Honor zero-hour PaperBench checkpoint selection - #169
Open
sylvesterkaczmarek wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
target_duration_hr=0as a valid PaperBench checkpoint targetNoneas the sentinel for selecting the latest available checkpointPBTask._select_checkpoint()currently uses a truthiness check when choosing the duration passed toget_file_at_duration(). Because0is falsey, an explicittarget_duration_hr=0is replaced with10000, which selects the latest checkpoint instead of the checkpoint at the start of the run.The configuration type and
get_file_at_duration()both support zero as a valid non-negative duration. This change switches the fallback check tois not None, so zero keeps its documented meaning while the existingNonebehavior remains unchanged.