Fix Preference Loss and Refactor for Readability #484
+10
−10
Conversation
This file contains 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
Signed-off-by: Austin Liu <austin362667@gmail.com>
Signed-off-by: Austin Liu <austin362667@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
Thanks to @winglian and @shivam15s noticed and fixed this #481.
This PR suggests negating the preference loss terms to align with the formulas in the docstrings, while maintaining the base preference structure as
nll_loss + preference_loss. This would make our loss computations more consistent since both terms would represent losses to be minimized.This PR also tightened the tolerance in case of encountering a similar issue.
Testing Done
make testto ensure correctnessmake checkstyleto ensure code stylemake test-convergenceto ensure convergence