RipTide99 commited on
Commit
1c864d1
1 Parent(s): 1b47bad

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. README.md +54 -0
  2. config.json +271 -0
  3. special_tokens_map.json +7 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-cased
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: RipTide99/results
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # RipTide99/results
15
+
16
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.3095
19
+ - Validation Loss: 0.1495
20
+ - Epoch: 0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Epoch |
45
+ |:----------:|:---------------:|:-----:|
46
+ | 0.3095 | 0.1495 | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.41.2
52
+ - TensorFlow 2.15.0
53
+ - Datasets 2.20.0
54
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-FIRSTNAME",
15
+ "2": "I-FIRSTNAME",
16
+ "3": "B-LASTNAME",
17
+ "4": "I-LASTNAME",
18
+ "5": "B-MIDDLENAME",
19
+ "6": "I-MIDDLENAME",
20
+ "7": "B-FULLNAME",
21
+ "8": "I-FULLNAME",
22
+ "9": "B-USERNAME",
23
+ "10": "I-USERNAME",
24
+ "11": "B-PASSWORD",
25
+ "12": "I-PASSWORD",
26
+ "13": "B-EMAIL",
27
+ "14": "I-EMAIL",
28
+ "15": "B-PIN",
29
+ "16": "I-PIN",
30
+ "17": "B-AGE",
31
+ "18": "I-AGE",
32
+ "19": "B-DOB",
33
+ "20": "I-DOB",
34
+ "21": "B-GENDER",
35
+ "22": "I-GENDER",
36
+ "23": "B-SEX",
37
+ "24": "I-SEX",
38
+ "25": "B-MASKEDNUMBER",
39
+ "26": "I-MASKEDNUMBER",
40
+ "27": "B-ADDRESS",
41
+ "28": "I-ADDRESS",
42
+ "29": "B-SECONDARYADDRESS",
43
+ "30": "I-SECONDARYADDRESS",
44
+ "31": "B-BUILDINGNUMBER",
45
+ "32": "I-BUILDINGNUMBER",
46
+ "33": "B-STREET",
47
+ "34": "I-STREET",
48
+ "35": "B-CITY",
49
+ "36": "I-CITY",
50
+ "37": "B-COUNTY",
51
+ "38": "I-COUNTY",
52
+ "39": "B-STATE",
53
+ "40": "I-STATE",
54
+ "41": "B-ZIPCODE",
55
+ "42": "I-ZIPCODE",
56
+ "43": "B-PREFIX",
57
+ "44": "I-PREFIX",
58
+ "45": "B-NEARBYGPSCOORDINATE",
59
+ "46": "I-NEARBYGPSCOORDINATE",
60
+ "47": "B-ORDINALDIRECTION",
61
+ "48": "I-ORDINALDIRECTION",
62
+ "49": "B-ACCOUNTNAME",
63
+ "50": "I-ACCOUNTNAME",
64
+ "51": "B-ACCOUNTNUMBER",
65
+ "52": "I-ACCOUNTNUMBER",
66
+ "53": "B-CREDITCARDNUMBER",
67
+ "54": "I-CREDITCARDNUMBER",
68
+ "55": "B-CREDITCARDCVV",
69
+ "56": "I-CREDITCARDCVV",
70
+ "57": "B-CREDITCARDISSUER",
71
+ "58": "I-CREDITCARDISSUER",
72
+ "59": "B-IBAN",
73
+ "60": "I-IBAN",
74
+ "61": "B-BIC",
75
+ "62": "I-BIC",
76
+ "63": "B-PHONENUMBER",
77
+ "64": "I-PHONENUMBER",
78
+ "65": "B-PHONEIMEI",
79
+ "66": "I-PHONEIMEI",
80
+ "67": "B-IP",
81
+ "68": "I-IP",
82
+ "69": "B-IPV4",
83
+ "70": "I-IPV4",
84
+ "71": "B-IPV6",
85
+ "72": "I-IPV6",
86
+ "73": "B-MAC",
87
+ "74": "I-MAC",
88
+ "75": "B-USERAGENT",
89
+ "76": "I-USERAGENT",
90
+ "77": "B-URL",
91
+ "78": "I-URL",
92
+ "79": "B-SSN",
93
+ "80": "I-SSN",
94
+ "81": "B-PASSPORTNUMBER",
95
+ "82": "I-PASSPORTNUMBER",
96
+ "83": "B-DRIVINGLICENSE",
97
+ "84": "I-DRIVINGLICENSE",
98
+ "85": "B-VEHICLEVIN",
99
+ "86": "I-VEHICLEVIN",
100
+ "87": "B-VEHICLEVRM",
101
+ "88": "I-VEHICLEVRM",
102
+ "89": "B-EYECOLOR",
103
+ "90": "I-EYECOLOR",
104
+ "91": "B-HEIGHT",
105
+ "92": "I-HEIGHT",
106
+ "93": "B-BITCOINADDRESS",
107
+ "94": "I-BITCOINADDRESS",
108
+ "95": "B-ETHEREUMADDRESS",
109
+ "96": "I-ETHEREUMADDRESS",
110
+ "97": "B-LITECOINADDRESS",
111
+ "98": "I-LITECOINADDRESS",
112
+ "99": "B-DATE",
113
+ "100": "I-DATE",
114
+ "101": "B-TIME",
115
+ "102": "I-TIME",
116
+ "103": "B-JOBTITLE",
117
+ "104": "I-JOBTITLE",
118
+ "105": "B-JOBAREA",
119
+ "106": "I-JOBAREA",
120
+ "107": "B-JOBTYPE",
121
+ "108": "I-JOBTYPE",
122
+ "109": "B-COMPANYNAME",
123
+ "110": "I-COMPANYNAME",
124
+ "111": "B-CURRENCY",
125
+ "112": "I-CURRENCY",
126
+ "113": "B-CURRENCYSYMBOL",
127
+ "114": "I-CURRENCYSYMBOL",
128
+ "115": "B-CURRENCYCODE",
129
+ "116": "I-CURRENCYCODE",
130
+ "117": "B-CURRENCYNAME",
131
+ "118": "I-CURRENCYNAME",
132
+ "119": "B-AMOUNT",
133
+ "120": "I-AMOUNT"
134
+ },
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "label2id": {
138
+ "B-ACCOUNTNAME": 49,
139
+ "B-ACCOUNTNUMBER": 51,
140
+ "B-ADDRESS": 27,
141
+ "B-AGE": 17,
142
+ "B-AMOUNT": 119,
143
+ "B-BIC": 61,
144
+ "B-BITCOINADDRESS": 93,
145
+ "B-BUILDINGNUMBER": 31,
146
+ "B-CITY": 35,
147
+ "B-COMPANYNAME": 109,
148
+ "B-COUNTY": 37,
149
+ "B-CREDITCARDCVV": 55,
150
+ "B-CREDITCARDISSUER": 57,
151
+ "B-CREDITCARDNUMBER": 53,
152
+ "B-CURRENCY": 111,
153
+ "B-CURRENCYCODE": 115,
154
+ "B-CURRENCYNAME": 117,
155
+ "B-CURRENCYSYMBOL": 113,
156
+ "B-DATE": 99,
157
+ "B-DOB": 19,
158
+ "B-DRIVINGLICENSE": 83,
159
+ "B-EMAIL": 13,
160
+ "B-ETHEREUMADDRESS": 95,
161
+ "B-EYECOLOR": 89,
162
+ "B-FIRSTNAME": 1,
163
+ "B-FULLNAME": 7,
164
+ "B-GENDER": 21,
165
+ "B-HEIGHT": 91,
166
+ "B-IBAN": 59,
167
+ "B-IP": 67,
168
+ "B-IPV4": 69,
169
+ "B-IPV6": 71,
170
+ "B-JOBAREA": 105,
171
+ "B-JOBTITLE": 103,
172
+ "B-JOBTYPE": 107,
173
+ "B-LASTNAME": 3,
174
+ "B-LITECOINADDRESS": 97,
175
+ "B-MAC": 73,
176
+ "B-MASKEDNUMBER": 25,
177
+ "B-MIDDLENAME": 5,
178
+ "B-NEARBYGPSCOORDINATE": 45,
179
+ "B-ORDINALDIRECTION": 47,
180
+ "B-PASSPORTNUMBER": 81,
181
+ "B-PASSWORD": 11,
182
+ "B-PHONEIMEI": 65,
183
+ "B-PHONENUMBER": 63,
184
+ "B-PIN": 15,
185
+ "B-PREFIX": 43,
186
+ "B-SECONDARYADDRESS": 29,
187
+ "B-SEX": 23,
188
+ "B-SSN": 79,
189
+ "B-STATE": 39,
190
+ "B-STREET": 33,
191
+ "B-TIME": 101,
192
+ "B-URL": 77,
193
+ "B-USERAGENT": 75,
194
+ "B-USERNAME": 9,
195
+ "B-VEHICLEVIN": 85,
196
+ "B-VEHICLEVRM": 87,
197
+ "B-ZIPCODE": 41,
198
+ "I-ACCOUNTNAME": 50,
199
+ "I-ACCOUNTNUMBER": 52,
200
+ "I-ADDRESS": 28,
201
+ "I-AGE": 18,
202
+ "I-AMOUNT": 120,
203
+ "I-BIC": 62,
204
+ "I-BITCOINADDRESS": 94,
205
+ "I-BUILDINGNUMBER": 32,
206
+ "I-CITY": 36,
207
+ "I-COMPANYNAME": 110,
208
+ "I-COUNTY": 38,
209
+ "I-CREDITCARDCVV": 56,
210
+ "I-CREDITCARDISSUER": 58,
211
+ "I-CREDITCARDNUMBER": 54,
212
+ "I-CURRENCY": 112,
213
+ "I-CURRENCYCODE": 116,
214
+ "I-CURRENCYNAME": 118,
215
+ "I-CURRENCYSYMBOL": 114,
216
+ "I-DATE": 100,
217
+ "I-DOB": 20,
218
+ "I-DRIVINGLICENSE": 84,
219
+ "I-EMAIL": 14,
220
+ "I-ETHEREUMADDRESS": 96,
221
+ "I-EYECOLOR": 90,
222
+ "I-FIRSTNAME": 2,
223
+ "I-FULLNAME": 8,
224
+ "I-GENDER": 22,
225
+ "I-HEIGHT": 92,
226
+ "I-IBAN": 60,
227
+ "I-IP": 68,
228
+ "I-IPV4": 70,
229
+ "I-IPV6": 72,
230
+ "I-JOBAREA": 106,
231
+ "I-JOBTITLE": 104,
232
+ "I-JOBTYPE": 108,
233
+ "I-LASTNAME": 4,
234
+ "I-LITECOINADDRESS": 98,
235
+ "I-MAC": 74,
236
+ "I-MASKEDNUMBER": 26,
237
+ "I-MIDDLENAME": 6,
238
+ "I-NEARBYGPSCOORDINATE": 46,
239
+ "I-ORDINALDIRECTION": 48,
240
+ "I-PASSPORTNUMBER": 82,
241
+ "I-PASSWORD": 12,
242
+ "I-PHONEIMEI": 66,
243
+ "I-PHONENUMBER": 64,
244
+ "I-PIN": 16,
245
+ "I-PREFIX": 44,
246
+ "I-SECONDARYADDRESS": 30,
247
+ "I-SEX": 24,
248
+ "I-SSN": 80,
249
+ "I-STATE": 40,
250
+ "I-STREET": 34,
251
+ "I-TIME": 102,
252
+ "I-URL": 78,
253
+ "I-USERAGENT": 76,
254
+ "I-USERNAME": 10,
255
+ "I-VEHICLEVIN": 86,
256
+ "I-VEHICLEVRM": 88,
257
+ "I-ZIPCODE": 42,
258
+ "O": 0
259
+ },
260
+ "layer_norm_eps": 1e-12,
261
+ "max_position_embeddings": 512,
262
+ "model_type": "bert",
263
+ "num_attention_heads": 12,
264
+ "num_hidden_layers": 12,
265
+ "pad_token_id": 0,
266
+ "position_embedding_type": "absolute",
267
+ "transformers_version": "4.41.2",
268
+ "type_vocab_size": 2,
269
+ "use_cache": true,
270
+ "vocab_size": 28996
271
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ce65f3b0a698efc512f7f729490e93dc017e5cb71de6dd31822aadc3fcb149
3
+ size 431536556
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff