-
Notifications
You must be signed in to change notification settings - Fork 906
Open
Labels
bugSomething isn't workingSomething isn't working
Description
Describe the bug
问题1:在使用ppo训练Atom-7Bchat模型时,设置--lora_target_modules ALL \
报错,若指定名称则不报错,--lora_target_modules o_proj,up_proj,down_proj,v_proj,k_proj,gate_proj,q_proj \
问题2:在使用ppo训练Atom-7Bchat模型时,使用DDP+MP训练,如下图,报错。AttributeError: 'DistributedDataParallel' object has no attribute 'policy'
Your hardware and system info
ms-swift==2.6.0dev0
pytorch==2.4.0+cu121
python==3.11.10
CUDA==12.1
trl==0.11.4
transformers==4.45.2
GPU:H800-80G
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't working