ShekDass commited on
Commit
e9e9a2d
·
1 Parent(s): 7ff14b9

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: donut-base-smartenroll
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-smartenroll
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
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.30.2
51
+ - Pytorch 2.0.1+cu118
52
+ - Datasets 2.13.1
53
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Address>": 57592,
3
+ "</s_Age>": 57550,
4
+ "</s_City>": 57590,
5
+ "</s_County>": 57588,
6
+ "</s_Date of Birth (Month/Day/Year)>": 57548,
7
+ "</s_Dependent Status if Age 26 or Older>": 57546,
8
+ "</s_Dependent1>": 57556,
9
+ "</s_Dependent2>": 57544,
10
+ "</s_Effective Date>": 57586,
11
+ "</s_Employer/Group Name>": 57584,
12
+ "</s_Enrollment Status>": 57582,
13
+ "</s_First Name>": 57542,
14
+ "</s_Full-Time Hire (or Rehire) Date (Month/Day/Year)>": 57580,
15
+ "</s_Gender>": 57540,
16
+ "</s_Group Number>": 57578,
17
+ "</s_Home/Cell Phone>": 57576,
18
+ "</s_Hours Worked Per Week>": 57574,
19
+ "</s_Last Name>": 57538,
20
+ "</s_MI>": 57536,
21
+ "</s_Marital Status (Please check one)>": 57572,
22
+ "</s_Payroll Location>": 57570,
23
+ "</s_Product Selection(s)>": 57534,
24
+ "</s_Relationship to You?>": 57532,
25
+ "</s_Section1>": 57558,
26
+ "</s_Section2>": 57552,
27
+ "</s_Section3>": 57528,
28
+ "</s_Social Security Number>": 57530,
29
+ "</s_State>": 57568,
30
+ "</s_Zip>": 57566,
31
+ "</s_formheader>": 57564,
32
+ "</s_formsectionI>": 57562,
33
+ "</s_formsectionII>": 57554,
34
+ "</s_image_id>": 57526,
35
+ "</s_insurancecompany>": 57560,
36
+ "<s_Address>": 57591,
37
+ "<s_Age>": 57549,
38
+ "<s_City>": 57589,
39
+ "<s_County>": 57587,
40
+ "<s_Date of Birth (Month/Day/Year)>": 57547,
41
+ "<s_Dependent Status if Age 26 or Older>": 57545,
42
+ "<s_Dependent1>": 57555,
43
+ "<s_Dependent2>": 57543,
44
+ "<s_Effective Date>": 57585,
45
+ "<s_Employer/Group Name>": 57583,
46
+ "<s_Enrollment Status>": 57581,
47
+ "<s_First Name>": 57541,
48
+ "<s_Full-Time Hire (or Rehire) Date (Month/Day/Year)>": 57579,
49
+ "<s_Gender>": 57539,
50
+ "<s_Group Number>": 57577,
51
+ "<s_Home/Cell Phone>": 57575,
52
+ "<s_Hours Worked Per Week>": 57573,
53
+ "<s_Last Name>": 57537,
54
+ "<s_MI>": 57535,
55
+ "<s_Marital Status (Please check one)>": 57571,
56
+ "<s_Payroll Location>": 57569,
57
+ "<s_Product Selection(s)>": 57533,
58
+ "<s_Relationship to You?>": 57531,
59
+ "<s_Section1>": 57557,
60
+ "<s_Section2>": 57551,
61
+ "<s_Section3>": 57527,
62
+ "<s_Social Security Number>": 57529,
63
+ "<s_State>": 57567,
64
+ "<s_Zip>": 57565,
65
+ "<s_formheader>": 57563,
66
+ "<s_formsectionI>": 57561,
67
+ "<s_formsectionII>": 57553,
68
+ "<s_iitcdip>": 57523,
69
+ "<s_image_id>": 57525,
70
+ "<s_insurancecompany>": 57559,
71
+ "<s_synthdog>": 57524,
72
+ "<sep/>": 57522
73
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
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": "4.30.2"
8
+ }
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
+ 827,
24
+ 1169
25
+ ]
26
+ }
runs/Jul15_10-40-29_4804271ce6e4/events.out.tfevents.1689417709.4804271ce6e4.11035.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5c05d9fc6d5cd8b8f9d4fb3b973183b44d6d6cc962f7e1bd9dad21bb6bc392e
3
- size 8280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2035d6d8fde4b5379b56d7c0c0625c9104a8b83b23714c3fb4f143daed07ee4
3
+ size 8924
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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_image_id>",
4
+ "</s_image_id>",
5
+ "<s_Section3>",
6
+ "</s_Section3>",
7
+ "<s_Social Security Number>",
8
+ "</s_Social Security Number>",
9
+ "<s_Relationship to You?>",
10
+ "</s_Relationship to You?>",
11
+ "<s_Product Selection(s)>",
12
+ "</s_Product Selection(s)>",
13
+ "<s_MI>",
14
+ "</s_MI>",
15
+ "<s_Last Name>",
16
+ "</s_Last Name>",
17
+ "<s_Gender>",
18
+ "</s_Gender>",
19
+ "<s_First Name>",
20
+ "</s_First Name>",
21
+ "<s_Dependent2>",
22
+ "</s_Dependent2>",
23
+ "<s_Dependent Status if Age 26 or Older>",
24
+ "</s_Dependent Status if Age 26 or Older>",
25
+ "<s_Date of Birth (Month/Day/Year)>",
26
+ "</s_Date of Birth (Month/Day/Year)>",
27
+ "<s_Age>",
28
+ "</s_Age>",
29
+ "<s_Section2>",
30
+ "</s_Section2>",
31
+ "<s_formsectionII>",
32
+ "</s_formsectionII>",
33
+ "<s_Dependent1>",
34
+ "</s_Dependent1>",
35
+ "<s_Section1>",
36
+ "</s_Section1>",
37
+ "<s_insurancecompany>",
38
+ "</s_insurancecompany>",
39
+ "<s_formsectionI>",
40
+ "</s_formsectionI>",
41
+ "<s_formheader>",
42
+ "</s_formheader>",
43
+ "<s_Zip>",
44
+ "</s_Zip>",
45
+ "<s_State>",
46
+ "</s_State>",
47
+ "<s_Payroll Location>",
48
+ "</s_Payroll Location>",
49
+ "<s_Marital Status (Please check one)>",
50
+ "</s_Marital Status (Please check one)>",
51
+ "<s_Hours Worked Per Week>",
52
+ "</s_Hours Worked Per Week>",
53
+ "<s_Home/Cell Phone>",
54
+ "</s_Home/Cell Phone>",
55
+ "<s_Group Number>",
56
+ "</s_Group Number>",
57
+ "<s_Full-Time Hire (or Rehire) Date (Month/Day/Year)>",
58
+ "</s_Full-Time Hire (or Rehire) Date (Month/Day/Year)>",
59
+ "<s_Enrollment Status>",
60
+ "</s_Enrollment Status>",
61
+ "<s_Employer/Group Name>",
62
+ "</s_Employer/Group Name>",
63
+ "<s_Effective Date>",
64
+ "</s_Effective Date>",
65
+ "<s_County>",
66
+ "</s_County>",
67
+ "<s_City>",
68
+ "</s_City>",
69
+ "<s_Address>",
70
+ "</s_Address>",
71
+ "<s>",
72
+ "</s>"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": {
78
+ "content": "<mask>",
79
+ "lstrip": true,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false
83
+ },
84
+ "pad_token": "<pad>",
85
+ "sep_token": "</s>",
86
+ "unk_token": "<unk>"
87
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }