Liu Yang

Hi, I was using the SGDW implementation in this repo, and I wonder if anything is wrong with this line: https://github.com/jettify/pytorch-optimizer/blob/910b414565427f0a66e20040475e7e4385e066a5/torch_optimizer/sgdw.py#L121 Let weight decay be $\lambda$ and learning rate be...

Hi, I open this pull request for the issue I submitted regarding SGDW: https://github.com/jettify/pytorch-optimizer/issues/454#issue-1332395921 Hope this change makes sense. Thanks! Best Regards, Liu