A practical Python Coding Guide In this guide I train RoBERTa using PyTorch Lightning on a Multilabel classification task. In particular the unhealthy comment corpus this creates a language model that can classify whether an online comment contains attributes such as sarcasm, hostility or dismissiveness.

TUTORIAL NOTEBOOK
https://colab.research.google.com/dri...
remember to press copy to drive to save a copy of the notebook for yourself

Intro: 00:00:00
Video / project outline: 00:00:27
Getting Google Colab set up: 00:02:00
Imports: 00:03:23
Inspect data: 00:07:05
Pytorch dataset: 00:11:15
Pytorch lightning data module: 00:27:08
Creating the model / classifier: 00:35:45
Training and evaluating model: 01:07:30

This series attempts to offer a casual guide to Hugging Face and Transformer models focused on implementation rather than theory. Let me know if you enjoy them! Will be doing future videos on computer vision if that is something people are interested in, let me know in the comments :)

Research material for theory
RoBERTa paper: https://arxiv.org/abs/1907.11692
HuggingFace: https://huggingface.co/
Unhealthy Comment Corpus paper: https://arxiv.org/abs/2010.07410

Check out my website: https://www.rupert.digital