Open
Conversation
| # Both samples exist, calculate the accuracy | ||
| other_logprob, other_is_correct = self._pending.pop(item_id) | ||
| # Verify that only one of the samples is correct | ||
| assert other_is_correct != is_correct, "Both samples cannot be correct or incorrect at the same time" |
Contributor
There was a problem hiding this comment.
Is this a check of the dataset itself?
Contributor
Author
There was a problem hiding this comment.
No, I rather think of it as sanity-checking that the computation in the task itself works correctly.
src/eval_framework/metrics/loglikelihood/accuracy_loglikelihood.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Prabhu Teja <prabhu.sivaprasad@aleph-alpha-research.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Checklist
/docs/).What type of PR is this? (check all applicable)
Description
PR to match GenQA tasks with OLMES:
HELLASWAG_OLMES(train split),SQuAD_OLMES(OLMES-style prompt with SQuAD-normalized F1),WINOGRANDECloze(partial-evaluation cloze with custom metric)NaturalQsOpen(OLMES prompt format, DROP F1/EM metric, fixed fewshot target formatting bug),DropCompletion_OLMES(added reading comprehension initial prompt)F1SquadNormalized(SQuAD-style F1 with article/punctuation removal),PartialEvalAccuracy(stateful metric pairing two samples per Winogrande item to compute p(suffix | prefix + option))normalize()andtokenize()hooks for subclass customizationAdded/updated tests?
have not been included