scoring dataset schemas

This commit is contained in:
Xi Yan 2025-03-12 23:56:19 -07:00
parent c5f2861a7e
commit 10f6528164
3 changed files with 83 additions and 5 deletions

View file

@ -4718,6 +4718,9 @@ components:
- post-training/messages
- eval/question-answer
- eval/messages-answer
- scoring/question-generation-answer
- scoring/messages-generation-answer
- scoring/generation-answer
title: DatasetPurpose
description: >-
Purpose of the dataset. Each purpose has a required input data schema.
@ -6070,7 +6073,11 @@ components:
type: string
enum:
- post-training/messages
- eval/question-answer
- eval/messages-answer
- scoring/question-generation-answer
- scoring/messages-generation-answer
- scoring/generation-answer
title: DatasetPurpose
description: >-
Purpose of the dataset. Each purpose has a required input data schema.
@ -6779,6 +6786,9 @@ components:
- post-training/messages
- eval/question-answer
- eval/messages-answer
- scoring/question-generation-answer
- scoring/messages-generation-answer
- scoring/generation-answer
description: >-
The purpose of the dataset. One of - "post-training/messages": The dataset
contains a messages column with list of messages for post-training. {
@ -6790,7 +6800,18 @@ components:
column for evaluation. { "messages": [ {"role": "user", "content": "Hello,
my name is John Doe."}, {"role": "assistant", "content": "Hello, John
Doe. How can I help you today?"}, {"role": "user", "content": "What's
my name?"}, ], "answer": "John Doe" }
my name?"}, ], "answer": "John Doe" } - "scoring/question-generation-answer":
The dataset contains a question column, a generation column and an answer
column for scoring. { "question": "What is the capital of France?", "generation":
"Paris", "answer": "Paris" } - "scoring/messages-generation-answer": The
dataset contains a messages column with list of messages, a generation
column and an answer column for scoring. { "messages": [ {"role": "user",
"content": "Hello, my name is John Doe."}, {"role": "assistant", "content":
"Hello, John Doe. How can I help you today?"}, {"role": "user", "content":
"What's my name?"}, ], "generation": "John Doe", "answer": "John Doe"
} - "scoring/generation-answer": The dataset contains a generation column
and an answer column for scoring. { "generation": "Paris", "answer": "Paris"
}
source:
$ref: '#/components/schemas/DataSource'
description: >-