# Epoch (machine learning)

> A full training pass over the entire training set such that each example has been processed once. An epoch represents N/batch size training iterations, where N is the total number of examples.[^1]

A full training pass over the entire [training set](https://wiki.g15e.com/pages/Training%20data.txt) such that each [example](https://wiki.g15e.com/pages/Example%20(machine%20learning.txt)) has been processed once. An epoch represents N/[batch size](https://wiki.g15e.com/pages/Batch%20size%20(machine%20learning.txt)) training [iterations](https://wiki.g15e.com/pages/Iteration%20(machine%20learning.txt)), where N is the total number of examples.[^1]

For instance, suppose the following:

- The dataset consists of 1,000 examples.
- The batch size is 50 examples.

Therefore, a single epoch requires 20 iterations. (1 epoch = 1,000 / 50 = 20)

## Number of epochs

The number of epochs is a [hyperparameter](https://wiki.g15e.com/pages/Hyperparameter.txt) you set before the model begins training. In many cases, you'll need to experiment with how many epochs it takes for the model to [converge](https://wiki.g15e.com/pages/Convergence%20(machine%20learning.txt)). In general, more epochs produces a better model, but also takes more time to train.[^2]

## Footnotes

[^1]: https://developers.google.com/machine-learning/glossary#epoch
[^2]: https://developers.google.com/machine-learning/crash-course/linear-regression/hyperparameters