Preparing data for multimodal fine-tuning

The following are guidelines and requirements for preparing data for fine-tuning Understanding models:

Designing effective training examples

Your training data should demonstrate the behavior you want the model to exhibit. SFT teaches the model how to respond, not what to know. If you find yourself creating training examples primarily to inject factual knowledge (for example, "What does error code E-45 mean?" with the answer "E-45 indicates a sensor timeout"), consider whether RAG or prompt engineering could achieve the same result without fine-tuning.

When converting source data into the conversational format, follow these principles:

Common data transformation patterns

The following patterns illustrate how to convert common enterprise data formats into effective SFT training examples.

Pattern 1: Structured records to classification or lookup

When your source data is a table or database of records with fields such as issue, cause, and resolution, frame each record as a user question with the relevant input fields and the assistant response as the target output fields.

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a technical support assistant. Given an issue description, identify the most likely root cause and recommended resolution."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "A user reports: 'Application crashes on startup after the latest update.' What is the likely cause and resolution?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Cause: Incompatible configuration file from the previous version.\nResolution: Delete the local configuration cache and restart the application to regenerate default settings."
        }
      ]
    }
  ]
}

Pattern 2: Hierarchical or taxonomy data to structured Q&A

When your source data is a code hierarchy or taxonomy such as product category trees or classification systems, generate questions that ask the model to navigate the hierarchy. Include the classification context in the system prompt or user turn.

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a product catalog assistant. Answer questions about product categories and classifications accurately."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What top-level category does product code 'EL-4520' belong to, and what subcategories does it include?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Product code EL-4520 belongs to the Electronics category. It includes the subcategories: Audio Equipment, Portable Speakers, and Wireless Accessories."
        }
      ]
    }
  ]
}

Pattern 3: Procedural documents to instructional dialog

When your source data consists of standard operating procedures, runbooks, or step-by-step guides, convert procedures into task-oriented questions. The user asks how to perform a task and the assistant provides the steps in a consistent format.

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are an IT operations assistant. Provide step-by-step instructions based on approved runbooks and standard operating procedures."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "How do I reset a user's multi-factor authentication when they have lost access to their device?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Follow these steps to reset a user's multi-factor authentication:\n1. Verify the user's identity using the approved verification procedure.\n2. Disable the existing MFA configuration in the identity management console.\n3. Generate a new temporary access code and send it to the user's verified email.\n4. Instruct the user to log in with the temporary code and re-enroll their new device.\n5. Confirm the new MFA device is working by requesting a test authentication.\n6. Document the reset in the support ticket."
        }
      ]
    }
  ]
}

Example dataset formats

The following example dataset formats provide a guide for you to follow.

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a digital assistant with a friendly personality"
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What is the capital of Mars?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Mars does not have a capital. Perhaps it will one day."
        }
      ]
    }
  ]
}

// train.jsonl{
    "schemaVersion": "bedrock-conversation-2024",
    "system": [{
        "text": "You are a smart assistant that answers questions respectfully"
    }],
    "messages": [{
            "role": "user",
            "content": [{
                    "text": "What does the text in this image say?"
                },
                {
                    "image": {
                        "format": "png",
                        "source": {
                            "s3Location": {
                                "uri": "s3://your-bucket/your-path/your-image.png",
                                "bucketOwner": "your-aws-account-id"
                            }
                        }
                    }
                }
            ]
        },
        {
            "role": "assistant",
            "content": [{
                "text": "The text in the attached image says 'LOL'."
            }]
        }
    ]
}

{
    "schemaVersion": "bedrock-conversation-2024",
    "system": [{
        "text": "You are a helpful assistant designed to answer questions crisply and to the point"
    }],
    "messages": [{
            "role": "user",
            "content": [{
                    "text": "How many white items are visible in this video?"
                },
                {
                    "video": {
                        "format": "mp4",
                        "source": {
                            "s3Location": {
                                "uri": "s3://your-bucket/your-path/your-video.mp4",
                                "bucketOwner": "your-aws-account-id"
                            }
                        }
                    }
                }
            ]
        },
        {
            "role": "assistant",
            "content": [{
                "text": "There are at least eight visible items that are white"
            }]
        }
    ]
}

Dataset constraints

Amazon Nova applies the following constraints on model customizations for Understanding models.