{ "cells": [ { "cell_type": "markdown", "id": "dea00c9e-ab6a-4a56-8e91-782b06002f6c", "metadata": { "id": "dea00c9e-ab6a-4a56-8e91-782b06002f6c" }, "source": [ "# Fine-tuning a BERT model with skorch and Hugging Face" ] }, { "cell_type": "markdown", "id": "11b4d0cc-40c5-48a9-bd52-fdd522498acf", "metadata": { "id": "11b4d0cc-40c5-48a9-bd52-fdd522498acf" }, "source": [ "In this notebook, we follow the fine-tuning guideline from [Hugging Face documentation](https://huggingface.co/docs/transformers/training). Please check it out if we you want to know more about BERT and fine-tuning. Here, we assume that you're familiar with the general ideas.\n", "\n", "You will learn how to:\n", "- integrate the [Hugging Face transformers](https://huggingface.co/docs/transformers/index) library with skorch\n", "- use skorch to fine-tune a BERT model on a text classification task\n", "- use skorch with the [Hugging Face accelerate](https://huggingface.co/docs/accelerate/index) library for automatic mixed precision (AMP) training" ] }, { "cell_type": "markdown", "id": "922bfcd7", "metadata": { "id": "922bfcd7" }, "source": [ "
\n", "\n", " Run in Google Colab \n", " | \n", "View source on GitHub |