Traceback (most recent call last):
File "C:\ChatGLM-6B\ptuning\main.py", line 430, in
main()
File "C:\ChatGLM-6B\ptuning\main.py", line 99, in main
raw_datasets = load_dataset(
File "C:\Python\Python\lib\site-packages\datasets\load.py", line 1797, in load_dataset
builder_instance.download_and_prepare(
File "C:\Python\Python\lib\site-packages\datasets\builder.py", line 890, in download_and_prepare
self._download_and_prepare(
File "C:\Python\Python\lib\site-packages\datasets\builder.py", line 985, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "C:\Python\Python\lib\site-packages\datasets\builder.py", line 1746, in _prepare_split
for job_id, done, content in self._prepare_split_single(
File "C:\Python\Python\lib\site-packages\datasets\builder.py", line 1891, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.builder.DatasetGenerationError: An error occurred while generating the dataset
训练自己的问题库时, 这两个json文件分别写什么内容呢
我看了下demo文件中的这俩文件,除了一个数量量大点,一个数据量小点,其它没什么区别
想去训练自己的库,把问题库写好了json格式,取名train.json,再复制了一份,取名dev.json,能正常跑下去。
不知有何区别
Environment
- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :