🔥 40% Off Crucial Exams Memberships — This Week Only

3 days, 10 hours remaining!
Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You need to fine-tune the gpt-35-turbo model in Azure OpenAI so that it produces legal citations in a specific format. You prepare a training file in JSONL format where each line contains the keys "prompt" and "completion". When you submit the job with the Azure OpenAI fine-tuning REST API, the request is rejected during data validation. What is the most likely cause of the failure?

  • Chat models such as gpt-35-turbo require a "messages" array per record; using "prompt" and "completion" causes validation to fail.

  • The file uses Windows (CRLF) line endings instead of Unix (LF) line endings.

  • The JSONL file is larger than 100 MB, exceeding the maximum size supported for fine-tuning.

  • The training dataset contains more than 50 000 tokens across all examples.

Microsoft Azure AI Engineer Associate AI-102
Implement generative AI solutions
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot