fix: change grpo default to use 64 prompts per step and 32 generation…#111
Merged
parthchadha merged 2 commits intomainfrom Apr 1, 2025
Merged
fix: change grpo default to use 64 prompts per step and 32 generation…#111parthchadha merged 2 commits intomainfrom
parthchadha merged 2 commits intomainfrom
