class netket.callbacks.EarlyStopping[source]#

Bases: object

A simple callback to stop NetKet if there are no more improvements in the training. based on driver._loss_name.

Inheritance diagram of netket.callbacks.EarlyStopping
baseline: Optional[float] = None#

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

min_delta: float = 0.0#

Minimum change in the monitored quantity to qualify as an improvement.

min_reldelta: float = 0.0#

Minimum relative change in the monitored quantity to qualify as an improvement.

This behaves similarly to min_delta but is more useful for intensive quantities that converge to 0, where absolute tolerances might not be effective.

monitor: str = 'mean'#

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

patience: Union[int, float] = 0#

Number of epochs with no improvement after which training will be stopped.

__call__(step, log_data, driver)[source]#

A boolean function that determines whether or not to stop training.

  • step – An integer corresponding to the step (iteration or epoch) in training.

  • log_data – A dictionary containing log data for training.

  • driver – A NetKet variational driver.


A boolean. If True, training continues, else, it does not.


Returns a new object replacing the specified fields with new values.