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.

Sign up for GitHub

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

Jump to bottom

[Feature] Support the DatasetInfoHook of DPO training #787

Merged
merged 2 commits into from
Jul 11, 2024
Merged

[Feature] Support the DatasetInfoHook of DPO training #787

merged 2 commits into from
Jul 11, 2024

Conversation

xu-song
Copy link
Contributor

@xu-song xu-song commented Jun 20, 2024 •
edited
Loading

DatasetInfoHook gets error when dpo training.

DPO dataset get chosen_ids and rejected_ids instead of input_ids.

xtuner/xtuner/engine/hooks/dataset_info_hook.py

Line 30 in 8adc8d4

input_ids = dataset[0]['input_ids']

To Reproduce

You can reproduce with any dpo training, such as internlm2_chat_1_8b_dpo_full

@pppppM pppppM requested a review from HIT-cwh July 9, 2024 00:44
@HIT-cwh
Copy link
Collaborator

HIT-cwh commented Jul 11, 2024

Thanks a lot!

@HIT-cwh HIT-cwh merged commit b92481f into InternLM:main Jul 11, 2024
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@HIT-cwh HIT-cwh HIT-cwh approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@xu-song @HIT-cwh