[BUG/Help] 在bash evaluate.sh的时候报错 <title>OSError: Can't load the configuration of './output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000'. If you were trying to load it from 'https://huggingface.co/models'

[jingtian11]

Is there an existing issue for this?

• [X] I have searched the existing issues

Current Behavior

OSError: Can't load the configuration of './output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000' is the correct path to a directory containing a config.json file

Expected Behavior

求问各位大佬怎么解决一下啊~~~ 这里要换成自己的路径嘛

Steps To Reproduce

train已经完成，在evalute的时候报错

Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :

Anything else?

No response

[duzx16]

请确保./output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000这个目录是存在的，不然的话要换成你微调后的checkpoint目录，在evaluate.sh里面

[jingtian11]

请确保./output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000这个目录是存在的，不然的话要换成你微调后的checkpoint目录，在evaluate.sh里面

好的好的，已经解决啦~！！！ 太感谢了

[BLAIR-wy]

请问是怎么解决的呀？我也遇到了这个问题。 是要改train.sh里面的什么参数吗？

[BLAIR-wy]

请确保./output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000这个目录是存在的，不然的话要换成你微调后的checkpoint目录，在evaluate.sh里面

请问这个chekpoint是自动生成的吧？ 我运行bash train.sh之后 没有找到checkpoint文件是什么原因呢