CPOTrainer - Incorrect handling of different length chosen/rejected p… #4639
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…rompts. on line 495, zip() function has a flag `strict=True`, and only after that we calculate the num_diff_len, which we can not reach in case the chosen and rejected prompt lengths differ by 1 (as zip raises an exception). Therefore, we should take only the first `prompt_len_input_ids` common parts of the prompts, and find length differences afterwards.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
…rompts.
on line 495, zip() function has a flag
strict=True, and only after that we calculate the num_diff_len, which we can not reach in case the chosen and rejected prompt lengths differ by 1 (as zip raises an exception). Therefore, we should take only the firstprompt_len_input_idscommon parts of the prompts, and find the length differences between the prompts afterwards.What does this PR do?
Fixes # issue with handling different length chosen/rejected prompts.