Skip to content

训练数据中,当 "role": "tool_call" 时,添加 "loss": false,该轮数据也会进行 loss 计算? #9029

@wulaoshi

Description

@wulaoshi

Checklist / 检查清单

  • I have searched existing issues, and this is a new question or discussion topic. / 我已经搜索过现有的 issues,确认这是一个新的问题与讨论。

Question Description / 问题描述

有没有什么更好的办法让 指定的 "role": "tool_call" 轮数据不进行 loss 计算?

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions