How to set input to validate of T5 Model

I’m fintuning T5 for superglue datasets.

Now, I use first half of ‘validation’ set as validation set and the second half of ‘validation’ set as test set.

I’m little bit confused of how to pass decoder_input_ids on validation step.

For example,
input_ids, attention_mask could be obtained from tokenize("My model outperformed baseline models").
And in my opinion, I should give just start token as decoder_input_ids with the variables above to forward() . Is it correct?
This results in the length of the output become 1(same as start token).
Do I need to just pass tokenized ‘labels’ without decoder_input_ids like in training step?

And I’m not sure if I need to use generate() instead of forward().

Hey @kwonmha :wave: Have you seen our examples? This one, focused on GLUE, may give you the answers you need :slight_smile: