data-juicer日志文件路径出现了问题,按照官方网站的技术文档的uv pip方式下载的data-juicer,运行后出现报错,求问是出现了什么问题
我的配置文件是
project_name: 'windows-fix'
dataset_path: 'D:/WorkRes/EnvDataJuicer/dj-practice/raw_data.jsonl'
np: 4
export_path: 'D:/WorkRes/EnvDataJuicer/dj-practice/processed_data.jsonl'
process:
- language_id_score_filter:
lang: 'zh'
min_score: 0.8
(D:\WorkRes\condaData\envs_dirs\env2-dj) PS D:\WorkRes\EnvDataJuicer\dj-practice> dj-process --config .\process.yaml
2026-03-20 14:18:24.879 | ERROR | __main__:10 - An error has been caught in function '<module>', process 'MainProcess' (16736), thread 'MainThread' (30512):
Traceback (most recent call last):
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
│ │ └ {'__name__': '__main__', '__doc__': None, '__package__': '', '__loader__': <zipimporter object "D:\WorkRes\condaData\envs_dir...
│ └ <code object <module> at 0x000001A6B57DFD60, file "D:\WorkRes\condaData\envs_dirs\env2-dj\Scripts\dj-process.exe\__main__.py"...
└ <function _run_code at 0x000001A6B557F640>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
│ └ {'__name__': '__main__', '__doc__': None, '__package__': '', '__loader__': <zipimporter object "D:\WorkRes\condaData\envs_dir...
└ <code object <module> at 0x000001A6B57DFD60, file "D:\WorkRes\condaData\envs_dirs\env2-dj\Scripts\dj-process.exe\__main__.py"...
> File "D:\WorkRes\condaData\envs_dirs\env2-dj\Scripts\dj-process.exe\__main__.py", line 10, in <module>
sys.exit(main())
│ │ └ <function main at 0x000001A6A7A15C60>
│ └ <built-in function exit>
└ <module 'sys' (built-in)>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\Lib\site-packages\tools\process_data.py", line 21, in main
cfg = init_configs()
└ <function init_configs at 0x000001A69E5049D0>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\config\config.py", line 824, in init_configs
cfg = init_setup_from_cfg(cfg, load_configs_only)
│ │ └ False
│ └ Namespace(config=[Path_fr(.\process.yaml, cwd=D:\WorkRes\EnvDataJuicer\dj-practice)], auto=False, auto_num=1000, hpo_config=N...
└ <function init_setup_from_cfg at 0x000001A69E504F70>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\config\config.py", line 920, in init_setup_from_cfg
setup_logger(
└ <function setup_logger at 0x000001A69C3383A0>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\utils\logger_utils.py", line 170, in setup_logger
logger.add(
│ └ <function Logger.add at 0x000001A6B76FE680>
└ <loguru.logger handlers=[(id=2, level=20, sink=<stderr>)]>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_file_sink.py", line 192, in __init__
self._create_file(path)
│ │ └ 'D:\\WorkRes\\EnvDataJuicer\\dj-practice\\20260320_061824_de1d34\\logs\\export_..\\processed_data.jsonl_time_20260320141824.txt'
│ └ <function FileSink._create_file at 0x000001A6B76917E0>
└ <loguru._file_sink.FileSink object at 0x000001A6A7B5D450>
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_file_sink.py", line 228, in _create_file
self._file = open(path, **self._kwargs)
│ │ │ │ └ {'mode': 'a', 'buffering': 1, 'encoding': 'utf8'}
│ │ │ └ <loguru._file_sink.FileSink object at 0x000001A6A7B5D450>
│ │ └ 'D:\\WorkRes\\EnvDataJuicer\\dj-practice\\20260320_061824_de1d34\\logs\\export_..\\processed_data.jsonl_time_20260320141824.txt'
│ └ None
└ <loguru._file_sink.FileSink object at 0x000001A6A7B5D450>
FileNotFoundError: [Errno 2] No such file or directory: 'D:\\WorkRes\\EnvDataJuicer\\dj-practice\\20260320_061824_de1d34\\logs\\export_..\\processed_data.jsonl_time_20260320141824.txt'
Traceback (most recent call last):
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\WorkRes\condaData\envs_dirs\env2-dj\Scripts\dj-process.exe\__main__.py", line 10, in <module>
sys.exit(main())
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_logger.py", line 1297, in catch_wrapper
return function(*args, **kwargs)
File "D:\WorkRes\condaData\envs_dirs\env2-dj\Lib\site-packages\tools\process_data.py", line 21, in main
cfg = init_configs()
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\config\config.py", line 824, in init_configs
cfg = init_setup_from_cfg(cfg, load_configs_only)
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\config\config.py", line 920, in init_setup_from_cfg
setup_logger(
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\data_juicer\utils\logger_utils.py", line 170, in setup_logger
logger.add(
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_logger.py", line 802, in add
wrapped_sink = FileSink(path, **kwargs)
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_file_sink.py", line 192, in __init__
self._create_file(path)
File "D:\WorkRes\condaData\envs_dirs\env2-dj\lib\site-packages\loguru\_file_sink.py", line 228, in _create_file
self._file = open(path, **self._kwargs)
FileNotFoundError: [Errno 2] No such file or directory: 'D:\\WorkRes\\EnvDataJuicer\\dj-practice\\20260320_061824_de1d34\\logs\\export_..\\processed_data.jsonl_time_20260320141824.txt'