search

rui-ye / OpenFedLLM

Apache License 2.0
311 stars 47 forks source link

Need help with evaluation #23

Open xavi0007 opened 3 months ago

xavi0007 commented 3 months ago

Thanks to the authors for contributing OpenFedLLM to the open source community. Currently, I finished training the model using the default run_sft.sh script, and save to model to the output file, checkpoint-XX. When I try to use the evaluation script and loading the checkpoint path, I'm not able to run due to some config error (Can't load the configuration of , 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 is the correct path to a directory containing a config.json file).

Any help or advice?

xavi0007 commented 3 months ago

I also could not run merge and unload, as its not able to find adapter_config even though its in the file.

motigrez commented 3 months ago

Sorry for the late response. Based on your description, we initially suspect that the model checkpoint might not have been saved correctly during training. Please ensure that the contents of your checkpoint-XX folder match those shown in the image below. If there are any missing files, check for error messages during the training process. Please provide more error information for our reference. 2024-06-28_221624