Skip to content
masterclass Buddy
Start learning

PyTorch · Class

optim.AdamW

The functional AdamW API performs one AdamW update from parameter tensors, gradients, and optimizer state. It supports options such as AMSGrad, foreach, fused execution, graph capture, differentiation, and maximizing.

Last updated

Syntax

torch.optim.adamw.adamw(params, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, foreach=None, capturable=False, differentiable=False, fused=None, grad_scale=None, found_inf=None, has_complex=False, *, amsgrad, beta1, beta2, lr, weight_decay, eps, maximize)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • torch.optim.adamw.AdamW
  • torch.optim.Optimizer.add_param_group
  • torch.optim.Optimizer.load_state_dict

Source: torch.optim.adamw.adamw — PyTorch 2.13 documentation. Checked 2026-11-03.