netket.callbacks.EarlyStopping

class netket.callbacks.EarlyStopping

Bases: AbstractCallback

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

Inheritance

__init__(min_delta=0.0, min_reldelta=0.0, patience=0, baseline=None, start_from_step=0, monitor='mean')

Construct an early stopping callback.

Parameters:

• min_delta (float) – Minimum change in the monitored quantity to qualify as an improvement.

• min_reldelta (float) – Minimum relative change in the monitored quantity to qualify as an improvement.

• patience (int | float) – Number of epochs with no improvement after which training will be stopped.

• baseline (float | None) – Baseline value for the monitored quantity. Training will stop if the driver does not drop below the baseline.

• monitor (str) – Loss statistic to monitor. Should be one of ‘mean’, ‘variance’, ‘error_of_mean’.

• start_from_step (int) – Number of steps to wait before the callback has any effect. Defaults to 0.

Attributes

callback_order

min_delta: float

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

min_reldelta: float

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.

patience: int | float

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

baseline: float | None

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

monitor: str

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

start_from_step: int

Number of steps to wait before the callback has any effect.

Methods

before_parameter_update(step, log_data, driver)

Called after all update logic has been computed and the step has been accepted, but before the driver applies the parameter update.

At this point:

• The loss and its gradient have been computed by compute_loss_and_update().

• The step has been accepted (not rejected by on_compute_update_end()).

• driver.step_count still refers to the current step — it has not yet been incremented.

• The variational state parameters have not yet changed.

This is the right place to estimate additional observables, add data to log_data, or take a snapshot of the state for logging. Callbacks with a lower callback_order run first, so observables callbacks (order 0) are guaranteed to populate log_data before logger callbacks (order 10) read it.

on_compute_update_end(step, log_data, driver)

Callback called at the end of the compute update phase, after computing the loss and its gradient.

This is called before the parameters are updated, so it can be used to implement custom logic for rejecting a step based on the computed loss or gradient.

Return type:

bool

Returns:

A boolean indicating whether to reject the step (i.e. repeat it with the same parameters). If it returns None, it is treated as False.

on_compute_update_start(step, log_data, driver)

on_run_end(step, driver)

on_run_error(step, error, driver)

on_run_start(step, driver)

on_step_end(step, log_data, driver)

on_step_start(step, log_data, driver)

replace(**kwargs)

Replace the values of the fields of the object with the values of the keyword arguments. If the object is a dataclass, dataclasses.replace will be used. Otherwise, a new object will be created with the same type as the original object.

Return type:

TypeVar(P, bound= Pytree)

Parameters:

• self (P)

• kwargs (Any)