MinhTriet commited on
Commit
2138b24
·
verified ·
1 Parent(s): d5388ad

Upload folder using huggingface_hub

Browse files
classification_report.json CHANGED
@@ -13,14 +13,14 @@
13
  },
14
  "CITY": {
15
  "precision": 0.9851,
16
- "recall": 0.9803,
17
- "f1-score": 0.9827,
18
  "support": 203
19
  },
20
  "CREDITCARDNUMBER": {
21
  "precision": 1.0,
22
- "recall": 1.0,
23
- "f1-score": 1.0,
24
  "support": 27
25
  },
26
  "DATE": {
@@ -30,9 +30,9 @@
30
  "support": 153
31
  },
32
  "DRIVERLICENSENUM": {
33
- "precision": 0.9333,
34
- "recall": 0.6667,
35
- "f1-score": 0.7778,
36
  "support": 21
37
  },
38
  "EMAIL": {
@@ -48,39 +48,39 @@
48
  "support": 70
49
  },
50
  "GIVENNAME": {
51
- "precision": 0.9678,
52
- "recall": 0.9894,
53
- "f1-score": 0.9785,
54
  "support": 850
55
  },
56
  "IDCARDNUM": {
57
- "precision": 0.9394,
58
- "recall": 0.949,
59
- "f1-score": 0.9442,
60
  "support": 98
61
  },
62
  "PASSPORTNUM": {
63
- "precision": 0.9091,
64
- "recall": 0.9756,
65
- "f1-score": 0.9412,
66
  "support": 41
67
  },
68
  "SOCIALNUM": {
69
- "precision": 0.8966,
70
- "recall": 0.8966,
71
- "f1-score": 0.8966,
72
  "support": 29
73
  },
74
  "STREET": {
75
- "precision": 1.0,
76
  "recall": 0.9735,
77
- "f1-score": 0.9865,
78
  "support": 113
79
  },
80
  "SURNAME": {
81
- "precision": 0.9419,
82
- "recall": 0.8391,
83
- "f1-score": 0.8875,
84
  "support": 348
85
  },
86
  "TAXNUM": {
@@ -114,21 +114,21 @@
114
  "support": 51
115
  },
116
  "OVERALL_MICRO": {
117
- "precision": 0.9719,
118
- "recall": 0.9644,
119
- "f1-score": 0.9681,
120
  "support": 2723
121
  },
122
  "OVERALL_MACRO": {
123
- "precision": 0.9663,
124
- "recall": 0.9543,
125
- "f1-score": 0.9588,
126
  "support": 2723
127
  },
128
  "OVERALL_WEIGHTED": {
129
- "precision": 0.9715,
130
- "recall": 0.9644,
131
- "f1-score": 0.9673,
132
  "support": 2723
133
  }
134
  }
 
13
  },
14
  "CITY": {
15
  "precision": 0.9851,
16
+ "recall": 0.9754,
17
+ "f1-score": 0.9802,
18
  "support": 203
19
  },
20
  "CREDITCARDNUMBER": {
21
  "precision": 1.0,
22
+ "recall": 0.8889,
23
+ "f1-score": 0.9412,
24
  "support": 27
25
  },
26
  "DATE": {
 
30
  "support": 153
31
  },
32
  "DRIVERLICENSENUM": {
33
+ "precision": 0.7895,
34
+ "recall": 0.7143,
35
+ "f1-score": 0.75,
36
  "support": 21
37
  },
38
  "EMAIL": {
 
48
  "support": 70
49
  },
50
  "GIVENNAME": {
51
+ "precision": 0.9711,
52
+ "recall": 0.9882,
53
+ "f1-score": 0.9796,
54
  "support": 850
55
  },
56
  "IDCARDNUM": {
57
+ "precision": 0.9,
58
+ "recall": 0.9184,
59
+ "f1-score": 0.9091,
60
  "support": 98
61
  },
62
  "PASSPORTNUM": {
63
+ "precision": 0.9286,
64
+ "recall": 0.9512,
65
+ "f1-score": 0.9398,
66
  "support": 41
67
  },
68
  "SOCIALNUM": {
69
+ "precision": 0.931,
70
+ "recall": 0.931,
71
+ "f1-score": 0.931,
72
  "support": 29
73
  },
74
  "STREET": {
75
+ "precision": 0.991,
76
  "recall": 0.9735,
77
+ "f1-score": 0.9821,
78
  "support": 113
79
  },
80
  "SURNAME": {
81
+ "precision": 0.935,
82
+ "recall": 0.8678,
83
+ "f1-score": 0.9001,
84
  "support": 348
85
  },
86
  "TAXNUM": {
 
114
  "support": 51
115
  },
116
  "OVERALL_MICRO": {
117
+ "precision": 0.9698,
118
+ "recall": 0.9655,
119
+ "f1-score": 0.9676,
120
  "support": 2723
121
  },
122
  "OVERALL_MACRO": {
123
+ "precision": 0.9588,
124
+ "recall": 0.951,
125
+ "f1-score": 0.9545,
126
  "support": 2723
127
  },
128
  "OVERALL_WEIGHTED": {
129
+ "precision": 0.9694,
130
+ "recall": 0.9655,
131
+ "f1-score": 0.9672,
132
  "support": 2723
133
  }
134
  }
classification_report_previous.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "AGE": {
3
+ "precision": 0.9516,
4
+ "recall": 0.9833,
5
+ "f1-score": 0.9672,
6
+ "support": 60
7
+ },
8
+ "BUILDINGNUM": {
9
+ "precision": 0.9808,
10
+ "recall": 0.9533,
11
+ "f1-score": 0.9668,
12
+ "support": 107
13
+ },
14
+ "CITY": {
15
+ "precision": 0.9851,
16
+ "recall": 0.9803,
17
+ "f1-score": 0.9827,
18
+ "support": 203
19
+ },
20
+ "CREDITCARDNUMBER": {
21
+ "precision": 1.0,
22
+ "recall": 1.0,
23
+ "f1-score": 1.0,
24
+ "support": 27
25
+ },
26
+ "DATE": {
27
+ "precision": 0.9935,
28
+ "recall": 1.0,
29
+ "f1-score": 0.9967,
30
+ "support": 153
31
+ },
32
+ "DRIVERLICENSENUM": {
33
+ "precision": 0.9333,
34
+ "recall": 0.6667,
35
+ "f1-score": 0.7778,
36
+ "support": 21
37
+ },
38
+ "EMAIL": {
39
+ "precision": 0.9912,
40
+ "recall": 1.0,
41
+ "f1-score": 0.9956,
42
+ "support": 112
43
+ },
44
+ "GENDER": {
45
+ "precision": 1.0,
46
+ "recall": 0.9857,
47
+ "f1-score": 0.9928,
48
+ "support": 70
49
+ },
50
+ "GIVENNAME": {
51
+ "precision": 0.9678,
52
+ "recall": 0.9894,
53
+ "f1-score": 0.9785,
54
+ "support": 850
55
+ },
56
+ "IDCARDNUM": {
57
+ "precision": 0.9394,
58
+ "recall": 0.949,
59
+ "f1-score": 0.9442,
60
+ "support": 98
61
+ },
62
+ "PASSPORTNUM": {
63
+ "precision": 0.9091,
64
+ "recall": 0.9756,
65
+ "f1-score": 0.9412,
66
+ "support": 41
67
+ },
68
+ "SOCIALNUM": {
69
+ "precision": 0.8966,
70
+ "recall": 0.8966,
71
+ "f1-score": 0.8966,
72
+ "support": 29
73
+ },
74
+ "STREET": {
75
+ "precision": 1.0,
76
+ "recall": 0.9735,
77
+ "f1-score": 0.9865,
78
+ "support": 113
79
+ },
80
+ "SURNAME": {
81
+ "precision": 0.9419,
82
+ "recall": 0.8391,
83
+ "f1-score": 0.8875,
84
+ "support": 348
85
+ },
86
+ "TAXNUM": {
87
+ "precision": 0.92,
88
+ "recall": 0.9583,
89
+ "f1-score": 0.9388,
90
+ "support": 24
91
+ },
92
+ "TELEPHONENUM": {
93
+ "precision": 0.9871,
94
+ "recall": 1.0,
95
+ "f1-score": 0.9935,
96
+ "support": 153
97
+ },
98
+ "TIME": {
99
+ "precision": 1.0,
100
+ "recall": 1.0,
101
+ "f1-score": 1.0,
102
+ "support": 144
103
+ },
104
+ "TITLE": {
105
+ "precision": 1.0,
106
+ "recall": 1.0,
107
+ "f1-score": 1.0,
108
+ "support": 119
109
+ },
110
+ "ZIPCODE": {
111
+ "precision": 0.9615,
112
+ "recall": 0.9804,
113
+ "f1-score": 0.9709,
114
+ "support": 51
115
+ },
116
+ "OVERALL_MICRO": {
117
+ "precision": 0.9719,
118
+ "recall": 0.9644,
119
+ "f1-score": 0.9681,
120
+ "support": 2723
121
+ },
122
+ "OVERALL_MACRO": {
123
+ "precision": 0.9663,
124
+ "recall": 0.9543,
125
+ "f1-score": 0.9588,
126
+ "support": 2723
127
+ },
128
+ "OVERALL_WEIGHTED": {
129
+ "precision": 0.9715,
130
+ "recall": 0.9644,
131
+ "f1-score": 0.9673,
132
+ "support": 2723
133
+ }
134
+ }
config.json CHANGED
@@ -105,7 +105,7 @@
105
  "pad_token_id": 0,
106
  "position_embedding_type": "absolute",
107
  "tie_word_embeddings": true,
108
- "transformers_version": "5.6.2",
109
  "type_vocab_size": 2,
110
  "use_cache": false,
111
  "vocab_size": 30522
 
105
  "pad_token_id": 0,
106
  "position_embedding_type": "absolute",
107
  "tie_word_embeddings": true,
108
+ "transformers_version": "5.13.0",
109
  "type_vocab_size": 2,
110
  "use_cache": false,
111
  "vocab_size": 30522
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a01797f695b9404aa34e067602c5513735345b43a800280907acb2d362ceced
3
  size 435709876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6bbc2d3903b68df21b24685af5e622a916a5764ae13eb37b84b7f72a11bc9f
3
  size 435709876
predictions.json CHANGED
@@ -17,7 +17,7 @@
17
  ],
18
  "predictions": [
19
  {
20
- "tag": "GIVENNAME",
21
  "start": 0,
22
  "end": 7,
23
  "value": "Erbagan"
@@ -423,8 +423,14 @@
423
  {
424
  "tag": "GIVENNAME",
425
  "start": 4,
426
- "end": 21,
427
- "value": "Samat Sandrakumar"
 
 
 
 
 
 
428
  },
429
  {
430
  "tag": "DRIVERLICENSENUM",
@@ -506,7 +512,7 @@
506
  "value": "Truchard"
507
  },
508
  {
509
- "tag": "CREDITCARDNUMBER",
510
  "start": 82,
511
  "end": 95,
512
  "value": "5038655754968"
@@ -924,7 +930,7 @@
924
  ],
925
  "predictions": [
926
  {
927
- "tag": "PASSPORTNUM",
928
  "start": 130,
929
  "end": 139,
930
  "value": "396886363"
@@ -2065,14 +2071,8 @@
2065
  {
2066
  "tag": "GIVENNAME",
2067
  "start": 22,
2068
- "end": 36,
2069
- "value": "Petagine Rühli"
2070
- },
2071
- {
2072
- "tag": "SURNAME",
2073
- "start": 37,
2074
- "end": 44,
2075
- "value": "Gauchet"
2076
  }
2077
  ]
2078
  },
@@ -2570,7 +2570,7 @@
2570
  "value": "Chayanne"
2571
  },
2572
  {
2573
- "tag": "GIVENNAME",
2574
  "start": 105,
2575
  "end": 115,
2576
  "value": "Sivalogini"
@@ -3187,8 +3187,14 @@
3187
  {
3188
  "tag": "GIVENNAME",
3189
  "start": 15,
3190
- "end": 27,
3191
- "value": "Ibraim Amara"
 
 
 
 
 
 
3192
  },
3193
  {
3194
  "tag": "ZIPCODE",
@@ -4403,8 +4409,14 @@
4403
  {
4404
  "tag": "GIVENNAME",
4405
  "start": 7,
4406
- "end": 15,
4407
- "value": "Zilke Ea"
 
 
 
 
 
 
4408
  },
4409
  {
4410
  "tag": "GIVENNAME",
@@ -4997,6 +5009,12 @@
4997
  "end": 38,
4998
  "value": "el Ka"
4999
  },
 
 
 
 
 
 
5000
  {
5001
  "tag": "STREET",
5002
  "start": 81,
@@ -5056,8 +5074,14 @@
5056
  {
5057
  "tag": "GIVENNAME",
5058
  "start": 5,
5059
- "end": 14,
5060
- "value": "Elijon Za"
 
 
 
 
 
 
5061
  },
5062
  {
5063
  "tag": "IDCARDNUM",
@@ -5327,14 +5351,14 @@
5327
  {
5328
  "tag": "GIVENNAME",
5329
  "start": 0,
5330
- "end": 8,
5331
- "value": "Kassiani"
5332
  },
5333
  {
5334
  "tag": "SURNAME",
5335
- "start": 9,
5336
- "end": 14,
5337
- "value": "Serve"
5338
  }
5339
  ]
5340
  },
@@ -5468,8 +5492,14 @@
5468
  {
5469
  "tag": "GIVENNAME",
5470
  "start": 76,
5471
- "end": 87,
5472
- "value": "Hussen Fred"
 
 
 
 
 
 
5473
  },
5474
  {
5475
  "tag": "BUILDINGNUM",
@@ -6095,8 +6125,14 @@
6095
  {
6096
  "tag": "GIVENNAME",
6097
  "start": 55,
 
 
 
 
 
 
6098
  "end": 70,
6099
- "value": "Silvian Insolia"
6100
  }
6101
  ]
6102
  },
@@ -6477,8 +6513,8 @@
6477
  {
6478
  "tag": "IDCARDNUM",
6479
  "start": 57,
6480
- "end": 67,
6481
- "value": "5O9EZWJDYB"
6482
  }
6483
  ]
6484
  },
@@ -6897,14 +6933,8 @@
6897
  {
6898
  "tag": "GIVENNAME",
6899
  "start": 27,
6900
- "end": 34,
6901
- "value": "Loghman"
6902
- },
6903
- {
6904
- "tag": "SURNAME",
6905
- "start": 35,
6906
  "end": 42,
6907
- "value": "Marsell"
6908
  }
6909
  ]
6910
  },
@@ -7283,8 +7313,14 @@
7283
  {
7284
  "tag": "GIVENNAME",
7285
  "start": 0,
7286
- "end": 11,
7287
- "value": "Pasha Frank"
 
 
 
 
 
 
7288
  },
7289
  {
7290
  "tag": "GIVENNAME",
@@ -7912,7 +7948,7 @@
7912
  "value": "Xhemail"
7913
  },
7914
  {
7915
- "tag": "IDCARDNUM",
7916
  "start": 71,
7917
  "end": 84,
7918
  "value": "ZA9QIW3XKU0DU"
@@ -8050,8 +8086,8 @@
8050
  {
8051
  "tag": "GIVENNAME",
8052
  "start": 118,
8053
- "end": 122,
8054
- "value": "Rust"
8055
  }
8056
  ]
8057
  },
@@ -8148,8 +8184,8 @@
8148
  {
8149
  "tag": "SOCIALNUM",
8150
  "start": 84,
8151
- "end": 86,
8152
- "value": "83"
8153
  }
8154
  ]
8155
  },
@@ -10181,8 +10217,14 @@
10181
  {
10182
  "tag": "GIVENNAME",
10183
  "start": 0,
 
 
 
 
 
 
10184
  "end": 12,
10185
- "value": "Aidas Yarali"
10186
  },
10187
  {
10188
  "tag": "IDCARDNUM",
@@ -13944,8 +13986,8 @@
13944
  {
13945
  "tag": "GIVENNAME",
13946
  "start": 0,
13947
- "end": 16,
13948
- "value": "Üsame Sivagnanas"
13949
  }
13950
  ]
13951
  },
@@ -15267,8 +15309,14 @@
15267
  {
15268
  "tag": "GIVENNAME",
15269
  "start": 0,
15270
- "end": 11,
15271
- "value": "Giselène Sü"
 
 
 
 
 
 
15272
  },
15273
  {
15274
  "tag": "TITLE",
@@ -16468,10 +16516,10 @@
16468
  ],
16469
  "predictions": [
16470
  {
16471
- "tag": "IDCARDNUM",
16472
  "start": 20,
16473
- "end": 30,
16474
- "value": "ZKSO2WCDUM"
16475
  },
16476
  {
16477
  "tag": "SOCIALNUM",
@@ -17310,17 +17358,11 @@
17310
  }
17311
  ],
17312
  "predictions": [
17313
- {
17314
- "tag": "GIVENNAME",
17315
- "start": 17,
17316
- "end": 26,
17317
- "value": "Liashenko"
17318
- },
17319
  {
17320
  "tag": "SURNAME",
17321
- "start": 27,
17322
  "end": 32,
17323
- "value": "Fuego"
17324
  },
17325
  {
17326
  "tag": "BUILDINGNUM",
@@ -17476,14 +17518,8 @@
17476
  {
17477
  "tag": "GIVENNAME",
17478
  "start": 127,
17479
- "end": 133,
17480
- "value": "Osanna"
17481
- },
17482
- {
17483
- "tag": "SURNAME",
17484
- "start": 134,
17485
  "end": 141,
17486
- "value": "Sejaric"
17487
  }
17488
  ]
17489
  },
@@ -19245,10 +19281,10 @@
19245
  ],
19246
  "predictions": [
19247
  {
19248
- "tag": "CITY",
19249
  "start": 59,
19250
- "end": 71,
19251
- "value": "Grand-Remous"
19252
  },
19253
  {
19254
  "tag": "BUILDINGNUM",
@@ -19769,8 +19805,8 @@
19769
  {
19770
  "tag": "SURNAME",
19771
  "start": 103,
19772
- "end": 105,
19773
- "value": "Am"
19774
  }
19775
  ]
19776
  },
@@ -21519,8 +21555,8 @@
21519
  {
21520
  "tag": "DRIVERLICENSENUM",
21521
  "start": 84,
21522
- "end": 87,
21523
- "value": "304"
21524
  }
21525
  ]
21526
  },
@@ -21642,14 +21678,8 @@
21642
  {
21643
  "tag": "GIVENNAME",
21644
  "start": 90,
21645
- "end": 95,
21646
- "value": "Munir"
21647
- },
21648
- {
21649
- "tag": "SURNAME",
21650
- "start": 96,
21651
  "end": 101,
21652
- "value": "Baset"
21653
  },
21654
  {
21655
  "tag": "STREET",
@@ -23550,7 +23580,7 @@
23550
  "value": "743.756.8915"
23551
  },
23552
  {
23553
- "tag": "CREDITCARDNUMBER",
23554
  "start": 179,
23555
  "end": 192,
23556
  "value": "4937483295656"
@@ -23642,10 +23672,10 @@
23642
  ],
23643
  "predictions": [
23644
  {
23645
- "tag": "TAXNUM",
23646
  "start": 47,
23647
- "end": 50,
23648
- "value": "326"
23649
  },
23650
  {
23651
  "tag": "TAXNUM",
@@ -23742,8 +23772,14 @@
23742
  {
23743
  "tag": "GIVENNAME",
23744
  "start": 23,
 
 
 
 
 
 
23745
  "end": 39,
23746
- "value": "Brooklyn Casiano"
23747
  },
23748
  {
23749
  "tag": "CITY",
@@ -23932,8 +23968,8 @@
23932
  {
23933
  "tag": "GIVENNAME",
23934
  "start": 20,
23935
- "end": 28,
23936
- "value": "Saïa Ron"
23937
  },
23938
  {
23939
  "tag": "CITY",
@@ -25760,17 +25796,11 @@
25760
  }
25761
  ],
25762
  "predictions": [
25763
- {
25764
- "tag": "GIVENNAME",
25765
- "start": 0,
25766
- "end": 6,
25767
- "value": "Sayuri"
25768
- },
25769
  {
25770
  "tag": "SURNAME",
25771
- "start": 7,
25772
  "end": 25,
25773
- "value": "Rybaniec Deschênes"
25774
  },
25775
  {
25776
  "tag": "TELEPHONENUM",
@@ -25824,8 +25854,14 @@
25824
  {
25825
  "tag": "GIVENNAME",
25826
  "start": 32,
25827
- "end": 48,
25828
- "value": "Hermella Nedjadi"
 
 
 
 
 
 
25829
  }
25830
  ]
25831
  },
@@ -27221,7 +27257,7 @@
27221
  "value": "1784327053"
27222
  },
27223
  {
27224
- "tag": "PASSPORTNUM",
27225
  "start": 52,
27226
  "end": 62,
27227
  "value": "9970474386"
@@ -27343,7 +27379,7 @@
27343
  "value": "372638754150211"
27344
  },
27345
  {
27346
- "tag": "CREDITCARDNUMBER",
27347
  "start": 148,
27348
  "end": 161,
27349
  "value": "4605255890885"
@@ -28060,8 +28096,8 @@
28060
  {
28061
  "tag": "CITY",
28062
  "start": 33,
28063
- "end": 41,
28064
- "value": "Homewood"
28065
  },
28066
  {
28067
  "tag": "GENDER",
@@ -28220,8 +28256,8 @@
28220
  {
28221
  "tag": "SURNAME",
28222
  "start": 57,
28223
- "end": 60,
28224
- "value": "Bug"
28225
  }
28226
  ]
28227
  },
@@ -28983,8 +29019,14 @@
28983
  {
28984
  "tag": "GIVENNAME",
28985
  "start": 64,
 
 
 
 
 
 
28986
  "end": 79,
28987
- "value": "Bertille Nassar"
28988
  }
28989
  ]
28990
  },
@@ -29592,8 +29634,8 @@
29592
  {
29593
  "tag": "SURNAME",
29594
  "start": 0,
29595
- "end": 2,
29596
- "value": "Zu"
29597
  }
29598
  ]
29599
  },
@@ -29744,10 +29786,10 @@
29744
  "value": "Glencairn"
29745
  },
29746
  {
29747
- "tag": "SOCIALNUM",
29748
  "start": 90,
29749
- "end": 94,
29750
- "value": "1653"
29751
  },
29752
  {
29753
  "tag": "PASSPORTNUM",
@@ -30138,10 +30180,10 @@
30138
  ],
30139
  "predictions": [
30140
  {
30141
- "tag": "IDCARDNUM",
30142
  "start": 130,
30143
- "end": 140,
30144
- "value": "NQICFCTM9X"
30145
  }
30146
  ]
30147
  },
@@ -30411,12 +30453,6 @@
30411
  }
30412
  ],
30413
  "predictions": [
30414
- {
30415
- "tag": "CITY",
30416
- "start": 20,
30417
- "end": 23,
30418
- "value": "acc"
30419
- },
30420
  {
30421
  "tag": "STREET",
30422
  "start": 80,
@@ -30773,8 +30809,8 @@
30773
  {
30774
  "tag": "GIVENNAME",
30775
  "start": 49,
30776
- "end": 63,
30777
- "value": "Lawrence Vicko"
30778
  },
30779
  {
30780
  "tag": "EMAIL",
@@ -31850,8 +31886,8 @@
31850
  {
31851
  "tag": "DRIVERLICENSENUM",
31852
  "start": 58,
31853
- "end": 59,
31854
- "value": "4"
31855
  }
31856
  ]
31857
  },
@@ -32016,8 +32052,8 @@
32016
  {
32017
  "tag": "SURNAME",
32018
  "start": 19,
32019
- "end": 22,
32020
- "value": "Maï"
32021
  },
32022
  {
32023
  "tag": "TAXNUM",
@@ -32219,8 +32255,8 @@
32219
  {
32220
  "tag": "SURNAME",
32221
  "start": 17,
32222
- "end": 35,
32223
- "value": "Domian Dangel here"
32224
  },
32225
  {
32226
  "tag": "IDCARDNUM",
@@ -32650,8 +32686,8 @@
32650
  {
32651
  "tag": "DRIVERLICENSENUM",
32652
  "start": 45,
32653
- "end": 48,
32654
- "value": "2J7"
32655
  }
32656
  ]
32657
  },
@@ -32736,8 +32772,14 @@
32736
  {
32737
  "tag": "GIVENNAME",
32738
  "start": 111,
32739
- "end": 121,
32740
- "value": "Dizara Val"
 
 
 
 
 
 
32741
  },
32742
  {
32743
  "tag": "DATE",
@@ -33474,8 +33516,14 @@
33474
  {
33475
  "tag": "GIVENNAME",
33476
  "start": 29,
 
 
 
 
 
 
33477
  "end": 42,
33478
- "value": "Astrite Fabia"
33479
  },
33480
  {
33481
  "tag": "EMAIL",
@@ -33788,8 +33836,8 @@
33788
  {
33789
  "tag": "TAXNUM",
33790
  "start": 20,
33791
- "end": 30,
33792
- "value": "0902009013"
33793
  }
33794
  ]
33795
  },
@@ -34088,10 +34136,10 @@
34088
  ],
34089
  "predictions": [
34090
  {
34091
- "tag": "PASSPORTNUM",
34092
  "start": 68,
34093
- "end": 77,
34094
- "value": "465528360"
34095
  },
34096
  {
34097
  "tag": "SOCIALNUM",
@@ -34475,8 +34523,14 @@
34475
  {
34476
  "tag": "GIVENNAME",
34477
  "start": 90,
34478
- "end": 99,
34479
- "value": "Dastan Go"
 
 
 
 
 
 
34480
  },
34481
  {
34482
  "tag": "CITY",
@@ -35023,8 +35077,8 @@
35023
  {
35024
  "tag": "GIVENNAME",
35025
  "start": 184,
35026
- "end": 190,
35027
- "value": "Palzom"
35028
  }
35029
  ]
35030
  },
@@ -36409,7 +36463,7 @@
36409
  "value": "Master"
36410
  },
36411
  {
36412
- "tag": "SURNAME",
36413
  "start": 30,
36414
  "end": 36,
36415
  "value": "Maddox"
@@ -37125,8 +37179,8 @@
37125
  {
37126
  "tag": "GIVENNAME",
37127
  "start": 78,
37128
- "end": 90,
37129
- "value": "Cris Caetana"
37130
  }
37131
  ]
37132
  },
@@ -37423,12 +37477,6 @@
37423
  "end": 7,
37424
  "value": "Suhreta"
37425
  },
37426
- {
37427
- "tag": "GIVENNAME",
37428
- "start": 9,
37429
- "end": 14,
37430
- "value": "Honey"
37431
- },
37432
  {
37433
  "tag": "BUILDINGNUM",
37434
  "start": 36,
@@ -37904,7 +37952,7 @@
37904
  "value": "OU6758730"
37905
  },
37906
  {
37907
- "tag": "IDCARDNUM",
37908
  "start": 82,
37909
  "end": 92,
37910
  "value": "CDBSROOFJA"
@@ -38305,8 +38353,8 @@
38305
  {
38306
  "tag": "CITY",
38307
  "start": 93,
38308
- "end": 103,
38309
- "value": "Fairmeadow"
38310
  }
38311
  ]
38312
  },
@@ -38330,14 +38378,14 @@
38330
  {
38331
  "tag": "GIVENNAME",
38332
  "start": 29,
38333
- "end": 35,
38334
- "value": "Merens"
38335
  },
38336
  {
38337
  "tag": "SURNAME",
38338
- "start": 36,
38339
  "end": 58,
38340
- "value": "Sarel Lunter Bahtijari"
38341
  }
38342
  ]
38343
  },
@@ -38521,8 +38569,14 @@
38521
  {
38522
  "tag": "GIVENNAME",
38523
  "start": 9,
38524
- "end": 20,
38525
- "value": "Dorothe Vaz"
 
 
 
 
 
 
38526
  }
38527
  ]
38528
  },
 
17
  ],
18
  "predictions": [
19
  {
20
+ "tag": "SURNAME",
21
  "start": 0,
22
  "end": 7,
23
  "value": "Erbagan"
 
423
  {
424
  "tag": "GIVENNAME",
425
  "start": 4,
426
+ "end": 9,
427
+ "value": "Samat"
428
+ },
429
+ {
430
+ "tag": "SURNAME",
431
+ "start": 10,
432
+ "end": 16,
433
+ "value": "Sandra"
434
  },
435
  {
436
  "tag": "DRIVERLICENSENUM",
 
512
  "value": "Truchard"
513
  },
514
  {
515
+ "tag": "IDCARDNUM",
516
  "start": 82,
517
  "end": 95,
518
  "value": "5038655754968"
 
930
  ],
931
  "predictions": [
932
  {
933
+ "tag": "TAXNUM",
934
  "start": 130,
935
  "end": 139,
936
  "value": "396886363"
 
2071
  {
2072
  "tag": "GIVENNAME",
2073
  "start": 22,
2074
+ "end": 33,
2075
+ "value": "Petagine Rü"
 
 
 
 
 
 
2076
  }
2077
  ]
2078
  },
 
2570
  "value": "Chayanne"
2571
  },
2572
  {
2573
+ "tag": "CITY",
2574
  "start": 105,
2575
  "end": 115,
2576
  "value": "Sivalogini"
 
3187
  {
3188
  "tag": "GIVENNAME",
3189
  "start": 15,
3190
+ "end": 33,
3191
+ "value": "Ibraim Amarasingha"
3192
+ },
3193
+ {
3194
+ "tag": "SURNAME",
3195
+ "start": 34,
3196
+ "end": 43,
3197
+ "value": "Käshammer"
3198
  },
3199
  {
3200
  "tag": "ZIPCODE",
 
4409
  {
4410
  "tag": "GIVENNAME",
4411
  "start": 7,
4412
+ "end": 12,
4413
+ "value": "Zilke"
4414
+ },
4415
+ {
4416
+ "tag": "SURNAME",
4417
+ "start": 13,
4418
+ "end": 23,
4419
+ "value": "Eades Joos"
4420
  },
4421
  {
4422
  "tag": "GIVENNAME",
 
5009
  "end": 38,
5010
  "value": "el Ka"
5011
  },
5012
+ {
5013
+ "tag": "SURNAME",
5014
+ "start": 41,
5015
+ "end": 53,
5016
+ "value": "Frundi Bagic"
5017
+ },
5018
  {
5019
  "tag": "STREET",
5020
  "start": 81,
 
5074
  {
5075
  "tag": "GIVENNAME",
5076
  "start": 5,
5077
+ "end": 11,
5078
+ "value": "Elijon"
5079
+ },
5080
+ {
5081
+ "tag": "SURNAME",
5082
+ "start": 12,
5083
+ "end": 37,
5084
+ "value": "Zabedin Qalandari Sikiric"
5085
  },
5086
  {
5087
  "tag": "IDCARDNUM",
 
5351
  {
5352
  "tag": "GIVENNAME",
5353
  "start": 0,
5354
+ "end": 16,
5355
+ "value": "Kassiani Serveta"
5356
  },
5357
  {
5358
  "tag": "SURNAME",
5359
+ "start": 17,
5360
+ "end": 36,
5361
+ "value": "Ajith Sonnentrücker"
5362
  }
5363
  ]
5364
  },
 
5492
  {
5493
  "tag": "GIVENNAME",
5494
  "start": 76,
5495
+ "end": 82,
5496
+ "value": "Hussen"
5497
+ },
5498
+ {
5499
+ "tag": "SURNAME",
5500
+ "start": 83,
5501
+ "end": 88,
5502
+ "value": "Frede"
5503
  },
5504
  {
5505
  "tag": "BUILDINGNUM",
 
6125
  {
6126
  "tag": "GIVENNAME",
6127
  "start": 55,
6128
+ "end": 62,
6129
+ "value": "Silvian"
6130
+ },
6131
+ {
6132
+ "tag": "SURNAME",
6133
+ "start": 63,
6134
  "end": 70,
6135
+ "value": "Insolia"
6136
  }
6137
  ]
6138
  },
 
6513
  {
6514
  "tag": "IDCARDNUM",
6515
  "start": 57,
6516
+ "end": 64,
6517
+ "value": "5O9EZWJ"
6518
  }
6519
  ]
6520
  },
 
6933
  {
6934
  "tag": "GIVENNAME",
6935
  "start": 27,
 
 
 
 
 
 
6936
  "end": 42,
6937
+ "value": "Loghman Marsell"
6938
  }
6939
  ]
6940
  },
 
7313
  {
7314
  "tag": "GIVENNAME",
7315
  "start": 0,
7316
+ "end": 5,
7317
+ "value": "Pasha"
7318
+ },
7319
+ {
7320
+ "tag": "SURNAME",
7321
+ "start": 6,
7322
+ "end": 14,
7323
+ "value": "Franklim"
7324
  },
7325
  {
7326
  "tag": "GIVENNAME",
 
7948
  "value": "Xhemail"
7949
  },
7950
  {
7951
+ "tag": "DRIVERLICENSENUM",
7952
  "start": 71,
7953
  "end": 84,
7954
  "value": "ZA9QIW3XKU0DU"
 
8086
  {
8087
  "tag": "GIVENNAME",
8088
  "start": 118,
8089
+ "end": 125,
8090
+ "value": "Rustemi"
8091
  }
8092
  ]
8093
  },
 
8184
  {
8185
  "tag": "SOCIALNUM",
8186
  "start": 84,
8187
+ "end": 94,
8188
+ "value": "8358776121"
8189
  }
8190
  ]
8191
  },
 
10217
  {
10218
  "tag": "GIVENNAME",
10219
  "start": 0,
10220
+ "end": 5,
10221
+ "value": "Aidas"
10222
+ },
10223
+ {
10224
+ "tag": "SURNAME",
10225
+ "start": 6,
10226
  "end": 12,
10227
+ "value": "Yarali"
10228
  },
10229
  {
10230
  "tag": "IDCARDNUM",
 
13986
  {
13987
  "tag": "GIVENNAME",
13988
  "start": 0,
13989
+ "end": 14,
13990
+ "value": "Üsame Sivagnan"
13991
  }
13992
  ]
13993
  },
 
15309
  {
15310
  "tag": "GIVENNAME",
15311
  "start": 0,
15312
+ "end": 8,
15313
+ "value": "Giselène"
15314
+ },
15315
+ {
15316
+ "tag": "SURNAME",
15317
+ "start": 9,
15318
+ "end": 14,
15319
+ "value": "Süsli"
15320
  },
15321
  {
15322
  "tag": "TITLE",
 
16516
  ],
16517
  "predictions": [
16518
  {
16519
+ "tag": "DRIVERLICENSENUM",
16520
  "start": 20,
16521
+ "end": 21,
16522
+ "value": "Z"
16523
  },
16524
  {
16525
  "tag": "SOCIALNUM",
 
17358
  }
17359
  ],
17360
  "predictions": [
 
 
 
 
 
 
17361
  {
17362
  "tag": "SURNAME",
17363
+ "start": 17,
17364
  "end": 32,
17365
+ "value": "Liashenko Fuego"
17366
  },
17367
  {
17368
  "tag": "BUILDINGNUM",
 
17518
  {
17519
  "tag": "GIVENNAME",
17520
  "start": 127,
 
 
 
 
 
 
17521
  "end": 141,
17522
+ "value": "Osanna Sejaric"
17523
  }
17524
  ]
17525
  },
 
19281
  ],
19282
  "predictions": [
19283
  {
19284
+ "tag": "STREET",
19285
  "start": 59,
19286
+ "end": 67,
19287
+ "value": "Grand-Re"
19288
  },
19289
  {
19290
  "tag": "BUILDINGNUM",
 
19805
  {
19806
  "tag": "SURNAME",
19807
  "start": 103,
19808
+ "end": 119,
19809
+ "value": "Ambeau Cothereau"
19810
  }
19811
  ]
19812
  },
 
21555
  {
21556
  "tag": "DRIVERLICENSENUM",
21557
  "start": 84,
21558
+ "end": 92,
21559
+ "value": "30451213"
21560
  }
21561
  ]
21562
  },
 
21678
  {
21679
  "tag": "GIVENNAME",
21680
  "start": 90,
 
 
 
 
 
 
21681
  "end": 101,
21682
+ "value": "Munir Baset"
21683
  },
21684
  {
21685
  "tag": "STREET",
 
23580
  "value": "743.756.8915"
23581
  },
23582
  {
23583
+ "tag": "IDCARDNUM",
23584
  "start": 179,
23585
  "end": 192,
23586
  "value": "4937483295656"
 
23672
  ],
23673
  "predictions": [
23674
  {
23675
+ "tag": "PASSPORTNUM",
23676
  "start": 47,
23677
+ "end": 56,
23678
+ "value": "326522619"
23679
  },
23680
  {
23681
  "tag": "TAXNUM",
 
23772
  {
23773
  "tag": "GIVENNAME",
23774
  "start": 23,
23775
+ "end": 31,
23776
+ "value": "Brooklyn"
23777
+ },
23778
+ {
23779
+ "tag": "SURNAME",
23780
+ "start": 32,
23781
  "end": 39,
23782
+ "value": "Casiano"
23783
  },
23784
  {
23785
  "tag": "CITY",
 
23968
  {
23969
  "tag": "GIVENNAME",
23970
  "start": 20,
23971
+ "end": 33,
23972
+ "value": "Saïa Rongfang"
23973
  },
23974
  {
23975
  "tag": "CITY",
 
25796
  }
25797
  ],
25798
  "predictions": [
 
 
 
 
 
 
25799
  {
25800
  "tag": "SURNAME",
25801
+ "start": 0,
25802
  "end": 25,
25803
+ "value": "Sayuri Rybaniec Deschênes"
25804
  },
25805
  {
25806
  "tag": "TELEPHONENUM",
 
25854
  {
25855
  "tag": "GIVENNAME",
25856
  "start": 32,
25857
+ "end": 40,
25858
+ "value": "Hermella"
25859
+ },
25860
+ {
25861
+ "tag": "SURNAME",
25862
+ "start": 41,
25863
+ "end": 44,
25864
+ "value": "Ned"
25865
  }
25866
  ]
25867
  },
 
27257
  "value": "1784327053"
27258
  },
27259
  {
27260
+ "tag": "SOCIALNUM",
27261
  "start": 52,
27262
  "end": 62,
27263
  "value": "9970474386"
 
27379
  "value": "372638754150211"
27380
  },
27381
  {
27382
+ "tag": "IDCARDNUM",
27383
  "start": 148,
27384
  "end": 161,
27385
  "value": "4605255890885"
 
28096
  {
28097
  "tag": "CITY",
28098
  "start": 33,
28099
+ "end": 37,
28100
+ "value": "Home"
28101
  },
28102
  {
28103
  "tag": "GENDER",
 
28256
  {
28257
  "tag": "SURNAME",
28258
  "start": 57,
28259
+ "end": 63,
28260
+ "value": "Bugnon"
28261
  }
28262
  ]
28263
  },
 
29019
  {
29020
  "tag": "GIVENNAME",
29021
  "start": 64,
29022
+ "end": 72,
29023
+ "value": "Bertille"
29024
+ },
29025
+ {
29026
+ "tag": "SURNAME",
29027
+ "start": 73,
29028
  "end": 79,
29029
+ "value": "Nassar"
29030
  }
29031
  ]
29032
  },
 
29634
  {
29635
  "tag": "SURNAME",
29636
  "start": 0,
29637
+ "end": 25,
29638
+ "value": "Zufferey Gutenhan Morella"
29639
  }
29640
  ]
29641
  },
 
29786
  "value": "Glencairn"
29787
  },
29788
  {
29789
+ "tag": "IDCARDNUM",
29790
  "start": 90,
29791
+ "end": 100,
29792
+ "value": "1653144036"
29793
  },
29794
  {
29795
  "tag": "PASSPORTNUM",
 
30180
  ],
30181
  "predictions": [
30182
  {
30183
+ "tag": "DRIVERLICENSENUM",
30184
  "start": 130,
30185
+ "end": 136,
30186
+ "value": "NQICFC"
30187
  }
30188
  ]
30189
  },
 
30453
  }
30454
  ],
30455
  "predictions": [
 
 
 
 
 
 
30456
  {
30457
  "tag": "STREET",
30458
  "start": 80,
 
30809
  {
30810
  "tag": "GIVENNAME",
30811
  "start": 49,
30812
+ "end": 61,
30813
+ "value": "Lawrence Vic"
30814
  },
30815
  {
30816
  "tag": "EMAIL",
 
31886
  {
31887
  "tag": "DRIVERLICENSENUM",
31888
  "start": 58,
31889
+ "end": 68,
31890
+ "value": "4KIEV2OWI9"
31891
  }
31892
  ]
31893
  },
 
32052
  {
32053
  "tag": "SURNAME",
32054
  "start": 19,
32055
+ "end": 23,
32056
+ "value": "Maïc"
32057
  },
32058
  {
32059
  "tag": "TAXNUM",
 
32255
  {
32256
  "tag": "SURNAME",
32257
  "start": 17,
32258
+ "end": 30,
32259
+ "value": "Domian Dangel"
32260
  },
32261
  {
32262
  "tag": "IDCARDNUM",
 
32686
  {
32687
  "tag": "DRIVERLICENSENUM",
32688
  "start": 45,
32689
+ "end": 55,
32690
+ "value": "2J7FRU8TWG"
32691
  }
32692
  ]
32693
  },
 
32772
  {
32773
  "tag": "GIVENNAME",
32774
  "start": 111,
32775
+ "end": 117,
32776
+ "value": "Dizara"
32777
+ },
32778
+ {
32779
+ "tag": "SURNAME",
32780
+ "start": 118,
32781
+ "end": 127,
32782
+ "value": "Valquiria"
32783
  },
32784
  {
32785
  "tag": "DATE",
 
33516
  {
33517
  "tag": "GIVENNAME",
33518
  "start": 29,
33519
+ "end": 36,
33520
+ "value": "Astrite"
33521
+ },
33522
+ {
33523
+ "tag": "SURNAME",
33524
+ "start": 37,
33525
  "end": 42,
33526
+ "value": "Fabia"
33527
  },
33528
  {
33529
  "tag": "EMAIL",
 
33836
  {
33837
  "tag": "TAXNUM",
33838
  "start": 20,
33839
+ "end": 22,
33840
+ "value": "09"
33841
  }
33842
  ]
33843
  },
 
34136
  ],
34137
  "predictions": [
34138
  {
34139
+ "tag": "IDCARDNUM",
34140
  "start": 68,
34141
+ "end": 70,
34142
+ "value": "46"
34143
  },
34144
  {
34145
  "tag": "SOCIALNUM",
 
34523
  {
34524
  "tag": "GIVENNAME",
34525
  "start": 90,
34526
+ "end": 96,
34527
+ "value": "Dastan"
34528
+ },
34529
+ {
34530
+ "tag": "SURNAME",
34531
+ "start": 97,
34532
+ "end": 104,
34533
+ "value": "Gonçala"
34534
  },
34535
  {
34536
  "tag": "CITY",
 
35077
  {
35078
  "tag": "GIVENNAME",
35079
  "start": 184,
35080
+ "end": 187,
35081
+ "value": "Pal"
35082
  }
35083
  ]
35084
  },
 
36463
  "value": "Master"
36464
  },
36465
  {
36466
+ "tag": "GIVENNAME",
36467
  "start": 30,
36468
  "end": 36,
36469
  "value": "Maddox"
 
37179
  {
37180
  "tag": "GIVENNAME",
37181
  "start": 78,
37182
+ "end": 85,
37183
+ "value": "Cris Ca"
37184
  }
37185
  ]
37186
  },
 
37477
  "end": 7,
37478
  "value": "Suhreta"
37479
  },
 
 
 
 
 
 
37480
  {
37481
  "tag": "BUILDINGNUM",
37482
  "start": 36,
 
37952
  "value": "OU6758730"
37953
  },
37954
  {
37955
+ "tag": "DRIVERLICENSENUM",
37956
  "start": 82,
37957
  "end": 92,
37958
  "value": "CDBSROOFJA"
 
38353
  {
38354
  "tag": "CITY",
38355
  "start": 93,
38356
+ "end": 99,
38357
+ "value": "Fairme"
38358
  }
38359
  ]
38360
  },
 
38378
  {
38379
  "tag": "GIVENNAME",
38380
  "start": 29,
38381
+ "end": 41,
38382
+ "value": "Merens Sarel"
38383
  },
38384
  {
38385
  "tag": "SURNAME",
38386
+ "start": 42,
38387
  "end": 58,
38388
+ "value": "Lunter Bahtijari"
38389
  }
38390
  ]
38391
  },
 
38569
  {
38570
  "tag": "GIVENNAME",
38571
  "start": 9,
38572
+ "end": 16,
38573
+ "value": "Dorothe"
38574
+ },
38575
+ {
38576
+ "tag": "SURNAME",
38577
+ "start": 17,
38578
+ "end": 23,
38579
+ "value": "Vaz Do"
38580
  }
38581
  ]
38582
  },
tokenizer_config.json CHANGED
@@ -6,11 +6,18 @@
6
  "is_local": false,
7
  "local_files_only": false,
8
  "mask_token": "[MASK]",
 
9
  "model_max_length": 512,
 
10
  "pad_token": "[PAD]",
 
 
11
  "sep_token": "[SEP]",
 
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",
 
 
15
  "unk_token": "[UNK]"
16
  }
 
6
  "is_local": false,
7
  "local_files_only": false,
8
  "mask_token": "[MASK]",
9
+ "max_length": 384,
10
  "model_max_length": 512,
11
+ "pad_to_multiple_of": null,
12
  "pad_token": "[PAD]",
13
+ "pad_token_type_id": 0,
14
+ "padding_side": "right",
15
  "sep_token": "[SEP]",
16
+ "stride": 0,
17
  "strip_accents": null,
18
  "tokenize_chinese_chars": true,
19
  "tokenizer_class": "BertTokenizer",
20
+ "truncation_side": "right",
21
+ "truncation_strategy": "longest_first",
22
  "unk_token": "[UNK]"
23
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32f180fda1cc3e0abeb3d5df703a0997be2c3b4b4212d652bc2f7527c678259
3
- size 5265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9073550f506e98bd4ef79da1ca106d11b7da106199513c29f9e40509e1b49eca
3
+ size 5201