Mosaabx commited on
Commit
3edcf6e
·
verified ·
1 Parent(s): 4bfb9e0

distillBERT_ar_pii_detector

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: afl-3.0
4
+ base_model: Davlan/distilbert-base-multilingual-cased-ner-hrl
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: exp1
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # exp1
21
+
22
+ This model is a fine-tuned version of [Davlan/distilbert-base-multilingual-cased-ner-hrl](https://huggingface.co/Davlan/distilbert-base-multilingual-cased-ner-hrl) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0695
25
+ - Precision: 0.9266
26
+ - Recall: 0.9478
27
+ - F1: 0.9371
28
+ - Accuracy: 0.9838
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 7
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.0981 | 1.0 | 11771 | 0.0893 | 0.8784 | 0.9084 | 0.8932 | 0.9656 |
60
+ | 0.0752 | 2.0 | 23542 | 0.0737 | 0.8950 | 0.9317 | 0.9129 | 0.9740 |
61
+ | 0.0587 | 3.0 | 35313 | 0.0671 | 0.9067 | 0.9383 | 0.9222 | 0.9780 |
62
+ | 0.0444 | 4.0 | 47084 | 0.0684 | 0.9099 | 0.9462 | 0.9277 | 0.9802 |
63
+ | 0.0336 | 5.0 | 58855 | 0.0675 | 0.9257 | 0.9428 | 0.9342 | 0.9828 |
64
+ | 0.023 | 6.0 | 70626 | 0.0683 | 0.9218 | 0.9471 | 0.9343 | 0.9833 |
65
+ | 0.0216 | 7.0 | 82397 | 0.0695 | 0.9266 | 0.9478 | 0.9371 | 0.9838 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.51.3
71
+ - Pytorch 2.6.0+cu124
72
+ - Datasets 3.6.0
73
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-ACCOUNTNUMBER",
13
+ "2": "B-AGE",
14
+ "3": "B-AMOUNT",
15
+ "4": "B-BIC",
16
+ "5": "B-BITCOINADDRESS",
17
+ "6": "B-BUILDINGNUMBER",
18
+ "7": "B-CITY",
19
+ "8": "B-COMPANYNAME",
20
+ "9": "B-COUNTY",
21
+ "10": "B-CREDITCARDCVV",
22
+ "11": "B-CREDITCARDINUMBER",
23
+ "12": "B-CREDITCARDISSUER",
24
+ "13": "B-CREDITCARDNUMBER",
25
+ "14": "B-CURRENCY",
26
+ "15": "B-CURRENCYCODE",
27
+ "16": "B-CURRENCYNAME",
28
+ "17": "B-CURRENCYSYMBOL",
29
+ "18": "B-DATE",
30
+ "19": "B-DOB",
31
+ "20": "B-EMAIL",
32
+ "21": "B-ETHEREUMADDRESS",
33
+ "22": "B-EYECOLOR",
34
+ "23": "B-GENDER",
35
+ "24": "B-HEIGHT",
36
+ "25": "B-IBAN",
37
+ "26": "B-IP",
38
+ "27": "B-IPV4",
39
+ "28": "B-IPV6",
40
+ "29": "B-JOBTITLE",
41
+ "30": "B-JOBTYPE",
42
+ "31": "B-LITECOINADDRESS",
43
+ "32": "B-MAC",
44
+ "33": "B-MASKEDNUMBER",
45
+ "34": "B-NEARBYGPSCOORDINATE",
46
+ "35": "B-ORDINALDIRECTION",
47
+ "36": "B-PASSWORD",
48
+ "37": "B-PERSONNAME",
49
+ "38": "B-PHONEIMEI",
50
+ "39": "B-PHONENUMBER",
51
+ "40": "B-PIN",
52
+ "41": "B-PREFIX",
53
+ "42": "B-SECONDARYADDRESS",
54
+ "43": "B-SEX",
55
+ "44": "B-SSN",
56
+ "45": "B-STATE",
57
+ "46": "B-STREET",
58
+ "47": "B-TIME",
59
+ "48": "B-URL",
60
+ "49": "B-USERAGENT",
61
+ "50": "B-USERNAME",
62
+ "51": "B-VEHICLEVIN",
63
+ "52": "B-VEHICLEVRM",
64
+ "53": "B-ZIPCODE",
65
+ "54": "I-ACCOUNTNAME",
66
+ "55": "I-ACCOUNTNUMBER",
67
+ "56": "I-AGE",
68
+ "57": "I-AMOUNT",
69
+ "58": "I-BIC",
70
+ "59": "I-BITCOINADDRESS",
71
+ "60": "I-BUILDINGNUMBER",
72
+ "61": "I-CITY",
73
+ "62": "I-COMPANYNAME",
74
+ "63": "I-COUNTY",
75
+ "64": "I-CREDITCARDCVV",
76
+ "65": "I-CREDITCARDISSUER",
77
+ "66": "I-CREDITCARDNUMBER",
78
+ "67": "I-CURRENCY",
79
+ "68": "I-CURRENCYCODE",
80
+ "69": "I-CURRENCYNAME",
81
+ "70": "I-CURRENCYSYMBOL",
82
+ "71": "I-DATE",
83
+ "72": "I-DOB",
84
+ "73": "I-EMAIL",
85
+ "74": "I-ETHEREUMADDRESS",
86
+ "75": "I-EYECOLOR",
87
+ "76": "I-GENDER",
88
+ "77": "I-HEIGHT",
89
+ "78": "I-IBAN",
90
+ "79": "I-IP",
91
+ "80": "I-IPV4",
92
+ "81": "I-IPV6",
93
+ "82": "I-JOBTITLE",
94
+ "83": "I-JOBTYPE",
95
+ "84": "I-LITECOINADDRESS",
96
+ "85": "I-MAC",
97
+ "86": "I-MASKEDNUMBER",
98
+ "87": "I-NEARBYGPSCOORDINATE",
99
+ "88": "I-ORDINALDIRECTION",
100
+ "89": "I-PASSWORD",
101
+ "90": "I-PERSONNAME",
102
+ "91": "I-PHONEIMEI",
103
+ "92": "I-PHONENUMBER",
104
+ "93": "I-PIN",
105
+ "94": "I-PREFIX",
106
+ "95": "I-SECONDARYADDRESS",
107
+ "96": "I-SEX",
108
+ "97": "I-SSN",
109
+ "98": "I-STATE",
110
+ "99": "I-STREET",
111
+ "100": "I-TIME",
112
+ "101": "I-URL",
113
+ "102": "I-USERAGENT",
114
+ "103": "I-USERNAME",
115
+ "104": "I-VEHICLEVIN",
116
+ "105": "I-VEHICLEVRM",
117
+ "106": "I-ZIPCODE",
118
+ "107": "B-ACCOUNTNAME"
119
+ },
120
+ "initializer_range": 0.02,
121
+ "label2id": {
122
+ "B-ACCOUNTNAME": 107,
123
+ "B-ACCOUNTNUMBER": 1,
124
+ "B-AGE": 2,
125
+ "B-AMOUNT": 3,
126
+ "B-BIC": 4,
127
+ "B-BITCOINADDRESS": 5,
128
+ "B-BUILDINGNUMBER": 6,
129
+ "B-CITY": 7,
130
+ "B-COMPANYNAME": 8,
131
+ "B-COUNTY": 9,
132
+ "B-CREDITCARDCVV": 10,
133
+ "B-CREDITCARDINUMBER": 11,
134
+ "B-CREDITCARDISSUER": 12,
135
+ "B-CREDITCARDNUMBER": 13,
136
+ "B-CURRENCY": 14,
137
+ "B-CURRENCYCODE": 15,
138
+ "B-CURRENCYNAME": 16,
139
+ "B-CURRENCYSYMBOL": 17,
140
+ "B-DATE": 18,
141
+ "B-DOB": 19,
142
+ "B-EMAIL": 20,
143
+ "B-ETHEREUMADDRESS": 21,
144
+ "B-EYECOLOR": 22,
145
+ "B-GENDER": 23,
146
+ "B-HEIGHT": 24,
147
+ "B-IBAN": 25,
148
+ "B-IP": 26,
149
+ "B-IPV4": 27,
150
+ "B-IPV6": 28,
151
+ "B-JOBTITLE": 29,
152
+ "B-JOBTYPE": 30,
153
+ "B-LITECOINADDRESS": 31,
154
+ "B-MAC": 32,
155
+ "B-MASKEDNUMBER": 33,
156
+ "B-NEARBYGPSCOORDINATE": 34,
157
+ "B-ORDINALDIRECTION": 35,
158
+ "B-PASSWORD": 36,
159
+ "B-PERSONNAME": 37,
160
+ "B-PHONEIMEI": 38,
161
+ "B-PHONENUMBER": 39,
162
+ "B-PIN": 40,
163
+ "B-PREFIX": 41,
164
+ "B-SECONDARYADDRESS": 42,
165
+ "B-SEX": 43,
166
+ "B-SSN": 44,
167
+ "B-STATE": 45,
168
+ "B-STREET": 46,
169
+ "B-TIME": 47,
170
+ "B-URL": 48,
171
+ "B-USERAGENT": 49,
172
+ "B-USERNAME": 50,
173
+ "B-VEHICLEVIN": 51,
174
+ "B-VEHICLEVRM": 52,
175
+ "B-ZIPCODE": 53,
176
+ "I-ACCOUNTNAME": 54,
177
+ "I-ACCOUNTNUMBER": 55,
178
+ "I-AGE": 56,
179
+ "I-AMOUNT": 57,
180
+ "I-BIC": 58,
181
+ "I-BITCOINADDRESS": 59,
182
+ "I-BUILDINGNUMBER": 60,
183
+ "I-CITY": 61,
184
+ "I-COMPANYNAME": 62,
185
+ "I-COUNTY": 63,
186
+ "I-CREDITCARDCVV": 64,
187
+ "I-CREDITCARDISSUER": 65,
188
+ "I-CREDITCARDNUMBER": 66,
189
+ "I-CURRENCY": 67,
190
+ "I-CURRENCYCODE": 68,
191
+ "I-CURRENCYNAME": 69,
192
+ "I-CURRENCYSYMBOL": 70,
193
+ "I-DATE": 71,
194
+ "I-DOB": 72,
195
+ "I-EMAIL": 73,
196
+ "I-ETHEREUMADDRESS": 74,
197
+ "I-EYECOLOR": 75,
198
+ "I-GENDER": 76,
199
+ "I-HEIGHT": 77,
200
+ "I-IBAN": 78,
201
+ "I-IP": 79,
202
+ "I-IPV4": 80,
203
+ "I-IPV6": 81,
204
+ "I-JOBTITLE": 82,
205
+ "I-JOBTYPE": 83,
206
+ "I-LITECOINADDRESS": 84,
207
+ "I-MAC": 85,
208
+ "I-MASKEDNUMBER": 86,
209
+ "I-NEARBYGPSCOORDINATE": 87,
210
+ "I-ORDINALDIRECTION": 88,
211
+ "I-PASSWORD": 89,
212
+ "I-PERSONNAME": 90,
213
+ "I-PHONEIMEI": 91,
214
+ "I-PHONENUMBER": 92,
215
+ "I-PIN": 93,
216
+ "I-PREFIX": 94,
217
+ "I-SECONDARYADDRESS": 95,
218
+ "I-SEX": 96,
219
+ "I-SSN": 97,
220
+ "I-STATE": 98,
221
+ "I-STREET": 99,
222
+ "I-TIME": 100,
223
+ "I-URL": 101,
224
+ "I-USERAGENT": 102,
225
+ "I-USERNAME": 103,
226
+ "I-VEHICLEVIN": 104,
227
+ "I-VEHICLEVRM": 105,
228
+ "I-ZIPCODE": 106,
229
+ "O": 0
230
+ },
231
+ "max_position_embeddings": 512,
232
+ "model_type": "distilbert",
233
+ "n_heads": 12,
234
+ "n_layers": 6,
235
+ "output_past": true,
236
+ "pad_token_id": 0,
237
+ "qa_dropout": 0.1,
238
+ "seq_classif_dropout": 0.2,
239
+ "sinusoidal_pos_embds": false,
240
+ "tie_weights_": true,
241
+ "torch_dtype": "float32",
242
+ "transformers_version": "4.51.3",
243
+ "vocab_size": 119547
244
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838eb2b1bfa15e31c16445d55685842b8d7402c492ff8f63ab3a52fbf9efa4dd
3
+ size 539280896
runs/May26_12-26-38_08382f3ccf39/events.out.tfevents.1748262400.08382f3ccf39.35.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a1bb6bc7afa0d73909d97b455763f7b6d74fdf6fbb4b6f712d35411d37be55
3
+ size 48838
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ "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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4350d8b4a0489f7b53e8cf97f04d9fca22cc42bc6bf00cc98504852b6d9f545
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff