open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-25 17:10:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

cfg

Browse source
This commit is contained in:
Oliver 2025-04-22 20:34:37 +01:00
parent 1ccd62bc1a
commit 1343bcf63e
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
training/configs/external_generalisation/math_curriculum_qwen_7b.yaml
View file

@ -90,7 +90,7 @@ actor_rollout_ref:
grad_clip: 1.0
clip_ratio: 0.2
entropy_coeff: 0.001
use_kl_loss: True # True for GRPO
use_kl_loss: False # True for GRPO
kl_loss_coef: 0.001 # for grpo
kl_loss_type: low_var_kl # for grpo
ppo_epochs: 1