njallskarp / finetune-qa-powerset

Finetuning BERT models on a powerset of different linguistic domains
https://lvl.ru.is/
5 stars 0 forks source link

Feat/init td #52

Closed lsig closed 1 year ago

lsig commented 1 year ago

Making DataLoader for model

In this PR I completed the training_datasets/init.py where i make all the different DataLoaders for each set in the powerset of domains. I also had to change the run_training function a little bit to match the data_format, but no functionality was changed.

Testing