CPU报错

[Harry-hash]

为什么在CPU上跑tasks/squad/train.py的时候会有这个报错
“”“
Traceback (most recent call last):
File "/Users/hodge/Documents/GitHub/diceLoss/tasks/squad/train.py", line 369, in
main()
File "/Users/hodge/Documents/GitHub/diceLoss/tasks/squad/train.py", line 363, in main
trainer.fit(model)
File "/Users/hodge/opt/anaconda3/envs/diceloss/lib/python3.6/site-packages/pytorch_lightning/trainer/states.py", line 48, in wrapped_fn
result = fn(self, *args, **kwargs)
File "/Users/hodge/opt/anaconda3/envs/diceloss/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 1083, in fit
self.accelerator_backend.setup(model)
File "/Users/hodge/opt/anaconda3/envs/diceloss/lib/python3.6/site-packages/pytorch_lightning/accelerators/cpu_backend.py", line 26, in setup
raise MisconfigurationException('amp + cpu is not supported. Please use a GPU option')
pytorch_lightning.utilities.exceptions.MisconfigurationException: amp + cpu is not supported. Please use a GPU option
”“”
但是我已经把第一个参数--gpus="1"改成--gpus="0"了

[Harry-hash]

我的环境是这样的：
Package Version

---

absl-py 0.13.0
cachetools 4.2.2
certifi 2021.5.30
chardet 4.0.0
click 8.0.1
dataclasses 0.8
filelock 3.0.12
future 0.18.2
google-auth 1.32.1
google-auth-oauthlib 0.4.4
grpcio 1.38.1
idna 2.10
importlib-metadata 4.6.0
joblib 1.0.1
Markdown 3.3.4
mkl-fft 1.3.0
mkl-random 1.0.4
mkl-service 2.3.0
numpy 1.17.0
oauthlib 3.1.1
olefile 0.46
packaging 21.0
Pillow 8.2.0
pip 21.1.3
protobuf 3.17.3
pyasn1 0.4.8
pyasn1-modules 0.2.8
pyparsing 2.4.7
pytorch-lightning 0.9.0
PyYAML 5.4.1
regex 2021.7.1
requests 2.25.1
requests-oauthlib 1.3.0
rsa 4.7.2
sacremoses 0.0.45
sentencepiece 0.1.91
setuptools 52.0.0.post20210125
six 1.16.0
tensorboard 2.2.0
tensorboard-plugin-wit 1.8.0
tokenizers 0.9.3
torch 1.7.1
torchaudio 0.7.0a0+a853dff
torchvision 0.8.2
tqdm 4.61.1
transformers 3.5.1
typing-extensions 3.10.0.0
urllib3 1.26.6
Werkzeug 2.0.1
wheel 0.36.2
zipp 3.5.0

[xiaoya-li]

您好，非常抱歉，我们的repo是基于GPU机器进行开发的，并没有遇到您说的情况。
根据您提供的在CPU上运行的报错信息，感觉是这个--amp-backend这个参数设置的问题，麻烦请您参考pytorch-lightning==0.9.0的文档，https://pytorch-lightning.readthedocs.io/en/0.9.0/trainer.html#amp-backend
感谢！