AI-300 Practice Test 2 — 10 Questions

Question 1

Which THREE metrics can be logged during training to track performance in Azure ML?

Accepted Answer

Model accuracy.. Accuracy, loss, and custom metrics are standard loggable items.

Answer

Compute instance IP address.

Answer

Workspace subscription ID.

Question 2

What is the primary purpose of a 'Labeling Project' in Azure Machine Learning?

Accepted Answer

To facilitate manual data annotation for supervised learning.. Labeling projects are used to manage the process of annotating data (images, text) to create datasets for supervised learning.

Answer

To automatically version datasets.

Answer

To monitor model deployment drift.

Answer

To define model evaluation metrics.

Question 3

You want to perform hyperparameter tuning using the 'HyperDrive' service. You have a requirement to stop poor-performing runs early to save compute costs. Which policy should you use?

Accepted Answer

'MedianStoppingPolicy'.. The 'BanditPolicy' is the standard early-termination policy that stops runs based on a slack factor/amount compared to the best-performing run.

Answer

'TruncationSelectionPolicy'.

Answer

'RandomParameterSampling'.

Question 4

What is the benefit of using 'Model Catalog' in Azure AI Foundry?

Accepted Answer

It provides pre-optimized models with one-click deployment.. The Model Catalog provides a curated list of models that are pre-optimized for deployment on Azure infrastructure.

Answer

It provides free LLM usage for all models.

Answer

It eliminates the need for authentication.

Answer

It automatically builds your application UI.

Question 5

To optimize the cost of your AI infrastructure, which THREE actions should you consider?

Accepted Answer

Deleting unused model deployments.. Choosing the right SKU, cleaning up unused deployments, and using reserved capacity are standard cost-optimization steps.

Answer

Deploying all models in every available region.

Answer

Always selecting the 'Premium' SKU.

Question 6

What is the purpose of a 'System-Assigned Managed Identity' in the context of an Azure AI project?

Accepted Answer

To provide a secure identity for the resource to interact with other Azure services.. Managed identities allow the project or compute resource to securely access other Azure resources (like Key Vault or storage) without managing explicit credentials.

Answer

To automatically encrypt all data in transit.

Answer

To allow users to log in to the project portal.

Answer

To provide public IP connectivity.

Question 7

Which THREE items should you keep track of in your AI Foundry project to ensure good governance?

Accepted Answer

Quota usage.. Governance relies on tracking tags, role assignments, and quotas.

Answer

User passwords.

Answer

Personal browser history.

Question 8

You are moving a model from a local environment to Azure Machine Learning. Which file is required to define the entry script for the model inference?

Accepted Answer

'score.py'.. The entry script (often named 'score.py') is required to define 'init()' and 'run()' functions for the deployment.

Answer

'inference_config.json'.

Answer

'model.pkl'.

Answer

'environment.yml'.

Question 9

Which TWO methods are best for debugging an LLM pipeline that fails on complex queries?

Accepted Answer

Inspecting raw input and output tokens via logs.. Prompt logging and trace inspection are the best ways to understand why a model fails on specific inputs.

Answer

Increasing the number of API users.

Answer

Disabling all security controls.

Answer

Deleting the deployment and rebuilding it.

Question 10

You are troubleshooting a failed agent deployment. Which TWO areas should you inspect first?

Accepted Answer

The endpoint availability status.. Deployment logs and endpoint connectivity are the primary sources for identifying deployment failures.

Answer

The Azure status page.

Answer

The user profile settings.

Answer

The billing usage report.