Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

微调后测试问答,不起作用 #697

Closed
2 tasks
xayolink opened this issue Jan 12, 2025 · 1 comment
Closed
2 tasks

微调后测试问答,不起作用 #697

xayolink opened this issue Jan 12, 2025 · 1 comment
Assignees

Comments

@xayolink
Copy link

System Info / 系統信息

cuda12.2, python10, pytorch2.2.1

Who can help? / 谁可以帮助到您?

微调模块

Information / 问题信息

  • The official example scripts / 官方的示例脚本
  • My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

  1. 准备微调数据集,如下图(重复2条数据到2千次):
    32ef699c368aea8355d2b2fcee240fe
  2. 微调成功后选择对应的检查点开始测试聊天,回答得不到预期效果。

Expected behavior / 期待表现

预期能正确回答出两条语料的所有内容。

另外官方没有描述针对一个知识点的微调要准备多少条合适,希望能有一个实际操作的案例,比如数据集的构造、微调的数据量、微调多少轮、微调结果怎么应用。感谢

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR self-assigned this Jan 12, 2025
@zhipuch
Copy link
Collaborator

zhipuch commented Jan 16, 2025

你的数据集格式是llama factory的规定格式嘛,使用我们仓库的微调代码尝试呢?

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR closed this as not planned Won't fix, can't repro, duplicate, stale Jan 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants