ab-ai commited on
Commit
56f8180
1 Parent(s): faeaa4c

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-FIRSTNAME",
14
+ "2": "I-FIRSTNAME",
15
+ "3": "B-IPV4",
16
+ "4": "I-IPV4",
17
+ "5": "B-AGE",
18
+ "6": "I-AGE",
19
+ "7": "B-URL",
20
+ "8": "I-URL",
21
+ "9": "B-PASSWORD",
22
+ "10": "I-PASSWORD",
23
+ "11": "B-AMOUNT",
24
+ "12": "I-AMOUNT",
25
+ "13": "B-PHONENUMBER",
26
+ "14": "I-PHONENUMBER",
27
+ "15": "B-ACCOUNTNAME",
28
+ "16": "I-ACCOUNTNAME",
29
+ "17": "B-IP",
30
+ "18": "I-IP",
31
+ "19": "B-COUNTY",
32
+ "20": "I-COUNTY",
33
+ "21": "B-EMAIL",
34
+ "22": "I-EMAIL",
35
+ "23": "B-CREDITCARDNUMBER",
36
+ "24": "I-CREDITCARDNUMBER",
37
+ "25": "B-PREFIX",
38
+ "26": "I-PREFIX",
39
+ "27": "B-LASTNAME",
40
+ "28": "I-LASTNAME",
41
+ "29": "B-STREET",
42
+ "30": "I-STREET",
43
+ "31": "B-SECONDARYADDRESS",
44
+ "32": "I-SECONDARYADDRESS",
45
+ "33": "B-ZIPCODE",
46
+ "34": "I-ZIPCODE",
47
+ "35": "B-STATE",
48
+ "36": "I-STATE",
49
+ "37": "B-MIDDLENAME",
50
+ "38": "I-MIDDLENAME",
51
+ "39": "B-IPV6",
52
+ "40": "I-IPV6",
53
+ "41": "B-USERNAME",
54
+ "42": "I-USERNAME",
55
+ "43": "B-GENDER",
56
+ "44": "I-GENDER",
57
+ "45": "B-COMPANYNAME",
58
+ "46": "I-COMPANYNAME",
59
+ "47": "B-DATE",
60
+ "48": "I-DATE",
61
+ "49": "B-IBAN",
62
+ "50": "I-IBAN",
63
+ "51": "B-CREDITCARDCVV",
64
+ "52": "I-CREDITCARDCVV",
65
+ "53": "B-DOB",
66
+ "54": "I-DOB",
67
+ "55": "B-ACCOUNTNUMBER",
68
+ "56": "I-ACCOUNTNUMBER",
69
+ "57": "B-SEX",
70
+ "58": "I-SEX",
71
+ "59": "B-PHONEIMEI",
72
+ "60": "I-PHONEIMEI",
73
+ "61": "B-SSN",
74
+ "62": "I-SSN",
75
+ "63": "B-CREDITCARDISSUER",
76
+ "64": "I-CREDITCARDISSUER",
77
+ "65": "B-BUILDINGNUMBER",
78
+ "66": "I-BUILDINGNUMBER",
79
+ "67": "B-PIN",
80
+ "68": "I-PIN",
81
+ "69": "B-MASKEDNUMBER",
82
+ "70": "I-MASKEDNUMBER",
83
+ "71": "B-VEHICLEVRM",
84
+ "72": "I-VEHICLEVRM",
85
+ "73": "B-CITY",
86
+ "74": "I-CITY",
87
+ "75": "B-VEHICLEVIN",
88
+ "76": "I-VEHICLEVIN"
89
+ },
90
+ "initializer_range": 0.02,
91
+ "label2id": {
92
+ "B-ACCOUNTNAME": 15,
93
+ "B-ACCOUNTNUMBER": 55,
94
+ "B-AGE": 5,
95
+ "B-AMOUNT": 11,
96
+ "B-BUILDINGNUMBER": 65,
97
+ "B-CITY": 73,
98
+ "B-COMPANYNAME": 45,
99
+ "B-COUNTY": 19,
100
+ "B-CREDITCARDCVV": 51,
101
+ "B-CREDITCARDISSUER": 63,
102
+ "B-CREDITCARDNUMBER": 23,
103
+ "B-DATE": 47,
104
+ "B-DOB": 53,
105
+ "B-EMAIL": 21,
106
+ "B-FIRSTNAME": 1,
107
+ "B-GENDER": 43,
108
+ "B-IBAN": 49,
109
+ "B-IP": 17,
110
+ "B-IPV4": 3,
111
+ "B-IPV6": 39,
112
+ "B-LASTNAME": 27,
113
+ "B-MASKEDNUMBER": 69,
114
+ "B-MIDDLENAME": 37,
115
+ "B-PASSWORD": 9,
116
+ "B-PHONEIMEI": 59,
117
+ "B-PHONENUMBER": 13,
118
+ "B-PIN": 67,
119
+ "B-PREFIX": 25,
120
+ "B-SECONDARYADDRESS": 31,
121
+ "B-SEX": 57,
122
+ "B-SSN": 61,
123
+ "B-STATE": 35,
124
+ "B-STREET": 29,
125
+ "B-URL": 7,
126
+ "B-USERNAME": 41,
127
+ "B-VEHICLEVIN": 75,
128
+ "B-VEHICLEVRM": 71,
129
+ "B-ZIPCODE": 33,
130
+ "I-ACCOUNTNAME": 16,
131
+ "I-ACCOUNTNUMBER": 56,
132
+ "I-AGE": 6,
133
+ "I-AMOUNT": 12,
134
+ "I-BUILDINGNUMBER": 66,
135
+ "I-CITY": 74,
136
+ "I-COMPANYNAME": 46,
137
+ "I-COUNTY": 20,
138
+ "I-CREDITCARDCVV": 52,
139
+ "I-CREDITCARDISSUER": 64,
140
+ "I-CREDITCARDNUMBER": 24,
141
+ "I-DATE": 48,
142
+ "I-DOB": 54,
143
+ "I-EMAIL": 22,
144
+ "I-FIRSTNAME": 2,
145
+ "I-GENDER": 44,
146
+ "I-IBAN": 50,
147
+ "I-IP": 18,
148
+ "I-IPV4": 4,
149
+ "I-IPV6": 40,
150
+ "I-LASTNAME": 28,
151
+ "I-MASKEDNUMBER": 70,
152
+ "I-MIDDLENAME": 38,
153
+ "I-PASSWORD": 10,
154
+ "I-PHONEIMEI": 60,
155
+ "I-PHONENUMBER": 14,
156
+ "I-PIN": 68,
157
+ "I-PREFIX": 26,
158
+ "I-SECONDARYADDRESS": 32,
159
+ "I-SEX": 58,
160
+ "I-SSN": 62,
161
+ "I-STATE": 36,
162
+ "I-STREET": 30,
163
+ "I-URL": 8,
164
+ "I-USERNAME": 42,
165
+ "I-VEHICLEVIN": 76,
166
+ "I-VEHICLEVRM": 72,
167
+ "I-ZIPCODE": 34,
168
+ "O": 0
169
+ },
170
+ "max_position_embeddings": 512,
171
+ "model_type": "distilbert",
172
+ "n_heads": 12,
173
+ "n_layers": 6,
174
+ "pad_token_id": 0,
175
+ "qa_dropout": 0.1,
176
+ "seq_classif_dropout": 0.2,
177
+ "sinusoidal_pos_embds": false,
178
+ "tie_weights_": true,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": "4.38.2",
181
+ "vocab_size": 30522
182
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38dc87bd33339f2409abbeb4c0a4e8845ae9153196502c4a5d2683b7d56ed12
3
+ size 265700724
runs/Mar15_19-49-43_fac3aeac03a7/events.out.tfevents.1710532184.fac3aeac03a7.1051.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3ad568648cba83c0c2eb8e577dd3ac1e892768dadc15515aee68f2821e8f2e
3
+ size 9516
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2375ffc6a8ed2cb7e7fe19493e865c005ab172b499ee10d2d76742fb24e916
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff