Early stopping on the AI Learning track. Early stopping ends training when validation has not improved for a set number of checks. It is a simple regularizer and a way to save the best weights, not the last weights.
This lesson assumes you already worked through Regularization.
The idea in practice
Keep a checkpoint of the best validation score. Patience of a few checks avoids stopping on a single noisy dip. Restore the best checkpoint, not the final one.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Early stopping',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
Saving the last epoch after validation has already degraded. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Write the rule: save when, stop when, restore which file.
Self-check
- Say Early stopping in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.