_data,\n",
    "    predictions=sentence_output)\n",
    "loss = mlm_loss + sentence_loss\n",
    "\n",
    "print(loss)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wrmSs8GjHxVw"
   },
   "source": [
    "With the loss, you can optimize the model.\n",
    "After training, we can save the weights of TransformerEncoder for the downstream fine-tuning tasks. Please see [run_pretraining.py](https://github.com/tensorflow/models/blob/master/official/legacy/bert/run_pretraining.py) for the full example.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "k8cQVFvBCV4s"
   },
   "source": [
    "## Span labeling model\n",
    "\n",
    "Span labeling is the task to assign labels to a span of the text, for example, label a span of text as the answer of a given question.\n",
    "\n",
    "In this section, we will learn how to build a span labeling model. Again, we use dummy data for simplicity."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "xrLLEWpfknUW"
   },
   "source": [
    "### Build a BertSpanLabeler wrapping BertEncoder\n",
    "\n",
    "The `nlp.models.BertSpanLabeler` class implements a simple single-span start-end predictor (that is, a model that predicts two values: a start token index and an end token index), suitable for SQuAD-style tasks.\n",
    "\n",
    "Note that `nlp.models.BertSpanLabeler` wraps a `nlp.networks.BertEncoder`, the weights of which can be restored from the above pretraining model.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:11.357904Z",
     "iopub.status.busy": "2023-10-17T12:23:11.357352Z",
     "iopub.status.idle": "2023-10-17T12:23:11.887170Z",
     "shell.execute_reply": "2023-10-17T12:23:11.886371Z"
    },
    "id": "B941M4iUCejO"
   },
   "outputs": [],
   "source": [
    "network = nlp.networks.BertEncoder(\n",
    "        vocab_size=vocab_size, num_layers=2)\n",
    "\n",
    "# Create a BERT trainer with the created network.\n",
    "bert_span_labeler = nlp.models.BertSpanLabeler(network)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QpB9pgj4PpMg"
   },
   "source": [
    "Inspecting the `bert_span_labeler`, we see it wraps the encoder with additional `SpanLabeling` that outputs `start_position` and `end_position`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:11.891210Z",
     "iopub.status.busy": "2023-10-17T12:23:11.890962Z",
     "iopub.status.idle": "2023-10-17T12:23:12.036502Z",
     "shell.execute_reply": "2023-10-17T12:23:12.035670Z"
    },
    "id": "RbqRNJCLJu4H"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.keras.utils.plot_model(bert_span_labeler, show_shapes=True, expand_nested=True, dpi=48)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.041356Z",
     "iopub.status.busy": "2023-10-17T12:23:12.040703Z",
     "iopub.status.idle": "2023-10-17T12:23:12.108424Z",
     "shell.execute_reply": "2023-10-17T12:23:12.107758Z"
    },
    "id": "fUf1vRxZJwio"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "start_logits: shape=(2, 16), dtype=tf.float32\n",
      "end_logits: shape=(2, 16), dtype=tf.float32\n"
     ]
    }
   ],
   "source": [
    "# Create a set of 2-dimensional data tensors to feed into the model.\n",
    "word_id_data = np.random.randint(vocab_size, size=(batch_size, sequence_length))\n",
    "mask_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "type_id_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "\n",
    "# Feed the data to the model.\n",
    "start_logits, end_logits = bert_span_labeler([word_id_data, mask_data, type_id_data])\n",
    "\n",
    "print(f'start_logits: shape={start_logits.shape}, dtype={start_logits.dtype!r}')\n",
    "print(f'end_logits: shape={end_logits.shape}, dtype={end_logits.dtype!r}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WqhgQaN1lt-G"
   },
   "source": [
    "### Compute loss\n",
    "With `start_logits` and `end_logits`, we can compute loss:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.112029Z",
     "iopub.status.busy": "2023-10-17T12:23:12.111780Z",
     "iopub.status.idle": "2023-10-17T12:23:12.119652Z",
     "shell.execute_reply": "2023-10-17T12:23:12.119052Z"
    },
    "id": "waqs6azNl3Nn"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tf.Tensor(5.3621416, shape=(), dtype=float32)\n"
     ]
    }
   ],
   "source": [
    "start_positions = np.random.randint(sequence_length, size=(batch_size))\n",
    "end_positions = np.random.randint(sequence_length, size=(batch_size))\n",
    "\n",
    "start_loss = tf.keras.losses.sparse_categorical_crossentropy(\n",
    "    start_positions, start_logits, from_logits=True)\n",
    "end_loss = tf.keras.losses.sparse_categorical_crossentropy(\n",
    "    end_positions, end_logits, from_logits=True)\n",
    "\n",
    "total_loss = (tf.reduce_mean(start_loss) + tf.reduce_mean(end_loss)) / 2\n",
    "print(total_loss)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Zdf03YtZmd_d"
   },
   "source": [
    "With the `loss`, you can optimize the model. Please see [run_squad.py](https://github.com/tensorflow/models/blob/master/official/legacy/bert/run_squad.py) for the full example."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0A1XnGSTChg9"
   },
   "source": [
    "## Classification model\n",
    "\n",
    "In the last section, we show how to build a text classification model.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MSK8OpZgnQa9"
   },
   "source": [
    "### Build a BertClassifier model wrapping BertEncoder\n",
    "\n",
    "`nlp.models.BertClassifier` implements a [CLS] token classification model containing a single classification head."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.123113Z",
     "iopub.status.busy": "2023-10-17T12:23:12.122893Z",
     "iopub.status.idle": "2023-10-17T12:23:12.674009Z",
     "shell.execute_reply": "2023-10-17T12:23:12.673307Z"
    },
    "id": "cXXCsffkCphk"
   },
   "outputs": [],
   "source": [
    "network = nlp.networks.BertEncoder(\n",
    "        vocab_size=vocab_size, num_layers=2)\n",
    "\n",
    "# Create a BERT trainer with the created network.\n",
    "num_classes = 2\n",
    "bert_classifier = nlp.models.BertClassifier(\n",
    "    network, num_classes=num_classes)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8tZKueKYP4bB"
   },
   "source": [
    "Inspecting the `bert_classifier`, we see it wraps the `encoder` with additional `Classification` head."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.677860Z",
     "iopub.status.busy": "2023-10-17T12:23:12.677600Z",
     "iopub.status.idle": "2023-10-17T12:23:12.814483Z",
     "shell.execute_reply": "2023-10-17T12:23:12.813628Z"
    },
    "id": "snlutm9ZJgEZ"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.keras.utils.plot_model(bert_classifier, show_shapes=True, expand_nested=True, dpi=48)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.818382Z",
     "iopub.status.busy": "2023-10-17T12:23:12.818131Z",
     "iopub.status.idle": "2023-10-17T12:23:12.880705Z",
     "shell.execute_reply": "2023-10-17T12:23:12.880048Z"
    },
    "id": "yyHPHsqBJkCz"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "logits: shape=(2, 2), dtype=tf.float32\n"
     ]
    }
   ],
   "source": [
    "# Create a set of 2-dimensional data tensors to feed into the model.\n",
    "word_id_data = np.random.randint(vocab_size, size=(batch_size, sequence_length))\n",
    "mask_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "type_id_data = np.random.randint(2, size=(batch_size, sequence_length))\n",
    "\n",
    "# Feed the data to the model.\n",
    "logits = bert_classifier([word_id_data, mask_data, type_id_data])\n",
    "print(f'logits: shape={logits.shape}, dtype={logits.dtype!r}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "w--a2mg4nzKm"
   },
   "source": [
    "### Compute loss\n",
    "\n",
    "With `logits`, we can compute `loss`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-10-17T12:23:12.884301Z",
     "iopub.status.busy": "2023-10-17T12:23:12.883837Z",
     "iopub.status.idle": "2023-10-17T12:23:12.889624Z",
     "shell.execute_reply": "2023-10-17T12:23:12.889016Z"
    },
    "id": "9X0S1DoFn_5Q"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tf.Tensor([0.7332015 1.3447659], shape=(2,), dtype=float32)\n"
     ]
    }
   ],
   "source": [
    "labels = np.random.randint(num_classes, size=(batch_size))\n",
    "\n",
    "loss = tf.keras.losses.sparse_categorical_crossentropy(\n",
    "    labels, logits, from_logits=True)\n",
    "print(loss)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "mzBqOylZo3og"
   },
   "source": [
    "With the `loss`, you can optimize the model. Please see the [Fine tune_bert](https://www.tensorflow.org/text/tutorials/fine_tune_bert) notebook or the [model training documentation](https://github.com/tensorflow/models/blob/master/official/nlp/docs/train.md) for the full example."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "nlp_modeling_library_intro.ipynb",
   "provenance": [],
   "toc_visible": true
  },
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}