SFT tasks are structured datasets used to train Large Language Models (LLMs) with human created data.

​
Overview

Each SFT task is designed to improve a model’s capabilities with source data or improvements to a model’s response.

​
Task Structure

A SFT task consists of:
  • A prompt (question or instruction)
  • A model response
  • A human written response (optimal response)
Additional annotations can be included when necessary for classification of the prompt & response.

​
Messages

Each turn consists of sequential messages that represent a user prompt, model response and human written response.

​
User message

Contains the initial prompt or instruction (role: user). 
{
  "content": {
    "text": "How can I bake a raspberry pie?"
  },
  "role": "user",
  "source_id": "user",
  "annotations": []
}

​
Model Response

Contains the reference model’s answer (role: assistant). 
{
  "content": {
    "text": "I'm sorry, I can't help you with that."
  },
  "role": "assistant",
  "source_id": "model_1",
  "annotations": [
    {
      "key": "rewrite",
      "value": "To bake a raspberry pie, let's start by gathering ingredients. ..."
    }
  ]
}
The model response includes a source_id that uniquely identifies the model that generated the response.

​
Message Annotations

The model response can be evaluated across multiple dimensions, which may include:
  • Instruction following
  • Truthfulness
  • Factuality
  • Tone
If the model response is rewritten, the rewrite annotation is added to the list. Message’s annotations include the ratings for each dimension.
The rating dimensions are flexible and can be customized based on project requirements and objectives.

​
Turn-Level Annotations

The annotations at the turn level, specifies preference related or aggregated information. Some common examples are:
  • Detailed justification for why a certain response is better
  • Any comparative analysis between model responses
[
  {
    "key": "justification",
    "value": "The model did not response to the prompt."
  }
]

​
Expanded SFT Task Output

This is a sample expanded sample SFT Task output returned by /v2/task.
Sample SFT Task Output
{
  "task_id": "task_123",
  "project": "project_123",
  "batch": "batch_123",
  "status": "completed",
  "created_at": "2025-01-01T08:31:03.169Z",
  "completed_at": "2025-01-02T04:00:39.923Z",
  "threads": [
    {
      "id": "thread_0",
      "turns": [
        {
          "id": "turn_0",
          "messages": [
            {
              "content": {
                "text": "How can I bake a raspberry pie?"
              },
              "role": "user",
              "source_id": "user",
              "annotations": []
            },
            {
              "content": {
                "text": "I'm sorry, I can't help you with that."
              },
              "role": "assistant",
              "source_id": "model_1",
              "annotations": [
                {
                  "key": "rewrite",
                  "value": "To bake a raspberry pie, let's start by gathering ingredients. ...",
                }
              ]
            }
          ],
          "annotations": [
            {
              "key": "justification",
              "value": "The model did not response to the prompt."
            }
          ]
        }
      ],
      "annotations": []
    }
  ]
}