[BUG]: Missing Implementation for Loading after_scheduler Parameters #5119

class WarmupScheduler(_LRScheduler):
    """Starts with a linear warmup lr schedule until it reaches N epochs then applies
    the specific scheduler (For example: ReduceLROnPlateau).

    Args:
        optimizer (:class:`torch.optim.Optimizer`): Wrapped optimizer.
        warmup_epochs (int): Number of epochs to linearly warmup lr until starting applying the scheduler.
        after_scheduler (:class:`torch.optim.lr_scheduler`): After target_epoch, use this scheduler.
        last_epoch (int, optional): The index of last epoch, defaults to -1. When last_epoch=-1,
            the schedule is started from the beginning or When last_epoch=-1, sets initial lr as lr.
    """

    def __init__(self, optimizer, warmup_epochs, after_scheduler, last_epoch=-1):
        self.warmup_epochs = int(warmup_epochs)
        self.after_scheduler = after_scheduler
        self.finished = False
        super().__init__(optimizer, last_epoch)

    def state_dict(self):
        state_dict = {key: value for key, value in self.__dict__.items() if key not in "optimizer"}
        if isinstance(state_dict["after_scheduler"], _LRScheduler):
            state_dict["after_scheduler_type"] = type(state_dict["after_scheduler"]).__name__
            state_dict["after_scheduler_dict"] = state_dict["after_scheduler"].state_dict()
            del state_dict["after_scheduler"]
        else:
            raise NotImplementedError()
        return state_dict

    def get_lr(self):
        if self.last_epoch >= self.warmup_epochs:
            if not self.finished:
                self.after_scheduler.base_lrs = self.base_lrs
                self.finished = True
            return self.after_scheduler.get_lr()

        return [(self.last_epoch + 1) / self.warmup_epochs * lr for lr in self.base_lrs]

    def step(self, epoch=None):
        if self.finished:
            if epoch is None:
                self.after_scheduler.step(None)
                self._last_lr = self.after_scheduler.get_last_lr()
            else:
                self.after_scheduler.step(epoch - self.warmup_epochs)
                self._last_lr = self.after_scheduler.get_last_lr()
        else:
            return super().step(epoch)