feat(loss): add --pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)#2060
Closed
EazyReal wants to merge 1 commit into
Closed
feat(loss): add --pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)#2060EazyReal wants to merge 1 commit into
--pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)#2060EazyReal wants to merge 1 commit into