Training in progress epoch 0
Browse files- .gitignore +2 -0
- config.json +199 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
step_*
|
2 |
+
epoch_*
|
config.json
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-medical_record_number",
|
14 |
+
"2": "I-medical_record_number",
|
15 |
+
"3": "B-date_of_birth",
|
16 |
+
"4": "I-date_of_birth",
|
17 |
+
"5": "B-ssn",
|
18 |
+
"6": "I-ssn",
|
19 |
+
"7": "B-date",
|
20 |
+
"8": "I-date",
|
21 |
+
"9": "B-first_name",
|
22 |
+
"10": "I-first_name",
|
23 |
+
"11": "B-email",
|
24 |
+
"12": "I-email",
|
25 |
+
"13": "B-last_name",
|
26 |
+
"14": "I-last_name",
|
27 |
+
"15": "B-customer_id",
|
28 |
+
"16": "I-customer_id",
|
29 |
+
"17": "B-employee_id",
|
30 |
+
"18": "I-employee_id",
|
31 |
+
"19": "B-name",
|
32 |
+
"20": "I-name",
|
33 |
+
"21": "B-street_address",
|
34 |
+
"22": "I-street_address",
|
35 |
+
"23": "B-phone_number",
|
36 |
+
"24": "I-phone_number",
|
37 |
+
"25": "B-ipv4",
|
38 |
+
"26": "I-ipv4",
|
39 |
+
"27": "B-credit_card_number",
|
40 |
+
"28": "I-credit_card_number",
|
41 |
+
"29": "B-license_plate",
|
42 |
+
"30": "I-license_plate",
|
43 |
+
"31": "B-address",
|
44 |
+
"32": "I-address",
|
45 |
+
"33": "B-user_name",
|
46 |
+
"34": "I-user_name",
|
47 |
+
"35": "B-device_identifier",
|
48 |
+
"36": "I-device_identifier",
|
49 |
+
"37": "B-bank_routing_number",
|
50 |
+
"38": "I-bank_routing_number",
|
51 |
+
"39": "B-date_time",
|
52 |
+
"40": "I-date_time",
|
53 |
+
"41": "B-company_name",
|
54 |
+
"42": "I-company_name",
|
55 |
+
"43": "B-unique_identifier",
|
56 |
+
"44": "I-unique_identifier",
|
57 |
+
"45": "B-biometric_identifier",
|
58 |
+
"46": "I-biometric_identifier",
|
59 |
+
"47": "B-account_number",
|
60 |
+
"48": "I-account_number",
|
61 |
+
"49": "B-city",
|
62 |
+
"50": "I-city",
|
63 |
+
"51": "B-certificate_license_number",
|
64 |
+
"52": "I-certificate_license_number",
|
65 |
+
"53": "B-time",
|
66 |
+
"54": "I-time",
|
67 |
+
"55": "B-postcode",
|
68 |
+
"56": "I-postcode",
|
69 |
+
"57": "B-vehicle_identifier",
|
70 |
+
"58": "I-vehicle_identifier",
|
71 |
+
"59": "B-coordinate",
|
72 |
+
"60": "I-coordinate",
|
73 |
+
"61": "B-country",
|
74 |
+
"62": "I-country",
|
75 |
+
"63": "B-api_key",
|
76 |
+
"64": "I-api_key",
|
77 |
+
"65": "B-ipv6",
|
78 |
+
"66": "I-ipv6",
|
79 |
+
"67": "B-password",
|
80 |
+
"68": "I-password",
|
81 |
+
"69": "B-health_plan_beneficiary_number",
|
82 |
+
"70": "I-health_plan_beneficiary_number",
|
83 |
+
"71": "B-national_id",
|
84 |
+
"72": "I-national_id",
|
85 |
+
"73": "B-tax_id",
|
86 |
+
"74": "I-tax_id",
|
87 |
+
"75": "B-url",
|
88 |
+
"76": "I-url",
|
89 |
+
"77": "B-state",
|
90 |
+
"78": "I-state",
|
91 |
+
"79": "B-swift_bic",
|
92 |
+
"80": "I-swift_bic",
|
93 |
+
"81": "B-cvv",
|
94 |
+
"82": "I-cvv",
|
95 |
+
"83": "B-pin",
|
96 |
+
"84": "I-pin"
|
97 |
+
},
|
98 |
+
"initializer_range": 0.02,
|
99 |
+
"intermediate_size": 3072,
|
100 |
+
"label2id": {
|
101 |
+
"B-account_number": 47,
|
102 |
+
"B-address": 31,
|
103 |
+
"B-api_key": 63,
|
104 |
+
"B-bank_routing_number": 37,
|
105 |
+
"B-biometric_identifier": 45,
|
106 |
+
"B-certificate_license_number": 51,
|
107 |
+
"B-city": 49,
|
108 |
+
"B-company_name": 41,
|
109 |
+
"B-coordinate": 59,
|
110 |
+
"B-country": 61,
|
111 |
+
"B-credit_card_number": 27,
|
112 |
+
"B-customer_id": 15,
|
113 |
+
"B-cvv": 81,
|
114 |
+
"B-date": 7,
|
115 |
+
"B-date_of_birth": 3,
|
116 |
+
"B-date_time": 39,
|
117 |
+
"B-device_identifier": 35,
|
118 |
+
"B-email": 11,
|
119 |
+
"B-employee_id": 17,
|
120 |
+
"B-first_name": 9,
|
121 |
+
"B-health_plan_beneficiary_number": 69,
|
122 |
+
"B-ipv4": 25,
|
123 |
+
"B-ipv6": 65,
|
124 |
+
"B-last_name": 13,
|
125 |
+
"B-license_plate": 29,
|
126 |
+
"B-medical_record_number": 1,
|
127 |
+
"B-name": 19,
|
128 |
+
"B-national_id": 71,
|
129 |
+
"B-password": 67,
|
130 |
+
"B-phone_number": 23,
|
131 |
+
"B-pin": 83,
|
132 |
+
"B-postcode": 55,
|
133 |
+
"B-ssn": 5,
|
134 |
+
"B-state": 77,
|
135 |
+
"B-street_address": 21,
|
136 |
+
"B-swift_bic": 79,
|
137 |
+
"B-tax_id": 73,
|
138 |
+
"B-time": 53,
|
139 |
+
"B-unique_identifier": 43,
|
140 |
+
"B-url": 75,
|
141 |
+
"B-user_name": 33,
|
142 |
+
"B-vehicle_identifier": 57,
|
143 |
+
"I-account_number": 48,
|
144 |
+
"I-address": 32,
|
145 |
+
"I-api_key": 64,
|
146 |
+
"I-bank_routing_number": 38,
|
147 |
+
"I-biometric_identifier": 46,
|
148 |
+
"I-certificate_license_number": 52,
|
149 |
+
"I-city": 50,
|
150 |
+
"I-company_name": 42,
|
151 |
+
"I-coordinate": 60,
|
152 |
+
"I-country": 62,
|
153 |
+
"I-credit_card_number": 28,
|
154 |
+
"I-customer_id": 16,
|
155 |
+
"I-cvv": 82,
|
156 |
+
"I-date": 8,
|
157 |
+
"I-date_of_birth": 4,
|
158 |
+
"I-date_time": 40,
|
159 |
+
"I-device_identifier": 36,
|
160 |
+
"I-email": 12,
|
161 |
+
"I-employee_id": 18,
|
162 |
+
"I-first_name": 10,
|
163 |
+
"I-health_plan_beneficiary_number": 70,
|
164 |
+
"I-ipv4": 26,
|
165 |
+
"I-ipv6": 66,
|
166 |
+
"I-last_name": 14,
|
167 |
+
"I-license_plate": 30,
|
168 |
+
"I-medical_record_number": 2,
|
169 |
+
"I-name": 20,
|
170 |
+
"I-national_id": 72,
|
171 |
+
"I-password": 68,
|
172 |
+
"I-phone_number": 24,
|
173 |
+
"I-pin": 84,
|
174 |
+
"I-postcode": 56,
|
175 |
+
"I-ssn": 6,
|
176 |
+
"I-state": 78,
|
177 |
+
"I-street_address": 22,
|
178 |
+
"I-swift_bic": 80,
|
179 |
+
"I-tax_id": 74,
|
180 |
+
"I-time": 54,
|
181 |
+
"I-unique_identifier": 44,
|
182 |
+
"I-url": 76,
|
183 |
+
"I-user_name": 34,
|
184 |
+
"I-vehicle_identifier": 58,
|
185 |
+
"O": 0
|
186 |
+
},
|
187 |
+
"layer_norm_eps": 1e-12,
|
188 |
+
"max_position_embeddings": 512,
|
189 |
+
"model_type": "bert",
|
190 |
+
"num_attention_heads": 12,
|
191 |
+
"num_hidden_layers": 12,
|
192 |
+
"pad_token_id": 0,
|
193 |
+
"position_embedding_type": "absolute",
|
194 |
+
"torch_dtype": "float32",
|
195 |
+
"transformers_version": "4.51.3",
|
196 |
+
"type_vocab_size": 2,
|
197 |
+
"use_cache": true,
|
198 |
+
"vocab_size": 30522
|
199 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1027adbc85c6985c2eb5d00fb7728368ee1492234f6fe50a5df0d1cbf3089cbe
|
3 |
+
size 435851396
|
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
|
|