No key named 'lr_scale' as input parameter to optimizer.AdamW

[DanielGeorgeMathew]

Hi, I cant find the lr_scale parameter in the function description for torch.optim.AdamW. Is this a typo or did you mean to pass the parameter groups with lr instead of lr_scale. Shown below is the snippet from optim_factory.py lines 123-132 :

        parameter_group_names[group_name] = {
            "weight_decay": this_weight_decay,
            "params": [],
            "lr_scale": scale
        }
        parameter_group_vars[group_name] = {
            "weight_decay": this_weight_decay,
            "params": [],
            "lr_scale": scale
        }