torch.optim.radam.radam#

torch.optim.radam.radam(params, grads, exp_avgs, exp_avg_sqs, state_steps, decoupled_weight_decay=False, foreach=None, differentiable=False, capturable=False, has_complex=False, maximize=False, *, beta1, beta2, lr, weight_decay, eps)[source]#

Functional API that performs RAdam algorithm computation.