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

官方可以提供一份run train_with_qlora.py的示例脚本吗 #112

Open
zhangfan-algo opened this issue Sep 18, 2023 · 4 comments
Open

Comments

@zhangfan-algo
Copy link

主要是不太懂需要配置那些参数,辛苦大佬帮忙给一份示例跑train_with_qlora微调代码的脚本

@i4never
Copy link
Contributor

i4never commented Sep 18, 2023

python train_with_qloara.py \
--model_name_or_path TigerResearch/tigerbot-7b-chat \
--data_files ./*.jsonl \
--do_train \
--output_dir ./tigerbot-7b-chat-qlora \
--do_train \
--num_train_epochs 3 \
--learning_rate 2e-5 \
--save_strategy "steps" \
--save_steps 100 \
--logging_steps 1

以上是一个示例启动参数吗,其余参数可以参考transformers training_args以及train_with_qlora中的PeftConfig部份。

@zhangfan-algo
Copy link
Author

好的 感谢

@zhangfan-algo
Copy link
Author

还有一个问题想问下,就是8*A100 80G的机器 可以微调 70B-chat版本的模型吗

@i4never
Copy link
Contributor

i4never commented Sep 26, 2023

@zhangfan-algo 可以试试zero3+offload的方式、我们没有在这个配置下跑过、但是大概率全量微调没有问题。

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

2 participants