PuxAI commited on
Commit
bd979db
·
verified ·
1 Parent(s): d8db0c2

Auto-upload fine-tuned roberta-base + Reports

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst 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
 
 
34
  *.zst 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
roberta-base/classification_report.txt ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ ACCOUNTNAME 0.97 0.99 0.98 135
4
+ ACCOUNTNUMBER 0.98 0.99 0.99 132
5
+ AGE 0.94 0.98 0.96 137
6
+ AMOUNT 0.99 1.00 0.99 148
7
+ BIC 1.00 1.00 1.00 35
8
+ BITCOINADDRESS 0.95 1.00 0.98 119
9
+ BUILDINGNUMBER 0.92 0.95 0.94 133
10
+ CITY 0.98 0.95 0.97 132
11
+ COMPANYNAME 0.98 1.00 0.99 125
12
+ COUNTY 0.97 0.97 0.97 120
13
+ CREDITCARDCVV 0.92 0.87 0.89 39
14
+ CREDITCARDISSUER 1.00 1.00 1.00 65
15
+ CREDITCARDNUMBER 0.83 0.98 0.90 108
16
+ CURRENCY 0.61 0.84 0.71 88
17
+ CURRENCYCODE 0.88 0.83 0.86 36
18
+ CURRENCYNAME 0.28 0.18 0.22 38
19
+ CURRENCYSYMBOL 0.92 0.98 0.95 121
20
+ DATE 0.82 0.98 0.89 219
21
+ DOB 0.90 0.54 0.68 100
22
+ EMAIL 1.00 1.00 1.00 214
23
+ ETHEREUMADDRESS 1.00 1.00 1.00 74
24
+ EYECOLOR 0.98 0.98 0.98 47
25
+ FIRSTNAME 0.96 0.95 0.96 638
26
+ GENDER 0.99 0.97 0.98 111
27
+ HEIGHT 1.00 1.00 1.00 48
28
+ IBAN 1.00 1.00 1.00 116
29
+ IP 0.11 0.04 0.06 105
30
+ IPV4 0.69 0.98 0.81 120
31
+ IPV6 0.61 0.93 0.74 116
32
+ JOBAREA 0.98 0.98 0.98 144
33
+ JOBTITLE 0.95 1.00 0.98 147
34
+ JOBTYPE 0.95 0.97 0.96 133
35
+ LASTNAME 0.93 0.95 0.94 258
36
+ LITECOINADDRESS 0.98 0.90 0.94 49
37
+ MAC 1.00 1.00 1.00 61
38
+ MASKEDNUMBER 0.96 0.77 0.86 93
39
+ MIDDLENAME 0.71 0.75 0.73 134
40
+ NEARBYGPSCOORDINATE 1.00 1.00 1.00 89
41
+ ORDINALDIRECTION 0.88 0.94 0.91 52
42
+ PASSWORD 0.99 1.00 0.99 135
43
+ PHONEIMEI 1.00 1.00 1.00 89
44
+ PHONENUMBER 0.98 1.00 0.99 113
45
+ PIN 0.86 0.82 0.84 38
46
+ PREFIX 0.87 0.97 0.92 196
47
+ SECONDARYADDRESS 1.00 1.00 1.00 119
48
+ SEX 0.99 1.00 0.99 138
49
+ SSN 0.97 0.99 0.98 97
50
+ STATE 0.94 1.00 0.97 153
51
+ STREET 0.99 0.99 0.99 136
52
+ TIME 0.98 0.98 0.98 139
53
+ URL 1.00 1.00 1.00 143
54
+ USERAGENT 1.00 1.00 1.00 102
55
+ USERNAME 0.99 1.00 0.99 155
56
+ VEHICLEVIN 1.00 1.00 1.00 41
57
+ VEHICLEVRM 1.00 1.00 1.00 39
58
+ ZIPCODE 0.92 0.94 0.93 125
59
+
60
+ micro avg 0.92 0.94 0.93 6737
61
+ macro avg 0.91 0.93 0.91 6737
62
+ weighted avg 0.92 0.94 0.93 6737
roberta-base/config.json ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-ACCOUNTNAME",
17
+ "2": "I-ACCOUNTNAME",
18
+ "3": "B-ACCOUNTNUMBER",
19
+ "4": "I-ACCOUNTNUMBER",
20
+ "5": "B-AGE",
21
+ "6": "I-AGE",
22
+ "7": "B-AMOUNT",
23
+ "8": "I-AMOUNT",
24
+ "9": "B-BIC",
25
+ "10": "I-BIC",
26
+ "11": "B-BITCOINADDRESS",
27
+ "12": "I-BITCOINADDRESS",
28
+ "13": "B-BUILDINGNUMBER",
29
+ "14": "I-BUILDINGNUMBER",
30
+ "15": "B-CITY",
31
+ "16": "I-CITY",
32
+ "17": "B-COMPANYNAME",
33
+ "18": "I-COMPANYNAME",
34
+ "19": "B-COUNTY",
35
+ "20": "I-COUNTY",
36
+ "21": "B-CREDITCARDCVV",
37
+ "22": "I-CREDITCARDCVV",
38
+ "23": "B-CREDITCARDISSUER",
39
+ "24": "I-CREDITCARDISSUER",
40
+ "25": "B-CREDITCARDNUMBER",
41
+ "26": "I-CREDITCARDNUMBER",
42
+ "27": "B-CURRENCY",
43
+ "28": "I-CURRENCY",
44
+ "29": "B-CURRENCYCODE",
45
+ "30": "I-CURRENCYCODE",
46
+ "31": "B-CURRENCYNAME",
47
+ "32": "I-CURRENCYNAME",
48
+ "33": "B-CURRENCYSYMBOL",
49
+ "34": "I-CURRENCYSYMBOL",
50
+ "35": "B-DATE",
51
+ "36": "I-DATE",
52
+ "37": "B-DOB",
53
+ "38": "I-DOB",
54
+ "39": "B-EMAIL",
55
+ "40": "I-EMAIL",
56
+ "41": "B-ETHEREUMADDRESS",
57
+ "42": "I-ETHEREUMADDRESS",
58
+ "43": "B-EYECOLOR",
59
+ "44": "I-EYECOLOR",
60
+ "45": "B-FIRSTNAME",
61
+ "46": "I-FIRSTNAME",
62
+ "47": "B-GENDER",
63
+ "48": "I-GENDER",
64
+ "49": "B-HEIGHT",
65
+ "50": "I-HEIGHT",
66
+ "51": "B-IBAN",
67
+ "52": "I-IBAN",
68
+ "53": "B-IP",
69
+ "54": "I-IP",
70
+ "55": "B-IPV4",
71
+ "56": "I-IPV4",
72
+ "57": "B-IPV6",
73
+ "58": "I-IPV6",
74
+ "59": "B-JOBAREA",
75
+ "60": "I-JOBAREA",
76
+ "61": "B-JOBTITLE",
77
+ "62": "I-JOBTITLE",
78
+ "63": "B-JOBTYPE",
79
+ "64": "I-JOBTYPE",
80
+ "65": "B-LASTNAME",
81
+ "66": "I-LASTNAME",
82
+ "67": "B-LITECOINADDRESS",
83
+ "68": "I-LITECOINADDRESS",
84
+ "69": "B-MAC",
85
+ "70": "I-MAC",
86
+ "71": "B-MASKEDNUMBER",
87
+ "72": "I-MASKEDNUMBER",
88
+ "73": "B-MIDDLENAME",
89
+ "74": "I-MIDDLENAME",
90
+ "75": "B-NEARBYGPSCOORDINATE",
91
+ "76": "I-NEARBYGPSCOORDINATE",
92
+ "77": "B-ORDINALDIRECTION",
93
+ "78": "I-ORDINALDIRECTION",
94
+ "79": "B-PASSWORD",
95
+ "80": "I-PASSWORD",
96
+ "81": "B-PHONEIMEI",
97
+ "82": "I-PHONEIMEI",
98
+ "83": "B-PHONENUMBER",
99
+ "84": "I-PHONENUMBER",
100
+ "85": "B-PIN",
101
+ "86": "I-PIN",
102
+ "87": "B-PREFIX",
103
+ "88": "I-PREFIX",
104
+ "89": "B-SECONDARYADDRESS",
105
+ "90": "I-SECONDARYADDRESS",
106
+ "91": "B-SEX",
107
+ "92": "I-SEX",
108
+ "93": "B-SSN",
109
+ "94": "I-SSN",
110
+ "95": "B-STATE",
111
+ "96": "I-STATE",
112
+ "97": "B-STREET",
113
+ "98": "I-STREET",
114
+ "99": "B-TIME",
115
+ "100": "I-TIME",
116
+ "101": "B-URL",
117
+ "102": "I-URL",
118
+ "103": "B-USERAGENT",
119
+ "104": "I-USERAGENT",
120
+ "105": "B-USERNAME",
121
+ "106": "I-USERNAME",
122
+ "107": "B-VEHICLEVIN",
123
+ "108": "I-VEHICLEVIN",
124
+ "109": "B-VEHICLEVRM",
125
+ "110": "I-VEHICLEVRM",
126
+ "111": "B-ZIPCODE",
127
+ "112": "I-ZIPCODE"
128
+ },
129
+ "initializer_range": 0.02,
130
+ "intermediate_size": 3072,
131
+ "is_decoder": false,
132
+ "label2id": {
133
+ "B-ACCOUNTNAME": 1,
134
+ "B-ACCOUNTNUMBER": 3,
135
+ "B-AGE": 5,
136
+ "B-AMOUNT": 7,
137
+ "B-BIC": 9,
138
+ "B-BITCOINADDRESS": 11,
139
+ "B-BUILDINGNUMBER": 13,
140
+ "B-CITY": 15,
141
+ "B-COMPANYNAME": 17,
142
+ "B-COUNTY": 19,
143
+ "B-CREDITCARDCVV": 21,
144
+ "B-CREDITCARDISSUER": 23,
145
+ "B-CREDITCARDNUMBER": 25,
146
+ "B-CURRENCY": 27,
147
+ "B-CURRENCYCODE": 29,
148
+ "B-CURRENCYNAME": 31,
149
+ "B-CURRENCYSYMBOL": 33,
150
+ "B-DATE": 35,
151
+ "B-DOB": 37,
152
+ "B-EMAIL": 39,
153
+ "B-ETHEREUMADDRESS": 41,
154
+ "B-EYECOLOR": 43,
155
+ "B-FIRSTNAME": 45,
156
+ "B-GENDER": 47,
157
+ "B-HEIGHT": 49,
158
+ "B-IBAN": 51,
159
+ "B-IP": 53,
160
+ "B-IPV4": 55,
161
+ "B-IPV6": 57,
162
+ "B-JOBAREA": 59,
163
+ "B-JOBTITLE": 61,
164
+ "B-JOBTYPE": 63,
165
+ "B-LASTNAME": 65,
166
+ "B-LITECOINADDRESS": 67,
167
+ "B-MAC": 69,
168
+ "B-MASKEDNUMBER": 71,
169
+ "B-MIDDLENAME": 73,
170
+ "B-NEARBYGPSCOORDINATE": 75,
171
+ "B-ORDINALDIRECTION": 77,
172
+ "B-PASSWORD": 79,
173
+ "B-PHONEIMEI": 81,
174
+ "B-PHONENUMBER": 83,
175
+ "B-PIN": 85,
176
+ "B-PREFIX": 87,
177
+ "B-SECONDARYADDRESS": 89,
178
+ "B-SEX": 91,
179
+ "B-SSN": 93,
180
+ "B-STATE": 95,
181
+ "B-STREET": 97,
182
+ "B-TIME": 99,
183
+ "B-URL": 101,
184
+ "B-USERAGENT": 103,
185
+ "B-USERNAME": 105,
186
+ "B-VEHICLEVIN": 107,
187
+ "B-VEHICLEVRM": 109,
188
+ "B-ZIPCODE": 111,
189
+ "I-ACCOUNTNAME": 2,
190
+ "I-ACCOUNTNUMBER": 4,
191
+ "I-AGE": 6,
192
+ "I-AMOUNT": 8,
193
+ "I-BIC": 10,
194
+ "I-BITCOINADDRESS": 12,
195
+ "I-BUILDINGNUMBER": 14,
196
+ "I-CITY": 16,
197
+ "I-COMPANYNAME": 18,
198
+ "I-COUNTY": 20,
199
+ "I-CREDITCARDCVV": 22,
200
+ "I-CREDITCARDISSUER": 24,
201
+ "I-CREDITCARDNUMBER": 26,
202
+ "I-CURRENCY": 28,
203
+ "I-CURRENCYCODE": 30,
204
+ "I-CURRENCYNAME": 32,
205
+ "I-CURRENCYSYMBOL": 34,
206
+ "I-DATE": 36,
207
+ "I-DOB": 38,
208
+ "I-EMAIL": 40,
209
+ "I-ETHEREUMADDRESS": 42,
210
+ "I-EYECOLOR": 44,
211
+ "I-FIRSTNAME": 46,
212
+ "I-GENDER": 48,
213
+ "I-HEIGHT": 50,
214
+ "I-IBAN": 52,
215
+ "I-IP": 54,
216
+ "I-IPV4": 56,
217
+ "I-IPV6": 58,
218
+ "I-JOBAREA": 60,
219
+ "I-JOBTITLE": 62,
220
+ "I-JOBTYPE": 64,
221
+ "I-LASTNAME": 66,
222
+ "I-LITECOINADDRESS": 68,
223
+ "I-MAC": 70,
224
+ "I-MASKEDNUMBER": 72,
225
+ "I-MIDDLENAME": 74,
226
+ "I-NEARBYGPSCOORDINATE": 76,
227
+ "I-ORDINALDIRECTION": 78,
228
+ "I-PASSWORD": 80,
229
+ "I-PHONEIMEI": 82,
230
+ "I-PHONENUMBER": 84,
231
+ "I-PIN": 86,
232
+ "I-PREFIX": 88,
233
+ "I-SECONDARYADDRESS": 90,
234
+ "I-SEX": 92,
235
+ "I-SSN": 94,
236
+ "I-STATE": 96,
237
+ "I-STREET": 98,
238
+ "I-TIME": 100,
239
+ "I-URL": 102,
240
+ "I-USERAGENT": 104,
241
+ "I-USERNAME": 106,
242
+ "I-VEHICLEVIN": 108,
243
+ "I-VEHICLEVRM": 110,
244
+ "I-ZIPCODE": 112,
245
+ "O": 0
246
+ },
247
+ "layer_norm_eps": 1e-05,
248
+ "max_position_embeddings": 514,
249
+ "model_type": "roberta",
250
+ "num_attention_heads": 12,
251
+ "num_hidden_layers": 12,
252
+ "pad_token_id": 1,
253
+ "tie_word_embeddings": true,
254
+ "transformers_version": "5.2.0",
255
+ "type_vocab_size": 1,
256
+ "use_cache": false,
257
+ "vocab_size": 50265
258
+ }
roberta-base/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce40559d26f6a2d1ee1ded99c712a1f1cc599485e3a02f693900ef393b0edb4
3
+ size 496591660
roberta-base/predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b6a12ca911b4f7605e659a49ca3eca917ae8dc3a615f83dde2446d09d3965a
3
+ size 53030080
roberta-base/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
roberta-base/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
roberta-base/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0d87b08283cc0ef9d78864e748493563becc0cd2658b8ae6df3116c52fc948
3
+ size 5201