netket.callbacks.ConvergenceStopping

class netket.callbacks.ConvergenceStopping

Bases: object

A simple callback to stop the optimisation if the loss gets below a certain threshold. based on driver._loss_name.

Inheritance

Attributes

monitor: str = 'mean'

Loss statistic to monitor. Should be one of ‘mean’, ‘variance’, ‘sigma’.

patience: int = 10

The loss must be consistently below this value for this number of iterations in order to stop the optimisation.

smoothing_window: int = 10

The loss is smoothed over the last smoothing_window iterations to reduce statistical fluctuations

target: float

Target value for the monitored quantity. Training will stop if the driver hits the baseline.