Glossary term
Glossary term
Foundations
A plot of loss as a function of the number of training iterations. The following plot shows a typical loss curve:
Loss curves can help you determine when your model is converging or overfitting.
Loss curves can plot all of the following types of loss:
See also generalization curve.
See Overfitting: Interpreting loss curves in Machine Learning Crash Course for more information.
Created for this library
An ML platform team examines loss curves at every release to confirm training reached convergence without divergence.
A research team uses loss curves across runs to compare optimization stability of candidate hyperparameter settings.
A startup engineer uses loss curves to identify when learning rate is too high and training is diverging.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License