[ allennlp.training.momentum_schedulers.inverted_triangular ]
class InvertedTriangular(MomentumScheduler): | def __init__( | self, | optimizer: torch.optim.Optimizer, | cool_down: int, | warm_up: int, | ratio: int = 10, | last_epoch: int = -1 | ) -> None
Adjust momentum during training according to an inverted triangle-like schedule.
The momentum starts off high, then decreases linearly for
1 / ratio th of the original value. Then the momentum increases
warm_up epochs until reaching its original value again. If there
are still more epochs left over to train, the momentum will stay flat at the original
Registered as a
MomentumScheduler with name "inverted_triangular". The "optimizer" argument
does not get an entry in a configuration file for the object.
class InvertedTriangular(MomentumScheduler): | ... | def get_values(self)