open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-27 17:23:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

cfg

Browse source
This commit is contained in:
Oliver 2025-04-29 09:03:19 +01:00
parent fe479916bf
commit be28d6f5f0
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
training/configs/external_generalisation/math_curriculum_qwen_7b.yaml
View file

@ -61,9 +61,9 @@ actor_rollout_ref:
use_remove_padding: True
actor:
strategy: fsdp # This is for backward-compatibility
ppo_mini_batch_size: 16
ppo_mini_batch_size: 8
ppo_micro_batch_size: null # will be deprecated, use ppo_micro_batch_size_per_gpu
ppo_micro_batch_size_per_gpu: 16
ppo_micro_batch_size_per_gpu: 8
use_dynamic_bsz: False
ppo_max_token_len_per_gpu: 49152 # n * ${data.max_prompt_length} + ${data.max_response_length}
grad_clip: 1.0