Skip to content

Add final score summary and submission ID logging #36

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.

Sign up for GitHub

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

Open
ScuttleBot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add final score summary and submission ID logging #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions scripts/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -620,6 +620,12 @@ def main():
output_path = output_dir / f"{run_id}_{model_slug}.json"
output_path.write_text(json.dumps(aggregate, indent=2), encoding="utf-8")

# Calculate and log final score summary
total_score = sum(grades_by_task_id[tid]["mean"] for tid in grades_by_task_id)
max_score = float(len(grades_by_task_id)) # Each task has max_score of 1.0
score_pct = (total_score / max_score * 100) if max_score > 0 else 0
logger.info("📊 Final score: %.2f/%.0f (%.1f%%)", total_score, max_score, score_pct)

logger.info("Saved results to %s", output_path)
_log_efficiency_summary(efficiency, grades_by_task_id)
if args.no_upload:
Expand All @@ -629,6 +635,8 @@ def main():
from lib_upload import UploadError, upload_results

result = upload_results(output_path, official_key=args.official_key)
if result.submission_id:
logger.info("Submission ID: %s", result.submission_id)
if result.rank is not None:
logger.info("Uploaded to leaderboard: rank #%s", result.rank)
if result.leaderboard_url:
Expand Down