Closed jvhoffbauer closed 1 year ago
That makes sense since batches need to be padded. However, it would make sense to verify that the pad tokens are indeed ignored and you are padding on the correct side. E.g. running two samples separately and in a batch through the pipeline and checking the scores match would be good.
When I use
EleutherAI/pythia-160M
as base-model for my reward model, then running the actual training script fails with the following error. This seems to be caused by GPTNeoXForSequenceClassification requiring a pad token when running in batched mode. Note that I have a reward model (reward_model) that was trained using the examples script and merged with the peft adapter.There is a quick fix by running the following code after initialising the sentiment prediction pipeline to ensure we have the pad token set.
However - I wanted to cross check if this is expected behaviour and the fix is correct.
The full stack trace: