Hyperparameter --lr_finetuning_init and --lr_unlearning_init seems to be not used in ./defense/abl/abl.py

[mo666666]

Thank you for your excellent work. I found that the hyperparameters --lr_finetuning_init and --lr_unlearning_init seem to be not used in the ./defense/abl/abl.py. Is that a bug?

[mdzhangst]

Yes, because the experiment found that unlearn had a high sensitivity to lr, so the lr given in the original text was retained without using hyperparameters. In order not to affect you, we will make changes in later versions.

[mo666666]

Ok, thank you for your replies!