early_stop: Early Stopping Specification

In kindling: Higher-Level Interface of 'torch' Package to Auto-Train Neural Networks

Early Stopping Specification

Description

early_stop() is a helper function to be supplied on early_stopping arguments.

Usage

early_stop(
  patience = 5L,
  min_delta = 1e-04,
  restore_best_weights = TRUE,
  monitor = "val_loss"
)

Arguments

patience	Integer. Epochs to wait after last improvement. Default 5.
min_delta	Numeric. Minimum improvement to qualify as better. Default 1e-4.
restore_best_weights	Logical. Restore weights from best epoch. Default TRUE.
monitor	Character. Metric to monitor. One of "val_loss" (default) or "train_loss".

Value

An object of class "early_stop_spec".

kindling documentation built on March 3, 2026, 9:07 a.m.