{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "mount_file_id": "1npJ_m9j344UPF9JAmHTQ-_k6aMVugCpk",
      "authorship_tag": "ABX9TyM0uPiqoelXhWIVmGBY/QDu",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/lloydakresi/toxic_comment_moderator_api/blob/main/Train_Notebook.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": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "R_OdgWC3J90I",
        "outputId": "798bca08-f949-4c70-e6d2-cd28f020492b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/drive/MyDrive\n"
          ]
        }
      ],
      "source": [
        "%cd .."
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!rm -rf toxic_comment_moderator_api"
      ],
      "metadata": {
        "id": "QUk1Q6CEi4HD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!git clone https://github.com/lloydakresi/toxic_comment_moderator_api.git"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Sp0Up667g4Xy",
        "outputId": "b21c7fd0-f539-42e1-992b-0ab8392a52ec"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'toxic_comment_moderator_api'...\n",
            "remote: Enumerating objects: 49, done.\u001b[K\n",
            "remote: Counting objects: 100% (49/49), done.\u001b[K\n",
            "remote: Compressing objects: 100% (28/28), done.\u001b[K\n",
            "remote: Total 49 (delta 23), reused 45 (delta 19), pack-reused 0 (from 0)\u001b[K\n",
            "Receiving objects: 100% (49/49), 32.99 KiB | 3.67 MiB/s, done.\n",
            "Resolving deltas: 100% (23/23), done.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%cd toxic_comment_moderator_api"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XzFpM_OThNor",
        "outputId": "e646206d-06b4-4bd5-c06d-059604892416"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/drive/MyDrive/toxic_comment_moderator_api\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install transformers==5.12.1 datasets==5.0.0 evaluate==0.4.6 accelerate==1.14.0 scikit-learn==1.9.0 iterative-stratification==0.1.9 -q"
      ],
      "metadata": {
        "id": "GscPa1Bihx9H"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!python train.py"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LBmM7I26imWc",
        "outputId": "bd9c3a9f-d3f8-41f3-f09f-c0c0f9986293"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['id', 'comment_text', 'toxic', 'severe_toxic', 'obscene', 'threat', 'insult', 'identity_hate']\n",
            "143613\n",
            "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
            "Map: 100% 143613/143613 [00:43<00:00, 3280.74 examples/s]\n",
            "Map: 100% 15958/15958 [00:05<00:00, 2756.07 examples/s]\n",
            "Loading weights: 100% 100/100 [00:00<00:00, 5538.28it/s]\n",
            "[transformers] \u001b[1mDistilBertForSequenceClassification LOAD REPORT\u001b[0m from: distilbert-base-uncased\n",
            "Key                     | Status     | \n",
            "------------------------+------------+-\n",
            "vocab_layer_norm.bias   | \u001b[38;5;208mUNEXPECTED\u001b[0m | \n",
            "vocab_transform.bias    | \u001b[38;5;208mUNEXPECTED\u001b[0m | \n",
            "vocab_transform.weight  | \u001b[38;5;208mUNEXPECTED\u001b[0m | \n",
            "vocab_projector.bias    | \u001b[38;5;208mUNEXPECTED\u001b[0m | \n",
            "vocab_layer_norm.weight | \u001b[38;5;208mUNEXPECTED\u001b[0m | \n",
            "pre_classifier.bias     | \u001b[31mMISSING\u001b[0m    | \n",
            "pre_classifier.weight   | \u001b[31mMISSING\u001b[0m    | \n",
            "classifier.bias         | \u001b[31mMISSING\u001b[0m    | \n",
            "classifier.weight       | \u001b[31mMISSING\u001b[0m    | \n",
            "\n",
            "Notes:\n",
            "- \u001b[38;5;208mUNEXPECTED:\u001b[0m\t\u001b[3mcan be ignored when loading from different task/architecture; not ok if you expect identical arch.\u001b[0m\n",
            "- \u001b[31mMISSING:\u001b[0m\t\u001b[3mthose params were newly initialized because missing from the checkpoint. Consider training on your downstream task.\u001b[0m\n",
            "True\n",
            "Tesla T4\n",
            "Model device: cuda:0\n",
            "  3% 391/11220 [19:08<8:13:13,  2.73s/it]"
          ]
        }
      ]
    }
  ]
}