gaodrew commited on
Commit
1657243
1 Parent(s): 3a449d5

Training in progress, step 100

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "B-account_number",
12
+ "1": "B-address",
13
+ "2": "B-api_key",
14
+ "3": "B-bank_routing_number",
15
+ "4": "B-biometric_identifier",
16
+ "5": "B-certificate_license_number",
17
+ "6": "B-city",
18
+ "7": "B-company_name",
19
+ "8": "B-coordinate",
20
+ "9": "B-country",
21
+ "10": "B-credit_card_number",
22
+ "11": "B-customer_id",
23
+ "12": "B-cvv",
24
+ "13": "B-date",
25
+ "14": "B-date_of_birth",
26
+ "15": "B-date_time",
27
+ "16": "B-device_identifier",
28
+ "17": "B-email",
29
+ "18": "B-employee_id",
30
+ "19": "B-first_name",
31
+ "20": "B-health_plan_beneficiary_number",
32
+ "21": "B-ipv4",
33
+ "22": "B-ipv6",
34
+ "23": "B-last_name",
35
+ "24": "B-license_plate",
36
+ "25": "B-medical_record_number",
37
+ "26": "B-name",
38
+ "27": "B-national_id",
39
+ "28": "B-password",
40
+ "29": "B-phone_number",
41
+ "30": "B-pin",
42
+ "31": "B-postcode",
43
+ "32": "B-ssn",
44
+ "33": "B-state",
45
+ "34": "B-street_address",
46
+ "35": "B-swift_bic",
47
+ "36": "B-tax_id",
48
+ "37": "B-time",
49
+ "38": "B-unique_identifier",
50
+ "39": "B-url",
51
+ "40": "B-user_name",
52
+ "41": "B-vehicle_identifier",
53
+ "42": "I-account_number",
54
+ "43": "I-address",
55
+ "44": "I-api_key",
56
+ "45": "I-bank_routing_number",
57
+ "46": "I-biometric_identifier",
58
+ "47": "I-certificate_license_number",
59
+ "48": "I-city",
60
+ "49": "I-company_name",
61
+ "50": "I-coordinate",
62
+ "51": "I-country",
63
+ "52": "I-credit_card_number",
64
+ "53": "I-customer_id",
65
+ "54": "I-cvv",
66
+ "55": "I-date",
67
+ "56": "I-date_of_birth",
68
+ "57": "I-date_time",
69
+ "58": "I-device_identifier",
70
+ "59": "I-email",
71
+ "60": "I-employee_id",
72
+ "61": "I-first_name",
73
+ "62": "I-health_plan_beneficiary_number",
74
+ "63": "I-ipv4",
75
+ "64": "I-ipv6",
76
+ "65": "I-last_name",
77
+ "66": "I-license_plate",
78
+ "67": "I-medical_record_number",
79
+ "68": "I-name",
80
+ "69": "I-national_id",
81
+ "70": "I-password",
82
+ "71": "I-phone_number",
83
+ "72": "I-pin",
84
+ "73": "I-postcode",
85
+ "74": "I-ssn",
86
+ "75": "I-state",
87
+ "76": "I-street_address",
88
+ "77": "I-swift_bic",
89
+ "78": "I-tax_id",
90
+ "79": "I-time",
91
+ "80": "I-unique_identifier",
92
+ "81": "I-url",
93
+ "82": "I-user_name",
94
+ "83": "I-vehicle_identifier",
95
+ "84": "O"
96
+ },
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 4096,
99
+ "label2id": {
100
+ "B-account_number": 0,
101
+ "B-address": 1,
102
+ "B-api_key": 2,
103
+ "B-bank_routing_number": 3,
104
+ "B-biometric_identifier": 4,
105
+ "B-certificate_license_number": 5,
106
+ "B-city": 6,
107
+ "B-company_name": 7,
108
+ "B-coordinate": 8,
109
+ "B-country": 9,
110
+ "B-credit_card_number": 10,
111
+ "B-customer_id": 11,
112
+ "B-cvv": 12,
113
+ "B-date": 13,
114
+ "B-date_of_birth": 14,
115
+ "B-date_time": 15,
116
+ "B-device_identifier": 16,
117
+ "B-email": 17,
118
+ "B-employee_id": 18,
119
+ "B-first_name": 19,
120
+ "B-health_plan_beneficiary_number": 20,
121
+ "B-ipv4": 21,
122
+ "B-ipv6": 22,
123
+ "B-last_name": 23,
124
+ "B-license_plate": 24,
125
+ "B-medical_record_number": 25,
126
+ "B-name": 26,
127
+ "B-national_id": 27,
128
+ "B-password": 28,
129
+ "B-phone_number": 29,
130
+ "B-pin": 30,
131
+ "B-postcode": 31,
132
+ "B-ssn": 32,
133
+ "B-state": 33,
134
+ "B-street_address": 34,
135
+ "B-swift_bic": 35,
136
+ "B-tax_id": 36,
137
+ "B-time": 37,
138
+ "B-unique_identifier": 38,
139
+ "B-url": 39,
140
+ "B-user_name": 40,
141
+ "B-vehicle_identifier": 41,
142
+ "I-account_number": 42,
143
+ "I-address": 43,
144
+ "I-api_key": 44,
145
+ "I-bank_routing_number": 45,
146
+ "I-biometric_identifier": 46,
147
+ "I-certificate_license_number": 47,
148
+ "I-city": 48,
149
+ "I-company_name": 49,
150
+ "I-coordinate": 50,
151
+ "I-country": 51,
152
+ "I-credit_card_number": 52,
153
+ "I-customer_id": 53,
154
+ "I-cvv": 54,
155
+ "I-date": 55,
156
+ "I-date_of_birth": 56,
157
+ "I-date_time": 57,
158
+ "I-device_identifier": 58,
159
+ "I-email": 59,
160
+ "I-employee_id": 60,
161
+ "I-first_name": 61,
162
+ "I-health_plan_beneficiary_number": 62,
163
+ "I-ipv4": 63,
164
+ "I-ipv6": 64,
165
+ "I-last_name": 65,
166
+ "I-license_plate": 66,
167
+ "I-medical_record_number": 67,
168
+ "I-name": 68,
169
+ "I-national_id": 69,
170
+ "I-password": 70,
171
+ "I-phone_number": 71,
172
+ "I-pin": 72,
173
+ "I-postcode": 73,
174
+ "I-ssn": 74,
175
+ "I-state": 75,
176
+ "I-street_address": 76,
177
+ "I-swift_bic": 77,
178
+ "I-tax_id": 78,
179
+ "I-time": 79,
180
+ "I-unique_identifier": 80,
181
+ "I-url": 81,
182
+ "I-user_name": 82,
183
+ "I-vehicle_identifier": 83,
184
+ "O": 84
185
+ },
186
+ "layer_norm_eps": 1e-07,
187
+ "max_position_embeddings": 512,
188
+ "max_relative_positions": -1,
189
+ "model_type": "deberta-v2",
190
+ "norm_rel_ebd": "layer_norm",
191
+ "num_attention_heads": 16,
192
+ "num_hidden_layers": 24,
193
+ "pad_token_id": 0,
194
+ "pooler_dropout": 0,
195
+ "pooler_hidden_act": "gelu",
196
+ "pooler_hidden_size": 1024,
197
+ "pos_att_type": [
198
+ "p2c",
199
+ "c2p"
200
+ ],
201
+ "position_biased_input": false,
202
+ "position_buckets": 256,
203
+ "relative_attention": true,
204
+ "share_att_key": true,
205
+ "torch_dtype": "float32",
206
+ "transformers_version": "4.44.2",
207
+ "type_vocab_size": 0,
208
+ "vocab_size": 128100
209
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7054483e0e7dff1e7e74eaa23f3c1e53c89ed0ac74386c5c4b48bcfc28557917
3
+ size 1736446172
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
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
+ "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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de796e6f7bdc70eb9fac4bff56c71423943343598b1f11a1c99fb73f8a81cce2
3
+ size 5176