alexbeta80 commited on
Commit
aff6567
1 Parent(s): d7f4f1d

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: alexbeta80/donut-test
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # donut-test
17
 
18
- This model is a fine-tuned version of [alexbeta80/donut-test](https://huggingface.co/alexbeta80/donut-test) on the imagefolder dataset.
19
 
20
  ## Model description
21
 
@@ -34,17 +34,13 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 2e-05
38
- - train_batch_size: 2
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
-
45
- ### Training results
46
-
47
-
48
 
49
  ### Framework versions
50
 
 
1
  ---
2
  license: mit
3
+ base_model: naver-clova-ix/donut-base
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
15
 
16
  # donut-test
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
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 5e-06
38
+ - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 50
 
 
 
 
44
 
45
  ### Framework versions
46
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "alexbeta80/donut-test",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "naver-clova-ix/donut-base",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
generation_config.json CHANGED
@@ -1,10 +1,8 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
- "decoder_start_token_id": 0,
5
  "eos_token_id": 2,
6
  "forced_eos_token_id": 2,
7
- "max_length": 512,
8
  "pad_token_id": 1,
9
  "transformers_version": "4.34.0"
10
  }
 
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": "4.34.0"
8
  }
preprocessor_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "height": 960,
24
- "width": 720
25
- }
26
  }
 
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
+ "size": [
23
+ 720,
24
+ 960
25
+ ]
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c3b9a31f1e601e9c6e293768b33858819c1a6b38b2b7ddbc58a4f23d278a1c
3
  size 809285846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4e07ab41ceda7a98a8f9f0500a920bee562dac6db6a3607b007d0e1d6574e3
3
  size 809285846
special_tokens_map.json CHANGED
@@ -1,10 +1,5 @@
1
  {
2
  "additional_special_tokens": [
3
- "<s>",
4
- "<pad>",
5
- "</s>",
6
- "<unk>",
7
- "<mask>",
8
  "<s_iitcdip>",
9
  "<s_synthdog>",
10
  "<s_Total_Packages>",
@@ -21,12 +16,14 @@
21
  "</s_Consignee>",
22
  "<s_Second_Notify_Country>",
23
  "<s_Marks>",
 
24
  "<s_Total_Weight>",
25
  "</s_Notify>",
26
  "</s_Goods_Description>",
27
  "<s_Second_Notify>",
28
  "<s_Total_Volume>",
29
  "</s_Total_Weight>",
 
30
  "<s_Consignee>",
31
  "</s_Second_Notify>",
32
  "</s_Total_Volume>",
 
1
  {
2
  "additional_special_tokens": [
 
 
 
 
 
3
  "<s_iitcdip>",
4
  "<s_synthdog>",
5
  "<s_Total_Packages>",
 
16
  "</s_Consignee>",
17
  "<s_Second_Notify_Country>",
18
  "<s_Marks>",
19
+ "<s>",
20
  "<s_Total_Weight>",
21
  "</s_Notify>",
22
  "</s_Goods_Description>",
23
  "<s_Second_Notify>",
24
  "<s_Total_Volume>",
25
  "</s_Total_Weight>",
26
+ "</s>",
27
  "<s_Consignee>",
28
  "</s_Second_Notify>",
29
  "</s_Total_Volume>",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,9 +2,9 @@
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<s>",
5
- "lstrip": false,
6
  "normalized": false,
7
- "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
@@ -18,9 +18,9 @@
18
  },
19
  "2": {
20
  "content": "</s>",
21
- "lstrip": false,
22
  "normalized": false,
23
- "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
@@ -35,7 +35,7 @@
35
  "57521": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
@@ -274,11 +274,6 @@
274
  }
275
  },
276
  "additional_special_tokens": [
277
- "<s>",
278
- "<pad>",
279
- "</s>",
280
- "<unk>",
281
- "<mask>",
282
  "<s_iitcdip>",
283
  "<s_synthdog>",
284
  "<s_Total_Packages>",
@@ -295,12 +290,14 @@
295
  "</s_Consignee>",
296
  "<s_Second_Notify_Country>",
297
  "<s_Marks>",
 
298
  "<s_Total_Weight>",
299
  "</s_Notify>",
300
  "</s_Goods_Description>",
301
  "<s_Second_Notify>",
302
  "<s_Total_Volume>",
303
  "</s_Total_Weight>",
 
304
  "<s_Consignee>",
305
  "</s_Second_Notify>",
306
  "</s_Total_Volume>",
@@ -313,18 +310,11 @@
313
  "cls_token": "<s>",
314
  "eos_token": "</s>",
315
  "mask_token": "<mask>",
316
- "max_length": 512,
317
  "model_max_length": 1000000000000000019884624838656,
318
- "pad_to_multiple_of": null,
319
  "pad_token": "<pad>",
320
- "pad_token_type_id": 0,
321
- "padding_side": "right",
322
  "processor_class": "DonutProcessor",
323
  "sep_token": "</s>",
324
  "sp_model_kwargs": {},
325
- "stride": 0,
326
  "tokenizer_class": "XLMRobertaTokenizer",
327
- "truncation_side": "right",
328
- "truncation_strategy": "longest_first",
329
  "unk_token": "<unk>"
330
  }
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<s>",
5
+ "lstrip": true,
6
  "normalized": false,
7
+ "rstrip": true,
8
  "single_word": false,
9
  "special": true
10
  },
 
18
  },
19
  "2": {
20
  "content": "</s>",
21
+ "lstrip": true,
22
  "normalized": false,
23
+ "rstrip": true,
24
  "single_word": false,
25
  "special": true
26
  },
 
35
  "57521": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
+ "normalized": true,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
274
  }
275
  },
276
  "additional_special_tokens": [
 
 
 
 
 
277
  "<s_iitcdip>",
278
  "<s_synthdog>",
279
  "<s_Total_Packages>",
 
290
  "</s_Consignee>",
291
  "<s_Second_Notify_Country>",
292
  "<s_Marks>",
293
+ "<s>",
294
  "<s_Total_Weight>",
295
  "</s_Notify>",
296
  "</s_Goods_Description>",
297
  "<s_Second_Notify>",
298
  "<s_Total_Volume>",
299
  "</s_Total_Weight>",
300
+ "</s>",
301
  "<s_Consignee>",
302
  "</s_Second_Notify>",
303
  "</s_Total_Volume>",
 
310
  "cls_token": "<s>",
311
  "eos_token": "</s>",
312
  "mask_token": "<mask>",
 
313
  "model_max_length": 1000000000000000019884624838656,
 
314
  "pad_token": "<pad>",
 
 
315
  "processor_class": "DonutProcessor",
316
  "sep_token": "</s>",
317
  "sp_model_kwargs": {},
 
318
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
319
  "unk_token": "<unk>"
320
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9434c72ee9bed05405abc2c8f4f2d57aa138e300ccc2c01b9509f0f5630c4bca
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309e66b6aaf8a988285f29eaaabeaa7fb4f01ecf655dfe445354b2167aa6ce56
3
  size 4600