Early Stopping on Val Loss
Stop before you overfit.
Training Too Long Hurts
More epochs are not always better. Past a point the model starts memorizing noise, and validation results get worse. Early stopping ends training at the sweet spot.
Watch Validation Loss
The signal you track is validation loss. While it keeps falling the model is still generalizing better, so you let training continue.
All lessons in this course
- Split Train, Validation & Test
- An Epoch Loop with Validation
- Save & Load with state_dict
- Early Stopping on Val Loss