Suho Lee

> Maybe a bug in [class NT_Xent(nn.Module)](https://github.com/Spijkervet/SimCLR/blob/04bcf2baa1fb5631a0a636825aabe469865ad8a9/simclr/modules/nt_xent.py#L7) when using multi-gpus. The `mask` and `positive/negative pairs` are wrong I think. I agree. To make the implementation work on multi node or...

Thanks. I'll try again with the updated command. By the way, I found that `hparams['lr_classifier']` does not affect the learning rate in the optimizer for `ERM` in https://github.com/zhengzangw/DoPrompt/blob/main/domainbed/algorithms.py#L111. I think...