Bin Wang comments

Repositories
Issues
Comments

Results 13 comments of


                                            Bin Wang

LLama RuntimeError: CUDA error: device-side assert triggered

@YSLLYW Yes. I figured it out. Should add torchrun.

training results of alpaca-lora 7b and original llama 7b

I tried to fine-tune with my own dataset. Similarly, it seems not learning much. Should I adjust the learning rate or parameters for LORA? Any advice?

Error running model.train()

@Chilicy I have solved it. I cannot remember how. I will check it tomorrow and back to you.