netket.callbacks.EarlyStopping#

class netket.callbacks.EarlyStopping[source]#

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

Attributes

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.

Methods

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

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

Parameters:

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.

Returns:

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

replace(**updates)#: Returns a new object replacing the specified fields with new values.

netket.callbacks.EarlyStopping