End of training
Browse files- README.md +14 -8
- added_tokens.json +12 -20
- generation_config.json +1 -2
- runs/Jul07_18-12-00_b0eb49c1b48f/events.out.tfevents.1688754594.b0eb49c1b48f.1228.1 +2 -2
- special_tokens_map.json +4 -12
- tokenizer.json +12 -84
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
|
@@ -16,12 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 44.4471
|
| 21 |
-
- eval_samples_per_second: 0.652
|
| 22 |
-
- eval_steps_per_second: 0.09
|
| 23 |
-
- epoch: 4.21
|
| 24 |
-
- step: 1100
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -40,13 +36,23 @@ More information needed
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
-
- learning_rate:
|
| 44 |
- train_batch_size: 1
|
| 45 |
- eval_batch_size: 8
|
| 46 |
- seed: 42
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
### Framework versions
|
| 52 |
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: naver-clova-ix/donut-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3411
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
- train_batch_size: 1
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.5504 | 0.69 | 50 | 0.3411 |
|
| 52 |
+
| 0.6696 | 1.39 | 100 | 0.3411 |
|
| 53 |
+
| 0.6016 | 2.08 | 150 | 0.3411 |
|
| 54 |
+
| 0.5543 | 2.78 | 200 | 0.3411 |
|
| 55 |
+
|
| 56 |
|
| 57 |
### Framework versions
|
| 58 |
|
added_tokens.json
CHANGED
|
@@ -1,29 +1,21 @@
|
|
| 1 |
{
|
| 2 |
-
"</
|
| 3 |
-
"</
|
| 4 |
-
"</
|
| 5 |
-
"</
|
| 6 |
-
"</
|
| 7 |
-
"</
|
| 8 |
-
"</s_Description_2>": 57538,
|
| 9 |
-
"</s_Description_2_price>": 57536,
|
| 10 |
-
"</s_Description_other>": 57552,
|
| 11 |
-
"</s_Description_other_price>": 57550,
|
| 12 |
"</s_Invoice Date>": 57534,
|
| 13 |
"</s_Invoice Number>": 57532,
|
| 14 |
"</s_Payment_details>": 57530,
|
| 15 |
"</s_Time of Buying>": 57528,
|
| 16 |
"</s_Total_price>": 57526,
|
| 17 |
-
"<
|
| 18 |
-
"<
|
| 19 |
-
"<
|
| 20 |
-
"<
|
| 21 |
-
"<
|
| 22 |
-
"<
|
| 23 |
-
"<s_Description_2>": 57537,
|
| 24 |
-
"<s_Description_2_price>": 57535,
|
| 25 |
-
"<s_Description_other>": 57551,
|
| 26 |
-
"<s_Description_other_price>": 57549,
|
| 27 |
"<s_Invoice Date>": 57533,
|
| 28 |
"<s_Invoice Number>": 57531,
|
| 29 |
"<s_Payment_details>": 57529,
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s_Company Address>": 57542,
|
| 3 |
+
"</s_Company Name>": 57540,
|
| 4 |
+
"</s_Description_1>": 57538,
|
| 5 |
+
"</s_Description_1_price>": 57536,
|
| 6 |
+
"</s_Description_2>": 57546,
|
| 7 |
+
"</s_Description_2_price>": 57544,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"</s_Invoice Date>": 57534,
|
| 9 |
"</s_Invoice Number>": 57532,
|
| 10 |
"</s_Payment_details>": 57530,
|
| 11 |
"</s_Time of Buying>": 57528,
|
| 12 |
"</s_Total_price>": 57526,
|
| 13 |
+
"<s_Company Address>": 57541,
|
| 14 |
+
"<s_Company Name>": 57539,
|
| 15 |
+
"<s_Description_1>": 57537,
|
| 16 |
+
"<s_Description_1_price>": 57535,
|
| 17 |
+
"<s_Description_2>": 57545,
|
| 18 |
+
"<s_Description_2_price>": 57543,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"<s_Invoice Date>": 57533,
|
| 20 |
"<s_Invoice Number>": 57531,
|
| 21 |
"<s_Payment_details>": 57529,
|
generation_config.json
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 0,
|
| 3 |
-
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
-
"max_length": 512,
|
| 7 |
"pad_token_id": 1,
|
| 8 |
"transformers_version": "4.31.0.dev0"
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
|
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
|
|
|
| 6 |
"pad_token_id": 1,
|
| 7 |
"transformers_version": "4.31.0.dev0"
|
| 8 |
}
|
runs/Jul07_18-12-00_b0eb49c1b48f/events.out.tfevents.1688754594.b0eb49c1b48f.1228.1
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:a7dc9ff2bcec1c88816b978a56f729e01ca08aedc9f3f69bc43c4746dda5a5f2
|
| 3 |
+
size 10679
|
special_tokens_map.json
CHANGED
|
@@ -10,10 +10,6 @@
|
|
| 10 |
"</s_Invoice Number>",
|
| 11 |
"<s_Invoice Date>",
|
| 12 |
"</s_Invoice Date>",
|
| 13 |
-
"<s_Description_2_price>",
|
| 14 |
-
"</s_Description_2_price>",
|
| 15 |
-
"<s_Description_2>",
|
| 16 |
-
"</s_Description_2>",
|
| 17 |
"<s_Description_1_price>",
|
| 18 |
"</s_Description_1_price>",
|
| 19 |
"<s_Description_1>",
|
|
@@ -22,14 +18,10 @@
|
|
| 22 |
"</s_Company Name>",
|
| 23 |
"<s_Company Address>",
|
| 24 |
"</s_Company Address>",
|
| 25 |
-
"<
|
| 26 |
-
"</
|
| 27 |
-
"<
|
| 28 |
-
"</
|
| 29 |
-
"<s_Description_other>",
|
| 30 |
-
"</s_Description_other>",
|
| 31 |
-
"<s_Buyer Address>",
|
| 32 |
-
"</s_Buyer Address>",
|
| 33 |
"<s>",
|
| 34 |
"</s>"
|
| 35 |
],
|
|
|
|
| 10 |
"</s_Invoice Number>",
|
| 11 |
"<s_Invoice Date>",
|
| 12 |
"</s_Invoice Date>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"<s_Description_1_price>",
|
| 14 |
"</s_Description_1_price>",
|
| 15 |
"<s_Description_1>",
|
|
|
|
| 18 |
"</s_Company Name>",
|
| 19 |
"<s_Company Address>",
|
| 20 |
"</s_Company Address>",
|
| 21 |
+
"<s_Description_2_price>",
|
| 22 |
+
"</s_Description_2_price>",
|
| 23 |
+
"<s_Description_2>",
|
| 24 |
+
"</s_Description_2>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"<s>",
|
| 26 |
"</s>"
|
| 27 |
],
|
tokenizer.json
CHANGED
|
@@ -181,7 +181,7 @@
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 57535,
|
| 184 |
-
"content": "<
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
| 187 |
"rstrip": false,
|
|
@@ -190,7 +190,7 @@
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 57536,
|
| 193 |
-
"content": "</
|
| 194 |
"single_word": false,
|
| 195 |
"lstrip": false,
|
| 196 |
"rstrip": false,
|
|
@@ -199,7 +199,7 @@
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 57537,
|
| 202 |
-
"content": "<
|
| 203 |
"single_word": false,
|
| 204 |
"lstrip": false,
|
| 205 |
"rstrip": false,
|
|
@@ -208,7 +208,7 @@
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 57538,
|
| 211 |
-
"content": "</
|
| 212 |
"single_word": false,
|
| 213 |
"lstrip": false,
|
| 214 |
"rstrip": false,
|
|
@@ -217,7 +217,7 @@
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 57539,
|
| 220 |
-
"content": "<
|
| 221 |
"single_word": false,
|
| 222 |
"lstrip": false,
|
| 223 |
"rstrip": false,
|
|
@@ -226,7 +226,7 @@
|
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"id": 57540,
|
| 229 |
-
"content": "</
|
| 230 |
"single_word": false,
|
| 231 |
"lstrip": false,
|
| 232 |
"rstrip": false,
|
|
@@ -235,7 +235,7 @@
|
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"id": 57541,
|
| 238 |
-
"content": "<
|
| 239 |
"single_word": false,
|
| 240 |
"lstrip": false,
|
| 241 |
"rstrip": false,
|
|
@@ -244,7 +244,7 @@
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"id": 57542,
|
| 247 |
-
"content": "</
|
| 248 |
"single_word": false,
|
| 249 |
"lstrip": false,
|
| 250 |
"rstrip": false,
|
|
@@ -253,7 +253,7 @@
|
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"id": 57543,
|
| 256 |
-
"content": "<
|
| 257 |
"single_word": false,
|
| 258 |
"lstrip": false,
|
| 259 |
"rstrip": false,
|
|
@@ -262,7 +262,7 @@
|
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"id": 57544,
|
| 265 |
-
"content": "</
|
| 266 |
"single_word": false,
|
| 267 |
"lstrip": false,
|
| 268 |
"rstrip": false,
|
|
@@ -271,7 +271,7 @@
|
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"id": 57545,
|
| 274 |
-
"content": "<
|
| 275 |
"single_word": false,
|
| 276 |
"lstrip": false,
|
| 277 |
"rstrip": false,
|
|
@@ -280,79 +280,7 @@
|
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"id": 57546,
|
| 283 |
-
"content": "</
|
| 284 |
-
"single_word": false,
|
| 285 |
-
"lstrip": false,
|
| 286 |
-
"rstrip": false,
|
| 287 |
-
"normalized": false,
|
| 288 |
-
"special": true
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"id": 57547,
|
| 292 |
-
"content": "<s_Buyer Name>",
|
| 293 |
-
"single_word": false,
|
| 294 |
-
"lstrip": false,
|
| 295 |
-
"rstrip": false,
|
| 296 |
-
"normalized": false,
|
| 297 |
-
"special": true
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"id": 57548,
|
| 301 |
-
"content": "</s_Buyer Name>",
|
| 302 |
-
"single_word": false,
|
| 303 |
-
"lstrip": false,
|
| 304 |
-
"rstrip": false,
|
| 305 |
-
"normalized": false,
|
| 306 |
-
"special": true
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"id": 57549,
|
| 310 |
-
"content": "<s_Description_other_price>",
|
| 311 |
-
"single_word": false,
|
| 312 |
-
"lstrip": false,
|
| 313 |
-
"rstrip": false,
|
| 314 |
-
"normalized": false,
|
| 315 |
-
"special": true
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"id": 57550,
|
| 319 |
-
"content": "</s_Description_other_price>",
|
| 320 |
-
"single_word": false,
|
| 321 |
-
"lstrip": false,
|
| 322 |
-
"rstrip": false,
|
| 323 |
-
"normalized": false,
|
| 324 |
-
"special": true
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"id": 57551,
|
| 328 |
-
"content": "<s_Description_other>",
|
| 329 |
-
"single_word": false,
|
| 330 |
-
"lstrip": false,
|
| 331 |
-
"rstrip": false,
|
| 332 |
-
"normalized": false,
|
| 333 |
-
"special": true
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"id": 57552,
|
| 337 |
-
"content": "</s_Description_other>",
|
| 338 |
-
"single_word": false,
|
| 339 |
-
"lstrip": false,
|
| 340 |
-
"rstrip": false,
|
| 341 |
-
"normalized": false,
|
| 342 |
-
"special": true
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"id": 57553,
|
| 346 |
-
"content": "<s_Buyer Address>",
|
| 347 |
-
"single_word": false,
|
| 348 |
-
"lstrip": false,
|
| 349 |
-
"rstrip": false,
|
| 350 |
-
"normalized": false,
|
| 351 |
-
"special": true
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"id": 57554,
|
| 355 |
-
"content": "</s_Buyer Address>",
|
| 356 |
"single_word": false,
|
| 357 |
"lstrip": false,
|
| 358 |
"rstrip": false,
|
|
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 57535,
|
| 184 |
+
"content": "<s_Description_1_price>",
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
| 187 |
"rstrip": false,
|
|
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 57536,
|
| 193 |
+
"content": "</s_Description_1_price>",
|
| 194 |
"single_word": false,
|
| 195 |
"lstrip": false,
|
| 196 |
"rstrip": false,
|
|
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 57537,
|
| 202 |
+
"content": "<s_Description_1>",
|
| 203 |
"single_word": false,
|
| 204 |
"lstrip": false,
|
| 205 |
"rstrip": false,
|
|
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 57538,
|
| 211 |
+
"content": "</s_Description_1>",
|
| 212 |
"single_word": false,
|
| 213 |
"lstrip": false,
|
| 214 |
"rstrip": false,
|
|
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 57539,
|
| 220 |
+
"content": "<s_Company Name>",
|
| 221 |
"single_word": false,
|
| 222 |
"lstrip": false,
|
| 223 |
"rstrip": false,
|
|
|
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"id": 57540,
|
| 229 |
+
"content": "</s_Company Name>",
|
| 230 |
"single_word": false,
|
| 231 |
"lstrip": false,
|
| 232 |
"rstrip": false,
|
|
|
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"id": 57541,
|
| 238 |
+
"content": "<s_Company Address>",
|
| 239 |
"single_word": false,
|
| 240 |
"lstrip": false,
|
| 241 |
"rstrip": false,
|
|
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"id": 57542,
|
| 247 |
+
"content": "</s_Company Address>",
|
| 248 |
"single_word": false,
|
| 249 |
"lstrip": false,
|
| 250 |
"rstrip": false,
|
|
|
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"id": 57543,
|
| 256 |
+
"content": "<s_Description_2_price>",
|
| 257 |
"single_word": false,
|
| 258 |
"lstrip": false,
|
| 259 |
"rstrip": false,
|
|
|
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"id": 57544,
|
| 265 |
+
"content": "</s_Description_2_price>",
|
| 266 |
"single_word": false,
|
| 267 |
"lstrip": false,
|
| 268 |
"rstrip": false,
|
|
|
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"id": 57545,
|
| 274 |
+
"content": "<s_Description_2>",
|
| 275 |
"single_word": false,
|
| 276 |
"lstrip": false,
|
| 277 |
"rstrip": false,
|
|
|
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"id": 57546,
|
| 283 |
+
"content": "</s_Description_2>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 284 |
"single_word": false,
|
| 285 |
"lstrip": false,
|
| 286 |
"rstrip": false,
|