Skip to content

feat(rl): Filter incomplete trajectories that hit max_tokens limit#160

Open
EvanZhuang wants to merge 2 commits intothinking-machines-lab:mainfrom
EvanZhuang:add_stop_reason_in_rollout_generation
Open

feat(rl): Filter incomplete trajectories that hit max_tokens limit#160
EvanZhuang wants to merge 2 commits intothinking-machines-lab:mainfrom
EvanZhuang:add_stop_reason_in_rollout_generation

Commits

Commits on Dec 10, 2025