Unable to determine the device handle for GPU0000:4F:00.0: Unknown Error
liuhui0401 opened this issue · comments
Liuhui Wang commented
Question
When I finetuned the llava, I met such a problem "Unable to determine the device handle for GPU0000:4F:00.0: Unknown Error". I finetuned on eight A100 gpu. This problem usually occured after three hours of finetuning. I finetuned on two different servers and this problem occurred. Can anyone please tell me what causes this?