Skip to content
BENIBIX Learn

Epoch

AI📈 Machine LearningNeural Networks

Also known as Training Epoch

One full pass through all the training data. Training runs many of them.

Think of it like

Think of it like reading a whole book once. Two epochs means reading it twice.

Example

Jack has 50,000 photos and trains for 10 epochs. His model sees every photo 10 times, which is 500,000 looks in total.

Why it matters

The number of epochs is a key setting. Too few, and the model has not learned enough. Too many, and it memorises.

Definition

An epoch is one full pass through all of the training data. If you have 10,000 examples, one epoch is done when the model has seen all 10,000 once. Training usually runs for many epochs, so the model sees each example many times. Each pass, it learns a little more. With too many epochs, it starts to memorise the data.
The whole bar is one epoch. Training goes round it again and again.

Common mistake

Mixing up an epoch with a step. One step uses one small batch. One epoch is all the batches.

Key takeaways

  1. 1
    One full pass. Every example seen once.
  2. 2
    Many epochs. Each pass learns a bit more.
  3. 3
    Not too many. Or the model memorises.

Compare

Learn it properly