SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-epoch-iterations

With 1,000 training examples and a batch size of 50, how many iterations make one epoch?

20 iterations. 1,000 divided by 50.

Start playing free

  1. 50
  2. 1,000
  3. 20 ✔

Why: An epoch is one full pass over the training set, every example seen once. Each iteration processes one batch, so an epoch takes N divided by batch size iterations.

Huh, didn't know that: With a batch size of one (stochastic gradient descent), one epoch takes as many iterations as there are examples.

The dad joke
My model wanted to watch the training data one more time. I said fine, but this is the last epoch.
Like this card?
Play the game

References

Answer: 20. An epoch is one full pass over the training set, every example seen once. Each iteration processes one batch, so an epoch takes N divided by batch size iterations.

  1. Google Machine Learning Glossary: epoch developers.google.com/machine-learning/glossary
    1 epoch = (N/batch size) = (1,000 / 50) = 20 iterations
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceHow do AI, machine learning and deep learning fit together?Artificial IntelligenceWhat did Alan Turing call his 1950 test of machine intelligence?Artificial IntelligenceTuring predicted that by about 2000, judges would ID the machine at most what percent of the time?

That's stuff everyone should know.