Training loss

A metric representing a model’s loss during a particular training iteration. For example, suppose the loss function is MSE. Perhaps the training loss (the MSE) for the 10th iteration is 2.2, and the training loss for the 100th iteration is 1.9.¹

A loss curve plots training loss versus the number of iterations. A loss curve provides the following hints about training:¹

• A downward slope implies that the model is improving.
• An upward slope implies that the model is getting worse.
• A flat slope implies that the model has reached convergence.

Footnotes

1. developers.google.com/machine-learning/glossary#training-loss ↩ ↩²