# AdamW

Source: https://www.tensorplay.cn/docs/generated/tensorplay.optim.adamw.AdamW.html

# AdamW

class tensorplay.optim.adamw.AdamW(params, lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.01, amsgrad=False, *, maximize=False, foreach=None, capturable=False, differentiable=False, fused=None)[[source]](../_modules/tensorplay/optim/adamw.html#AdamW)

Adam with decoupled weight decay, matching torch.optim.AdamW.