fix: forward beta to GRPOConfig (GRPO ran with no KL term) and stop growing the vocab every run - #96

fix: forward beta to GRPOConfig (GRPO ran with no KL term) and stop growing the vocab every run#96

kayyar-roblox wants to merge 4 commits into

Roblox:mainRoblox/FAI-RL:mainfrom

kayyar-roblox:mps-grpo-smokekayyar-roblox/FAI-RL:mps-grpo-smokeCopy head branch name to clipboard