from torch.optim.swa_utils import SWALR
help(SWALR)

class SWALR(torch.optim.lr_scheduler._LRScheduler)
 |  SWALR(optimizer, swa_lr, anneal_epochs=10, anneal_strategy='cos', last_epoch=-1)
 |
 |  Anneals the learning rate in each parameter group to a fixed value.
 |
 |  This learning rate scheduler is meant to be used with Stochastic Weight
 |  Averaging (SWA) method (see `torch.optim.swa_utils.AveragedModel`).
 |
 |  Args:
 |      optimizer (torch.optim.Optimizer): wrapped optimizer
 |      swa_lrs (float or list): the learning rate value for all param groups
 |          together or separately for each group.
 |      annealing_epochs (int): number of epochs in the annealing phase
 |          (default: 10)
 |      annealing_strategy (str): "cos" or "linear"; specifies the annealing
 |          strategy: "cos" for cosine annealing, "linear" for linear annealing
 |          (default: "cos")
 |      last_epoch (int): the index of the last epoch (default: -1)
 |
 |  The :class:`SWALR` scheduler is can be used together with other
 |  schedulers to switch to a constant learning rate late in the training
 |  as in the example below.