DP-100 Question #525: Real Exam Question with Answer & Explanation

Question

You have fine-tuned an Azure OpenAI Service model by using the Azure AI Foundry portal. The fine-tuned model is overfitting. You plan to correct overfitting by fine-tuning the model again. You need to modify the default value of a fine-tuning task parameter to minimize the possibility of overfitting. Which modification should you apply?

Options

• AIncrease the batch_size.
• BIncrease the learning_rate_multiplier.
• CDecrease the batch_size.
• DDecrease the learning_rate_multiplier.

Explanation

{"question_number": 3, "correct_answer": "D", "explanation": "Overfitting means the model has learned the training data too aggressively and lacks generalization. A high learning_rate_multiplier causes the model to make large weight updates, which accelerates fitting to training examples and promotes overfitting. Decreasing the learning_rate_multiplier slows down the learning process, resulting in smaller, more conservative weight updates that reduce the risk of overfitting. Increasing batch_size (Option A) can also help, but the most direct lever for overfitting caused by aggressive learning is reducing the learning rate.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.