Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Github CI to test metrics integration #14

Merged
merged 14 commits into from
Sep 8, 2023

Conversation

uSaiPrashanth
Copy link
Member

This PR adds github CI to test metrics integration

For now, we trigger it manually. Can be automated if required later...

@uSaiPrashanth uSaiPrashanth self-assigned this Sep 7, 2023
Copy link
Collaborator

@alvin319 alvin319 left a comment

Choose a reason for hiding this comment

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

lgtm - left some small comments

calculate_metrics.py Outdated Show resolved Hide resolved
calculate_metrics.py Show resolved Hide resolved
@@ -242,7 +258,7 @@ def main():

for data_scheme in args.schemes if isinstance(args.schemes, list) else args.schemes.split(","):
LOGGER.info("Loading pre-computed features...")
precomputed_features = load_precomputed_features(data_scheme)
precomputed_features = load_precomputed_features(data_scheme, is_test = str(args.datasets) == "test")
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think we should just put this loop for dataset_name in args.datasets if isinstance(args.datasets, list) else args.datasets.split(",") right outside of the data_scheme loop, then we can calculate is_test directly off of the right dataset_name.

The current implementation would only work if we only run on test datasets

@uSaiPrashanth uSaiPrashanth merged commit 9ba9d92 into EleutherAI:master Sep 8, 2023
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants