course/videos/push_to_hub_tf.ipynb

{
 "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/pUh5cGmNV8Y?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/pUh5cGmNV8Y?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 huggingface_hub import notebook_login\n",
    "\n",
    "notebook_login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset, load_metric\n",
    "\n",
    "raw_datasets = load_dataset(\"glue\", \"cola\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "raw_datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "model_checkpoint = \"bert-base-cased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def preprocess_function(examples):\n",
    "    return tokenizer(examples[\"sentence\"], truncation=True)\n",
    "\n",
    "tokenized_datasets = raw_datasets.map(preprocess_function, batched=True)\n",
    "\n",
    "tokenized_datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import DataCollatorWithPadding\n",
    "\n",
    "collator = DataCollatorWithPadding(tokenizer=tokenizer,\n",
    "                                   return_tensors='tf')\n",
    "\n",
    "train_dataset = tokenized_datasets['train'].to_tf_dataset(\n",
    "    columns=['attention_mask', 'input_ids', 'labels', 'token_type_ids'],\n",
    "    collate_fn=collator,\n",
    "    batch_size=32,\n",
    "    shuffle=True\n",
    ")\n",
    "validation_dataset = tokenized_datasets['validation'].to_tf_dataset(\n",
    "    columns=['attention_mask', 'input_ids', 'labels', 'token_type_ids'],\n",
    "    collate_fn=collator,\n",
    "    batch_size=32,\n",
    "    shuffle=False\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import TFAutoModelForSequenceClassification\n",
    "\n",
    "model = TFAutoModelForSequenceClassification.from_pretrained(model_checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AdamWeightDecay\n",
    "\n",
    "optimizer = AdamWeightDecay(2e-5, weight_decay_rate=0.01)\n",
    "\n",
    "model.compile(optimizer=optimizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import PushToHubCallback\n",
    "\n",
    "callbacks = [PushToHubCallback(\"model_output/\", \n",
    "                               tokenizer=tokenizer,\n",
    "                               hub_model_id=\"bert-fine-tuned-cola\")]\n",
    "\n",
    "model.fit(train_dataset, validation_data=validation_dataset, epochs=2, callbacks=callbacks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.push_to_hub(\"bert-fine-tuned-cola\", commit_message=\"End of training\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "label_names = raw_datasets[\"train\"].features[\"label\"].names\n",
    "label_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.config.id2label = {str(i): lbl for i, lbl in enumerate(label_names)}\n",
    "model.config.label2id = {lbl: str(i) for i, lbl in enumerate(label_names)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "repo_name = \"bert-fine-tuned-cola\"\n",
    "model.config.push_to_hub(repo_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "loaded_model = TFAutoModelForSequenceClassification.from_pretrained('Rocketknight1/bert-fine-tuned-cola')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "The push to hub API (TensorFlow)",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}