Closed MemoryOldTime closed 2 days ago
8张Asend910A,数据集采用的alpaca_en(21.7MB)和alpaca_gpt4_en(41.3MB),利用lora技术进行混合微调
NPROC_PER_NODE=8 NNODES=1 RANK=0
ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 torchrun \ --nproc_per_node $NPROC_PER_NODE \ --nnodes $NNODES \ --node_rank $RANK \ src/train.py examples/train_lora/llama3_lora_sft_ds0.yaml
感觉不太像是数据集不够的原因,模型参数明显也不能改变了,不太像是正常情况,还有什么办法可以解决这种问题吗
No response
Reminder
System Info
8张Asend910A,数据集采用的alpaca_en(21.7MB)和alpaca_gpt4_en(41.3MB),利用lora技术进行混合微调
Reproduction
!/bin/bash
NPROC_PER_NODE=8 NNODES=1 RANK=0
ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 torchrun \ --nproc_per_node $NPROC_PER_NODE \ --nnodes $NNODES \ --node_rank $RANK \ src/train.py examples/train_lora/llama3_lora_sft_ds0.yaml
Expected behavior
感觉不太像是数据集不够的原因,模型参数明显也不能改变了,不太像是正常情况,还有什么办法可以解决这种问题吗![625](https://github.com/hiyouga/LLaMA-Factory/assets/131737760/b46e21d5-6471-4f5d-81a5-f33214f8d46d)
Others
No response