Training in progress epoch 0
Browse files- .gitignore +2 -0
- config.json +200 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.json +0 -0
.gitignore
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
step_*
|
| 2 |
+
epoch_*
|
config.json
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "B-medical_record_number",
|
| 15 |
+
"2": "I-medical_record_number",
|
| 16 |
+
"3": "B-date_of_birth",
|
| 17 |
+
"4": "I-date_of_birth",
|
| 18 |
+
"5": "B-ssn",
|
| 19 |
+
"6": "I-ssn",
|
| 20 |
+
"7": "B-date",
|
| 21 |
+
"8": "I-date",
|
| 22 |
+
"9": "B-first_name",
|
| 23 |
+
"10": "I-first_name",
|
| 24 |
+
"11": "B-email",
|
| 25 |
+
"12": "I-email",
|
| 26 |
+
"13": "B-last_name",
|
| 27 |
+
"14": "I-last_name",
|
| 28 |
+
"15": "B-customer_id",
|
| 29 |
+
"16": "I-customer_id",
|
| 30 |
+
"17": "B-employee_id",
|
| 31 |
+
"18": "I-employee_id",
|
| 32 |
+
"19": "B-name",
|
| 33 |
+
"20": "I-name",
|
| 34 |
+
"21": "B-street_address",
|
| 35 |
+
"22": "I-street_address",
|
| 36 |
+
"23": "B-phone_number",
|
| 37 |
+
"24": "I-phone_number",
|
| 38 |
+
"25": "B-ipv4",
|
| 39 |
+
"26": "I-ipv4",
|
| 40 |
+
"27": "B-credit_card_number",
|
| 41 |
+
"28": "I-credit_card_number",
|
| 42 |
+
"29": "B-license_plate",
|
| 43 |
+
"30": "I-license_plate",
|
| 44 |
+
"31": "B-address",
|
| 45 |
+
"32": "I-address",
|
| 46 |
+
"33": "B-user_name",
|
| 47 |
+
"34": "I-user_name",
|
| 48 |
+
"35": "B-device_identifier",
|
| 49 |
+
"36": "I-device_identifier",
|
| 50 |
+
"37": "B-bank_routing_number",
|
| 51 |
+
"38": "I-bank_routing_number",
|
| 52 |
+
"39": "B-date_time",
|
| 53 |
+
"40": "I-date_time",
|
| 54 |
+
"41": "B-company_name",
|
| 55 |
+
"42": "I-company_name",
|
| 56 |
+
"43": "B-unique_identifier",
|
| 57 |
+
"44": "I-unique_identifier",
|
| 58 |
+
"45": "B-biometric_identifier",
|
| 59 |
+
"46": "I-biometric_identifier",
|
| 60 |
+
"47": "B-account_number",
|
| 61 |
+
"48": "I-account_number",
|
| 62 |
+
"49": "B-city",
|
| 63 |
+
"50": "I-city",
|
| 64 |
+
"51": "B-certificate_license_number",
|
| 65 |
+
"52": "I-certificate_license_number",
|
| 66 |
+
"53": "B-time",
|
| 67 |
+
"54": "I-time",
|
| 68 |
+
"55": "B-postcode",
|
| 69 |
+
"56": "I-postcode",
|
| 70 |
+
"57": "B-vehicle_identifier",
|
| 71 |
+
"58": "I-vehicle_identifier",
|
| 72 |
+
"59": "B-coordinate",
|
| 73 |
+
"60": "I-coordinate",
|
| 74 |
+
"61": "B-country",
|
| 75 |
+
"62": "I-country",
|
| 76 |
+
"63": "B-api_key",
|
| 77 |
+
"64": "I-api_key",
|
| 78 |
+
"65": "B-ipv6",
|
| 79 |
+
"66": "I-ipv6",
|
| 80 |
+
"67": "B-password",
|
| 81 |
+
"68": "I-password",
|
| 82 |
+
"69": "B-health_plan_beneficiary_number",
|
| 83 |
+
"70": "I-health_plan_beneficiary_number",
|
| 84 |
+
"71": "B-national_id",
|
| 85 |
+
"72": "I-national_id",
|
| 86 |
+
"73": "B-tax_id",
|
| 87 |
+
"74": "I-tax_id",
|
| 88 |
+
"75": "B-url",
|
| 89 |
+
"76": "I-url",
|
| 90 |
+
"77": "B-state",
|
| 91 |
+
"78": "I-state",
|
| 92 |
+
"79": "B-swift_bic",
|
| 93 |
+
"80": "I-swift_bic",
|
| 94 |
+
"81": "B-cvv",
|
| 95 |
+
"82": "I-cvv",
|
| 96 |
+
"83": "B-pin",
|
| 97 |
+
"84": "I-pin"
|
| 98 |
+
},
|
| 99 |
+
"initializer_range": 0.02,
|
| 100 |
+
"intermediate_size": 3072,
|
| 101 |
+
"label2id": {
|
| 102 |
+
"B-account_number": 47,
|
| 103 |
+
"B-address": 31,
|
| 104 |
+
"B-api_key": 63,
|
| 105 |
+
"B-bank_routing_number": 37,
|
| 106 |
+
"B-biometric_identifier": 45,
|
| 107 |
+
"B-certificate_license_number": 51,
|
| 108 |
+
"B-city": 49,
|
| 109 |
+
"B-company_name": 41,
|
| 110 |
+
"B-coordinate": 59,
|
| 111 |
+
"B-country": 61,
|
| 112 |
+
"B-credit_card_number": 27,
|
| 113 |
+
"B-customer_id": 15,
|
| 114 |
+
"B-cvv": 81,
|
| 115 |
+
"B-date": 7,
|
| 116 |
+
"B-date_of_birth": 3,
|
| 117 |
+
"B-date_time": 39,
|
| 118 |
+
"B-device_identifier": 35,
|
| 119 |
+
"B-email": 11,
|
| 120 |
+
"B-employee_id": 17,
|
| 121 |
+
"B-first_name": 9,
|
| 122 |
+
"B-health_plan_beneficiary_number": 69,
|
| 123 |
+
"B-ipv4": 25,
|
| 124 |
+
"B-ipv6": 65,
|
| 125 |
+
"B-last_name": 13,
|
| 126 |
+
"B-license_plate": 29,
|
| 127 |
+
"B-medical_record_number": 1,
|
| 128 |
+
"B-name": 19,
|
| 129 |
+
"B-national_id": 71,
|
| 130 |
+
"B-password": 67,
|
| 131 |
+
"B-phone_number": 23,
|
| 132 |
+
"B-pin": 83,
|
| 133 |
+
"B-postcode": 55,
|
| 134 |
+
"B-ssn": 5,
|
| 135 |
+
"B-state": 77,
|
| 136 |
+
"B-street_address": 21,
|
| 137 |
+
"B-swift_bic": 79,
|
| 138 |
+
"B-tax_id": 73,
|
| 139 |
+
"B-time": 53,
|
| 140 |
+
"B-unique_identifier": 43,
|
| 141 |
+
"B-url": 75,
|
| 142 |
+
"B-user_name": 33,
|
| 143 |
+
"B-vehicle_identifier": 57,
|
| 144 |
+
"I-account_number": 48,
|
| 145 |
+
"I-address": 32,
|
| 146 |
+
"I-api_key": 64,
|
| 147 |
+
"I-bank_routing_number": 38,
|
| 148 |
+
"I-biometric_identifier": 46,
|
| 149 |
+
"I-certificate_license_number": 52,
|
| 150 |
+
"I-city": 50,
|
| 151 |
+
"I-company_name": 42,
|
| 152 |
+
"I-coordinate": 60,
|
| 153 |
+
"I-country": 62,
|
| 154 |
+
"I-credit_card_number": 28,
|
| 155 |
+
"I-customer_id": 16,
|
| 156 |
+
"I-cvv": 82,
|
| 157 |
+
"I-date": 8,
|
| 158 |
+
"I-date_of_birth": 4,
|
| 159 |
+
"I-date_time": 40,
|
| 160 |
+
"I-device_identifier": 36,
|
| 161 |
+
"I-email": 12,
|
| 162 |
+
"I-employee_id": 18,
|
| 163 |
+
"I-first_name": 10,
|
| 164 |
+
"I-health_plan_beneficiary_number": 70,
|
| 165 |
+
"I-ipv4": 26,
|
| 166 |
+
"I-ipv6": 66,
|
| 167 |
+
"I-last_name": 14,
|
| 168 |
+
"I-license_plate": 30,
|
| 169 |
+
"I-medical_record_number": 2,
|
| 170 |
+
"I-name": 20,
|
| 171 |
+
"I-national_id": 72,
|
| 172 |
+
"I-password": 68,
|
| 173 |
+
"I-phone_number": 24,
|
| 174 |
+
"I-pin": 84,
|
| 175 |
+
"I-postcode": 56,
|
| 176 |
+
"I-ssn": 6,
|
| 177 |
+
"I-state": 78,
|
| 178 |
+
"I-street_address": 22,
|
| 179 |
+
"I-swift_bic": 80,
|
| 180 |
+
"I-tax_id": 74,
|
| 181 |
+
"I-time": 54,
|
| 182 |
+
"I-unique_identifier": 44,
|
| 183 |
+
"I-url": 76,
|
| 184 |
+
"I-user_name": 34,
|
| 185 |
+
"I-vehicle_identifier": 58,
|
| 186 |
+
"O": 0
|
| 187 |
+
},
|
| 188 |
+
"layer_norm_eps": 1e-05,
|
| 189 |
+
"max_position_embeddings": 514,
|
| 190 |
+
"model_type": "roberta",
|
| 191 |
+
"num_attention_heads": 12,
|
| 192 |
+
"num_hidden_layers": 12,
|
| 193 |
+
"pad_token_id": 1,
|
| 194 |
+
"position_embedding_type": "absolute",
|
| 195 |
+
"torch_dtype": "float32",
|
| 196 |
+
"transformers_version": "4.51.3",
|
| 197 |
+
"type_vocab_size": 1,
|
| 198 |
+
"use_cache": true,
|
| 199 |
+
"vocab_size": 50265
|
| 200 |
+
}
|
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:f8cd71967a44a90a9ea38fa7b14a04e781e7bd4b4971427db4fd219f1248a501
|
| 3 |
+
size 496505556
|
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
|
|
|