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

[BUG] <title>基于CoCo2017数据集进行qlora的finetune后,示例图片中的目标都无法定位到 #459

Open
2 tasks done
drenched9 opened this issue Aug 28, 2024 · 0 comments

Comments

@drenched9
Copy link

drenched9 commented Aug 28, 2024

是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?

  • 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?

  • 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

基于COCO2017数据集,将部分验证集,转换为Qwen-VL所需格式,并将目标归一化为(0, 1000],训练后效果很差。不但使用训练数据无法框出目标,连一开始可以的示例图片来测试也是报no box!
另外,不知道为啥,加载模型会出现如下很多layer层没有加载的警告,是不是因为跳过了这些层导致效果不佳呢?
Some weights of the model checkpoint at qwen/Qwen-VL-Chat-INT4 were not used when initializing QWenLMHeadModel: ... ...
20240828160757

期望行为 | Expected Behavior

期望能准确框出目标的位置

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS: Ubuntu 18.04
- Python:3.10.13
- Transformers:4.32.0
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):12.1

备注 | Anything else?

No response

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

1 participant