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

add use kl param

Browse source
This commit is contained in:
Oliver 2025-04-24 20:42:57 +01:00
parent e39b6b5f27
commit 1ee3b0bbb8
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
training/configs/external_generalisation/math_curriculum_qwen_7b.yaml
View file

@ -155,6 +155,7 @@ algorithm:
gamma: 1.0
lam: 1.0
adv_estimator: grpo
use_kl_in_reward: False
kl_penalty: kl # how to estimate kl divergence
kl_ctrl:
type: fixed