Skip to content

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

Draft
kayyar-roblox wants to merge 4 commits into
Roblox:mainfrom
kayyar-roblox:mps-grpo-smoke
Draft

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:mainfrom
kayyar-roblox:mps-grpo-smoke

fix: forward beta to GRPOConfig and stop growing the vocab on every run

57670de
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs