hardMultiple Choice
AIF-C01 Practice Question: A machine learning engineer notices that the…
A machine learning engineer notices that the training loss decreases steadily, but the validation loss starts increasing after a few epochs. Which of the following is the MOST likely cause?
⚠ Common exam trap
AWS AI Practitioner often tests the distinction between overfitting and underfitting by describing loss curves; the trap here is that candidates may confuse a rising validation loss with a learning rate issue or data leakage, but the steady decrease in training loss rules out underfitting and points directly to overfitting.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Overfitting
The scenario describes training loss decreasing while validation loss increases after a few epochs, which is the classic signature of overfitting. The model is memorizing the training data (including noise) rather than learning generalizable patterns, causing it to perform poorly on unseen validation data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Learning rate too low
Why it's wrong here
A learning rate that is too low slows convergence, so both training and validation loss decrease gradually without the validation curve turning upward. It is tempting because low learning rates do cause poor training progress, but that is the correct diagnosis when loss plateaus early, not when validation loss diverges after several epochs.
- ✓
Overfitting
Why this is correct
Overfitting occurs when the model memorises training data, so training loss keeps falling while validation loss rises from poor generalisation to unseen samples. The diverging loss curves after a few epochs are the classic signature, satisfying the stem's observation of decreasing training loss alongside increasing validation loss.
- ✗
Underfitting
Why it's wrong here
Underfitting produces high training loss alongside high validation loss, since the model fails to capture the underlying pattern in either set. It is tempting because both conditions involve poor generalisation, but underfitting is the correct diagnosis when training loss itself stays elevated, not when it decreases steadily while validation loss rises.
- ✗
Data leakage from validation set into training set
Why it's wrong here
Leakage from the validation set into training would typically make validation loss track training loss closely and appear artificially low, not rise after several epochs. It is tempting because leakage is a genuine concern in pipeline design, but it is the correct diagnosis when validation metrics look suspiciously optimistic, not when they diverge upward.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.