Glossary · Phase 4 · Deep learning
Training loop
The repeated cycle of training: predict, measure the loss, backpropagate, update the weights.
Try it now
Every neural network ever trained runs this loop. Forgetting the third step is a classic bug.
Learn it properly
The training loop · Forward, loss, backward, step, repeat. About 35 minutes.
Other terms from the same lesson
- checkpoint: A saved copy of a model's weights at some point in training, so you can go back to it or resume later.
- state_dict: PyTorch's dictionary of a model's weights by name. Saving and loading it is how you keep or restore a trained model.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.