Isotonic commited on
Commit
a132f7d
1 Parent(s): be49252

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip 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
 
 
33
  *.zip 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-PHONEIMEI",
13
+ "2": "I-PHONEIMEI",
14
+ "3": "B-JOBAREA",
15
+ "4": "I-JOBAREA",
16
+ "5": "B-FIRSTNAME",
17
+ "6": "I-FIRSTNAME",
18
+ "7": "B-VEHICLEVIN",
19
+ "8": "I-VEHICLEVIN",
20
+ "9": "B-GENDER",
21
+ "10": "I-GENDER",
22
+ "11": "B-HEIGHT",
23
+ "12": "I-HEIGHT",
24
+ "13": "B-BUILDINGNUMBER",
25
+ "14": "I-BUILDINGNUMBER",
26
+ "15": "B-MASKEDNUMBER",
27
+ "16": "I-MASKEDNUMBER",
28
+ "17": "B-AGE",
29
+ "18": "B-PASSWORD",
30
+ "19": "I-PASSWORD",
31
+ "20": "B-DOB",
32
+ "21": "I-DOB",
33
+ "22": "B-IPV6",
34
+ "23": "I-IPV6",
35
+ "24": "B-NEARBYGPSCOORDINATE",
36
+ "25": "I-NEARBYGPSCOORDINATE",
37
+ "26": "B-USERAGENT",
38
+ "27": "I-USERAGENT",
39
+ "28": "B-TIME",
40
+ "29": "I-TIME",
41
+ "30": "B-JOBTITLE",
42
+ "31": "I-JOBTITLE",
43
+ "32": "B-COUNTY",
44
+ "33": "B-EMAIL",
45
+ "34": "I-EMAIL",
46
+ "35": "B-ACCOUNTNUMBER",
47
+ "36": "I-ACCOUNTNUMBER",
48
+ "37": "B-PIN",
49
+ "38": "I-PIN",
50
+ "39": "B-EYECOLOR",
51
+ "40": "I-EYECOLOR",
52
+ "41": "B-LASTNAME",
53
+ "42": "I-LASTNAME",
54
+ "43": "B-IPV4",
55
+ "44": "I-IPV4",
56
+ "45": "B-DATE",
57
+ "46": "I-DATE",
58
+ "47": "B-STREET",
59
+ "48": "I-STREET",
60
+ "49": "B-CITY",
61
+ "50": "I-CITY",
62
+ "51": "B-PREFIX",
63
+ "52": "I-PREFIX",
64
+ "53": "I-COUNTY",
65
+ "54": "B-CREDITCARDNUMBER",
66
+ "55": "I-CREDITCARDNUMBER",
67
+ "56": "B-CREDITCARDISSUER",
68
+ "57": "I-CREDITCARDISSUER",
69
+ "58": "B-VEHICLEVRM",
70
+ "59": "I-VEHICLEVRM",
71
+ "60": "B-ORDINALDIRECTION",
72
+ "61": "B-JOBTYPE",
73
+ "62": "I-JOBTYPE",
74
+ "63": "B-CURRENCYCODE",
75
+ "64": "I-CURRENCYCODE",
76
+ "65": "B-ACCOUNTNAME",
77
+ "66": "I-ACCOUNTNAME",
78
+ "67": "B-STATE",
79
+ "68": "I-STATE",
80
+ "69": "B-BITCOINADDRESS",
81
+ "70": "I-BITCOINADDRESS",
82
+ "71": "B-LITECOINADDRESS",
83
+ "72": "I-LITECOINADDRESS",
84
+ "73": "B-PHONENUMBER",
85
+ "74": "I-PHONENUMBER",
86
+ "75": "B-MAC",
87
+ "76": "I-MAC",
88
+ "77": "B-IBAN",
89
+ "78": "I-IBAN",
90
+ "79": "B-COMPANYNAME",
91
+ "80": "I-COMPANYNAME",
92
+ "81": "B-CURRENCYNAME",
93
+ "82": "I-CURRENCYNAME",
94
+ "83": "B-ZIPCODE",
95
+ "84": "I-ZIPCODE",
96
+ "85": "B-SSN",
97
+ "86": "I-SSN",
98
+ "87": "B-AMOUNT",
99
+ "88": "I-AMOUNT",
100
+ "89": "B-CURRENCY",
101
+ "90": "I-CURRENCY",
102
+ "91": "B-URL",
103
+ "92": "I-URL",
104
+ "93": "B-IP",
105
+ "94": "I-IP",
106
+ "95": "B-SECONDARYADDRESS",
107
+ "96": "I-SECONDARYADDRESS",
108
+ "97": "B-USERNAME",
109
+ "98": "I-USERNAME",
110
+ "99": "B-MIDDLENAME",
111
+ "100": "B-ETHEREUMADDRESS",
112
+ "101": "I-ETHEREUMADDRESS",
113
+ "102": "B-CREDITCARDCVV",
114
+ "103": "B-CURRENCYSYMBOL",
115
+ "104": "I-CURRENCYSYMBOL",
116
+ "105": "I-AGE",
117
+ "106": "I-MIDDLENAME",
118
+ "107": "B-SEX",
119
+ "108": "B-BIC",
120
+ "109": "I-BIC",
121
+ "110": "I-CREDITCARDCVV"
122
+ },
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 3072,
125
+ "label2id": {
126
+ "B-ACCOUNTNAME": 65,
127
+ "B-ACCOUNTNUMBER": 35,
128
+ "B-AGE": 17,
129
+ "B-AMOUNT": 87,
130
+ "B-BIC": 108,
131
+ "B-BITCOINADDRESS": 69,
132
+ "B-BUILDINGNUMBER": 13,
133
+ "B-CITY": 49,
134
+ "B-COMPANYNAME": 79,
135
+ "B-COUNTY": 32,
136
+ "B-CREDITCARDCVV": 102,
137
+ "B-CREDITCARDISSUER": 56,
138
+ "B-CREDITCARDNUMBER": 54,
139
+ "B-CURRENCY": 89,
140
+ "B-CURRENCYCODE": 63,
141
+ "B-CURRENCYNAME": 81,
142
+ "B-CURRENCYSYMBOL": 103,
143
+ "B-DATE": 45,
144
+ "B-DOB": 20,
145
+ "B-EMAIL": 33,
146
+ "B-ETHEREUMADDRESS": 100,
147
+ "B-EYECOLOR": 39,
148
+ "B-FIRSTNAME": 5,
149
+ "B-GENDER": 9,
150
+ "B-HEIGHT": 11,
151
+ "B-IBAN": 77,
152
+ "B-IP": 93,
153
+ "B-IPV4": 43,
154
+ "B-IPV6": 22,
155
+ "B-JOBAREA": 3,
156
+ "B-JOBTITLE": 30,
157
+ "B-JOBTYPE": 61,
158
+ "B-LASTNAME": 41,
159
+ "B-LITECOINADDRESS": 71,
160
+ "B-MAC": 75,
161
+ "B-MASKEDNUMBER": 15,
162
+ "B-MIDDLENAME": 99,
163
+ "B-NEARBYGPSCOORDINATE": 24,
164
+ "B-ORDINALDIRECTION": 60,
165
+ "B-PASSWORD": 18,
166
+ "B-PHONEIMEI": 1,
167
+ "B-PHONENUMBER": 73,
168
+ "B-PIN": 37,
169
+ "B-PREFIX": 51,
170
+ "B-SECONDARYADDRESS": 95,
171
+ "B-SEX": 107,
172
+ "B-SSN": 85,
173
+ "B-STATE": 67,
174
+ "B-STREET": 47,
175
+ "B-TIME": 28,
176
+ "B-URL": 91,
177
+ "B-USERAGENT": 26,
178
+ "B-USERNAME": 97,
179
+ "B-VEHICLEVIN": 7,
180
+ "B-VEHICLEVRM": 58,
181
+ "B-ZIPCODE": 83,
182
+ "I-ACCOUNTNAME": 66,
183
+ "I-ACCOUNTNUMBER": 36,
184
+ "I-AGE": 105,
185
+ "I-AMOUNT": 88,
186
+ "I-BIC": 109,
187
+ "I-BITCOINADDRESS": 70,
188
+ "I-BUILDINGNUMBER": 14,
189
+ "I-CITY": 50,
190
+ "I-COMPANYNAME": 80,
191
+ "I-COUNTY": 53,
192
+ "I-CREDITCARDCVV": 110,
193
+ "I-CREDITCARDISSUER": 57,
194
+ "I-CREDITCARDNUMBER": 55,
195
+ "I-CURRENCY": 90,
196
+ "I-CURRENCYCODE": 64,
197
+ "I-CURRENCYNAME": 82,
198
+ "I-CURRENCYSYMBOL": 104,
199
+ "I-DATE": 46,
200
+ "I-DOB": 21,
201
+ "I-EMAIL": 34,
202
+ "I-ETHEREUMADDRESS": 101,
203
+ "I-EYECOLOR": 40,
204
+ "I-FIRSTNAME": 6,
205
+ "I-GENDER": 10,
206
+ "I-HEIGHT": 12,
207
+ "I-IBAN": 78,
208
+ "I-IP": 94,
209
+ "I-IPV4": 44,
210
+ "I-IPV6": 23,
211
+ "I-JOBAREA": 4,
212
+ "I-JOBTITLE": 31,
213
+ "I-JOBTYPE": 62,
214
+ "I-LASTNAME": 42,
215
+ "I-LITECOINADDRESS": 72,
216
+ "I-MAC": 76,
217
+ "I-MASKEDNUMBER": 16,
218
+ "I-MIDDLENAME": 106,
219
+ "I-NEARBYGPSCOORDINATE": 25,
220
+ "I-PASSWORD": 19,
221
+ "I-PHONEIMEI": 2,
222
+ "I-PHONENUMBER": 74,
223
+ "I-PIN": 38,
224
+ "I-PREFIX": 52,
225
+ "I-SECONDARYADDRESS": 96,
226
+ "I-SSN": 86,
227
+ "I-STATE": 68,
228
+ "I-STREET": 48,
229
+ "I-TIME": 29,
230
+ "I-URL": 92,
231
+ "I-USERAGENT": 27,
232
+ "I-USERNAME": 98,
233
+ "I-VEHICLEVIN": 8,
234
+ "I-VEHICLEVRM": 59,
235
+ "I-ZIPCODE": 84,
236
+ "O": 0
237
+ },
238
+ "layer_norm_eps": 1e-07,
239
+ "max_position_embeddings": 512,
240
+ "max_relative_positions": -1,
241
+ "model_type": "deberta-v2",
242
+ "norm_rel_ebd": "layer_norm",
243
+ "num_attention_heads": 12,
244
+ "num_hidden_layers": 12,
245
+ "pad_token_id": 0,
246
+ "pooler_dropout": 0,
247
+ "pooler_hidden_act": "gelu",
248
+ "pooler_hidden_size": 768,
249
+ "pos_att_type": [
250
+ "p2c",
251
+ "c2p"
252
+ ],
253
+ "position_biased_input": false,
254
+ "position_buckets": 256,
255
+ "relative_attention": true,
256
+ "share_att_key": true,
257
+ "torch_dtype": "float32",
258
+ "transformers_version": "4.35.2",
259
+ "type_vocab_size": 0,
260
+ "vocab_size": 251000
261
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7e43bc418f48682695c10ab7f4a621467635c3c1c7906b64d6ca064bae4255
3
+ size 1113240948
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e087a6b152517e9330e0d7502fdd9ac54db09c96ae0963fcfc8b669f6cee3969
3
+ size 16331494
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b353cb8f05f3d66880dab06ade38b03889588b602ee17fd65f600907adf018
3
+ size 4664