MinhTriet commited on
Commit
039bbe5
·
verified ·
1 Parent(s): cdce641

Upload folder using huggingface_hub

Browse files
classification_report.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ACCOUNT_NUMBER": {
3
+ "precision": 1.0,
4
+ "recall": 0.9355,
5
+ "f1-score": 0.9667,
6
+ "support": 31
7
+ },
8
+ "ADDRESS": {
9
+ "precision": 0.8667,
10
+ "recall": 0.8273,
11
+ "f1-score": 0.8465,
12
+ "support": 110
13
+ },
14
+ "API_KEY": {
15
+ "precision": 0.9,
16
+ "recall": 0.9,
17
+ "f1-score": 0.9,
18
+ "support": 10
19
+ },
20
+ "BANK_ROUTING_NUMBER": {
21
+ "precision": 0.9811,
22
+ "recall": 1.0,
23
+ "f1-score": 0.9905,
24
+ "support": 52
25
+ },
26
+ "BIOMETRIC_IDENTIFIER": {
27
+ "precision": 0.9375,
28
+ "recall": 1.0,
29
+ "f1-score": 0.9677,
30
+ "support": 30
31
+ },
32
+ "CERTIFICATE_LICENSE_NUMBER": {
33
+ "precision": 1.0,
34
+ "recall": 1.0,
35
+ "f1-score": 1.0,
36
+ "support": 24
37
+ },
38
+ "CITY": {
39
+ "precision": 0.7619,
40
+ "recall": 0.64,
41
+ "f1-score": 0.6957,
42
+ "support": 25
43
+ },
44
+ "COMPANY_NAME": {
45
+ "precision": 0.8776,
46
+ "recall": 0.9149,
47
+ "f1-score": 0.8958,
48
+ "support": 47
49
+ },
50
+ "COORDINATE": {
51
+ "precision": 1.0,
52
+ "recall": 0.9091,
53
+ "f1-score": 0.9524,
54
+ "support": 22
55
+ },
56
+ "COUNTRY": {
57
+ "precision": 0.7857,
58
+ "recall": 0.8462,
59
+ "f1-score": 0.8148,
60
+ "support": 13
61
+ },
62
+ "CREDIT_CARD_NUMBER": {
63
+ "precision": 0.9833,
64
+ "recall": 1.0,
65
+ "f1-score": 0.9916,
66
+ "support": 118
67
+ },
68
+ "CUSTOMER_ID": {
69
+ "precision": 0.9903,
70
+ "recall": 0.9577,
71
+ "f1-score": 0.9737,
72
+ "support": 213
73
+ },
74
+ "CVV": {
75
+ "precision": 0.0,
76
+ "recall": 0.0,
77
+ "f1-score": 0.0,
78
+ "support": 1
79
+ },
80
+ "DATE": {
81
+ "precision": 0.963,
82
+ "recall": 0.9412,
83
+ "f1-score": 0.9519,
84
+ "support": 221
85
+ },
86
+ "DATE_OF_BIRTH": {
87
+ "precision": 0.9763,
88
+ "recall": 0.9826,
89
+ "f1-score": 0.9795,
90
+ "support": 461
91
+ },
92
+ "DATE_TIME": {
93
+ "precision": 0.9737,
94
+ "recall": 1.0,
95
+ "f1-score": 0.9867,
96
+ "support": 37
97
+ },
98
+ "DEVICE_IDENTIFIER": {
99
+ "precision": 1.0,
100
+ "recall": 0.9574,
101
+ "f1-score": 0.9783,
102
+ "support": 47
103
+ },
104
+ "EMAIL": {
105
+ "precision": 0.9901,
106
+ "recall": 0.995,
107
+ "f1-score": 0.9926,
108
+ "support": 202
109
+ },
110
+ "EMPLOYEE_ID": {
111
+ "precision": 0.9363,
112
+ "recall": 0.9502,
113
+ "f1-score": 0.9432,
114
+ "support": 201
115
+ },
116
+ "FIRST_NAME": {
117
+ "precision": 0.8682,
118
+ "recall": 0.8615,
119
+ "f1-score": 0.8649,
120
+ "support": 260
121
+ },
122
+ "HEALTH_PLAN_BENEFICIARY_NUMBER": {
123
+ "precision": 1.0,
124
+ "recall": 0.875,
125
+ "f1-score": 0.9333,
126
+ "support": 16
127
+ },
128
+ "IPADDRESS": {
129
+ "precision": 0.9947,
130
+ "recall": 1.0,
131
+ "f1-score": 0.9974,
132
+ "support": 189
133
+ },
134
+ "LAST_NAME": {
135
+ "precision": 0.839,
136
+ "recall": 0.8722,
137
+ "f1-score": 0.8553,
138
+ "support": 227
139
+ },
140
+ "LICENSE_PLATE": {
141
+ "precision": 1.0,
142
+ "recall": 0.9929,
143
+ "f1-score": 0.9964,
144
+ "support": 141
145
+ },
146
+ "MEDICAL_RECORD_NUMBER": {
147
+ "precision": 0.9697,
148
+ "recall": 0.9884,
149
+ "f1-score": 0.979,
150
+ "support": 518
151
+ },
152
+ "NAME": {
153
+ "precision": 0.8705,
154
+ "recall": 0.866,
155
+ "f1-score": 0.8682,
156
+ "support": 194
157
+ },
158
+ "NATIONAL_ID": {
159
+ "precision": 1.0,
160
+ "recall": 0.8,
161
+ "f1-score": 0.8889,
162
+ "support": 15
163
+ },
164
+ "PASSWORD": {
165
+ "precision": 0.8667,
166
+ "recall": 1.0,
167
+ "f1-score": 0.9286,
168
+ "support": 13
169
+ },
170
+ "PHONE_NUMBER": {
171
+ "precision": 1.0,
172
+ "recall": 1.0,
173
+ "f1-score": 1.0,
174
+ "support": 171
175
+ },
176
+ "POSTCODE": {
177
+ "precision": 1.0,
178
+ "recall": 0.8824,
179
+ "f1-score": 0.9375,
180
+ "support": 17
181
+ },
182
+ "SSN": {
183
+ "precision": 0.9941,
184
+ "recall": 1.0,
185
+ "f1-score": 0.9971,
186
+ "support": 339
187
+ },
188
+ "STATE": {
189
+ "precision": 0.0,
190
+ "recall": 0.0,
191
+ "f1-score": 0.0,
192
+ "support": 3
193
+ },
194
+ "STREET_ADDRESS": {
195
+ "precision": 0.9031,
196
+ "recall": 0.9316,
197
+ "f1-score": 0.9171,
198
+ "support": 190
199
+ },
200
+ "SWIFT_BIC": {
201
+ "precision": 1.0,
202
+ "recall": 0.5,
203
+ "f1-score": 0.6667,
204
+ "support": 6
205
+ },
206
+ "TAX_ID": {
207
+ "precision": 1.0,
208
+ "recall": 1.0,
209
+ "f1-score": 1.0,
210
+ "support": 4
211
+ },
212
+ "TIME": {
213
+ "precision": 0.9565,
214
+ "recall": 0.9565,
215
+ "f1-score": 0.9565,
216
+ "support": 23
217
+ },
218
+ "UNIQUE_IDENTIFIER": {
219
+ "precision": 0.9643,
220
+ "recall": 1.0,
221
+ "f1-score": 0.9818,
222
+ "support": 27
223
+ },
224
+ "URL": {
225
+ "precision": 1.0,
226
+ "recall": 1.0,
227
+ "f1-score": 1.0,
228
+ "support": 5
229
+ },
230
+ "USER_NAME": {
231
+ "precision": 0.9245,
232
+ "recall": 0.98,
233
+ "f1-score": 0.9515,
234
+ "support": 50
235
+ },
236
+ "VEHICLE_IDENTIFIER": {
237
+ "precision": 1.0,
238
+ "recall": 1.0,
239
+ "f1-score": 1.0,
240
+ "support": 21
241
+ },
242
+ "OVERALL_MICRO": {
243
+ "precision": 0.9502,
244
+ "recall": 0.9513,
245
+ "f1-score": 0.9508,
246
+ "support": 4294
247
+ },
248
+ "OVERALL_MACRO": {
249
+ "precision": 0.9019,
250
+ "recall": 0.8816,
251
+ "f1-score": 0.8887,
252
+ "support": 4294
253
+ },
254
+ "OVERALL_WEIGHTED": {
255
+ "precision": 0.9496,
256
+ "recall": 0.9513,
257
+ "f1-score": 0.9501,
258
+ "support": 4294
259
+ }
260
+ }
config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-ACCOUNT_NUMBER",
18
+ "2": "I-ACCOUNT_NUMBER",
19
+ "3": "B-ADDRESS",
20
+ "4": "I-ADDRESS",
21
+ "5": "B-API_KEY",
22
+ "6": "I-API_KEY",
23
+ "7": "B-BANK_ROUTING_NUMBER",
24
+ "8": "I-BANK_ROUTING_NUMBER",
25
+ "9": "B-BIOMETRIC_IDENTIFIER",
26
+ "10": "I-BIOMETRIC_IDENTIFIER",
27
+ "11": "B-CERTIFICATE_LICENSE_NUMBER",
28
+ "12": "I-CERTIFICATE_LICENSE_NUMBER",
29
+ "13": "B-CITY",
30
+ "14": "I-CITY",
31
+ "15": "B-COMPANY_NAME",
32
+ "16": "I-COMPANY_NAME",
33
+ "17": "B-COORDINATE",
34
+ "18": "I-COORDINATE",
35
+ "19": "B-COUNTRY",
36
+ "20": "I-COUNTRY",
37
+ "21": "B-CREDIT_CARD_NUMBER",
38
+ "22": "I-CREDIT_CARD_NUMBER",
39
+ "23": "B-CUSTOMER_ID",
40
+ "24": "I-CUSTOMER_ID",
41
+ "25": "B-CVV",
42
+ "26": "I-CVV",
43
+ "27": "B-DATE",
44
+ "28": "I-DATE",
45
+ "29": "B-DATE_OF_BIRTH",
46
+ "30": "I-DATE_OF_BIRTH",
47
+ "31": "B-DATE_TIME",
48
+ "32": "I-DATE_TIME",
49
+ "33": "B-DEVICE_IDENTIFIER",
50
+ "34": "I-DEVICE_IDENTIFIER",
51
+ "35": "B-EMAIL",
52
+ "36": "I-EMAIL",
53
+ "37": "B-EMPLOYEE_ID",
54
+ "38": "I-EMPLOYEE_ID",
55
+ "39": "B-FIRST_NAME",
56
+ "40": "I-FIRST_NAME",
57
+ "41": "B-HEALTH_PLAN_BENEFICIARY_NUMBER",
58
+ "42": "I-HEALTH_PLAN_BENEFICIARY_NUMBER",
59
+ "43": "B-IPADDRESS",
60
+ "44": "I-IPADDRESS",
61
+ "45": "B-LAST_NAME",
62
+ "46": "I-LAST_NAME",
63
+ "47": "B-LICENSE_PLATE",
64
+ "48": "I-LICENSE_PLATE",
65
+ "49": "B-MEDICAL_RECORD_NUMBER",
66
+ "50": "I-MEDICAL_RECORD_NUMBER",
67
+ "51": "B-NAME",
68
+ "52": "I-NAME",
69
+ "53": "B-NATIONAL_ID",
70
+ "54": "I-NATIONAL_ID",
71
+ "55": "B-PASSWORD",
72
+ "56": "I-PASSWORD",
73
+ "57": "B-PHONE_NUMBER",
74
+ "58": "I-PHONE_NUMBER",
75
+ "59": "B-PIN",
76
+ "60": "I-PIN",
77
+ "61": "B-POSTCODE",
78
+ "62": "I-POSTCODE",
79
+ "63": "B-SSN",
80
+ "64": "I-SSN",
81
+ "65": "B-STATE",
82
+ "66": "I-STATE",
83
+ "67": "B-STREET_ADDRESS",
84
+ "68": "I-STREET_ADDRESS",
85
+ "69": "B-SWIFT_BIC",
86
+ "70": "I-SWIFT_BIC",
87
+ "71": "B-TAX_ID",
88
+ "72": "I-TAX_ID",
89
+ "73": "B-TIME",
90
+ "74": "I-TIME",
91
+ "75": "B-UNIQUE_IDENTIFIER",
92
+ "76": "I-UNIQUE_IDENTIFIER",
93
+ "77": "B-URL",
94
+ "78": "I-URL",
95
+ "79": "B-USER_NAME",
96
+ "80": "I-USER_NAME",
97
+ "81": "B-VEHICLE_IDENTIFIER",
98
+ "82": "I-VEHICLE_IDENTIFIER"
99
+ },
100
+ "initializer_range": 0.02,
101
+ "intermediate_size": 3072,
102
+ "is_decoder": false,
103
+ "label2id": {
104
+ "B-ACCOUNT_NUMBER": 1,
105
+ "B-ADDRESS": 3,
106
+ "B-API_KEY": 5,
107
+ "B-BANK_ROUTING_NUMBER": 7,
108
+ "B-BIOMETRIC_IDENTIFIER": 9,
109
+ "B-CERTIFICATE_LICENSE_NUMBER": 11,
110
+ "B-CITY": 13,
111
+ "B-COMPANY_NAME": 15,
112
+ "B-COORDINATE": 17,
113
+ "B-COUNTRY": 19,
114
+ "B-CREDIT_CARD_NUMBER": 21,
115
+ "B-CUSTOMER_ID": 23,
116
+ "B-CVV": 25,
117
+ "B-DATE": 27,
118
+ "B-DATE_OF_BIRTH": 29,
119
+ "B-DATE_TIME": 31,
120
+ "B-DEVICE_IDENTIFIER": 33,
121
+ "B-EMAIL": 35,
122
+ "B-EMPLOYEE_ID": 37,
123
+ "B-FIRST_NAME": 39,
124
+ "B-HEALTH_PLAN_BENEFICIARY_NUMBER": 41,
125
+ "B-IPADDRESS": 43,
126
+ "B-LAST_NAME": 45,
127
+ "B-LICENSE_PLATE": 47,
128
+ "B-MEDICAL_RECORD_NUMBER": 49,
129
+ "B-NAME": 51,
130
+ "B-NATIONAL_ID": 53,
131
+ "B-PASSWORD": 55,
132
+ "B-PHONE_NUMBER": 57,
133
+ "B-PIN": 59,
134
+ "B-POSTCODE": 61,
135
+ "B-SSN": 63,
136
+ "B-STATE": 65,
137
+ "B-STREET_ADDRESS": 67,
138
+ "B-SWIFT_BIC": 69,
139
+ "B-TAX_ID": 71,
140
+ "B-TIME": 73,
141
+ "B-UNIQUE_IDENTIFIER": 75,
142
+ "B-URL": 77,
143
+ "B-USER_NAME": 79,
144
+ "B-VEHICLE_IDENTIFIER": 81,
145
+ "I-ACCOUNT_NUMBER": 2,
146
+ "I-ADDRESS": 4,
147
+ "I-API_KEY": 6,
148
+ "I-BANK_ROUTING_NUMBER": 8,
149
+ "I-BIOMETRIC_IDENTIFIER": 10,
150
+ "I-CERTIFICATE_LICENSE_NUMBER": 12,
151
+ "I-CITY": 14,
152
+ "I-COMPANY_NAME": 16,
153
+ "I-COORDINATE": 18,
154
+ "I-COUNTRY": 20,
155
+ "I-CREDIT_CARD_NUMBER": 22,
156
+ "I-CUSTOMER_ID": 24,
157
+ "I-CVV": 26,
158
+ "I-DATE": 28,
159
+ "I-DATE_OF_BIRTH": 30,
160
+ "I-DATE_TIME": 32,
161
+ "I-DEVICE_IDENTIFIER": 34,
162
+ "I-EMAIL": 36,
163
+ "I-EMPLOYEE_ID": 38,
164
+ "I-FIRST_NAME": 40,
165
+ "I-HEALTH_PLAN_BENEFICIARY_NUMBER": 42,
166
+ "I-IPADDRESS": 44,
167
+ "I-LAST_NAME": 46,
168
+ "I-LICENSE_PLATE": 48,
169
+ "I-MEDICAL_RECORD_NUMBER": 50,
170
+ "I-NAME": 52,
171
+ "I-NATIONAL_ID": 54,
172
+ "I-PASSWORD": 56,
173
+ "I-PHONE_NUMBER": 58,
174
+ "I-PIN": 60,
175
+ "I-POSTCODE": 62,
176
+ "I-SSN": 64,
177
+ "I-STATE": 66,
178
+ "I-STREET_ADDRESS": 68,
179
+ "I-SWIFT_BIC": 70,
180
+ "I-TAX_ID": 72,
181
+ "I-TIME": 74,
182
+ "I-UNIQUE_IDENTIFIER": 76,
183
+ "I-URL": 78,
184
+ "I-USER_NAME": 80,
185
+ "I-VEHICLE_IDENTIFIER": 82,
186
+ "O": 0
187
+ },
188
+ "layer_norm_eps": 1e-12,
189
+ "max_position_embeddings": 512,
190
+ "model_type": "bert",
191
+ "num_attention_heads": 12,
192
+ "num_hidden_layers": 12,
193
+ "pad_token_id": 0,
194
+ "position_embedding_type": "absolute",
195
+ "tie_word_embeddings": true,
196
+ "transformers_version": "5.6.2",
197
+ "type_vocab_size": 2,
198
+ "use_cache": false,
199
+ "vocab_size": 30522
200
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a432111236c62202c50cf71f1b2813ce8b1a36cb96179437711231df19c6e50d
3
+ size 435845220
predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbb441e18d796e4cdde0c0932d707881ecadb02eed875f8782058dd1b0ab43a
3
+ size 5265