PuxAI commited on
Commit
47a7bee
·
verified ·
1 Parent(s): d279710

Auto-upload fine-tuned distilbert-base-cased + Reports

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  bert-base-cased/predictions.json filter=lfs diff=lfs merge=lfs -text
37
  roberta-base/predictions.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  bert-base-cased/predictions.json filter=lfs diff=lfs merge=lfs -text
37
  roberta-base/predictions.json filter=lfs diff=lfs merge=lfs -text
38
+ distilbert-base-cased/predictions.json filter=lfs diff=lfs merge=lfs -text
distilbert-base-cased/classification_report.txt ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ ACCOUNTNAME 0.98 1.00 0.99 135
4
+ ACCOUNTNUMBER 0.99 1.00 0.99 132
5
+ AGE 0.92 0.97 0.95 137
6
+ AMOUNT 0.89 0.95 0.92 148
7
+ BIC 0.83 1.00 0.91 35
8
+ BITCOINADDRESS 0.93 1.00 0.96 119
9
+ BUILDINGNUMBER 0.86 0.90 0.88 133
10
+ CITY 0.93 0.89 0.91 132
11
+ COMPANYNAME 0.99 1.00 1.00 125
12
+ COUNTY 0.94 0.97 0.95 120
13
+ CREDITCARDCVV 0.79 0.85 0.81 39
14
+ CREDITCARDISSUER 0.98 1.00 0.99 65
15
+ CREDITCARDNUMBER 0.85 0.93 0.89 108
16
+ CURRENCY 0.61 0.89 0.73 88
17
+ CURRENCYCODE 0.82 0.80 0.81 35
18
+ CURRENCYNAME 0.12 0.03 0.04 38
19
+ CURRENCYSYMBOL 0.82 0.90 0.86 93
20
+ DATE 0.79 0.95 0.86 219
21
+ DOB 0.77 0.53 0.63 100
22
+ EMAIL 1.00 1.00 1.00 214
23
+ ETHEREUMADDRESS 1.00 1.00 1.00 74
24
+ EYECOLOR 0.95 0.87 0.91 47
25
+ FIRSTNAME 0.91 0.95 0.93 638
26
+ GENDER 0.94 0.93 0.93 111
27
+ HEIGHT 0.96 0.98 0.97 48
28
+ IBAN 1.00 1.00 1.00 116
29
+ IP 0.11 0.01 0.02 105
30
+ IPV4 0.68 0.98 0.81 120
31
+ IPV6 0.66 0.97 0.78 116
32
+ JOBAREA 0.92 0.97 0.95 144
33
+ JOBTITLE 0.95 0.99 0.97 147
34
+ JOBTYPE 0.93 0.98 0.96 133
35
+ LASTNAME 0.85 0.92 0.88 258
36
+ LITECOINADDRESS 0.89 0.86 0.88 49
37
+ MAC 1.00 1.00 1.00 61
38
+ MASKEDNUMBER 0.89 0.82 0.85 93
39
+ MIDDLENAME 0.70 0.54 0.61 134
40
+ NEARBYGPSCOORDINATE 1.00 1.00 1.00 88
41
+ ORDINALDIRECTION 0.96 0.98 0.97 52
42
+ PASSWORD 0.97 0.99 0.98 134
43
+ PHONEIMEI 1.00 1.00 1.00 89
44
+ PHONENUMBER 0.99 1.00 1.00 113
45
+ PIN 0.67 0.68 0.68 38
46
+ PREFIX 0.88 0.98 0.93 196
47
+ SECONDARYADDRESS 0.95 0.99 0.97 119
48
+ SEX 0.99 1.00 0.99 138
49
+ SSN 0.99 0.99 0.99 97
50
+ STATE 0.89 0.96 0.92 153
51
+ STREET 0.89 0.94 0.92 135
52
+ TIME 0.98 0.97 0.97 139
53
+ URL 1.00 1.00 1.00 143
54
+ USERAGENT 1.00 1.00 1.00 102
55
+ USERNAME 0.97 1.00 0.98 155
56
+ VEHICLEVIN 1.00 0.98 0.99 41
57
+ VEHICLEVRM 0.90 0.97 0.94 39
58
+ ZIPCODE 0.88 0.93 0.90 125
59
+
60
+ micro avg 0.90 0.93 0.91 6705
61
+ macro avg 0.88 0.91 0.89 6705
62
+ weighted avg 0.89 0.93 0.90 6705
distilbert-base-cased/config.json ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-ACCOUNTNAME",
16
+ "2": "I-ACCOUNTNAME",
17
+ "3": "B-ACCOUNTNUMBER",
18
+ "4": "I-ACCOUNTNUMBER",
19
+ "5": "B-AGE",
20
+ "6": "I-AGE",
21
+ "7": "B-AMOUNT",
22
+ "8": "I-AMOUNT",
23
+ "9": "B-BIC",
24
+ "10": "I-BIC",
25
+ "11": "B-BITCOINADDRESS",
26
+ "12": "I-BITCOINADDRESS",
27
+ "13": "B-BUILDINGNUMBER",
28
+ "14": "I-BUILDINGNUMBER",
29
+ "15": "B-CITY",
30
+ "16": "I-CITY",
31
+ "17": "B-COMPANYNAME",
32
+ "18": "I-COMPANYNAME",
33
+ "19": "B-COUNTY",
34
+ "20": "I-COUNTY",
35
+ "21": "B-CREDITCARDCVV",
36
+ "22": "I-CREDITCARDCVV",
37
+ "23": "B-CREDITCARDISSUER",
38
+ "24": "I-CREDITCARDISSUER",
39
+ "25": "B-CREDITCARDNUMBER",
40
+ "26": "I-CREDITCARDNUMBER",
41
+ "27": "B-CURRENCY",
42
+ "28": "I-CURRENCY",
43
+ "29": "B-CURRENCYCODE",
44
+ "30": "I-CURRENCYCODE",
45
+ "31": "B-CURRENCYNAME",
46
+ "32": "I-CURRENCYNAME",
47
+ "33": "B-CURRENCYSYMBOL",
48
+ "34": "I-CURRENCYSYMBOL",
49
+ "35": "B-DATE",
50
+ "36": "I-DATE",
51
+ "37": "B-DOB",
52
+ "38": "I-DOB",
53
+ "39": "B-EMAIL",
54
+ "40": "I-EMAIL",
55
+ "41": "B-ETHEREUMADDRESS",
56
+ "42": "I-ETHEREUMADDRESS",
57
+ "43": "B-EYECOLOR",
58
+ "44": "I-EYECOLOR",
59
+ "45": "B-FIRSTNAME",
60
+ "46": "I-FIRSTNAME",
61
+ "47": "B-GENDER",
62
+ "48": "I-GENDER",
63
+ "49": "B-HEIGHT",
64
+ "50": "I-HEIGHT",
65
+ "51": "B-IBAN",
66
+ "52": "I-IBAN",
67
+ "53": "B-IP",
68
+ "54": "I-IP",
69
+ "55": "B-IPV4",
70
+ "56": "I-IPV4",
71
+ "57": "B-IPV6",
72
+ "58": "I-IPV6",
73
+ "59": "B-JOBAREA",
74
+ "60": "I-JOBAREA",
75
+ "61": "B-JOBTITLE",
76
+ "62": "I-JOBTITLE",
77
+ "63": "B-JOBTYPE",
78
+ "64": "I-JOBTYPE",
79
+ "65": "B-LASTNAME",
80
+ "66": "I-LASTNAME",
81
+ "67": "B-LITECOINADDRESS",
82
+ "68": "I-LITECOINADDRESS",
83
+ "69": "B-MAC",
84
+ "70": "I-MAC",
85
+ "71": "B-MASKEDNUMBER",
86
+ "72": "I-MASKEDNUMBER",
87
+ "73": "B-MIDDLENAME",
88
+ "74": "I-MIDDLENAME",
89
+ "75": "B-NEARBYGPSCOORDINATE",
90
+ "76": "I-NEARBYGPSCOORDINATE",
91
+ "77": "B-ORDINALDIRECTION",
92
+ "78": "I-ORDINALDIRECTION",
93
+ "79": "B-PASSWORD",
94
+ "80": "I-PASSWORD",
95
+ "81": "B-PHONEIMEI",
96
+ "82": "I-PHONEIMEI",
97
+ "83": "B-PHONENUMBER",
98
+ "84": "I-PHONENUMBER",
99
+ "85": "B-PIN",
100
+ "86": "I-PIN",
101
+ "87": "B-PREFIX",
102
+ "88": "I-PREFIX",
103
+ "89": "B-SECONDARYADDRESS",
104
+ "90": "I-SECONDARYADDRESS",
105
+ "91": "B-SEX",
106
+ "92": "I-SEX",
107
+ "93": "B-SSN",
108
+ "94": "I-SSN",
109
+ "95": "B-STATE",
110
+ "96": "I-STATE",
111
+ "97": "B-STREET",
112
+ "98": "I-STREET",
113
+ "99": "B-TIME",
114
+ "100": "I-TIME",
115
+ "101": "B-URL",
116
+ "102": "I-URL",
117
+ "103": "B-USERAGENT",
118
+ "104": "I-USERAGENT",
119
+ "105": "B-USERNAME",
120
+ "106": "I-USERNAME",
121
+ "107": "B-VEHICLEVIN",
122
+ "108": "I-VEHICLEVIN",
123
+ "109": "B-VEHICLEVRM",
124
+ "110": "I-VEHICLEVRM",
125
+ "111": "B-ZIPCODE",
126
+ "112": "I-ZIPCODE"
127
+ },
128
+ "initializer_range": 0.02,
129
+ "label2id": {
130
+ "B-ACCOUNTNAME": 1,
131
+ "B-ACCOUNTNUMBER": 3,
132
+ "B-AGE": 5,
133
+ "B-AMOUNT": 7,
134
+ "B-BIC": 9,
135
+ "B-BITCOINADDRESS": 11,
136
+ "B-BUILDINGNUMBER": 13,
137
+ "B-CITY": 15,
138
+ "B-COMPANYNAME": 17,
139
+ "B-COUNTY": 19,
140
+ "B-CREDITCARDCVV": 21,
141
+ "B-CREDITCARDISSUER": 23,
142
+ "B-CREDITCARDNUMBER": 25,
143
+ "B-CURRENCY": 27,
144
+ "B-CURRENCYCODE": 29,
145
+ "B-CURRENCYNAME": 31,
146
+ "B-CURRENCYSYMBOL": 33,
147
+ "B-DATE": 35,
148
+ "B-DOB": 37,
149
+ "B-EMAIL": 39,
150
+ "B-ETHEREUMADDRESS": 41,
151
+ "B-EYECOLOR": 43,
152
+ "B-FIRSTNAME": 45,
153
+ "B-GENDER": 47,
154
+ "B-HEIGHT": 49,
155
+ "B-IBAN": 51,
156
+ "B-IP": 53,
157
+ "B-IPV4": 55,
158
+ "B-IPV6": 57,
159
+ "B-JOBAREA": 59,
160
+ "B-JOBTITLE": 61,
161
+ "B-JOBTYPE": 63,
162
+ "B-LASTNAME": 65,
163
+ "B-LITECOINADDRESS": 67,
164
+ "B-MAC": 69,
165
+ "B-MASKEDNUMBER": 71,
166
+ "B-MIDDLENAME": 73,
167
+ "B-NEARBYGPSCOORDINATE": 75,
168
+ "B-ORDINALDIRECTION": 77,
169
+ "B-PASSWORD": 79,
170
+ "B-PHONEIMEI": 81,
171
+ "B-PHONENUMBER": 83,
172
+ "B-PIN": 85,
173
+ "B-PREFIX": 87,
174
+ "B-SECONDARYADDRESS": 89,
175
+ "B-SEX": 91,
176
+ "B-SSN": 93,
177
+ "B-STATE": 95,
178
+ "B-STREET": 97,
179
+ "B-TIME": 99,
180
+ "B-URL": 101,
181
+ "B-USERAGENT": 103,
182
+ "B-USERNAME": 105,
183
+ "B-VEHICLEVIN": 107,
184
+ "B-VEHICLEVRM": 109,
185
+ "B-ZIPCODE": 111,
186
+ "I-ACCOUNTNAME": 2,
187
+ "I-ACCOUNTNUMBER": 4,
188
+ "I-AGE": 6,
189
+ "I-AMOUNT": 8,
190
+ "I-BIC": 10,
191
+ "I-BITCOINADDRESS": 12,
192
+ "I-BUILDINGNUMBER": 14,
193
+ "I-CITY": 16,
194
+ "I-COMPANYNAME": 18,
195
+ "I-COUNTY": 20,
196
+ "I-CREDITCARDCVV": 22,
197
+ "I-CREDITCARDISSUER": 24,
198
+ "I-CREDITCARDNUMBER": 26,
199
+ "I-CURRENCY": 28,
200
+ "I-CURRENCYCODE": 30,
201
+ "I-CURRENCYNAME": 32,
202
+ "I-CURRENCYSYMBOL": 34,
203
+ "I-DATE": 36,
204
+ "I-DOB": 38,
205
+ "I-EMAIL": 40,
206
+ "I-ETHEREUMADDRESS": 42,
207
+ "I-EYECOLOR": 44,
208
+ "I-FIRSTNAME": 46,
209
+ "I-GENDER": 48,
210
+ "I-HEIGHT": 50,
211
+ "I-IBAN": 52,
212
+ "I-IP": 54,
213
+ "I-IPV4": 56,
214
+ "I-IPV6": 58,
215
+ "I-JOBAREA": 60,
216
+ "I-JOBTITLE": 62,
217
+ "I-JOBTYPE": 64,
218
+ "I-LASTNAME": 66,
219
+ "I-LITECOINADDRESS": 68,
220
+ "I-MAC": 70,
221
+ "I-MASKEDNUMBER": 72,
222
+ "I-MIDDLENAME": 74,
223
+ "I-NEARBYGPSCOORDINATE": 76,
224
+ "I-ORDINALDIRECTION": 78,
225
+ "I-PASSWORD": 80,
226
+ "I-PHONEIMEI": 82,
227
+ "I-PHONENUMBER": 84,
228
+ "I-PIN": 86,
229
+ "I-PREFIX": 88,
230
+ "I-SECONDARYADDRESS": 90,
231
+ "I-SEX": 92,
232
+ "I-SSN": 94,
233
+ "I-STATE": 96,
234
+ "I-STREET": 98,
235
+ "I-TIME": 100,
236
+ "I-URL": 102,
237
+ "I-USERAGENT": 104,
238
+ "I-USERNAME": 106,
239
+ "I-VEHICLEVIN": 108,
240
+ "I-VEHICLEVRM": 110,
241
+ "I-ZIPCODE": 112,
242
+ "O": 0
243
+ },
244
+ "max_position_embeddings": 512,
245
+ "model_type": "distilbert",
246
+ "n_heads": 12,
247
+ "n_layers": 6,
248
+ "output_past": true,
249
+ "pad_token_id": 0,
250
+ "qa_dropout": 0.1,
251
+ "seq_classif_dropout": 0.2,
252
+ "sinusoidal_pos_embds": false,
253
+ "tie_weights_": true,
254
+ "tie_word_embeddings": true,
255
+ "transformers_version": "5.2.0",
256
+ "use_cache": false,
257
+ "vocab_size": 28996
258
+ }
distilbert-base-cased/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16dd06e83488a34ac48d369b81d403271db94eddb798d341743ef106e6dcfc1
3
+ size 261123580
distilbert-base-cased/predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eac9ae3966de09885d4370bb5a8671e3323fc86d19070b2dae906ca6fc15695
3
+ size 53262691
distilbert-base-cased/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distilbert-base-cased/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
distilbert-base-cased/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7adcc01f816bfe6027363d6e5b0489d52fda6718066efc9837a4a2aa18a67b
3
+ size 5201