Skip to content

[RL] Fix loss: use global token normalization instead of per-example#2376

Merged
AlienKevin merged 3 commits intomainfrom
kevin/rl-fix-regression
Jan 19, 2026
Merged

[RL] Fix loss: use global token normalization instead of per-example#2376
AlienKevin merged 3 commits intomainfrom
kevin/rl-fix-regression

Commits

Commits on Jan 18, 2026

Commits on Jan 19, 2026