hosa.callbacks.early_stopping.EarlyStoppingAtMinLoss.on_epoch_end

EarlyStoppingAtMinLoss.on_epoch_end(epoch, logs=None)[source]

Checks, based on the patience value, if the training should stop. After stopping, it restores the model’s weights from the epoch with the best value of the monitored quantity.

Parameters
  • epoch (int) – Index of epoch.

  • logs (dict) – Currently no data is passed to this argument for this method but that

  • future. (may change in the) –