Commit 12da24c6 authored by jameskrw's avatar jameskrw
Browse files

updated trainer yaml

parent 5711b0fb
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -130,6 +130,7 @@ critic:
  shuffle: ${actor_rollout_ref.actor.shuffle}
  grad_clip: 1.0
  cliprange_value: 0.5
  use_reward_mask: False

reward_model:
  enable: False