Training in progress, epoch 1
Browse files- added_tokens.json +3 -0
- config.json +205 -0
- model.safetensors +3 -0
- runs/Jul05_09-53-38_T2P-CPU010/events.out.tfevents.1720148021.T2P-CPU010 +3 -0
- runs/Jul05_23-22-15_T2P-CPU010/events.out.tfevents.1720196539.T2P-CPU010.451368.0 +3 -0
- runs/Jul08_15-54-20_T2P-CPU010/events.out.tfevents.1720428864.T2P-CPU010.3297.0 +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 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": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "0",
|
| 12 |
+
"1": "B-arrivalTrainNo",
|
| 13 |
+
"2": "I-arrivalTrainNo",
|
| 14 |
+
"3": "B-bookingNumber",
|
| 15 |
+
"4": "I-bookingNumber",
|
| 16 |
+
"5": "B-cardNumber",
|
| 17 |
+
"6": "I-cardNumber",
|
| 18 |
+
"7": "B-cardType",
|
| 19 |
+
"8": "I-cardType",
|
| 20 |
+
"9": "B-checkIn",
|
| 21 |
+
"10": "I-checkIn",
|
| 22 |
+
"11": "B-checkOut",
|
| 23 |
+
"12": "I-checkOut",
|
| 24 |
+
"13": "B-companyAddress",
|
| 25 |
+
"14": "I-companyAddress",
|
| 26 |
+
"15": "B-companyCity",
|
| 27 |
+
"16": "I-companyCity",
|
| 28 |
+
"17": "B-companyCountry",
|
| 29 |
+
"18": "I-companyCountry",
|
| 30 |
+
"19": "B-companyName",
|
| 31 |
+
"20": "I-companyName",
|
| 32 |
+
"21": "B-companyVATNumber",
|
| 33 |
+
"22": "I-companyVATNumber",
|
| 34 |
+
"23": "B-companyZipcode",
|
| 35 |
+
"24": "I-companyZipcode",
|
| 36 |
+
"25": "B-crewType",
|
| 37 |
+
"26": "I-crewType",
|
| 38 |
+
"27": "B-currencyCode",
|
| 39 |
+
"28": "I-currencyCode",
|
| 40 |
+
"29": "B-documentType",
|
| 41 |
+
"30": "I-documentType",
|
| 42 |
+
"31": "B-externalReservationNumber",
|
| 43 |
+
"32": "I-externalReservationNumber",
|
| 44 |
+
"33": "B-grossAmount",
|
| 45 |
+
"34": "I-grossAmount",
|
| 46 |
+
"35": "B-hotelAddress",
|
| 47 |
+
"36": "I-hotelAddress",
|
| 48 |
+
"37": "B-hotelBankAccount",
|
| 49 |
+
"38": "I-hotelBankAccount",
|
| 50 |
+
"39": "B-hotelCity",
|
| 51 |
+
"40": "I-hotelCity",
|
| 52 |
+
"41": "B-hotelCountry",
|
| 53 |
+
"42": "I-hotelCountry",
|
| 54 |
+
"43": "B-hotelEmail",
|
| 55 |
+
"44": "I-hotelEmail",
|
| 56 |
+
"45": "B-hotelFaxNumber",
|
| 57 |
+
"46": "I-hotelFaxNumber",
|
| 58 |
+
"47": "B-hotelName",
|
| 59 |
+
"48": "I-hotelName",
|
| 60 |
+
"49": "B-hotelPhoneNumber",
|
| 61 |
+
"50": "I-hotelPhoneNumber",
|
| 62 |
+
"51": "B-hotelTaxCode",
|
| 63 |
+
"52": "I-hotelTaxCode",
|
| 64 |
+
"53": "B-hotelVATNumber",
|
| 65 |
+
"54": "I-hotelVATNumber",
|
| 66 |
+
"55": "B-hotelZipCode",
|
| 67 |
+
"56": "I-hotelZipCode",
|
| 68 |
+
"57": "B-invoiceDate",
|
| 69 |
+
"58": "I-invoiceDate",
|
| 70 |
+
"59": "B-invoiceNumber",
|
| 71 |
+
"60": "I-invoiceNumber",
|
| 72 |
+
"61": "B-netAmount",
|
| 73 |
+
"62": "I-netAmount",
|
| 74 |
+
"63": "B-pageNo",
|
| 75 |
+
"64": "I-pageNo",
|
| 76 |
+
"65": "B-reservationNumber",
|
| 77 |
+
"66": "I-reservationNumber",
|
| 78 |
+
"67": "B-roomNo",
|
| 79 |
+
"68": "I-roomNo",
|
| 80 |
+
"69": "B-taxAmount",
|
| 81 |
+
"70": "I-taxAmount",
|
| 82 |
+
"71": "B-trafficDate",
|
| 83 |
+
"72": "I-trafficDate",
|
| 84 |
+
"73": "B-travellerName",
|
| 85 |
+
"74": "I-travellerName",
|
| 86 |
+
"75": "B-Bank_Account/bankInfo",
|
| 87 |
+
"76": "I-Bank_Account/bankInfo",
|
| 88 |
+
"77": "B-Bank_Account/IBAN",
|
| 89 |
+
"78": "I-Bank_Account/IBAN",
|
| 90 |
+
"79": "B-Bank_Account/BIC",
|
| 91 |
+
"80": "I-Bank_Account/BIC",
|
| 92 |
+
"81": "B-Bank_Account/currencyCode",
|
| 93 |
+
"82": "I-Bank_Account/currencyCode"
|
| 94 |
+
},
|
| 95 |
+
"initializer_range": 0.02,
|
| 96 |
+
"intermediate_size": 3072,
|
| 97 |
+
"label2id": {
|
| 98 |
+
"0": 0,
|
| 99 |
+
"B-Bank_Account/BIC": 79,
|
| 100 |
+
"B-Bank_Account/IBAN": 77,
|
| 101 |
+
"B-Bank_Account/bankInfo": 75,
|
| 102 |
+
"B-Bank_Account/currencyCode": 81,
|
| 103 |
+
"B-arrivalTrainNo": 1,
|
| 104 |
+
"B-bookingNumber": 3,
|
| 105 |
+
"B-cardNumber": 5,
|
| 106 |
+
"B-cardType": 7,
|
| 107 |
+
"B-checkIn": 9,
|
| 108 |
+
"B-checkOut": 11,
|
| 109 |
+
"B-companyAddress": 13,
|
| 110 |
+
"B-companyCity": 15,
|
| 111 |
+
"B-companyCountry": 17,
|
| 112 |
+
"B-companyName": 19,
|
| 113 |
+
"B-companyVATNumber": 21,
|
| 114 |
+
"B-companyZipcode": 23,
|
| 115 |
+
"B-crewType": 25,
|
| 116 |
+
"B-currencyCode": 27,
|
| 117 |
+
"B-documentType": 29,
|
| 118 |
+
"B-externalReservationNumber": 31,
|
| 119 |
+
"B-grossAmount": 33,
|
| 120 |
+
"B-hotelAddress": 35,
|
| 121 |
+
"B-hotelBankAccount": 37,
|
| 122 |
+
"B-hotelCity": 39,
|
| 123 |
+
"B-hotelCountry": 41,
|
| 124 |
+
"B-hotelEmail": 43,
|
| 125 |
+
"B-hotelFaxNumber": 45,
|
| 126 |
+
"B-hotelName": 47,
|
| 127 |
+
"B-hotelPhoneNumber": 49,
|
| 128 |
+
"B-hotelTaxCode": 51,
|
| 129 |
+
"B-hotelVATNumber": 53,
|
| 130 |
+
"B-hotelZipCode": 55,
|
| 131 |
+
"B-invoiceDate": 57,
|
| 132 |
+
"B-invoiceNumber": 59,
|
| 133 |
+
"B-netAmount": 61,
|
| 134 |
+
"B-pageNo": 63,
|
| 135 |
+
"B-reservationNumber": 65,
|
| 136 |
+
"B-roomNo": 67,
|
| 137 |
+
"B-taxAmount": 69,
|
| 138 |
+
"B-trafficDate": 71,
|
| 139 |
+
"B-travellerName": 73,
|
| 140 |
+
"I-Bank_Account/BIC": 80,
|
| 141 |
+
"I-Bank_Account/IBAN": 78,
|
| 142 |
+
"I-Bank_Account/bankInfo": 76,
|
| 143 |
+
"I-Bank_Account/currencyCode": 82,
|
| 144 |
+
"I-arrivalTrainNo": 2,
|
| 145 |
+
"I-bookingNumber": 4,
|
| 146 |
+
"I-cardNumber": 6,
|
| 147 |
+
"I-cardType": 8,
|
| 148 |
+
"I-checkIn": 10,
|
| 149 |
+
"I-checkOut": 12,
|
| 150 |
+
"I-companyAddress": 14,
|
| 151 |
+
"I-companyCity": 16,
|
| 152 |
+
"I-companyCountry": 18,
|
| 153 |
+
"I-companyName": 20,
|
| 154 |
+
"I-companyVATNumber": 22,
|
| 155 |
+
"I-companyZipcode": 24,
|
| 156 |
+
"I-crewType": 26,
|
| 157 |
+
"I-currencyCode": 28,
|
| 158 |
+
"I-documentType": 30,
|
| 159 |
+
"I-externalReservationNumber": 32,
|
| 160 |
+
"I-grossAmount": 34,
|
| 161 |
+
"I-hotelAddress": 36,
|
| 162 |
+
"I-hotelBankAccount": 38,
|
| 163 |
+
"I-hotelCity": 40,
|
| 164 |
+
"I-hotelCountry": 42,
|
| 165 |
+
"I-hotelEmail": 44,
|
| 166 |
+
"I-hotelFaxNumber": 46,
|
| 167 |
+
"I-hotelName": 48,
|
| 168 |
+
"I-hotelPhoneNumber": 50,
|
| 169 |
+
"I-hotelTaxCode": 52,
|
| 170 |
+
"I-hotelVATNumber": 54,
|
| 171 |
+
"I-hotelZipCode": 56,
|
| 172 |
+
"I-invoiceDate": 58,
|
| 173 |
+
"I-invoiceNumber": 60,
|
| 174 |
+
"I-netAmount": 62,
|
| 175 |
+
"I-pageNo": 64,
|
| 176 |
+
"I-reservationNumber": 66,
|
| 177 |
+
"I-roomNo": 68,
|
| 178 |
+
"I-taxAmount": 70,
|
| 179 |
+
"I-trafficDate": 72,
|
| 180 |
+
"I-travellerName": 74
|
| 181 |
+
},
|
| 182 |
+
"layer_norm_eps": 1e-07,
|
| 183 |
+
"max_position_embeddings": 512,
|
| 184 |
+
"max_relative_positions": -1,
|
| 185 |
+
"model_type": "deberta-v2",
|
| 186 |
+
"norm_rel_ebd": "layer_norm",
|
| 187 |
+
"num_attention_heads": 12,
|
| 188 |
+
"num_hidden_layers": 12,
|
| 189 |
+
"pad_token_id": 0,
|
| 190 |
+
"pooler_dropout": 0,
|
| 191 |
+
"pooler_hidden_act": "gelu",
|
| 192 |
+
"pooler_hidden_size": 768,
|
| 193 |
+
"pos_att_type": [
|
| 194 |
+
"p2c",
|
| 195 |
+
"c2p"
|
| 196 |
+
],
|
| 197 |
+
"position_biased_input": false,
|
| 198 |
+
"position_buckets": 256,
|
| 199 |
+
"relative_attention": true,
|
| 200 |
+
"share_att_key": true,
|
| 201 |
+
"torch_dtype": "float32",
|
| 202 |
+
"transformers_version": "4.40.2",
|
| 203 |
+
"type_vocab_size": 0,
|
| 204 |
+
"vocab_size": 128100
|
| 205 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae22fd63af176caabf9ed4a9cf7c7adde6f511a30d66780ba9a93823ec1215f4
|
| 3 |
+
size 735605900
|
runs/Jul05_09-53-38_T2P-CPU010/events.out.tfevents.1720148021.T2P-CPU010
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69050139c75a28791a5face0168f4537184669133f38bcc8b1a20621a3e84dc2
|
| 3 |
+
size 306779
|
runs/Jul05_23-22-15_T2P-CPU010/events.out.tfevents.1720196539.T2P-CPU010.451368.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88347ded986fab9e4c8b2df59076f0e416df1c8fbc7074305a0eb722a52825b5
|
| 3 |
+
size 604431
|
runs/Jul08_15-54-20_T2P-CPU010/events.out.tfevents.1720428864.T2P-CPU010.3297.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e365c1c58d00de57717a8daf666d6be76f0d6c3365ba91f198f22fa4f690575
|
| 3 |
+
size 46107
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[CLS]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "[SEP]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 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 |
+
"128000": {
|
| 37 |
+
"content": "[MASK]",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "[CLS]",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "[CLS]",
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d087cd836473fe658ce2e14285fbd281a2ce93b891f8ea5d19e4de38cce63c1
|
| 3 |
+
size 5048
|