kwy00 commited on
Commit
a075b2d
·
1 Parent(s): 22265ad

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: donut-base-sroie
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # donut-base-sroie
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
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.26.0.dev0
52
+ - Pytorch 1.13.0+cu117
53
+ - Datasets 2.7.1
54
+ - Tokenizers 0.13.2
added_tokens.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Annotation>": 57576,
3
+ "</s_Dataset>": 57566,
4
+ "</s_Images>": 57536,
5
+ "</s_acquistion_location>": 57564,
6
+ "</s_application_field>": 57562,
7
+ "</s_background>": 57560,
8
+ "</s_bbox>": 57526,
9
+ "</s_category>": 57574,
10
+ "</s_data>": 57534,
11
+ "</s_data_captured>": 57558,
12
+ "</s_height>": 57556,
13
+ "</s_id>": 57532,
14
+ "</s_identifier>": 57554,
15
+ "</s_label_path>": 57572,
16
+ "</s_media_type>": 57552,
17
+ "</s_name>": 57570,
18
+ "</s_object_recognition>": 57580,
19
+ "</s_pen_color>": 57550,
20
+ "</s_pen_type>": 57548,
21
+ "</s_src_path>": 57568,
22
+ "</s_text_language>": 57578,
23
+ "</s_type>": 57546,
24
+ "</s_width>": 57544,
25
+ "</s_writer_age>": 57542,
26
+ "</s_writer_sex>": 57540,
27
+ "</s_written_content>": 57538,
28
+ "</s_x>": 57530,
29
+ "</s_y>": 57528,
30
+ "<s_Annotation>": 57575,
31
+ "<s_Dataset>": 57565,
32
+ "<s_Images>": 57535,
33
+ "<s_acquistion_location>": 57563,
34
+ "<s_application_field>": 57561,
35
+ "<s_background>": 57559,
36
+ "<s_bbox>": 57525,
37
+ "<s_category>": 57573,
38
+ "<s_data>": 57533,
39
+ "<s_data_captured>": 57557,
40
+ "<s_height>": 57555,
41
+ "<s_id>": 57531,
42
+ "<s_identifier>": 57553,
43
+ "<s_iitcdip>": 57523,
44
+ "<s_label_path>": 57571,
45
+ "<s_media_type>": 57551,
46
+ "<s_name>": 57569,
47
+ "<s_object_recognition>": 57579,
48
+ "<s_pen_color>": 57549,
49
+ "<s_pen_type>": 57547,
50
+ "<s_src_path>": 57567,
51
+ "<s_synthdog>": 57524,
52
+ "<s_text_language>": 57577,
53
+ "<s_type>": 57545,
54
+ "<s_width>": 57543,
55
+ "<s_writer_age>": 57541,
56
+ "<s_writer_sex>": 57539,
57
+ "<s_written_content>": 57537,
58
+ "<s_x>": 57529,
59
+ "<s_y>": 57527,
60
+ "<sep/>": 57522
61
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "DonutImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
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:d7d9beeba9e36a607f86f02965b819f36aa668bf407de990ed8946d50d946b71
3
  size 809408281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a09af3b179c5f17f30bea092fcc92d333d5df4c7622df9aa911b32865aee8a2
3
  size 809408281
runs/Dec19_03-24-37_DESKTOP-V5FILME/events.out.tfevents.1671387902.DESKTOP-V5FILME.45984.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:842ad22d0d27bf7b8ea517b87624e1b7f202148469eba200b7b5f9b0155f7e9a
3
- size 8338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be956f7b4dadffc9c1d9a8d69731b65498c643a14a744fec2b3052ae34cebf8
3
+ size 8686
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_bbox>",
4
+ "</s_bbox>",
5
+ "<s_y>",
6
+ "</s_y>",
7
+ "<s_x>",
8
+ "</s_x>",
9
+ "<s_id>",
10
+ "</s_id>",
11
+ "<s_data>",
12
+ "</s_data>",
13
+ "<s_Images>",
14
+ "</s_Images>",
15
+ "<s_written_content>",
16
+ "</s_written_content>",
17
+ "<s_writer_sex>",
18
+ "</s_writer_sex>",
19
+ "<s_writer_age>",
20
+ "</s_writer_age>",
21
+ "<s_width>",
22
+ "</s_width>",
23
+ "<s_type>",
24
+ "</s_type>",
25
+ "<s_pen_type>",
26
+ "</s_pen_type>",
27
+ "<s_pen_color>",
28
+ "</s_pen_color>",
29
+ "<s_media_type>",
30
+ "</s_media_type>",
31
+ "<s_identifier>",
32
+ "</s_identifier>",
33
+ "<s_height>",
34
+ "</s_height>",
35
+ "<s_data_captured>",
36
+ "</s_data_captured>",
37
+ "<s_background>",
38
+ "</s_background>",
39
+ "<s_application_field>",
40
+ "</s_application_field>",
41
+ "<s_acquistion_location>",
42
+ "</s_acquistion_location>",
43
+ "<s_Dataset>",
44
+ "</s_Dataset>",
45
+ "<s_src_path>",
46
+ "</s_src_path>",
47
+ "<s_name>",
48
+ "</s_name>",
49
+ "<s_label_path>",
50
+ "</s_label_path>",
51
+ "<s_category>",
52
+ "</s_category>",
53
+ "<s_Annotation>",
54
+ "</s_Annotation>",
55
+ "<s_text_language>",
56
+ "</s_text_language>",
57
+ "<s_object_recognition>",
58
+ "</s_object_recognition>",
59
+ "<s>",
60
+ "</s>"
61
+ ],
62
+ "bos_token": "<s>",
63
+ "cls_token": "<s>",
64
+ "eos_token": "</s>",
65
+ "mask_token": {
66
+ "content": "<mask>",
67
+ "lstrip": true,
68
+ "normalized": true,
69
+ "rstrip": false,
70
+ "single_word": false
71
+ },
72
+ "pad_token": "<pad>",
73
+ "sep_token": "</s>",
74
+ "unk_token": "<unk>"
75
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "naver-clova-ix/donut-base",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }