Open iawen opened 1 year ago
This is a strange problem. I think you can do a small experiment to fine-tune the model with Code Alpaca and check whether the same problem exists. Maybe just fine-tune 1 epoch, 512 seqlen.
This is a strange problem. I think you can do a small experiment to fine-tune the model with Code Alpaca and check whether the same problem exists. Maybe just fine-tune 1 epoch, 512 seqlen.
How long would it take to fine-tune on an 8*A100 40G machine? I have 78,000 rows of data?
Hi, hello, I made fine-tuning based on WizardLM/WizardCoder-15B-V1.0, I trained the machine to be 8*V100 32G, trained for 22 hours, and then tested with checkpoint 1600
But the effect is very unsatisfactory, as if the model does not do any reasoning at all, can I help see what the problem is?
The training script I used is as follows:
The trained dataset is as follows:![image](https://github.com/nlpxucan/WizardLM/assets/25651000/31093793-fba6-464f-a7f9-034146769af2)
Neither input nor output have line breaks, which affects the effect of finetune??!