yangwang825 commited on
Commit
ff1e989
·
verified ·
1 Parent(s): 5341072

Training in progress epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ step_*
2
+ epoch_*
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "arcface_margin": 0.4,
3
+ "arcface_scale": 30.0,
4
+ "architectures": [
5
+ "AngularRobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-unique_identifier",
17
+ "2": "I-unique_identifier",
18
+ "3": "B-date_of_birth",
19
+ "4": "I-date_of_birth",
20
+ "5": "B-ssn",
21
+ "6": "I-ssn",
22
+ "7": "B-date_time",
23
+ "8": "I-date_time",
24
+ "9": "B-person_name",
25
+ "10": "I-person_name",
26
+ "11": "B-email",
27
+ "12": "I-email",
28
+ "13": "B-location",
29
+ "14": "I-location",
30
+ "15": "B-phone_number",
31
+ "16": "I-phone_number",
32
+ "17": "B-ipv4",
33
+ "18": "I-ipv4",
34
+ "19": "B-credit_card_number",
35
+ "20": "I-credit_card_number",
36
+ "21": "B-user_name",
37
+ "22": "I-user_name",
38
+ "23": "B-company_name",
39
+ "24": "I-company_name",
40
+ "25": "B-account_number",
41
+ "26": "I-account_number",
42
+ "27": "B-api_key",
43
+ "28": "I-api_key",
44
+ "29": "B-ipv6",
45
+ "30": "I-ipv6",
46
+ "31": "B-password",
47
+ "32": "I-password",
48
+ "33": "B-url",
49
+ "34": "I-url",
50
+ "35": "B-swift_bic",
51
+ "36": "I-swift_bic",
52
+ "37": "B-cvv",
53
+ "38": "I-cvv",
54
+ "39": "B-pin",
55
+ "40": "I-pin"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "B-account_number": 25,
61
+ "B-api_key": 27,
62
+ "B-company_name": 23,
63
+ "B-credit_card_number": 19,
64
+ "B-cvv": 37,
65
+ "B-date_of_birth": 3,
66
+ "B-date_time": 7,
67
+ "B-email": 11,
68
+ "B-ipv4": 17,
69
+ "B-ipv6": 29,
70
+ "B-location": 13,
71
+ "B-password": 31,
72
+ "B-person_name": 9,
73
+ "B-phone_number": 15,
74
+ "B-pin": 39,
75
+ "B-ssn": 5,
76
+ "B-swift_bic": 35,
77
+ "B-unique_identifier": 1,
78
+ "B-url": 33,
79
+ "B-user_name": 21,
80
+ "I-account_number": 26,
81
+ "I-api_key": 28,
82
+ "I-company_name": 24,
83
+ "I-credit_card_number": 20,
84
+ "I-cvv": 38,
85
+ "I-date_of_birth": 4,
86
+ "I-date_time": 8,
87
+ "I-email": 12,
88
+ "I-ipv4": 18,
89
+ "I-ipv6": 30,
90
+ "I-location": 14,
91
+ "I-password": 32,
92
+ "I-person_name": 10,
93
+ "I-phone_number": 16,
94
+ "I-pin": 40,
95
+ "I-ssn": 6,
96
+ "I-swift_bic": 36,
97
+ "I-unique_identifier": 2,
98
+ "I-url": 34,
99
+ "I-user_name": 22,
100
+ "O": 0
101
+ },
102
+ "layer_norm_eps": 1e-05,
103
+ "loss_type": "arcface",
104
+ "max_position_embeddings": 514,
105
+ "model_type": "roberta",
106
+ "num_attention_heads": 12,
107
+ "num_hidden_layers": 12,
108
+ "pad_token_id": 1,
109
+ "position_embedding_type": "absolute",
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.51.3",
112
+ "type_vocab_size": 1,
113
+ "use_cache": true,
114
+ "vocab_size": 50265
115
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bd88e02f21c3d0aaec85487410c36a4873e7931a8f1ab7ab051362962c067a
3
+ size 496370220
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff