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

The loss of sharegpt format #5828

Open
1 task done
ZijunSong opened this issue Oct 25, 2024 · 0 comments
Open
1 task done

The loss of sharegpt format #5828

ZijunSong opened this issue Oct 25, 2024 · 0 comments
Labels
pending This problem is yet to be addressed

Comments

@ZijunSong
Copy link

Reminder

  • I have read the README and searched the existing issues.

System Info

  • llamafactory version: 0.9.0
  • Platform: Linux-3.10.0-1127.el7.x86_64-x86_64-with-glibc2.31
  • Python version: 3.11.10
  • PyTorch version: 2.0.1+cu118 (GPU)
  • Transformers version: 4.45.0
  • Datasets version: 2.21.0
  • Accelerate version: 0.33.0
  • PEFT version: 0.12.0
  • TRL version: 0.9.6
  • GPU type: NVIDIA A100-SXM4-40G

Reproduction

我注意到sharegpt格式的数据在训练计算loss时,奇数位当作input不做训练(mask),偶数位认为是llm要生成的结果,需要逐token算loss,还有几个问题想详细了解下。
输入输出是分别把奇偶数位的内容concat吗,因而只能看见(输入)所有位置的内容,训练(输出)所有位置的内容,而不能选择只训练最后一个偶数位内容。

Expected behavior

No response

Others

No response

@github-actions github-actions bot added the pending This problem is yet to be addressed label Oct 25, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
pending This problem is yet to be addressed
Projects
None yet
Development

No branches or pull requests

1 participant