A loss curve is a plot showing how a model's loss changes over training iterations or epochs. It is used to assess convergence, diagnose underfitting or overfitting, and compare training, validation, or test loss over time.
A plot of loss as a function of the number of training iterations. The following plot shows a typical loss curve: !A Cartesian graph of loss versus training iterations, showing a rapid drop in loss for the initial iterations, followed by a gradual drop, and then a flat slope during the final iterations. Loss curves can help you determine when your model is converging or overfitting. Loss curves can plot all of the following types of loss: - training loss - validation loss - test loss See also generalization curve. See Overfitting: Interpreting loss curves in Machine Learning Crash Course for more information.