Bring-Your-Own-Dataset(BYOD) 任务支持的数据集格式

自定义评分器和 LLM-as-judge评估类型需要位于 S3 中的自定义数据集 JSONL 文件。 AWS 您必须以符合以下支持的格式之一的 JSON Lines 文件形式提供该文件。为清楚起见，本文档中的示例进行了扩展。

每种格式都有自己的细微差别，但至少所有格式都需要用户提示。

1。OpenAI 格式

{
    "messages": [
        {
            "role": "system",    # System prompt (looks for system role)
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",       # Query (looks for user role)
            "content": "Hello!"
        },
        {
            "role": "assistant",  # Ground truth (looks for assistant role)
            "content": "Hello to you!"
        }
    ]
}

2。 SageMaker 评估

{
   "system":"You are an English major with top marks in class who likes to give minimal word responses: ",
   "query":"What is the symbol that ends the sentence as a question",
   "response":"?", # Ground truth
   "category": "Grammar"
}

3。 HuggingFace 立即完成

支持标准格式和对话格式。

# Standard

{
    "prompt" : "What is the symbol that ends the sentence as a question", # Query
    "completion" : "?" # Ground truth
}

# Conversational
{
    "prompt": [
        {
            "role": "user", # Query (looks for user role)
            "content": "What is the symbol that ends the sentence as a question"
        }
    ],
    "completion": [
        {
            "role": "assistant", # Ground truth (looks for assistant role)
            "content": "?"
        }
    ]
}

4。 HuggingFace 偏好

Support 支持标准格式（字符串）和对话格式（消息数组）。

# Standard: {"prompt": "text", "chosen": "text", "rejected": "text"}
{
     "prompt" : "The sky is", # Query
     "chosen" : "blue", # Ground truth
     "rejected" : "green"
}

# Conversational:
{
    "prompt": [
        {
            "role": "user", # Query (looks for user role)
            "content": "What color is the sky?"
        }
    ],
    "chosen": [
        {
            "role": "assistant", # Ground truth (looks for assistant role)
            "content": "It is blue."
        }
    ],
    "rejected": [
        {
            "role": "assistant",
            "content": "It is green."
        }
    ]
}

5。Verl 格式

强化学习用例支持 Verl 格式（当前格式和传统格式）。Verl 文档供参考：https://verl.readthedocs.io/en/latest/preparation/prepare_data.html

VERL 格式的用户通常不提供真实答复。无论如何都要提供一个，请extra_info优先使用extra_info.answer或reward_model.ground_truth; 中的任何一个字段。

SageMaker 如果存在以下特定于 VERL 的字段，则保留为元数据：

# Newest VERL format where `prompt` is an array of messages.
{
  "data_source": "openai/gsm8k",
  "prompt": [
    {
      "content": "You are a helpful math tutor who explains solutions to questions step-by-step.",
      "role": "system"
    },
    {
      "content": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Let's think step by step and output the final answer after \"####\".",
      "role": "user"
    }
  ],
  "ability": "math",
  "extra_info": {
    "answer": "Natalia sold 48/2 = <<48/2=24>>24 clips in May.\nNatalia sold 48+24 = <<48+24=72>>72 clips altogether in April and May.\n#### 72",
    "index": 0,
    "question": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?",
    "split": "train"
  },
  "reward_model": {
    "ground_truth": "72" # Ignored in favor of extra_info.answer
  }
}

# Legacy VERL format where `prompt` is a string. Also supported.
{
  "data_source": "openai/gsm8k",
  "prompt": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Let's think step by step and output the final answer after \"####\".",
  "extra_info": {
    "answer": "Natalia sold 48/2 = <<48/2=24>>24 clips in May.\nNatalia sold 48+24 = <<48+24=72>>72 clips altogether in April and May.\n#### 72",
    "index": 0,
    "question": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?",
    "split": "train"
  }
}