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

在使用PeftModel 和已经存在的training_args.peft_path进行继续训练的的模型权重冻结的问题 #576

Open
3 tasks done
dshwei opened this issue Oct 17, 2024 · 1 comment
Labels

Comments

@dshwei
Copy link

dshwei commented Oct 17, 2024

提交前必须检查以下项目

  • 请确保使用的是仓库最新代码(git pull),一些问题已被解决和修复。
  • 我已阅读项目文档FAQ章节并且已在Issue中对问题进行了搜索,没有找到相似问题和解决方案。
  • 第三方插件问题:例如llama.cppLangChaintext-generation-webui等,同时建议到对应的项目中查找解决方案。

问题类型

模型训练与精调

基础模型

Others

操作系统

Linux

详细描述问题

sh  Chinese-LLaMA-Alpaca-2/scripts/training/run_sft.sh

依赖情况(代码类问题务必提供)

bitsandbytes                             0.42.0
peft                                     0.11.1
sentence-transformers                    2.2.2
sentencepiece                            0.2.0
torch                                    2.4.0
torchaudio                               2.1.2
torchdata                                0.8.0
torchvision                              0.19.0
transformers                             4.43.4
transformers-stream-generator            0.0.5

运行日志或截图

ValueError: optimizer got an empty parameter list
Copy link

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.

@github-actions github-actions bot added the stale label Nov 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

1 participant