Review Epoch

An epoch is one full pass through a training dataset during model training.

An epoch is completed when a training process has worked through every example in the training set once. One epoch usually contains many batches and parameter updates.

Epochs provide a common way to describe training progress, compare learning curves, and decide when additional passes stop helping or begin to overfit.

A dataset has 1,000 examples and the batch size is 100. Ten training iterations complete one epoch.

One epoch is not one update. The number of updates in an epoch depends on the dataset and batch size.

One epoch is one full pass through the training set.

* [[batch|Batch]] * [[training|Training]] * [[dataset|Dataset]] * [[loss-function|Loss Function]]

* [Google for Developers, “Machine Learning Glossary”](https://developers.google.com/machine-learning/glossary) — provides established boundaries for core machine-learning vocabulary.

* Compare [[batch|Batch]], [[training|Training]], [[dataset|Dataset]], and [[loss-function|Loss Function]] to place Epoch in the surrounding system. * Follow the cited source material above for the method, standard, or research context behind this draft.