BERT classifier fine-tuning with PyTorch, HuggingFace, and Catalyst. Part 1. Intro
In the 1st part of the tutorial we describe the reusable BERT fine-tuning pipeline
I’m sharing the pipeline that I actually use at work (that’s not a Kaggle Notebook anymore) which follows a modular approach, is easy to run and be reproduced.
The follow-up parts of this tutorial cover:
- data preparation for training, from CSV files to PyTorch DataLoaders
- understanding the BERT classifier model by HuggingFace, digging into the code of the transformers library
- running the pipeline with Catalyst and GPUs
5 views
621
193
11 months ago 00:09:11 1
Transformers, explained: Understand the model behind GPT, BERT, and T5
2 years ago 01:22:50 3
DL2022: Трансформер (часть 2)
3 years ago 00:36:30 3
Multi-Topic (Multi-Class) Text Classification Part E: A Deep Learning Model with Embedding Layer
3 years ago 00:10:11 5
Research talk: DeepXML: A deep extreme classification framework for recommending millions of items
3 years ago 00:29:14 4
Text Classification Using BERT & Tensorflow | Deep Learning Tutorial 47 (Tensorflow, Keras & Python)
4 years ago 00:14:34 5
BERT classifier fine-tuning with PyTorch, HuggingFace, and Catalyst. Part 1. Intro
4 years ago 00:51:48 9
BERT classifier fine-tuning with PyTorch, HuggingFace, and Catalyst. Part 4. Training with Catalyst