We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
训练过程中 loss 突然降为零
No response
- OS: - Python: - Transformers: - PyTorch: - CUDA (`python -c 'import torch; print(torch.version.cuda)'`):
The text was updated successfully, but these errors were encountered:
我也遇到了单轮对话全量SFT,loss 变为零的情况,8卡训练会一直出现,4卡训练基本不出现
Sorry, something went wrong.
遇到了单论对话lora sft,loss 从step2 开始就为0的情况 8卡训练出现,单卡训练不出现
把 tune vision 设置为 false 之后这个问题不再出现了
有没有可能是设置的有效长度太短,导致loss都不计算了
这种情况应该不会后面loss全都变零
No branches or pull requests
是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?
当前行为 | Current Behavior
训练过程中 loss 突然降为零
期望行为 | Expected Behavior
No response
复现方法 | Steps To Reproduce
No response
运行环境 | Environment
备注 | Anything else?
No response
The text was updated successfully, but these errors were encountered: