{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true, "id": "QeLkrw3YcwXk" }, "outputs": [], "source": [ "%pip install transformers\n", "%pip install torch\n", "%pip install pandas\n", "%pip install scikit-learn\n", "%pip install datasets\n", "%pip install evaluate\n", "%pip install tqdm\n", "%pip install openpyxl" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "PelpmuZhT5E1", "outputId": "581a84b2-c2fa-41bd-90b9-267715404a15" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mounted at /content/drive\n" ] } ], "source": [ "from google.colab import drive\n", "drive.mount('/content/drive')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "cEpWVgUyd0Xw" }, "outputs": [], "source": [ "from transformers import AutoTokenizer, AutoModelForMaskedLM, DataCollatorWithPadding, AutoModelForSequenceClassification, TrainingArguments, Trainer, DataCollator\n", "from datasets import Dataset, DatasetDict\n", "import torch\n", "import pandas as pd\n", "from sklearn.model_selection import train_test_split\n", "import re" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 272, "referenced_widgets": [ "b463fdb9f6e84e16b6ab8669ed2184c8", "590d6b50a1864b77b11bbc0d838efdd8", "1fcfe520a82a4e74aa602d5f5577c800", "cbc816ba8e8443caa9b407c8a8a9bbbe", "95daf36d87d74583b2b0aec60df020cd", "76c856cc8b4746e28e3b89e89b2545dc", "90bfb51397904c06a4d701e511118bd5", "808b60b122d240f5920d3f8a261f7687", "46f314085db64d3c8813564006706937", "9c8ab70717e042af995970733bff333b", "7fbba388113949cfaa15b49a4e3373ad", "70cb331b2d1f4f28826e2464a9d360fc", "aeb6a94508984c84a60f2c0f5f2cfe6d", "feb3279ea02548aaac6888af3156603a", "2da2a80f5e8e4387a967439458b6455b", "06455ff833144975b3e33dc128a2e1e7", "f214b85aaa5a45aebb46dbb4c5e38b68", "a8f15671f7b84a2fa434a410b567954b", "473fc6be317645b5b9aea90d9dc9a0ec", "c45072293e2d4289b334e409a53daa13", "85b001ad3aef40dbbdeedc2275d27eaf", "af95e4e60fd444f0b5225bfc580b0bf6", "f23cd374731144f1ac0d14a65ad33fc7", "ea9ca8c84d25409d9fd5f74da39e03d2", "e3a3c23842114d8b86d944a9543be38a", "7e91bae77abc4c1fa3a69e3d6c6bf21d", "993e8d054ab84c978c49a5d81139ba30", "2df2b56d7b0d42d38aeeb6dcc0e95072", "028c7dfca27c49f99f1e97f5a45dffa3", "6d4f6438eb3341b1bf690bbdfd2cadc9", "f7ccc805e6c3424db54d1ec28c620dbc", "91d68c865e01466d91980ffaf5ef75fa", "67ed03fe39f94e5ba87f0adef1da4ca6", "7ef2ad9ed0cc4fb1a032af05f6b6db7f", "26ce1bea48e84116a3003e443dea982c", "2892dbd6cfd64b46b25d09d00db02f84", "1a2dd92799f940b894eeaccefc0af016", "25d9970aaa2f414c88e4a02acb023fd2", "c87bd4c1516f4acd9b8d304f5ac11ef5", "fe24614f1d304ab2b65b6d5e2d2b01d1", "c2ddec0fb5f04b9ea9dd0e93c1de6d24", "39afc69cf65f467186b933b21f8e2ff4", "b950207798d54923874c9afcb69b0493", "4d5f66e9f2df4ed89628f7cdf919750f" ] }, "id": "2GbEdK5dd5Ty", "outputId": "77d3eb43-c40e-4f4a-b9df-b1e1ca9d55b8" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n", "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", "You will be able to reuse this secret in all of your notebooks.\n", "Please note that authentication is recommended but still optional to access public models or datasets.\n", " warnings.warn(\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "b463fdb9f6e84e16b6ab8669ed2184c8", "version_major": 2, "version_minor": 0 }, "text/plain": [ "tokenizer_config.json: 0%| | 0.00/25.0 [00:00