Skip to content

Merge remote-tracking branch 'origin/grpo-metrics' into gspo

15ae8d6
Select commit
Loading
Failed to load commit list.
Open

gspo: GSPO loss + DeepSpeed parity fixes (loss/grad divisors, SDP, fp32_lm_head, docs_per_step, temperature) #502

Merge remote-tracking branch 'origin/grpo-metrics' into gspo
15ae8d6
Select commit
Loading
Failed to load commit list.

There are no checks for this commit