MLS-C01 Modeling Practice Question
A team is training a large language model using SageMaker's distributed training. They notice that the training loss is not decreasing after the first few epochs. Which action is MOST likely to resolve this issue?
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
✓
Reduce the learning rate
When training loss plateaus or does not decrease after the first few epochs, a common cause is that the learning rate is too high, causing the optimizer to overshoot minima. Reducing the learning rate helps the model converge. Increasing the batch size (option A) mainly affects gradient variance and training speed but does not address an overly large step size. Adding L2 regularization (option B) helps prevent overfitting but does not resolve a high learning rate. Switching from Adam to SGD (option D) may not help because Adam typically adapts learning rates per parameter; if the base learning rate is too high, both optimizers can struggle. Therefore, reducing the learning rate is the most direct and effective action.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the batch size
Why it's wrong here
Increasing batch size can stabilize training by reducing gradient noise, but it does not directly resolve a plateau caused by a learning rate that is too high. It may even lead to convergence to sharp minima.
- ✗
Add L2 regularization
Why it's wrong here
L2 regularization adds a penalty on large weights to prevent overfitting. However, if the loss is not decreasing, the issue is likely with the optimization dynamics (e.g., learning rate), not overfitting.
- ✓
Reduce the learning rate
Why this is correct
A high learning rate can cause the loss to plateau or oscillate. Reducing the learning rate allows the optimizer to take smaller steps, enabling the loss to continue decreasing. This is the most direct fix.
- ✗
Switch from Adam to SGD optimizer
Why it's wrong here
Adam is an adaptive optimizer that adjusts learning rates per parameter. Switching to SGD may require careful tuning of the learning rate and momentum, and typically does not resolve a plateau caused by a learning rate that is too high.
Visual reference
Go deeper
Related to this question
About these practice questions
This MLS-C01 question is part of Courseiva's 1,672-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 →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLS-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 MLS-C01 exam.