open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-23 16:55:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add grpo launch script

Browse source
This commit is contained in:
Andreas Koepf 2025-02-17 20:52:03 +00:00
parent b1e07b7782
commit c40069e616
4 changed files with 212 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/veRL/launch_on_4gpu.sh
View file

@ -6,4 +6,4 @@ export ROLLOUT_TP_SIZE=2
export EXPERIMENT_NAME=chain_sum_llama
export VLLM_ATTENTION_BACKEND=XFORMERS
bash ./train.sh
bash ./train_grpo.sh