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

DocOwl1.5 training code? #51

Open
coder4nlp opened this issue Apr 16, 2024 · 12 comments
Open

DocOwl1.5 training code? #51

coder4nlp opened this issue Apr 16, 2024 · 12 comments

Comments

@coder4nlp
Copy link

When will the training code be released?Thx.

@coder4nlp coder4nlp changed the title training code? DocOwl1.5 training code? Apr 16, 2024
@HAWLYQ
Copy link
Collaborator

HAWLYQ commented Apr 16, 2024

Hi, @coder4nlp , the training code is scheduled for release at the end of this month. If you are urgent to finetune our model, you can refer to the training code of mPLUG-Owl2 and make some revisions to adjust to our model. Some hyper-parameters can refer to our paper.

@whalefa1I
Copy link

Hi, @coder4nlp , the training code is scheduled for release at the end of this month. If you are urgent to finetune our model, you can refer to the training code of mPLUG-Owl2 and make some revisions to adjust to our model. Some hyper-parameters can refer to our paper.

almost there!

@HAWLYQ
Copy link
Collaborator

HAWLYQ commented Apr 29, 2024

Hi, @coder4nlp , the training code is scheduled for release at the end of this month. If you are urgent to finetune our model, you can refer to the training code of mPLUG-Owl2 and make some revisions to adjust to our model. Some hyper-parameters can refer to our paper.

almost there!

training codes with DeepSpeed is under debugging and testing 。゚・ (>﹏<) ・゚。

@coder4nlp
Copy link
Author

Hi, @coder4nlp , the training code is scheduled for release at the end of this month. If you are urgent to finetune our model, you can refer to the training code of mPLUG-Owl2 and make some revisions to adjust to our model. Some hyper-parameters can refer to our paper.

almost there!

training codes with DeepSpeed is under debugging and testing 。゚・ (>﹏<) ・゚。

@HAWLYQ So sad......。゚・ (>﹏<) ・゚。

@AR-javis
Copy link

AR-javis commented May 2, 2024

@HAWLYQ can you test for deepspeed stage 3 integrations, specifically for deadlock issues while training/fine-tuning?

@HAWLYQ
Copy link
Collaborator

HAWLYQ commented May 2, 2024

@HAWLYQ can you test for deepspeed stage 3 integrations, specifically for deadlock issues while training/fine-tuning?

Hi, @AR-javis , I'm debugging with deepspeed zero3~ I will try my best to release it within a week~

@coder4nlp
Copy link
Author

where are the schedules?

@HAWLYQ
Copy link
Collaborator

HAWLYQ commented May 6, 2024

where are the schedules?

Within this week~

@HAWLYQ
Copy link
Collaborator

HAWLYQ commented May 8, 2024

Hi, @coder4nlp @whalefa1I @AR-javis We have released training codes for finetuning docowl1.5 in https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl1.5. It's temporarily supported by DeepSpeed zero2. We meet deadlock issues with zero3, if you have any suggestions to share with us, we will appreciate very much~

@coder4nlp
Copy link
Author

@HAWLYQ Thank you very much!

@Coobiw
Copy link

Coobiw commented May 12, 2024

hello, how about the venv requirements? I've not seen the requirements.txt.

@HAWLYQ
Copy link
Collaborator

HAWLYQ commented May 12, 2024

hello, how about the venv requirements? I've not seen the requirements.txt.

Hi, @Coobiw , our environment is the same as mPLUG-Owl2, you can follow instructions at https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2 to prepare environments.

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

5 participants