AI engineering glossary · Deep learning core
What is checkpoint?
Checkpoint (also called Model checkpoint): A saved snapshot of a model's weights, and usually optimiser state and epoch number, written to disk during training. It allows resuming after an interruption and keeping the best-performing version.
Checkpoint: an example
Saving a file every epoch lets a Colab run that disconnects at epoch 12 resume from epoch 12.
Related terms
More Deep learning core terms
- Cross-entropy loss
- Curriculum learning
- Cyclical learning rate
- Data parallelism
- Deep learning
- Deep neural network
- DropConnect
- Dropout
Where you learn it
Checkpoint is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.