多卡训练 bash scripts/finetune.sh报错

Facico / Chinese-Vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

https://github.com/Facico/Chinese-Vicuna

Apache License 2.0

4.14k stars 425 forks source link

多卡训练 bash scripts/finetune.sh报错 #245

Open hdjghjb opened 1 year ago

hdjghjb commented 1 year ago

两张2080ti运行bash scripts/finetune.sh报错修改的内容有MODEL_PATH改为已经下载到本地的模型路径，DATA_PATH修改为merge.json

错误信息如下： WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 586 closing signal SIGTERM ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 1 (pid: 587) of binary: /data/anaconda3/envs/vicuna/bin/python

teachyourselfcoding commented 11 months ago

有解决办法了吗？