Skip to content

Keep the qed_math_env answer-mode reference server-side and stop scoring after done in reasoning_gym_env and finqa_env - #1552

Open
jimmy-holdout wants to merge 3 commits into
openenv:mainfrom
jimmy-holdout:fix/hide-gold-and-end-episodes
Open

Keep the qed_math_env answer-mode reference server-side and stop scoring after done in reasoning_gym_env and finqa_env#1552
jimmy-holdout wants to merge 3 commits into
openenv:mainfrom
jimmy-holdout:fix/hide-gold-and-end-episodes

finqa_env: stop scoring tool calls after the episode ends

9920bc0
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar