Reading the curves on the How to Train Models track. Overfitting shows up as training loss down and validation loss up. Underfitting shows both high. A noisy validation curve on a tiny set is not a deep insight.
This lesson assumes you already worked through Validation during the run.
The idea in practice
Smooth the curve by evaluating more validation batches before you change the model.
A concrete check
goal = {
'track': 'How to Train Models',
'lesson': 'Reading the curves',
}
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
Stopping at the first tiny validation bump on a tiny set. 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
Label two sketched curves as overfit or underfit.
Self-check
- Say Reading the curves 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.