course/videos/mlm_processing.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/8PmhEIXhBvI?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/8PmhEIXhBvI?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\n",
    "\n",
    "raw_datasets = load_dataset(\"wikitext\", \"wikitext-2-raw-v1\")\n",
    "raw_datasets[\"train\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset\n",
    "from transformers import AutoTokenizer\n",
    "\n",
    "raw_datasets = load_dataset(\"imdb\")\n",
    "raw_datasets = raw_datasets.remove_columns(\"label\")\n",
    "\n",
    "model_checkpoint = \"distilbert-base-cased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)\n",
    "context_length = 128\n",
    "\n",
    "def tokenize_pad_and_truncate(texts):\n",
    "    return tokenizer(texts[\"text\"], truncation=True, padding=\"max_length\", max_length=context_length)\n",
    "\n",
    "tokenized_datasets = raw_datasets.map(tokenize_pad_and_truncate, batched=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def tokenize_and_chunk(texts):\n",
    "    return tokenizer(\n",
    "        texts[\"text\"], truncation=True, max_length=context_length,\n",
    "        return_overflowing_tokens=True\n",
    "    )\n",
    "\n",
    "tokenized_datasets = raw_datasets.map(\n",
    "    tokenize_and_chunk, batched=True, remove_columns=[\"text\"]\n",
    ")\n",
    "\n",
    "len(raw_datasets[\"train\"]), len(tokenized_datasets[\"train\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def tokenize_and_chunk(texts):\n",
    "    all_input_ids = []\n",
    "    for input_ids in tokenizer(texts[\"text\"])[\"input_ids\"]:\n",
    "        all_input_ids.extend(input_ids)\n",
    "        all_input_ids.append(tokenizer.eos_token_id)\n",
    "    \n",
    "    chunks = []\n",
    "    for idx in range(0, len(all_input_ids), context_length):\n",
    "        chunks.append(all_input_ids[idx: idx + context_length])\n",
    "    return {\"input_ids\": chunks}\n",
    "\n",
    "tokenized_datasets = raw_datasets.map(tokenize_and_chunk, batched=True, remove_columns=[\"text\"])\n",
    "\n",
    "len(raw_datasets[\"train\"]), len(tokenized_datasets[\"train\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import DataCollatorForLanguageModeling\n",
    "\n",
    "data_collator = DataCollatorForLanguageModeling(tokenizer, mlm_probability=0.15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Data processing for Masked Language Modeling",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}