Skip to content

fix: use mean().mean() for console metrics to match wandb #2056

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

Merged
mikasenghaas merged 1 commit into from
Mar 20, 2026
Merged

fix: use mean().mean() for console metrics to match wandb #2056

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
7 changes: 6 additions & 1 deletion src/prime_rl/orchestrator/orchestrator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -791,7 +791,12 @@ def compute_solve_rates(df):
step=progress.step,
)

step_message = f"Step {progress.step} | Time: {step_time:.2f}s | Reward: {results_df.reward.mean():.4f} |{f' Val. Reward: {val_results_df.reward.mean():.4f} |' if val_results_df is not None else ''} Seq. Length: {results_df.groupby('example_id').seq_len.mean().mean():.1f} tokens/sample | Async Level: {scheduler.async_level} | Max. Off-Policy Level: {scheduler.max_off_policy_level}"
reward_mean = by_example.reward.mean().mean()
val_reward_str = ""
if val_results_df is not None:
val_reward_mean = val_results_df.groupby("example_id").reward.mean().mean()
val_reward_str = f" Val. Reward: {val_reward_mean:.4f} |"
step_message = f"Step {progress.step} | Time: {step_time:.2f}s | Reward: {reward_mean:.4f} |{val_reward_str} Seq. Length: {by_example.seq_len.mean().mean():.1f} tokens/sample | Async Level: {scheduler.async_level} | Max. Off-Policy Level: {scheduler.max_off_policy_level}"
logger.success(step_message)

# Increment step
Expand Down
Loading