OpenLLMAI / OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
https://openrlhf.readthedocs.io/
Apache License 2.0
1.71k stars 160 forks source link

启用PPO Ray后无响应 #292

Closed victorShawFan closed 1 month ago

victorShawFan commented 1 month ago

使用ray start命令的反应:

image

运行train_ppo_llama.sh后的反应

image
victorShawFan commented 1 month ago
image

脚本修改情况

hijkzzz commented 1 month ago

可能是 脚本目录下 文件太多 ray 一直在打包上传文件 如果有大文件建议移出 openrlhf 目录

victorShawFan commented 1 month ago

是这个问题,已解决 thanks