Skip to content

train_ppo_ray.py: unrecognized arguments #1

@YuZhiyin

Description

@YuZhiyin

Hi, thank you for your great work!

I was trying to run the training using the script:

sh examples/scripts/train_reinforce_qwen_ray_riv.sh

However, I encountered the following error:

train_ppo_ray.py: error: unrecognized arguments: --logging_path /CoVo/run_outputs/riv/qwen_riv.jsonl --enable_accuracy_filter --save_output_path /CoVo/run_outputs/riv --intrinsic_reward riv

It seems that the current version of train_ppo_ray.py does not recognize these arguments. Just wondering — could it be that the updated version of train_ppo_ray.py with support for these arguments hasn’t been included in the open-source release yet?

Would you mind checking if that file was accidentally left out?

Thanks again for your amazing work, and looking forward to your reply!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions