core.utils.trainutils.EarlyStopping

core.utils.trainutils.EarlyStopping(
    patience=5,
    verbose=False,
    delta=0.0,
    metric='validation',
)

Implement early stopping during training, once the validation loss stops decreasing for a certain number of epochs (the patience).

If val_loss > min_val_loss - delta for more than patience epochs, then returns early stopping occurs.

Parameters

Name Type Description Default
patience int Number of epochs to wait before stopping. 5
verbose bool Whether to print counter increments. False
delta float Amount by which loss must decrease in patience epochs. 0.0
metric Literal['training', 'validation'] Whether to use the training loss to determine early stopping (“training”) or the test loss (“validation”) 'validation'

Attributes

Name Description
best_score
counter
delta
early_stop
metric
patience
val_loss_min
verbose