Mosaabx commited on
Commit
4994d82
·
verified ·
1 Parent(s): 8feaacb

cameltools_mix_ar_pii_detector

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: CAMeL-Lab/bert-base-arabic-camelbert-mix-ner
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: pii_ar_detector
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
+ # pii_ar_detector
21
+
22
+ This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-mix-ner](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-mix-ner) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0931
25
+ - Precision: 0.9476
26
+ - Recall: 0.9620
27
+ - F1: 0.9547
28
+ - Accuracy: 0.9870
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: 10
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.0886 | 1.0 | 12425 | 0.0917 | 0.8918 | 0.9041 | 0.8979 | 0.9652 |
60
+ | 0.0624 | 2.0 | 24850 | 0.0775 | 0.9037 | 0.9343 | 0.9187 | 0.9747 |
61
+ | 0.0422 | 3.0 | 37275 | 0.0634 | 0.9205 | 0.9461 | 0.9331 | 0.9823 |
62
+ | 0.0274 | 4.0 | 49700 | 0.0682 | 0.9316 | 0.9521 | 0.9418 | 0.9840 |
63
+ | 0.0195 | 5.0 | 62125 | 0.0702 | 0.9365 | 0.9567 | 0.9465 | 0.9853 |
64
+ | 0.0135 | 6.0 | 74550 | 0.0737 | 0.9394 | 0.9583 | 0.9487 | 0.9857 |
65
+ | 0.0084 | 7.0 | 86975 | 0.0801 | 0.9444 | 0.9595 | 0.9519 | 0.9864 |
66
+ | 0.0069 | 8.0 | 99400 | 0.0857 | 0.9449 | 0.9624 | 0.9536 | 0.9870 |
67
+ | 0.0043 | 9.0 | 111825 | 0.0887 | 0.9488 | 0.9608 | 0.9548 | 0.9869 |
68
+ | 0.003 | 10.0 | 124250 | 0.0931 | 0.9476 | 0.9620 | 0.9547 | 0.9870 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.51.3
74
+ - Pytorch 2.6.0+cu124
75
+ - Datasets 3.6.0
76
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-ACCOUNTNUMBER",
14
+ "2": "B-AGE",
15
+ "3": "B-AMOUNT",
16
+ "4": "B-BIC",
17
+ "5": "B-BITCOINADDRESS",
18
+ "6": "B-BUILDINGNUMBER",
19
+ "7": "B-CITY",
20
+ "8": "B-COMPANYNAME",
21
+ "9": "B-COUNTY",
22
+ "10": "B-CREDITCARDCVV",
23
+ "11": "B-CREDITCARDINUMBER",
24
+ "12": "B-CREDITCARDISSUER",
25
+ "13": "B-CREDITCARDNUMBER",
26
+ "14": "B-CURRENCY",
27
+ "15": "B-CURRENCYCODE",
28
+ "16": "B-CURRENCYNAME",
29
+ "17": "B-CURRENCYSYMBOL",
30
+ "18": "B-DATE",
31
+ "19": "B-DOB",
32
+ "20": "B-EMAIL",
33
+ "21": "B-ETHEREUMADDRESS",
34
+ "22": "B-EYECOLOR",
35
+ "23": "B-GENDER",
36
+ "24": "B-HEIGHT",
37
+ "25": "B-IBAN",
38
+ "26": "B-IP",
39
+ "27": "B-IPV4",
40
+ "28": "B-IPV6",
41
+ "29": "B-JOBTITLE",
42
+ "30": "B-JOBTYPE",
43
+ "31": "B-LITECOINADDRESS",
44
+ "32": "B-MAC",
45
+ "33": "B-MASKEDNUMBER",
46
+ "34": "B-NEARBYGPSCOORDINATE",
47
+ "35": "B-ORDINALDIRECTION",
48
+ "36": "B-PASSWORD",
49
+ "37": "B-PERSONNAME",
50
+ "38": "B-PHONEIMEI",
51
+ "39": "B-PHONENUMBER",
52
+ "40": "B-PIN",
53
+ "41": "B-PREFIX",
54
+ "42": "B-SECONDARYADDRESS",
55
+ "43": "B-SEX",
56
+ "44": "B-SSN",
57
+ "45": "B-STATE",
58
+ "46": "B-STREET",
59
+ "47": "B-TIME",
60
+ "48": "B-URL",
61
+ "49": "B-USERAGENT",
62
+ "50": "B-USERNAME",
63
+ "51": "B-VEHICLEVIN",
64
+ "52": "B-VEHICLEVRM",
65
+ "53": "B-ZIPCODE",
66
+ "54": "I-ACCOUNTNAME",
67
+ "55": "I-ACCOUNTNUMBER",
68
+ "56": "I-AGE",
69
+ "57": "I-AMOUNT",
70
+ "58": "I-BIC",
71
+ "59": "I-BITCOINADDRESS",
72
+ "60": "I-BUILDINGNUMBER",
73
+ "61": "I-CITY",
74
+ "62": "I-COMPANYNAME",
75
+ "63": "I-COUNTY",
76
+ "64": "I-CREDITCARDCVV",
77
+ "65": "I-CREDITCARDISSUER",
78
+ "66": "I-CREDITCARDNUMBER",
79
+ "67": "I-CURRENCY",
80
+ "68": "I-CURRENCYCODE",
81
+ "69": "I-CURRENCYNAME",
82
+ "70": "I-CURRENCYSYMBOL",
83
+ "71": "I-DATE",
84
+ "72": "I-DOB",
85
+ "73": "I-EMAIL",
86
+ "74": "I-ETHEREUMADDRESS",
87
+ "75": "I-EYECOLOR",
88
+ "76": "I-GENDER",
89
+ "77": "I-HEIGHT",
90
+ "78": "I-IBAN",
91
+ "79": "I-IP",
92
+ "80": "I-IPV4",
93
+ "81": "I-IPV6",
94
+ "82": "I-JOBTITLE",
95
+ "83": "I-JOBTYPE",
96
+ "84": "I-LITECOINADDRESS",
97
+ "85": "I-MAC",
98
+ "86": "I-MASKEDNUMBER",
99
+ "87": "I-NEARBYGPSCOORDINATE",
100
+ "88": "I-ORDINALDIRECTION",
101
+ "89": "I-PASSWORD",
102
+ "90": "I-PERSONNAME",
103
+ "91": "I-PHONEIMEI",
104
+ "92": "I-PHONENUMBER",
105
+ "93": "I-PIN",
106
+ "94": "I-PREFIX",
107
+ "95": "I-SECONDARYADDRESS",
108
+ "96": "I-SEX",
109
+ "97": "I-SSN",
110
+ "98": "I-STATE",
111
+ "99": "I-STREET",
112
+ "100": "I-TIME",
113
+ "101": "I-URL",
114
+ "102": "I-USERAGENT",
115
+ "103": "I-USERNAME",
116
+ "104": "I-VEHICLEVIN",
117
+ "105": "I-VEHICLEVRM",
118
+ "106": "I-ZIPCODE",
119
+ "107": "B-ACCOUNTNAME"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "label2id": {
124
+ "B-ACCOUNTNAME": 107,
125
+ "B-ACCOUNTNUMBER": 1,
126
+ "B-AGE": 2,
127
+ "B-AMOUNT": 3,
128
+ "B-BIC": 4,
129
+ "B-BITCOINADDRESS": 5,
130
+ "B-BUILDINGNUMBER": 6,
131
+ "B-CITY": 7,
132
+ "B-COMPANYNAME": 8,
133
+ "B-COUNTY": 9,
134
+ "B-CREDITCARDCVV": 10,
135
+ "B-CREDITCARDINUMBER": 11,
136
+ "B-CREDITCARDISSUER": 12,
137
+ "B-CREDITCARDNUMBER": 13,
138
+ "B-CURRENCY": 14,
139
+ "B-CURRENCYCODE": 15,
140
+ "B-CURRENCYNAME": 16,
141
+ "B-CURRENCYSYMBOL": 17,
142
+ "B-DATE": 18,
143
+ "B-DOB": 19,
144
+ "B-EMAIL": 20,
145
+ "B-ETHEREUMADDRESS": 21,
146
+ "B-EYECOLOR": 22,
147
+ "B-GENDER": 23,
148
+ "B-HEIGHT": 24,
149
+ "B-IBAN": 25,
150
+ "B-IP": 26,
151
+ "B-IPV4": 27,
152
+ "B-IPV6": 28,
153
+ "B-JOBTITLE": 29,
154
+ "B-JOBTYPE": 30,
155
+ "B-LITECOINADDRESS": 31,
156
+ "B-MAC": 32,
157
+ "B-MASKEDNUMBER": 33,
158
+ "B-NEARBYGPSCOORDINATE": 34,
159
+ "B-ORDINALDIRECTION": 35,
160
+ "B-PASSWORD": 36,
161
+ "B-PERSONNAME": 37,
162
+ "B-PHONEIMEI": 38,
163
+ "B-PHONENUMBER": 39,
164
+ "B-PIN": 40,
165
+ "B-PREFIX": 41,
166
+ "B-SECONDARYADDRESS": 42,
167
+ "B-SEX": 43,
168
+ "B-SSN": 44,
169
+ "B-STATE": 45,
170
+ "B-STREET": 46,
171
+ "B-TIME": 47,
172
+ "B-URL": 48,
173
+ "B-USERAGENT": 49,
174
+ "B-USERNAME": 50,
175
+ "B-VEHICLEVIN": 51,
176
+ "B-VEHICLEVRM": 52,
177
+ "B-ZIPCODE": 53,
178
+ "I-ACCOUNTNAME": 54,
179
+ "I-ACCOUNTNUMBER": 55,
180
+ "I-AGE": 56,
181
+ "I-AMOUNT": 57,
182
+ "I-BIC": 58,
183
+ "I-BITCOINADDRESS": 59,
184
+ "I-BUILDINGNUMBER": 60,
185
+ "I-CITY": 61,
186
+ "I-COMPANYNAME": 62,
187
+ "I-COUNTY": 63,
188
+ "I-CREDITCARDCVV": 64,
189
+ "I-CREDITCARDISSUER": 65,
190
+ "I-CREDITCARDNUMBER": 66,
191
+ "I-CURRENCY": 67,
192
+ "I-CURRENCYCODE": 68,
193
+ "I-CURRENCYNAME": 69,
194
+ "I-CURRENCYSYMBOL": 70,
195
+ "I-DATE": 71,
196
+ "I-DOB": 72,
197
+ "I-EMAIL": 73,
198
+ "I-ETHEREUMADDRESS": 74,
199
+ "I-EYECOLOR": 75,
200
+ "I-GENDER": 76,
201
+ "I-HEIGHT": 77,
202
+ "I-IBAN": 78,
203
+ "I-IP": 79,
204
+ "I-IPV4": 80,
205
+ "I-IPV6": 81,
206
+ "I-JOBTITLE": 82,
207
+ "I-JOBTYPE": 83,
208
+ "I-LITECOINADDRESS": 84,
209
+ "I-MAC": 85,
210
+ "I-MASKEDNUMBER": 86,
211
+ "I-NEARBYGPSCOORDINATE": 87,
212
+ "I-ORDINALDIRECTION": 88,
213
+ "I-PASSWORD": 89,
214
+ "I-PERSONNAME": 90,
215
+ "I-PHONEIMEI": 91,
216
+ "I-PHONENUMBER": 92,
217
+ "I-PIN": 93,
218
+ "I-PREFIX": 94,
219
+ "I-SECONDARYADDRESS": 95,
220
+ "I-SEX": 96,
221
+ "I-SSN": 97,
222
+ "I-STATE": 98,
223
+ "I-STREET": 99,
224
+ "I-TIME": 100,
225
+ "I-URL": 101,
226
+ "I-USERAGENT": 102,
227
+ "I-USERNAME": 103,
228
+ "I-VEHICLEVIN": 104,
229
+ "I-VEHICLEVRM": 105,
230
+ "I-ZIPCODE": 106,
231
+ "O": 0
232
+ },
233
+ "layer_norm_eps": 1e-12,
234
+ "max_position_embeddings": 512,
235
+ "model_type": "bert",
236
+ "num_attention_heads": 12,
237
+ "num_hidden_layers": 12,
238
+ "pad_token_id": 0,
239
+ "position_embedding_type": "absolute",
240
+ "torch_dtype": "float32",
241
+ "transformers_version": "4.51.3",
242
+ "type_vocab_size": 2,
243
+ "use_cache": true,
244
+ "vocab_size": 30000
245
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08a762373c7858d94a6c0e89b0306d2259ae37a1e20ee37111f3648c1a10cbb
3
+ size 434318560
runs/May29_12-54-00_299cf62caf00/events.out.tfevents.1748523243.299cf62caf00.35.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc381839139e58d247815b807029d60fe76a99f31e5409d9577a43ee646cf5e
3
+ size 10113
runs/May29_13-00-04_299cf62caf00/events.out.tfevents.1748523606.299cf62caf00.35.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415c43e1140486fd06b3e01eb371eabee92e1deea997f8829a41ece29c5ca3fd
3
+ size 68466
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c913acfac6ece9bde59b8cbb1d86d3b9834d297b345c5eb490c5cfd3bfffb67
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff