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

Update Training Guidelines #150

Merged
merged 16 commits into from Aug 24, 2023
Merged

Update Training Guidelines #150

merged 16 commits into from Aug 24, 2023

Conversation

iMountTai
Copy link
Collaborator

Description

This PR adds the following features:

  • Fix the issue of incorrect type for loading lora_model in the 🤗transformers inference script.
  • Add the device_map parameter to address the issue of insufficient CPU memory during training.
  • Fix the naming issue when re-generating training data with a new length.

Related Issue

#110 #27

@iMountTai iMountTai requested a review from airaria August 17, 2023 06:14
airaria
airaria previously approved these changes Aug 17, 2023
--lora_dropout ${lora_dropout} \
--torch_dtype float16 \
--validation_file ${validation_file} \
--peft_path ${peft_model} \
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please explain more on the modifications?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

peft_path与lora相关训练参数互斥,因此以设置lora可训练参数为例。

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some users may use the script to pre-train the model from scratch.
But with these modifications, the default behavior of script is continual training chinese-llama-2.
I think it may lead to some confusions.
I would advise keeping modules_to_save.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I agree with your suggestion.

@ymcui ymcui dismissed airaria’s stale review August 22, 2023 09:14

further modifications were required.

@iMountTai iMountTai requested a review from airaria August 23, 2023 00:43
@ymcui ymcui merged commit aae35b2 into ymcui:main Aug 24, 2023
1 check passed
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

Successfully merging this pull request may close these issues.

None yet

3 participants