FineTune_BERT_Model.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/sudama-inc/llm_finetuning/blob/main/FineTune_BERT_Model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ImW5xLg5Ezyo"
      },
      "outputs": [],
      "source": [
        "# https://huggingface.co/transformers/v3.2.0/custom_datasets.html"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install transformers -U"
      ],
      "metadata": {
        "id": "l5ceeO9LhWkU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd"
      ],
      "metadata": {
        "id": "8HNUE5fXIb-W"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge/data\n",
        "data = pd.read_csv(\"/content/drive/MyDrive/Youtube Tutorials/datasets/toxic_commnets.csv\",error_bad_lines=False, engine=\"python\")\n",
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 299
        },
        "id": "ZLuKyvHJ47xK",
        "outputId": "ae5dbe57-baca-44f9-c947-f341a8c6206a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py:2882: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version.\n",
            "\n",
            "\n",
            "  exec(code_obj, self.user_global_ns, self.user_ns)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                 id                                       comment_text  toxic  \\\n",
              "0  0000997932d777bf  Explanation\\nWhy the edits made under my usern...      0   \n",
              "1  000103f0d9cfb60f  D'aww! He matches this background colour I'm s...      0   \n",
              "2  000113f07ec002fd  Hey man, I'm really not trying to edit war. It...      0   \n",
              "3  0001b41b1c6bb37e  \"\\nMore\\nI can't make any real suggestions on ...      0   \n",
              "4  0001d958c54c6e35  You, sir, are my hero. Any chance you remember...      0   \n",
              "\n",
              "   severe_toxic  obscene  threat  insult  identity_hate  \n",
              "0             0        0       0       0              0  \n",
              "1             0        0       0       0              0  \n",
              "2             0        0       0       0              0  \n",
              "3             0        0       0       0              0  \n",
              "4             0        0       0       0              0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-8f0d3e72-856f-4030-839d-b5f293d65809\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>comment_text</th>\n",
              "      <th>toxic</th>\n",
              "      <th>severe_toxic</th>\n",
              "      <th>obscene</th>\n",
              "      <th>threat</th>\n",
              "      <th>insult</th>\n",
              "      <th>identity_hate</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0000997932d777bf</td>\n",
              "      <td>Explanation\\nWhy the edits made under my usern...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>000103f0d9cfb60f</td>\n",
              "      <td>D'aww! He matches this background colour I'm s...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>000113f07ec002fd</td>\n",
              "      <td>Hey man, I'm really not trying to edit war. It...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0001b41b1c6bb37e</td>\n",
              "      <td>\"\\nMore\\nI can't make any real suggestions on ...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0001d958c54c6e35</td>\n",
              "      <td>You, sir, are my hero. Any chance you remember...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8f0d3e72-856f-4030-839d-b5f293d65809')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-8f0d3e72-856f-4030-839d-b5f293d65809 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-8f0d3e72-856f-4030-839d-b5f293d65809');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# data.to_csv(\"/content/drive/MyDrive/Youtube Tutorials/datasets/toxic_commnets.csv\",index=False)"
      ],
      "metadata": {
        "id": "zn7OlLJnwZJH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data['toxic'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5dbrirLG5D0A",
        "outputId": "c64ef77c-2bb8-4243-8b89-66e0e1a3e6cc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    144277\n",
              "1     15294\n",
              "Name: toxic, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = data[['comment_text','toxic']]\n",
        "data = data[0:1000]\n",
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "U2HyJRvG5trP",
        "outputId": "e01ac8ee-cacd-4fcb-921d-21074d9874dc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                        comment_text  toxic\n",
              "0  Explanation\\nWhy the edits made under my usern...      0\n",
              "1  D'aww! He matches this background colour I'm s...      0\n",
              "2  Hey man, I'm really not trying to edit war. It...      0\n",
              "3  \"\\nMore\\nI can't make any real suggestions on ...      0\n",
              "4  You, sir, are my hero. Any chance you remember...      0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-342664ee-790d-4b22-8758-c29059ac53fc\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>comment_text</th>\n",
              "      <th>toxic</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Explanation\\nWhy the edits made under my usern...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>D'aww! He matches this background colour I'm s...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Hey man, I'm really not trying to edit war. It...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>\"\\nMore\\nI can't make any real suggestions on ...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>You, sir, are my hero. Any chance you remember...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-342664ee-790d-4b22-8758-c29059ac53fc')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-342664ee-790d-4b22-8758-c29059ac53fc button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-342664ee-790d-4b22-8758-c29059ac53fc');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import accuracy_score, recall_score, precision_score, f1_score\n",
        "import torch\n",
        "from transformers import TrainingArguments, Trainer\n",
        "from transformers import BertTokenizer, BertForSequenceClassification"
      ],
      "metadata": {
        "id": "s32nl2kn56cH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers import BertTokenizer, BertForSequenceClassification\n",
        "tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')\n",
        "model = BertForSequenceClassification.from_pretrained('bert-base-uncased',num_labels=2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Z1JlB3eYiV8a",
        "outputId": "4f606d36-bba0-4880-e3a2-c59eb25f9727"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.bias', 'cls.predictions.decoder.weight']\n",
            "- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model"
      ],
      "metadata": {
        "id": "WPKswImmYUjO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = model.to('cuda')"
      ],
      "metadata": {
        "id": "nCIO165RiZfC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "sample_data = [\"I am eating\",\"I am playing \"]\n",
        "tokenizer(sample_data, padding=True, truncation=True, max_length=512)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tESWTOfVHEqA",
        "outputId": "a0e86b55-9484-4d50-c9be-aa5db6971a00"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input_ids': [[101, 1045, 2572, 5983, 102], [101, 1045, 2572, 2652, 102]], 'token_type_ids': [[0, 0, 0, 0, 0], [0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1], [1, 1, 1, 1, 1]]}"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X = list(data[\"comment_text\"])\n",
        "y = list(data[\"toxic\"])\n",
        "X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2,stratify=y)\n",
        "X_train_tokenized = tokenizer(X_train, padding=True, truncation=True, max_length=512)\n",
        "X_val_tokenized = tokenizer(X_val, padding=True, truncation=True, max_length=512)"
      ],
      "metadata": {
        "id": "WyWcZBQuid2V"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train_tokenized.keys()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ll_YffE1rrKV",
        "outputId": "9112756a-535e-483a-f767-f10a4a904b89"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['input_ids', 'token_type_ids', 'attention_mask'])"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(X_train_tokenized['attention_mask'][0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "O5TGibGZIAZT",
        "outputId": "a1afaceb-f6c2-480a-f2e1-619a1dc6f1bc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(X_train),len(X_val)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d2bs25fZish6",
        "outputId": "b6d99fb5-803e-437f-9977-c21990b488a4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(800, 200)"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Create torch dataset\n",
        "class Dataset(torch.utils.data.Dataset):\n",
        "    def __init__(self, encodings, labels=None):\n",
        "        self.encodings = encodings\n",
        "        self.labels = labels\n",
        "\n",
        "    def __getitem__(self, idx):\n",
        "        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}\n",
        "        if self.labels:\n",
        "            item[\"labels\"] = torch.tensor(self.labels[idx])\n",
        "        return item\n",
        "\n",
        "    def __len__(self):\n",
        "        return len(self.encodings[\"input_ids\"])"
      ],
      "metadata": {
        "id": "0Dq__AdmjiEh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_dataset = Dataset(X_train_tokenized, y_train)\n",
        "val_dataset = Dataset(X_val_tokenized, y_val)"
      ],
      "metadata": {
        "id": "52bjWWitkMRw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_dataset[5]"
      ],
      "metadata": {
        "id": "gqrFeE7Trgtd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def compute_metrics(p):\n",
        "    print(type(p))\n",
        "    pred, labels = p\n",
        "    pred = np.argmax(pred, axis=1)\n",
        "\n",
        "    accuracy = accuracy_score(y_true=labels, y_pred=pred)\n",
        "    recall = recall_score(y_true=labels, y_pred=pred)\n",
        "    precision = precision_score(y_true=labels, y_pred=pred)\n",
        "    f1 = f1_score(y_true=labels, y_pred=pred)\n",
        "\n",
        "    return {\"accuracy\": accuracy, \"precision\": precision, \"recall\": recall, \"f1\": f1}"
      ],
      "metadata": {
        "id": "rSYfH_aIkOwf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Define Trainer\n",
        "args = TrainingArguments(\n",
        "    output_dir=\"output\",\n",
        "    num_train_epochs=1,\n",
        "    per_device_train_batch_size=8\n",
        "\n",
        ")\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    args=args,\n",
        "    train_dataset=train_dataset,\n",
        "    eval_dataset=val_dataset,\n",
        "    compute_metrics=compute_metrics\n",
        ")"
      ],
      "metadata": {
        "id": "vFcXgFFNkRDP"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.train()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 388
        },
        "id": "topNq2I6kTnX",
        "outputId": "eb8b1262-9301-46b4-f69d-347a47b3539e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/transformers/optimization.py:310: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
            "  FutureWarning,\n",
            "***** Running training *****\n",
            "  Num examples = 800\n",
            "  Num Epochs = 1\n",
            "  Instantaneous batch size per device = 8\n",
            "  Total train batch size (w. parallel, distributed & accumulation) = 8\n",
            "  Gradient Accumulation steps = 1\n",
            "  Total optimization steps = 100\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='100' max='100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [100/100 01:13, Epoch 1/1]\n",
              "    </div>\n",
              "    <table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              " <tr style=\"text-align: left;\">\n",
              "      <th>Step</th>\n",
              "      <th>Training Loss</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "  </tbody>\n",
              "</table><p>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n",
            "\n",
            "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
            "\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "TrainOutput(global_step=100, training_loss=0.2768418312072754, metrics={'train_runtime': 74.1181, 'train_samples_per_second': 10.794, 'train_steps_per_second': 1.349, 'total_flos': 210488844288000.0, 'train_loss': 0.2768418312072754, 'epoch': 1.0})"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.evaluate()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 274
        },
        "id": "Ia14Y_UmN7qM",
        "outputId": "91ff6e21-fdf0-40bf-c501-7ec880bd72a7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "***** Running Evaluation *****\n",
            "  Num examples = 200\n",
            "  Batch size = 8\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='25' max='25' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [25/25 00:06]\n",
              "    </div>\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'transformers.trainer_utils.EvalPrediction'>\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'epoch': 1.0,\n",
              " 'eval_accuracy': 0.945,\n",
              " 'eval_f1': 0.6666666666666667,\n",
              " 'eval_loss': 0.14731189608573914,\n",
              " 'eval_precision': 0.9166666666666666,\n",
              " 'eval_recall': 0.5238095238095238,\n",
              " 'eval_runtime': 7.2372,\n",
              " 'eval_samples_per_second': 27.635,\n",
              " 'eval_steps_per_second': 3.454}"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.set_printoptions(suppress=True)"
      ],
      "metadata": {
        "id": "KX1xAXjhqibr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "text = \"That was good point\"\n",
        "# text = \"go to hell\"\n",
        "inputs = tokenizer(text,padding = True, truncation = True, return_tensors='pt').to('cuda')\n",
        "outputs = model(**inputs)\n",
        "print(outputs)\n",
        "predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)\n",
        "print(predictions)\n",
        "predictions = predictions.cpu().detach().numpy()\n",
        "predictions"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AdVqrPN0kVLY",
        "outputId": "3c63ea34-68f0-4afe-f7e0-235128d8311c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "SequenceClassifierOutput(loss=None, logits=tensor([[ 1.4725, -2.1523]], device='cuda:0', grad_fn=<AddmmBackward0>), hidden_states=None, attentions=None)\n",
            "tensor([[0.9740, 0.0260]], device='cuda:0', grad_fn=<SoftmaxBackward0>)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.9740369 , 0.02596313]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.save_model('CustomModel')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6zGTQP62MbAr",
        "outputId": "a4c7049f-127d-4feb-fc32-4a8abcbb80db"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Saving model checkpoint to CustomModel\n",
            "Configuration saved in CustomModel/config.json\n",
            "Model weights saved in CustomModel/pytorch_model.bin\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# trainer.save_model('/content/drive/MyDrive/Youtube Tutorials/toxic')\n",
        "# model_2 = BertForSequenceClassification.from_pretrained(\"/content/drive/MyDrive/Youtube Tutorials/toxic\")\n",
        "# model_2.to('cuda')"
      ],
      "metadata": {
        "id": "eLnznjr1PYVG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_2 = BertForSequenceClassification.from_pretrained(\"CustomModel\")\n",
        "model_2.to('cuda')"
      ],
      "metadata": {
        "id": "zTu-SoK6MeVJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# text = \"That was good point\"\n",
        "text = \"go to hell\"\n",
        "inputs = tokenizer(text,padding = True, truncation = True, return_tensors='pt').to('cuda')\n",
        "outputs = model_2(**inputs)\n",
        "predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)\n",
        "predictions = predictions.cpu().detach().numpy()\n",
        "predictions"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v8dqYXZwM12Z",
        "outputId": "606bd583-b60c-4279-c1ea-5640ccdee634"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00004367, 0.99995637]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "owBTtpMkPm0l"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}