Task 3 - forward() got an unexpected keyword argument 'labels' #76
-
Hello, for task 3 we are using
This comes as a surprise since this model should already be fine tuned to Squad and we want to explicitly use if for QA (and not for Sequence Classification, which uses the The shape of our training set looks like following:
Please help 🏳 |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
Update: when using a custom training loop with loss and custom optimizer (instead of |
Beta Was this translation helpful? Give feedback.
Update: when using a custom training loop with loss and custom optimizer (instead of
Trainer.train()
) the fine tuning works fine 🤗