Short Answer

How can you tell a development set has been overused?

Question: In one to three sentences, explain what pattern shows that a development set has started to reflect the optimizer's choices rather than true model quality.

Sample answer: A warning sign is that the model scores much better on the set you keep checking than on a separate, untouched evaluation set. That mismatch means the repeated tuning is fitting the checked set's details instead of improving general performance.

Key points:

  • Compare the score on the repeatedly consulted set with an independent evaluation set
  • A sizable gap, with the consulted set looking better, indicates overfitting to that set

Rubric: Full credit if the answer identifies a strong score gap between the consulted development set and an independent holdout set as the sign of overfitting.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI