yangwang825 commited on
Commit
e793298
·
verified ·
1 Parent(s): d0189c3

Training in progress epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ step_*
2
+ epoch_*
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "arcface_margin": 0.4,
3
+ "arcface_scale": 30.0,
4
+ "architectures": [
5
+ "AngularBertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-unique_identifier",
16
+ "2": "I-unique_identifier",
17
+ "3": "B-date_of_birth",
18
+ "4": "I-date_of_birth",
19
+ "5": "B-ssn",
20
+ "6": "I-ssn",
21
+ "7": "B-date_time",
22
+ "8": "I-date_time",
23
+ "9": "B-person_name",
24
+ "10": "I-person_name",
25
+ "11": "B-email",
26
+ "12": "I-email",
27
+ "13": "B-location",
28
+ "14": "I-location",
29
+ "15": "B-phone_number",
30
+ "16": "I-phone_number",
31
+ "17": "B-ipv4",
32
+ "18": "I-ipv4",
33
+ "19": "B-credit_card_number",
34
+ "20": "I-credit_card_number",
35
+ "21": "B-user_name",
36
+ "22": "I-user_name",
37
+ "23": "B-company_name",
38
+ "24": "I-company_name",
39
+ "25": "B-account_number",
40
+ "26": "I-account_number",
41
+ "27": "B-api_key",
42
+ "28": "I-api_key",
43
+ "29": "B-ipv6",
44
+ "30": "I-ipv6",
45
+ "31": "B-password",
46
+ "32": "I-password",
47
+ "33": "B-url",
48
+ "34": "I-url",
49
+ "35": "B-swift_bic",
50
+ "36": "I-swift_bic",
51
+ "37": "B-cvv",
52
+ "38": "I-cvv",
53
+ "39": "B-pin",
54
+ "40": "I-pin"
55
+ },
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "label2id": {
59
+ "B-account_number": 25,
60
+ "B-api_key": 27,
61
+ "B-company_name": 23,
62
+ "B-credit_card_number": 19,
63
+ "B-cvv": 37,
64
+ "B-date_of_birth": 3,
65
+ "B-date_time": 7,
66
+ "B-email": 11,
67
+ "B-ipv4": 17,
68
+ "B-ipv6": 29,
69
+ "B-location": 13,
70
+ "B-password": 31,
71
+ "B-person_name": 9,
72
+ "B-phone_number": 15,
73
+ "B-pin": 39,
74
+ "B-ssn": 5,
75
+ "B-swift_bic": 35,
76
+ "B-unique_identifier": 1,
77
+ "B-url": 33,
78
+ "B-user_name": 21,
79
+ "I-account_number": 26,
80
+ "I-api_key": 28,
81
+ "I-company_name": 24,
82
+ "I-credit_card_number": 20,
83
+ "I-cvv": 38,
84
+ "I-date_of_birth": 4,
85
+ "I-date_time": 8,
86
+ "I-email": 12,
87
+ "I-ipv4": 18,
88
+ "I-ipv6": 30,
89
+ "I-location": 14,
90
+ "I-password": 32,
91
+ "I-person_name": 10,
92
+ "I-phone_number": 16,
93
+ "I-pin": 40,
94
+ "I-ssn": 6,
95
+ "I-swift_bic": 36,
96
+ "I-unique_identifier": 2,
97
+ "I-url": 34,
98
+ "I-user_name": 22,
99
+ "O": 0
100
+ },
101
+ "layer_norm_eps": 1e-12,
102
+ "loss_type": "arcface",
103
+ "max_position_embeddings": 512,
104
+ "model_type": "bert",
105
+ "num_attention_heads": 12,
106
+ "num_hidden_layers": 12,
107
+ "pad_token_id": 0,
108
+ "position_embedding_type": "absolute",
109
+ "torch_dtype": "float32",
110
+ "transformers_version": "4.51.3",
111
+ "type_vocab_size": 2,
112
+ "use_cache": true,
113
+ "vocab_size": 30522
114
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61397ccb99dbf4af79ed11e19b0ef2b48be136d461930a313158881be4bf6546
3
+ size 435716060
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff