Skip to content

feat(loss): add --pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)#2060

Closed
EazyReal wants to merge 1 commit into
THUDM:mainfrom
EazyReal:upstream-pr/drgrpo-reducer-example
Closed

feat(loss): add --pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)#2060
EazyReal wants to merge 1 commit into
THUDM:mainfrom
EazyReal:upstream-pr/drgrpo-reducer-example

Commits

Commits on Jun 12, 2026