Get Your CertAIF-C01PlayCompete
‹ All AIF-C01 questions

AIF-C01 Practice Question 76: Fine Tuning Dataset Format

AWS Certified AI Practitioner (AIF-C01) · Test 8 · question 6 of 10

Applications of Foundation Modelsmedium

A team is about to submit an Amazon Bedrock fine-tuning job for a non-conversational summarisation task and is preparing the training data. In what form must the dataset be supplied?

Select one answer
Show answer and explanation

Answer:

  • C. A .jsonl file in Amazon S3 in which each line is a JSON record with a prompt field and a completion field

AWS is specific: *to prepare training and validation datasets for your custom model, you create .jsonl files, where each line is a JSON object corresponding to a record*. For non-conversational tasks (summarisation, translation, question answering, extraction) *each dataset sample includes a prompt field containing the input text and a completion field with the expected output*, giving records that look like {"prompt": "Summarize the article about climate change.", "completion": "..."}. The file lives in Amazon S3 and the customization job reads it from there (option C).

- A is wrong because CSV is not an accepted format for a Bedrock customization dataset. The content would be right, but the job expects JSON Lines and would reject the file. - B is wrong on a deeper point than format: unlabelled documents carry no target output, so there is nothing for supervised fine-tuning to learn to produce. A corpus of raw documents is the shape of data used for pre-training approaches, not for supervised fine-tuning. - D is wrong because the customization job's input path is Amazon S3. There is no DynamoDB source for a Bedrock fine-tuning dataset.

Reference: Prepare data for fine-tuning your models

Practice Test 8 ›

Study guides for AIF-C01

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
How AWS Certification Exams Work: Scoring and RenewalHow AWS certification exams work: levels, booking, question types, unscored questions, scaled scores, pass marks, validity and how recertification works.
What Is Amazon Bedrock? Models, Pricing and GuardrailsWhat is Amazon Bedrock? How a request reaches a model, what happens to your data, token pricing, Guardrails, Knowledge Bases, AgentCore and the exam traps.
Google Cloud Generative AI Leader vs AWS AI PractitionerGoogle Cloud Generative AI Leader vs AWS AI Practitioner: format, cost, topics, free preparation and which certification to take first.
AWS certification cost in 2026, and free ways to prepareWhat every AWS certification costs in 2026 in USD and INR, retake and reschedule rules, the 50% voucher, and the free official ways to prepare.
AWS Generative AI Developer Professional (AIP-C01) guideWhat the AWS Certified Generative AI Developer – Professional (AIP-C01) exam covers - format, cost, the five domains, the services, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Which AWS certification should you get? 2026 roadmapWhich AWS certification to get first, by role and experience, with each exam's status in October 2026, what is changing, and prices in USD and INR.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.