15. Validation Loss

Validation Code

You can take a look at the complete validation code in the previous notebook directory, or, directly in the Github repository .

Validation Set: Takeaways

We create a validation set to

1. Measure how well a model generalizes, during training
2. Tell us when to stop training a model; when the validation loss stops decreasing (and especially when the validation loss starts increasing and the training loss is still decreasing)