Evaluation with failed samples #195
Unanswered
paverGulyaevich
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi
Looks like if there are failed samples during evaluation the final metrics are not calculated. I can see only
run.jsonl
anderror.jsonl
in the outputs folder. Is there any way to calculate metrics even with the failed samples (as in overall.json)?Beta Was this translation helpful? Give feedback.
All reactions