PuxAI commited on
Commit
322a2d1
·
verified ·
1 Parent(s): 9e996b5

Auto-upload fine-tuned albert-base-v2 + Reports

Browse files
.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* 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
38
  distilbert-base-cased/predictions.json 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
38
  distilbert-base-cased/predictions.json filter=lfs diff=lfs merge=lfs -text
39
+ albert-base-v2/predictions.json filter=lfs diff=lfs merge=lfs -text
albert-base-v2/classification_report.txt ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ ACCOUNTNAME 0.99 1.00 1.00 135
4
+ ACCOUNTNUMBER 0.99 1.00 1.00 132
5
+ AGE 0.96 0.98 0.97 137
6
+ AMOUNT 0.97 0.99 0.98 148
7
+ BIC 0.94 0.94 0.94 35
8
+ BITCOINADDRESS 0.91 0.97 0.94 119
9
+ BUILDINGNUMBER 0.86 0.92 0.89 133
10
+ CITY 0.92 0.92 0.92 132
11
+ COMPANYNAME 1.00 1.00 1.00 125
12
+ COUNTY 0.97 0.93 0.95 120
13
+ CREDITCARDCVV 0.77 0.85 0.80 39
14
+ CREDITCARDISSUER 0.95 0.97 0.96 65
15
+ CREDITCARDNUMBER 0.83 0.94 0.88 108
16
+ CURRENCY 0.59 0.82 0.69 88
17
+ CURRENCYCODE 0.56 0.69 0.62 36
18
+ CURRENCYNAME 0.12 0.05 0.07 38
19
+ CURRENCYSYMBOL 0.87 0.90 0.88 110
20
+ DATE 0.78 0.96 0.86 219
21
+ DOB 0.73 0.54 0.62 100
22
+ EMAIL 1.00 1.00 1.00 214
23
+ ETHEREUMADDRESS 1.00 1.00 1.00 74
24
+ EYECOLOR 1.00 0.96 0.98 47
25
+ FIRSTNAME 0.96 0.97 0.96 638
26
+ GENDER 0.93 0.94 0.93 111
27
+ HEIGHT 1.00 1.00 1.00 48
28
+ IBAN 0.97 0.99 0.98 116
29
+ IP 0.04 0.03 0.03 105
30
+ IPV4 0.67 0.97 0.79 120
31
+ IPV6 0.52 0.86 0.65 116
32
+ JOBAREA 0.92 0.93 0.93 144
33
+ JOBTITLE 0.94 0.99 0.97 147
34
+ JOBTYPE 0.89 0.93 0.91 133
35
+ LASTNAME 0.95 0.95 0.95 258
36
+ LITECOINADDRESS 0.80 0.90 0.85 49
37
+ MAC 0.98 0.98 0.98 61
38
+ MASKEDNUMBER 0.91 0.84 0.87 93
39
+ MIDDLENAME 0.87 0.86 0.86 134
40
+ NEARBYGPSCOORDINATE 1.00 1.00 1.00 89
41
+ ORDINALDIRECTION 0.98 1.00 0.99 52
42
+ PASSWORD 0.96 0.99 0.97 134
43
+ PHONEIMEI 1.00 1.00 1.00 89
44
+ PHONENUMBER 0.97 1.00 0.99 113
45
+ PIN 0.68 0.68 0.68 38
46
+ PREFIX 0.87 0.95 0.91 196
47
+ SECONDARYADDRESS 0.99 0.99 0.99 119
48
+ SEX 0.95 0.99 0.97 138
49
+ SSN 0.96 0.98 0.97 97
50
+ STATE 0.93 0.97 0.95 153
51
+ STREET 0.96 0.97 0.97 136
52
+ TIME 0.97 0.96 0.97 139
53
+ URL 0.99 0.99 0.99 143
54
+ USERAGENT 0.98 0.98 0.98 102
55
+ USERNAME 0.98 0.99 0.99 155
56
+ VEHICLEVIN 0.98 1.00 0.99 41
57
+ VEHICLEVRM 0.97 1.00 0.99 39
58
+ ZIPCODE 0.91 0.92 0.91 125
59
+
60
+ micro avg 0.90 0.93 0.91 6725
61
+ macro avg 0.88 0.91 0.89 6725
62
+ weighted avg 0.90 0.93 0.91 6725
albert-base-v2/config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "down_scale_factor": 1,
9
+ "dtype": "float32",
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "B-ACCOUNTNAME",
19
+ "2": "I-ACCOUNTNAME",
20
+ "3": "B-ACCOUNTNUMBER",
21
+ "4": "I-ACCOUNTNUMBER",
22
+ "5": "B-AGE",
23
+ "6": "I-AGE",
24
+ "7": "B-AMOUNT",
25
+ "8": "I-AMOUNT",
26
+ "9": "B-BIC",
27
+ "10": "I-BIC",
28
+ "11": "B-BITCOINADDRESS",
29
+ "12": "I-BITCOINADDRESS",
30
+ "13": "B-BUILDINGNUMBER",
31
+ "14": "I-BUILDINGNUMBER",
32
+ "15": "B-CITY",
33
+ "16": "I-CITY",
34
+ "17": "B-COMPANYNAME",
35
+ "18": "I-COMPANYNAME",
36
+ "19": "B-COUNTY",
37
+ "20": "I-COUNTY",
38
+ "21": "B-CREDITCARDCVV",
39
+ "22": "I-CREDITCARDCVV",
40
+ "23": "B-CREDITCARDISSUER",
41
+ "24": "I-CREDITCARDISSUER",
42
+ "25": "B-CREDITCARDNUMBER",
43
+ "26": "I-CREDITCARDNUMBER",
44
+ "27": "B-CURRENCY",
45
+ "28": "I-CURRENCY",
46
+ "29": "B-CURRENCYCODE",
47
+ "30": "I-CURRENCYCODE",
48
+ "31": "B-CURRENCYNAME",
49
+ "32": "I-CURRENCYNAME",
50
+ "33": "B-CURRENCYSYMBOL",
51
+ "34": "I-CURRENCYSYMBOL",
52
+ "35": "B-DATE",
53
+ "36": "I-DATE",
54
+ "37": "B-DOB",
55
+ "38": "I-DOB",
56
+ "39": "B-EMAIL",
57
+ "40": "I-EMAIL",
58
+ "41": "B-ETHEREUMADDRESS",
59
+ "42": "I-ETHEREUMADDRESS",
60
+ "43": "B-EYECOLOR",
61
+ "44": "I-EYECOLOR",
62
+ "45": "B-FIRSTNAME",
63
+ "46": "I-FIRSTNAME",
64
+ "47": "B-GENDER",
65
+ "48": "I-GENDER",
66
+ "49": "B-HEIGHT",
67
+ "50": "I-HEIGHT",
68
+ "51": "B-IBAN",
69
+ "52": "I-IBAN",
70
+ "53": "B-IP",
71
+ "54": "I-IP",
72
+ "55": "B-IPV4",
73
+ "56": "I-IPV4",
74
+ "57": "B-IPV6",
75
+ "58": "I-IPV6",
76
+ "59": "B-JOBAREA",
77
+ "60": "I-JOBAREA",
78
+ "61": "B-JOBTITLE",
79
+ "62": "I-JOBTITLE",
80
+ "63": "B-JOBTYPE",
81
+ "64": "I-JOBTYPE",
82
+ "65": "B-LASTNAME",
83
+ "66": "I-LASTNAME",
84
+ "67": "B-LITECOINADDRESS",
85
+ "68": "I-LITECOINADDRESS",
86
+ "69": "B-MAC",
87
+ "70": "I-MAC",
88
+ "71": "B-MASKEDNUMBER",
89
+ "72": "I-MASKEDNUMBER",
90
+ "73": "B-MIDDLENAME",
91
+ "74": "I-MIDDLENAME",
92
+ "75": "B-NEARBYGPSCOORDINATE",
93
+ "76": "I-NEARBYGPSCOORDINATE",
94
+ "77": "B-ORDINALDIRECTION",
95
+ "78": "I-ORDINALDIRECTION",
96
+ "79": "B-PASSWORD",
97
+ "80": "I-PASSWORD",
98
+ "81": "B-PHONEIMEI",
99
+ "82": "I-PHONEIMEI",
100
+ "83": "B-PHONENUMBER",
101
+ "84": "I-PHONENUMBER",
102
+ "85": "B-PIN",
103
+ "86": "I-PIN",
104
+ "87": "B-PREFIX",
105
+ "88": "I-PREFIX",
106
+ "89": "B-SECONDARYADDRESS",
107
+ "90": "I-SECONDARYADDRESS",
108
+ "91": "B-SEX",
109
+ "92": "I-SEX",
110
+ "93": "B-SSN",
111
+ "94": "I-SSN",
112
+ "95": "B-STATE",
113
+ "96": "I-STATE",
114
+ "97": "B-STREET",
115
+ "98": "I-STREET",
116
+ "99": "B-TIME",
117
+ "100": "I-TIME",
118
+ "101": "B-URL",
119
+ "102": "I-URL",
120
+ "103": "B-USERAGENT",
121
+ "104": "I-USERAGENT",
122
+ "105": "B-USERNAME",
123
+ "106": "I-USERNAME",
124
+ "107": "B-VEHICLEVIN",
125
+ "108": "I-VEHICLEVIN",
126
+ "109": "B-VEHICLEVRM",
127
+ "110": "I-VEHICLEVRM",
128
+ "111": "B-ZIPCODE",
129
+ "112": "I-ZIPCODE"
130
+ },
131
+ "initializer_range": 0.02,
132
+ "inner_group_num": 1,
133
+ "intermediate_size": 3072,
134
+ "label2id": {
135
+ "B-ACCOUNTNAME": 1,
136
+ "B-ACCOUNTNUMBER": 3,
137
+ "B-AGE": 5,
138
+ "B-AMOUNT": 7,
139
+ "B-BIC": 9,
140
+ "B-BITCOINADDRESS": 11,
141
+ "B-BUILDINGNUMBER": 13,
142
+ "B-CITY": 15,
143
+ "B-COMPANYNAME": 17,
144
+ "B-COUNTY": 19,
145
+ "B-CREDITCARDCVV": 21,
146
+ "B-CREDITCARDISSUER": 23,
147
+ "B-CREDITCARDNUMBER": 25,
148
+ "B-CURRENCY": 27,
149
+ "B-CURRENCYCODE": 29,
150
+ "B-CURRENCYNAME": 31,
151
+ "B-CURRENCYSYMBOL": 33,
152
+ "B-DATE": 35,
153
+ "B-DOB": 37,
154
+ "B-EMAIL": 39,
155
+ "B-ETHEREUMADDRESS": 41,
156
+ "B-EYECOLOR": 43,
157
+ "B-FIRSTNAME": 45,
158
+ "B-GENDER": 47,
159
+ "B-HEIGHT": 49,
160
+ "B-IBAN": 51,
161
+ "B-IP": 53,
162
+ "B-IPV4": 55,
163
+ "B-IPV6": 57,
164
+ "B-JOBAREA": 59,
165
+ "B-JOBTITLE": 61,
166
+ "B-JOBTYPE": 63,
167
+ "B-LASTNAME": 65,
168
+ "B-LITECOINADDRESS": 67,
169
+ "B-MAC": 69,
170
+ "B-MASKEDNUMBER": 71,
171
+ "B-MIDDLENAME": 73,
172
+ "B-NEARBYGPSCOORDINATE": 75,
173
+ "B-ORDINALDIRECTION": 77,
174
+ "B-PASSWORD": 79,
175
+ "B-PHONEIMEI": 81,
176
+ "B-PHONENUMBER": 83,
177
+ "B-PIN": 85,
178
+ "B-PREFIX": 87,
179
+ "B-SECONDARYADDRESS": 89,
180
+ "B-SEX": 91,
181
+ "B-SSN": 93,
182
+ "B-STATE": 95,
183
+ "B-STREET": 97,
184
+ "B-TIME": 99,
185
+ "B-URL": 101,
186
+ "B-USERAGENT": 103,
187
+ "B-USERNAME": 105,
188
+ "B-VEHICLEVIN": 107,
189
+ "B-VEHICLEVRM": 109,
190
+ "B-ZIPCODE": 111,
191
+ "I-ACCOUNTNAME": 2,
192
+ "I-ACCOUNTNUMBER": 4,
193
+ "I-AGE": 6,
194
+ "I-AMOUNT": 8,
195
+ "I-BIC": 10,
196
+ "I-BITCOINADDRESS": 12,
197
+ "I-BUILDINGNUMBER": 14,
198
+ "I-CITY": 16,
199
+ "I-COMPANYNAME": 18,
200
+ "I-COUNTY": 20,
201
+ "I-CREDITCARDCVV": 22,
202
+ "I-CREDITCARDISSUER": 24,
203
+ "I-CREDITCARDNUMBER": 26,
204
+ "I-CURRENCY": 28,
205
+ "I-CURRENCYCODE": 30,
206
+ "I-CURRENCYNAME": 32,
207
+ "I-CURRENCYSYMBOL": 34,
208
+ "I-DATE": 36,
209
+ "I-DOB": 38,
210
+ "I-EMAIL": 40,
211
+ "I-ETHEREUMADDRESS": 42,
212
+ "I-EYECOLOR": 44,
213
+ "I-FIRSTNAME": 46,
214
+ "I-GENDER": 48,
215
+ "I-HEIGHT": 50,
216
+ "I-IBAN": 52,
217
+ "I-IP": 54,
218
+ "I-IPV4": 56,
219
+ "I-IPV6": 58,
220
+ "I-JOBAREA": 60,
221
+ "I-JOBTITLE": 62,
222
+ "I-JOBTYPE": 64,
223
+ "I-LASTNAME": 66,
224
+ "I-LITECOINADDRESS": 68,
225
+ "I-MAC": 70,
226
+ "I-MASKEDNUMBER": 72,
227
+ "I-MIDDLENAME": 74,
228
+ "I-NEARBYGPSCOORDINATE": 76,
229
+ "I-ORDINALDIRECTION": 78,
230
+ "I-PASSWORD": 80,
231
+ "I-PHONEIMEI": 82,
232
+ "I-PHONENUMBER": 84,
233
+ "I-PIN": 86,
234
+ "I-PREFIX": 88,
235
+ "I-SECONDARYADDRESS": 90,
236
+ "I-SEX": 92,
237
+ "I-SSN": 94,
238
+ "I-STATE": 96,
239
+ "I-STREET": 98,
240
+ "I-TIME": 100,
241
+ "I-URL": 102,
242
+ "I-USERAGENT": 104,
243
+ "I-USERNAME": 106,
244
+ "I-VEHICLEVIN": 108,
245
+ "I-VEHICLEVRM": 110,
246
+ "I-ZIPCODE": 112,
247
+ "O": 0
248
+ },
249
+ "layer_norm_eps": 1e-12,
250
+ "max_position_embeddings": 512,
251
+ "model_type": "albert",
252
+ "net_structure_type": 0,
253
+ "num_attention_heads": 12,
254
+ "num_hidden_groups": 1,
255
+ "num_hidden_layers": 12,
256
+ "num_memory_blocks": 0,
257
+ "pad_token_id": 0,
258
+ "tie_word_embeddings": true,
259
+ "transformers_version": "5.2.0",
260
+ "type_vocab_size": 2,
261
+ "use_cache": false,
262
+ "vocab_size": 30000
263
+ }
albert-base-v2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c8bafd6839f5fdc2d60470cc1ad5d4fff5c3d9f7fb0fa2674434d0a59afbd9
3
+ size 44722804
albert-base-v2/predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228546adec84d91ab76e0ca46c42401686902a8e4ab6db0248537bc2dcdd4370
3
+ size 53209779
albert-base-v2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
albert-base-v2/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "[SEP]",
8
+ "is_local": false,
9
+ "keep_accents": false,
10
+ "mask_token": "[MASK]",
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "AlbertTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
albert-base-v2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9d0864c12d2aa7d2e368b09d8e4f4f8fc7c7108e141ad1a360f95ca2ebd956
3
+ size 5201