kpfbert-kdpii / dataset_stats.json
townboy's picture
Upload KDPII fine-tuned model
c91ef0b verified
{
"source_file": "연대1_PII_dataset_V3.json",
"doc_count": 4981,
"sentence_count": 53778,
"examples_with_pii": 19037,
"positive_ratio": 0.353992,
"label_count": 33,
"entity_count_by_label": {
"PS_NAME": 2045,
"PS_NICKNAME": 1354,
"OGG_CLUB": 1269,
"LC_PLACE": 1201,
"CV_POSITION": 1166,
"LC_ADDRESS": 1154,
"OG_WORKPLACE": 1082,
"OGG_EDUCATION": 1045,
"OG_DEPARTMENT": 866,
"QT_CARD_NUMBER": 805,
"QT_ACCOUNT_NUMBER": 804,
"DT_BIRTH": 734,
"QT_PHONE": 713,
"FD_MAJOR": 711,
"QT_LENGTH": 707,
"QT_AGE": 700,
"QT_WEIGHT": 699,
"TMI_EMAIL": 618,
"LCP_COUNTRY": 613,
"QT_MOBILE": 608,
"PS_ID": 605,
"QT_GRADE": 564,
"OGG_RELIGION": 558,
"CV_SEX": 553,
"TM_BLOOD_TYPE": 467,
"TMI_SITE": 460,
"QT_PLATE_NUMBER": 457,
"CV_MILITARY_CAMP": 407,
"QT_DRIVER_NUMBER": 200,
"QT_RESIDENT_NUMBER": 200,
"QT_IP": 200,
"QT_ALIEN_NUMBER": 200,
"QT_PASSPORT_NUMBER": 200
},
"split_sentence_counts": {
"train": 42894,
"validation": 5463,
"test": 5421
},
"split_doc_counts": {
"train": 3984,
"validation": 498,
"test": 499
},
"seed": 42
}