huggingface / huggingface/alignment-handbook

DPO loss

Open
#38 8 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
5.7k
Forks
490
Avg merge
2m
Merged PRs (30d)
1

Description

I am training DPO with lora, the loss has weird behavior: will decrease sharply at the beginning of each epoch. I wonder if you have same issue before?
Screenshot 2023-11-17 at 12 28 28

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.