Skip to content

Conversation

@superdosh
Copy link
Contributor

@superdosh superdosh commented Jul 7, 2025

Addresses #24

@github-actions
Copy link

github-actions bot commented Jul 7, 2025

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

@superdosh superdosh marked this pull request as ready for review July 7, 2025 19:40
@superdosh superdosh requested a review from a team as a code owner July 7, 2025 19:40
@superdosh superdosh requested a review from bkorycki July 7, 2025 19:40
Copy link

@rogthefrog rogthefrog left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just one question. I don't know the code base enough to assess its importance.

@superdosh superdosh merged commit f112c33 into main Jul 8, 2025
3 checks passed
@superdosh superdosh deleted the tag-run-ids branch July 8, 2025 13:48
@github-actions github-actions bot locked and limited conversation to collaborators Jul 8, 2025
for annotator in annotators:
score = score_annotator(annotator, annotations_df, ground_truth_df)
for metric in score:
mlflow.log_metric(f"{annotator}_{metric}", score[metric])
Copy link
Contributor Author

@superdosh superdosh Jul 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I forgot to add a comment in the code, so adding here for posterity: the reason we need this now (and not before) is due to a bug introduced in mlflow 3 (from a newer version of graphql). We can track it here: mlflow/mlflow#16555

Basically if we try to log a nan or inf, it works on the mlflow side with no errors, but the gui crashes.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants