Identifying Overfitting from Loss Curves
Exhibit
Refer to the exhibit. Epoch 1/50 - loss: 2.4503 - val_loss: 2.4512 Epoch 10/50 - loss: 1.2345 - val_loss: 1.3456 Epoch 20/50 - loss: 0.9876 - val_loss: 1.1234 Epoch 30/50 - loss: 0.6543 - val_loss: 0.9876 Epoch 40/50 - loss: 0.4321 - val_loss: 0.8765 Epoch 50/50 - loss: 0.3210 - val_loss: 0.8321
Based on the exhibit, what is the most likely issue with the model training?
⚠ Common exam trap
CompTIA often tests the distinction between overfitting and underfitting by showing a diverging validation loss curve, which candidates may misinterpret as a learning rate issue or vanishing gradient.
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 exhibit shows training loss decreasing while validation loss increases after a certain point, which is a classic sign of overfitting. The model is memorizing the training data rather than generalizing, leading to poor performance 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.
- ✗
Vanishing gradient
Why it's wrong here
Vanishing gradients arise in deep networks using saturating activations, where backpropagated derivatives shrink toward zero and early layers stop updating. The exhibit shows training loss plateauing immediately with no learning, which fits that signature only if depth and activation choice support it. It would be correct for a deep sigmoid or tanh stack.
- ✗
Learning rate too high
Why it's wrong here
An excessively high learning rate causes the loss to oscillate or diverge rather than settle, with weights overshooting minima. The exhibit does not show that divergence pattern; a high rate would be indicated by erratic, non-decreasing loss across epochs.
- ✗
Underfitting
Why it's wrong here
Underfitting means the model performs poorly on both training and test data because it is too simple to capture the underlying pattern. The exhibit shows a different symptom; underfitting would appear as high error on the training set itself.
- ✓
Overfitting
Why this is correct
The exhibit shows training loss continuing to fall while validation loss rises after an early point, the classic divergence signature. The model has memorised training noise rather than generalising, so overfitting is the most likely issue indicated.
About these practice questions
Courseiva writes every AI0-001 question from scratch — 962 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI0-001 practice question is part of Courseiva's free CompTIA 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 AI0-001 exam.