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.

Sign up for GitHub

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

Jump to bottom

RuntimeError: "nll_loss_out_frame" not implemented for 'Half' #387

Open

Li-Jicheng opened this issue Jun 28, 2024 · 2 comments

Labels

bug

Li-Jicheng commented Jun 28, 2024

跑https://colab.research.google.com/github/shibing624/MedicalGPT/blob/main/run_training_dpo_pipeline.ipynb#scrollTo=J5kYehpzESyt （run_training_dpo_pipeline.ipynb）这个脚本时，pretrain阶段报错

截屏2024-06-28 17 16 41

截屏2024-06-28 17 16 58

Li-Jicheng added the bug label

Owner

shibing624 commented Jun 28, 2024

去掉--fp16, 设置 --torch_dtype auto

Author

Li-Jicheng commented Jun 28, 2024

去掉--fp16, 设置 --torch_dtype auto

感谢回复，操作后依然报错

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment