epochs

In machine learning, an epoch is one complete pass through the entire training dataset. When training a model, the algorithm learns by adjusting its parameters based on the data it sees. Since a dataset can be large, the model often processes it in smaller groups called batches. Multiple epochs mean the model revisits the entire dataset several times, allowing it to improve its predictions. Think of it like reviewing a textbook multiple times to better understand the material—each epoch helps the model learn more accurately from the data.