open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-28 17:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix

Browse source
This commit is contained in:
Oliver 2025-04-28 23:08:11 +01:00
parent a5aaa89de4
commit 39b6f8f7e2
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
training/trainers/ray_grpo_trainer.py
View file

@ -330,7 +330,7 @@ class RayGRPOTrainer(RayPPOTrainer):
batch.batch["token_level_scores"] = reward_tensor
# compute rewards. apply_kl_penalty if available
if config.algorithm.use_kl_in_reward:
if self.config.algorithm.use_kl_in_reward:
batch, kl_metrics = apply_kl_penalty(
batch, kl_ctrl=self.kl_ctrl_in_reward, kl_penalty=self.config.algorithm.kl_penalty
)