Notebook example showing how to fine-tune Transformer models using the Transformer Trainer class.
Install the conda environment with
conda env create -f environment.yml
then log into the environment
conda activate transformers-trainer
and run Jupyter notebooks with
CUDA_VISIBLE_DEVICES=X jupyter notebook
where X
is the number of the GPU you want to use for training.
environment.yml
: anaconda environment filetransformers-multiclass.ipynb
: notebook showint the usage of Transformer Trainer for a multiclass problemsimplify_labels.ipynb
: notebook used to simplify the dataset from multilabel to multiclassdata
: folder with multilabel and multiclass versions of the dataset