准备数据以用于多模态微调

以下是为微调理解模型准备数据要遵循的指南和要求：

设计有效的训练示例

您的训练数据应会表现出您希望模型表现的行为。SFT 仅传授模型如何响应，而不会传授需要知道的知识。如果您发现自己创建的训练示例主要是为了注入事实性知识（例如，“错误代码 E-45 是什么意思？”，答案为“E-45 表示传感器超时”），则应考虑 RAG 或提示工程是否能够在不进行微调的情况下获得相同的结果。

将源数据转换为对话格式时，应遵循以下原则：

常用数据转换模式

以下模式演示了如何将常用的企业数据格式转换为有效的 SFT 训练示例。

模式 1：将结构化数据转换为分类或查询

当源数据是由具有诸如 issue、cause 和 resolution 之类字段的记录组成的表或数据库时，则将每条具有相关输入字段的记录作为用户问题，并将具有目标输出字段的记录作为助手的响应。

// 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."
        }
      ]
    }
  ]
}

模式 2：将层次结构或分类法数据转换为结构化问答

当源数据是诸如产品类别树或分类系统之类的代码层次结构或分类法数据时，则将生成要求模型浏览层次结构的问题。在系统提示或用户轮次中包含分类上下文。

// 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."
        }
      ]
    }
  ]
}

模式 3：从流程文档转换为指令性对话

当源数据由标准操作程序、运行手册或分步指南组成时，则会将流程转换为以任务为导向的问题。当用户询问如何执行某个任务时，助手以一致的格式提供操作步骤。

// 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."
        }
      ]
    }
  ]
}

示例数据集格式

以下示例数据集格式可供参考。

// 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"
            }]
        }
    ]
}

数据集限制

Amazon Nova 对理解模型的模型自定义应用以下限制。