Add sample count to the results summary table#1285
Open
ErenAta16 wants to merge 1 commit into
Open
Conversation
The markdown table printed at the end of an evaluation run shows the metric value and its standard error, but not how many samples the metric was computed on. A task that silently evaluated zero (or very few) samples, for example because of a misconfigured hf_filter or split name, rendered the same as a task that ran normally and scored zero on every item. There was no way to tell the two apart from the table alone. DetailsLogger already records one Detail entry per evaluated sample through details_logger.log(), so aggregate() now also stores that count on each task's CompiledDetail as num_samples, along with the total across all tasks on CompiledDetailOverAllTasks. make_results_table reads the count from summary_tasks and adds a Samples column, falling back to a blank value for callers that do not pass summary_tasks at all, so existing callers keep working unchanged. Fixes huggingface#804
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The markdown table printed at the end of an evaluation run shows the metric value and its standard error, but not how many samples the metric was computed on. A task that silently evaluated zero (or very few) samples, for example because of a misconfigured hf_filter or split name, rendered the same as a task that ran normally and scored zero on every item. There was no way to tell the two apart from the table alone.
DetailsLogger already records one Detail entry per evaluated sample through details_logger.log(), so aggregate() now also stores that count on each task's CompiledDetail as num_samples, along with the total across all tasks on CompiledDetailOverAllTasks. make_results_table reads the count from summary_tasks and adds a Samples column, falling back to a blank value for callers that do not pass summary_tasks at all, so existing callers keep working unchanged.
Fixes #804