Identifying Overfitting from Loss Curves
Exhibit
Refer to the exhibit. ``` Epoch 1/10 - loss: 1.2345 - accuracy: 0.6543 - val_loss: 1.9876 - val_accuracy: 0.4321 Epoch 2/10 - loss: 1.0123 - accuracy: 0.7123 - val_loss: 2.3456 - val_accuracy: 0.3987 Epoch 3/10 - loss: 0.8765 - accuracy: 0.7654 - val_loss: 2.8765 - val_accuracy: 0.3654 ```
Refer to the exhibit. A deep learning model is being trained. Based on the training log, which problem is most evident?
Quick Answer
The answer is overfitting, as the divergence between a decreasing training loss and an increasing validation loss after a certain epoch is the definitive signature of this problem. This pattern occurs because the model begins to memorize noise and specific details from the training data rather than learning generalizable patterns, causing its performance to degrade on unseen validation data. On the CompTIA AI+ AI0-001 exam, this concept is frequently tested by presenting a loss curve exhibit and asking you to identify the most evident training issue, with overfitting being a common correct answer that traps candidates who focus only on the falling training loss. A reliable memory tip is to think of the “gap” between the two curves: when the validation loss starts rising while training loss keeps falling, you have a “divergence dilemma” signaling overfitting.
⚠ Common exam trap
CompTIA often tests the distinction between overfitting and underfitting by showing loss curves where training loss decreases but validation loss increases, which candidates may misinterpret as a normal training progression or as vanishing gradients.
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 training log shows that the training loss continues to decrease while the validation loss increases after a certain epoch, which is a classic sign of overfitting. The model is memorizing the training data rather than learning generalizable patterns, leading to poor performance on unseen 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 gradients
Why it's wrong here
Vanishing gradients would cause slow decrease in loss.
- ✓
Overfitting
Why this is correct
Training loss decreases, validation loss increases.
- ✗
Underfitting
Why it's wrong here
Underfitting would have high training loss as well.
- ✗
Data leakage
Why it's wrong here
Data leakage would cause abnormally high accuracy.
About these practice questions
This AI0-001 question is part of Courseiva's 754-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on AI0-001
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. Based on the exhibit, what is the most likely issue with the model training?
medium- A.Vanishing gradient
- B.Learning rate too high
- C.Underfitting
- ✓ D.Overfitting
Why D: 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.
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.