feat: 增加日志管理

pipeline/__init__.py

@@ -1,3 +1,4 @@
+import logging
 from .tokenizer import BpeTokenizer
 from .text import TextNormalizer
 from .packing import SequencePacker
@@ -5,6 +6,10 @@ from .io import IOHandler
 from .processors import ProcessorFactory, BaseProcessor
 from .export import export_dataset
 from .cache import cache_jsonl
+from .utils import setup_logging
+
+# 配置项目级日志记录
+setup_logging()
 
 __all__ = [
     'BpeTokenizer',