{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "te5uCzPlhBWx" }, "source": [ "# Processing the data (PyTorch)" ] }, { "cell_type": "markdown", "metadata": { "id": "eiQ3FKJDhBW0" }, "source": [ "Install the Transformers, Datasets, and Evaluate libraries to run this notebook." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "HedrkDuchBW2" }, "outputs": [], "source": [ "#let's install the necessary libraries from Hugging Face\n", "!pip install datasets evaluate transformers[sentencepiece] transformers[torch]" ] }, { "cell_type": "code", "source": [ "from huggingface_hub import notebook_login\n", "#authenticate into the huggin face\n", "notebook_login()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 145, "referenced_widgets": [ "2459586b900d4972893416101cf66518", "bb63af0e6e2d44d39dea0c7fb50f2675", "b84acaf57645444a93e8344e62b02f37", "0adacec9605245e8813c1eb6c375f97c", "3556f7c20dd942d9845a172d2fb3a308", "c9c4f33186b34af5bfe4b23f5a94cd92", "d9fce65fdc0f4f4e99511a95049b0627", "1dfa79c17ca34ccb8a15887162536305", "20b45c6e63d94306a2cd368e6dfc0719", "7853cc389609486e9774a6327cbc6d7f", "0bfa8f38be0c4d5e8b1a8f2a21623e2f", "f363053a53f442379a9be069597c70dc", "1c90fe7a114140a9b32d8107c2af011c", "b45e9bbed2c34078813f4d8be11ba856", "784ba2ebff4d451485ba312e0dd065e7", "74757608b6d945b186ce03761a04a067", "6f292a0a27234aaebaa90c47edbaa6bd", "d35e9d78443840a6af111a3e3245184d", "589080843ecd489488d86c10bc3c3d67", "404e6261b69646be85dd78a0fb1dc3cc", "adafd48f91e54326a4a5b2bb297e3d47", "56a61a4c28de4eb9833e571d4067c4c4", "954f23b0ee9249df81dd30725c9954b0", "ec75914e1c264260a9f573728880474a", "e998f2b2d75d4f3887c59669603793df", "eea3bf1ec05c4ba28cd5f1baa44bcfd8", "1b22a95ee6ff4fdca56a966d35c46ddf", "83c197270ac54969af02fa998fec28f1", "21453473c9f04ef992fe35419f6afff9", "3980e52353a14d538c1dc4b1b45d1396", "1fa7b92f0588403bb146f602942baea6", "20169140dbe04320b1a7d090d738f273" ] }, "id": "Z4IolwVzaQQh", "outputId": "7f4c4beb-0cdf-4549-cfb9-6496f50c7118" }, "execution_count": 137, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "VBox(children=(HTML(value='
Epoch | \n", "Training Loss | \n", "Validation Loss | \n", "Accuracy | \n", "Precision | \n", "Recall | \n", "F1 | \n", "
---|---|---|---|---|---|---|
1 | \n", "No log | \n", "1.137511 | \n", "0.774704 | \n", "0.730148 | \n", "0.774704 | \n", "0.744985 | \n", "
2 | \n", "No log | \n", "0.559548 | \n", "0.885375 | \n", "0.867484 | \n", "0.885375 | \n", "0.872829 | \n", "
3 | \n", "No log | \n", "0.430789 | \n", "0.920949 | \n", "0.906086 | \n", "0.920949 | \n", "0.910576 | \n", "
" ] }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, msg_start, len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, msg_start, len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, msg_start, len(result))\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "TrainOutput(global_step=339, training_loss=1.01418788313514, metrics={'train_runtime': 138.9845, 'train_samples_per_second': 19.513, 'train_steps_per_second': 2.439, 'total_flos': 245512156913712.0, 'train_loss': 1.01418788313514, 'epoch': 3.0})" ] }, "metadata": {}, "execution_count": 142 } ] }, { "cell_type": "code", "source": [ "#it's good. Let's push the model to the hugging face hub\n", "trainer.push_to_hub()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 70 }, "id": "DxFz2gWSMUI6", "outputId": "9e83f368-3084-4168-c828-1665b934e769" }, "execution_count": 143, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "CommitInfo(commit_url='https://huggingface.co/Marcuswas/bert-drug-review-to-condition/commit/d6f99808a6fad08574389e154a44694bbd24ad5d', commit_message='End of training', commit_description='', oid='d6f99808a6fad08574389e154a44694bbd24ad5d', pr_url=None, pr_revision=None, pr_num=None)" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" } }, "metadata": {}, "execution_count": 143 } ] } ], "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "language_info": { "name": "python" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "2459586b900d4972893416101cf66518": { "model_module": "@jupyter-widgets/controls", "model_name": "VBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "VBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "VBoxView", "box_style": "", "children": [ "IPY_MODEL_adafd48f91e54326a4a5b2bb297e3d47", "IPY_MODEL_56a61a4c28de4eb9833e571d4067c4c4", "IPY_MODEL_954f23b0ee9249df81dd30725c9954b0", "IPY_MODEL_ec75914e1c264260a9f573728880474a" ], "layout": "IPY_MODEL_d9fce65fdc0f4f4e99511a95049b0627" } }, "bb63af0e6e2d44d39dea0c7fb50f2675": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1dfa79c17ca34ccb8a15887162536305", "placeholder": "", "style": "IPY_MODEL_20b45c6e63d94306a2cd368e6dfc0719", "value": "