Closed MrLinNing closed 9 months ago
Thank you for bringing this to our attention. The mask path is correct, but there may be some issues with using rewind_epoch. By default, the rewind_epoch is set to zero in arg_parser.py, which is the typical setting for most use cases.
However, if the rewind epoch is set to a value other than zero, it is then necessary to provide a corresponding rewind_path as indicated in this section of arg_parser.py. The rewind_path should point to the model checkpoint corresponding to the specified rewind epoch.
To address this, you have two options:
Manually Set the Rewind Epoch to Zero: This is the default and preferred setting if you do not wish to use a specific rewind point. It simplifies the process as there's no need to specify a rewind_path.
Provide a rewind_path: If you choose to use a non-zero rewind epoch, ensure that you also provide a valid rewind_path. This path should lead to the appropriate model checkpoint that corresponds to the specified rewind epoch.
In summary, make sure to align the rewind_epoch setting with the corresponding rewind_path to ensure the framework functions as intended. If you're opting for the default behavior (rewind epoch of zero), no additional action is needed regarding the rewind_path.
If you still have trouble with the unlearning method, please feel free to ask.
Thank you,
Hello @ljcc0930 , I'm very happy to read your excellent work. I wonder to ask you which file is the mask model? when i run the retrain after pruning,
i have this issue
I have the trained files after run your pruning code
Can you help me? I'm looking forward to your reply~