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 loss_agg_mode

Browse source
This commit is contained in:
Oliver 2025-04-24 20:46:37 +01:00
parent 1ee3b0bbb8
commit 37b88d194b
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

@ -86,6 +86,7 @@ actor_rollout_ref:
ppo_max_token_len_per_gpu: 49152 # n * ${data.max_prompt_length} + ${data.max_response_length}
grad_clip: 1.0
clip_ratio: 0.2
loss_agg_mode: "token-mean" # / "seq-mean-token-sum" / "seq-mean-token-mean"
entropy_coeff: 0.001
use_kl_loss: False # True for GRPO
kl_loss_coef: 0.001 # for grpo