Commit ·
57a0a37
1
Parent(s): 1b97925
End of training
Browse files- README.md +1 -1
- added_tokens.json +0 -20
- pytorch_model.bin +1 -1
- runs/Mar23_03-49-15_ip-10-92-200-29/events.out.tfevents.1679543360.ip-10-92-200-29 +2 -2
- special_tokens_map.json +0 -20
- tokenizer.json +2 -196
README.md
CHANGED
|
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 200
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
added_tokens.json
CHANGED
|
@@ -1,25 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"</s_charge_date>": 57544,
|
| 3 |
-
"</s_charge_month>": 57542,
|
| 4 |
-
"</s_charge_period>": 57536,
|
| 5 |
-
"</s_invoice_date>": 57534,
|
| 6 |
-
"</s_invoice_number>": 57532,
|
| 7 |
-
"</s_issuer_address>": 57540,
|
| 8 |
-
"</s_issuer_company>": 57530,
|
| 9 |
-
"</s_recipient_address>": 57528,
|
| 10 |
-
"</s_site_id>": 57538,
|
| 11 |
-
"</s_total_amount>": 57526,
|
| 12 |
-
"<s_charge_date>": 57543,
|
| 13 |
-
"<s_charge_month>": 57541,
|
| 14 |
-
"<s_charge_period>": 57535,
|
| 15 |
"<s_iitcdip>": 57523,
|
| 16 |
-
"<s_invoice_date>": 57533,
|
| 17 |
-
"<s_invoice_number>": 57531,
|
| 18 |
-
"<s_issuer_address>": 57539,
|
| 19 |
-
"<s_issuer_company>": 57529,
|
| 20 |
-
"<s_recipient_address>": 57527,
|
| 21 |
-
"<s_site_id>": 57537,
|
| 22 |
"<s_synthdog>": 57524,
|
| 23 |
-
"<s_total_amount>": 57525,
|
| 24 |
"<sep/>": 57522
|
| 25 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"<s_synthdog>": 57524,
|
|
|
|
| 4 |
"<sep/>": 57522
|
| 5 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 809178905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62f654b3a997b0ae25bb9fff477f717126934b47cee2696a5ce29045bbd8ddd4
|
| 3 |
size 809178905
|
runs/Mar23_03-49-15_ip-10-92-200-29/events.out.tfevents.1679543360.ip-10-92-200-29
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da82d0f92f07d7fc6adf3025095d0bfd3bbb525a4911175ffba46fbd0ae76c21
|
| 3 |
+
size 3799061
|
special_tokens_map.json
CHANGED
|
@@ -1,25 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
"<s_total_amount>",
|
| 4 |
-
"</s_total_amount>",
|
| 5 |
-
"<s_recipient_address>",
|
| 6 |
-
"</s_recipient_address>",
|
| 7 |
-
"<s_issuer_company>",
|
| 8 |
-
"</s_issuer_company>",
|
| 9 |
-
"<s_invoice_number>",
|
| 10 |
-
"</s_invoice_number>",
|
| 11 |
-
"<s_invoice_date>",
|
| 12 |
-
"</s_invoice_date>",
|
| 13 |
-
"<s_charge_period>",
|
| 14 |
-
"</s_charge_period>",
|
| 15 |
-
"<s_site_id>",
|
| 16 |
-
"</s_site_id>",
|
| 17 |
-
"<s_issuer_address>",
|
| 18 |
-
"</s_issuer_address>",
|
| 19 |
-
"<s_charge_month>",
|
| 20 |
-
"</s_charge_month>",
|
| 21 |
-
"<s_charge_date>",
|
| 22 |
-
"</s_charge_date>",
|
| 23 |
"<s>",
|
| 24 |
"</s>"
|
| 25 |
],
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"<s>",
|
| 4 |
"</s>"
|
| 5 |
],
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 512
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 1,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
@@ -88,186 +74,6 @@
|
|
| 88 |
"rstrip": false,
|
| 89 |
"normalized": false,
|
| 90 |
"special": true
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"id": 57525,
|
| 94 |
-
"content": "<s_total_amount>",
|
| 95 |
-
"single_word": false,
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"normalized": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"id": 57526,
|
| 103 |
-
"content": "</s_total_amount>",
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"lstrip": false,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"normalized": false,
|
| 108 |
-
"special": true
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"id": 57527,
|
| 112 |
-
"content": "<s_recipient_address>",
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"lstrip": false,
|
| 115 |
-
"rstrip": false,
|
| 116 |
-
"normalized": false,
|
| 117 |
-
"special": true
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"id": 57528,
|
| 121 |
-
"content": "</s_recipient_address>",
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"lstrip": false,
|
| 124 |
-
"rstrip": false,
|
| 125 |
-
"normalized": false,
|
| 126 |
-
"special": true
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"id": 57529,
|
| 130 |
-
"content": "<s_issuer_company>",
|
| 131 |
-
"single_word": false,
|
| 132 |
-
"lstrip": false,
|
| 133 |
-
"rstrip": false,
|
| 134 |
-
"normalized": false,
|
| 135 |
-
"special": true
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"id": 57530,
|
| 139 |
-
"content": "</s_issuer_company>",
|
| 140 |
-
"single_word": false,
|
| 141 |
-
"lstrip": false,
|
| 142 |
-
"rstrip": false,
|
| 143 |
-
"normalized": false,
|
| 144 |
-
"special": true
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"id": 57531,
|
| 148 |
-
"content": "<s_invoice_number>",
|
| 149 |
-
"single_word": false,
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"rstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"special": true
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"id": 57532,
|
| 157 |
-
"content": "</s_invoice_number>",
|
| 158 |
-
"single_word": false,
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"normalized": false,
|
| 162 |
-
"special": true
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"id": 57533,
|
| 166 |
-
"content": "<s_invoice_date>",
|
| 167 |
-
"single_word": false,
|
| 168 |
-
"lstrip": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"normalized": false,
|
| 171 |
-
"special": true
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"id": 57534,
|
| 175 |
-
"content": "</s_invoice_date>",
|
| 176 |
-
"single_word": false,
|
| 177 |
-
"lstrip": false,
|
| 178 |
-
"rstrip": false,
|
| 179 |
-
"normalized": false,
|
| 180 |
-
"special": true
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"id": 57535,
|
| 184 |
-
"content": "<s_charge_period>",
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"lstrip": false,
|
| 187 |
-
"rstrip": false,
|
| 188 |
-
"normalized": false,
|
| 189 |
-
"special": true
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"id": 57536,
|
| 193 |
-
"content": "</s_charge_period>",
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"lstrip": false,
|
| 196 |
-
"rstrip": false,
|
| 197 |
-
"normalized": false,
|
| 198 |
-
"special": true
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"id": 57537,
|
| 202 |
-
"content": "<s_site_id>",
|
| 203 |
-
"single_word": false,
|
| 204 |
-
"lstrip": false,
|
| 205 |
-
"rstrip": false,
|
| 206 |
-
"normalized": false,
|
| 207 |
-
"special": true
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"id": 57538,
|
| 211 |
-
"content": "</s_site_id>",
|
| 212 |
-
"single_word": false,
|
| 213 |
-
"lstrip": false,
|
| 214 |
-
"rstrip": false,
|
| 215 |
-
"normalized": false,
|
| 216 |
-
"special": true
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"id": 57539,
|
| 220 |
-
"content": "<s_issuer_address>",
|
| 221 |
-
"single_word": false,
|
| 222 |
-
"lstrip": false,
|
| 223 |
-
"rstrip": false,
|
| 224 |
-
"normalized": false,
|
| 225 |
-
"special": true
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"id": 57540,
|
| 229 |
-
"content": "</s_issuer_address>",
|
| 230 |
-
"single_word": false,
|
| 231 |
-
"lstrip": false,
|
| 232 |
-
"rstrip": false,
|
| 233 |
-
"normalized": false,
|
| 234 |
-
"special": true
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"id": 57541,
|
| 238 |
-
"content": "<s_charge_month>",
|
| 239 |
-
"single_word": false,
|
| 240 |
-
"lstrip": false,
|
| 241 |
-
"rstrip": false,
|
| 242 |
-
"normalized": false,
|
| 243 |
-
"special": true
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"id": 57542,
|
| 247 |
-
"content": "</s_charge_month>",
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"lstrip": false,
|
| 250 |
-
"rstrip": false,
|
| 251 |
-
"normalized": false,
|
| 252 |
-
"special": true
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"id": 57543,
|
| 256 |
-
"content": "<s_charge_date>",
|
| 257 |
-
"single_word": false,
|
| 258 |
-
"lstrip": false,
|
| 259 |
-
"rstrip": false,
|
| 260 |
-
"normalized": false,
|
| 261 |
-
"special": true
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"id": 57544,
|
| 265 |
-
"content": "</s_charge_date>",
|
| 266 |
-
"single_word": false,
|
| 267 |
-
"lstrip": false,
|
| 268 |
-
"rstrip": false,
|
| 269 |
-
"normalized": false,
|
| 270 |
-
"special": true
|
| 271 |
}
|
| 272 |
],
|
| 273 |
"normalizer": {
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
| 76 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
}
|
| 78 |
],
|
| 79 |
"normalizer": {
|