[Bugfix] Check all responses when n>1 instead of only the first one#1197
Open
eldarkurtic wants to merge 1 commit intohuggingface:mainfrom
Open
[Bugfix] Check all responses when n>1 instead of only the first one#1197eldarkurtic wants to merge 1 commit intohuggingface:mainfrom
eldarkurtic wants to merge 1 commit intohuggingface:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When generating multiple completions (n>1 in sampling args), there might be cases when some of those completions have crashed/errored/etc and this breaks post-processing of results in lighteval as it attempts to compute metrics on empty responses. This is happening because the "non-emptiness check" is done only on the first completion, and not all of them.
Before this PR (sorry for screenshot; can provide full logs later if needed)
After this PR: post-processing and evals are completed correctly