Training proceeds in epochs, each a complete sweep through the dataset in shuffled batches. Too few and the model underfits; too many and it starts memorising.
The honest way to choose is to watch validation loss and stop when it turns upward, rather than to pick a round number in advance.
Also in Deep Learning
Apply
Begin the first module
Become AI native, it is the real deal today, and if it is not for you, you have lost nothing but learnt a new skill.