Unverified Commit 41c39b7f authored by Kangrui Wang's avatar Kangrui Wang Committed by GitHub
Browse files

Update debug_qwen0_5_4_gpu_grpo.sh

parent c79caef5

vagen/examples/sokoban/debug_qwen0_5_4_gpu_grpo.sh

+1 −1
Original line number Diff line number Diff line
@@ -40,7 +40,7 @@ python3 -m vagen.trainer.main_ppo \ 
    trainer.critic_warmup=0 \

    trainer.logger=['console','wandb'] \

    trainer.project_name='vagen' \

    trainer.experiment_name='qwen2_5_05b_function_rm' \

    trainer.experiment_name='debug_qwen0_5_4_gpu_grpo' \

    trainer.n_gpus_per_node=4 \

    trainer.nnodes=1 \

    trainer.save_freq=50 \

CRA Git | Maintained and supported by SUSTech CRA and CCSE