fix: keep every task's responses when reloading them from details - #1350
Open
tonycoder-hub wants to merge 1 commit into
Open
Conversation
_load_responses_from_details reassigned model_responses[sampling_method] for each task, so only the last task's responses survived and were then zipped with the documents of all tasks. Concatenate them instead, in the task order used to build sampling_docs. Co-authored-by: Tony Coder <407243179@qq.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
_load_responses_from_detailsreassignedmodel_responses[sampling_method]on every task, so only the last task's responses survived. Those were then zipped with the documents of all tasks when computing metrics.Concatenate every task's responses instead, in the same order used to build
self.sampling_docs.Does not overlap #1345 (
evaluation_tracker.pyfile-name matching). Distinct from #1336–#1345.Test plan
test_responses_of_all_tasks_are_loadedfails on current main (only the last task kept) and passes aftertest_responses_follow_the_document_orderrealigns details to pipeline task order regardless of load order