huggingface / huggingface/alignment-handbook
DPO loss
Open
- 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?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.