{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook regroups the code sample of the video below, which is a part of the [Hugging Face course](https://huggingface.co/course)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "cellView": "form"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/N9kO52itd0Q?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#@title\n",
    "from IPython.display import HTML\n",
    "\n",
    "HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/N9kO52itd0Q?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Install the Transformers and Datasets libraries to run this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install datasets transformers[sentencepiece]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset, load_metric\n",
    "from transformers import (\n",
    "    AutoTokenizer,\n",
    "    TFAutoModelForSequenceClassification,\n",
    ")\n",
    "\n",
    "raw_datasets = load_dataset(\"glue\", \"mnli\")\n",
    "\n",
    "model_checkpoint = \"distilbert-base-uncased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)\n",
    "\n",
    "\n",
    "def preprocess_function(examples):\n",
    "    return tokenizer(examples[\"premise\"], examples[\"hypothesis\"], truncation=True)\n",
    "\n",
    "\n",
    "tokenized_datasets = raw_datasets.map(preprocess_function, batched=True)\n",
    "model = TFAutoModelForSequenceClassification.from_pretrained(model_checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dataset = tokenized_datasets[\"train\"].to_tf_dataset(\n",
    "    columns=[\"input_ids\", \"labels\"], batch_size=16, shuffle=True\n",
    ")\n",
    "\n",
    "validation_dataset = tokenized_datasets[\"validation_matched\"].to_tf_dataset(\n",
    "    columns=[\"input_ids\", \"labels\"], batch_size=16, shuffle=True\n",
    ")\n",
    "\n",
    "model = TFAutoModelForSequenceClassification.from_pretrained(model_checkpoint)\n",
    "\n",
    "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer='adam')\n",
    "\n",
    "model.fit(train_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for batch in train_dataset:\n",
    "    break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='adam')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = TFAutoModelForSequenceClassification.from_pretrained(\n",
    "    model_checkpoint,\n",
    "    num_labels=3\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='adam')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Debugging the Training Pipeline (TensorFlow)",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}