Open liuyugeng opened 2 days ago
I think in the compute_loss function of trainer class, you should add num_items_in_batch=None
.
I just upgraded to the latest library (4.46.3) and found this issue.
Oh, you're right. The version of transformers
should be <4.46
, and we used 4.43.0
in our experiments.
Hi, when I try to train the model, it returns the following error.
I just followed the instructions
bash scripts/continual_tofu/idk_ap.sh
.