Prem11100 commited on
Commit
e24beaa
1 Parent(s): 2929016

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-Label-studio-200-invoices
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-Label-studio-200-invoices
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: 15
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.25.0.dev0
52
+ - Pytorch 1.12.1+cu113
53
+ - Datasets 2.6.1
54
+ - Tokenizers 0.13.2
added_tokens.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_BUY_ADD>": 57578,
3
+ "</s_BUY_PAN_ID>": 57600,
4
+ "</s_BUY_PAN_NO>": 57598,
5
+ "</s_CGST_ID>": 57576,
6
+ "</s_CGST_RATE>": 57574,
7
+ "</s_CGST_VALUE>": 57572,
8
+ "</s_CIN_ID>": 57596,
9
+ "</s_CIN_NO>": 57594,
10
+ "</s_CUSTOMER_NAME>": 57570,
11
+ "</s_CUSTOMER_PO_ID>": 57586,
12
+ "</s_CUSTOMER_PO_NO>": 57584,
13
+ "</s_GSTIN_ID>": 57568,
14
+ "</s_GSTIN_NO>": 57566,
15
+ "</s_GSTIN_SELL_ID>": 57564,
16
+ "</s_GSTIN_SELL_NO>": 57562,
17
+ "</s_IGST_ID>": 57592,
18
+ "</s_IGST_RATE>": 57560,
19
+ "</s_IGST_VALUE>": 57558,
20
+ "</s_INVOICE_DATE_ID>": 57556,
21
+ "</s_INVOICE_DATE_NO>": 57554,
22
+ "</s_INVOICE_ID>": 57552,
23
+ "</s_INVOICE_NO>": 57550,
24
+ "</s_MODE_OF_PAY_ID>": 57548,
25
+ "</s_MODE_OF_PAY_NO>": 57546,
26
+ "</s_REVERSE_CHARGE_ID>": 57588,
27
+ "</s_REVERSE_CHARGE_NO>": 57602,
28
+ "</s_SELL_ADD>": 57544,
29
+ "</s_SELL_PAN_ID>": 57582,
30
+ "</s_SELL_PAN_NO>": 57580,
31
+ "</s_SGST_ID>": 57542,
32
+ "</s_SGST_RATE>": 57540,
33
+ "</s_SGST_VALUE>": 57538,
34
+ "</s_SUBTOTAL_ID>": 57536,
35
+ "</s_SUBTOTAL_VALUE>": 57534,
36
+ "</s_TOTAL_ID>": 57532,
37
+ "</s_TOTAL_NO>": 57530,
38
+ "</s_VEHICLE_ID>": 57590,
39
+ "</s_VEHICLE_NO>": 57528,
40
+ "</s_VENDER_NAME>": 57526,
41
+ "<s_BUY_ADD>": 57577,
42
+ "<s_BUY_PAN_ID>": 57599,
43
+ "<s_BUY_PAN_NO>": 57597,
44
+ "<s_CGST_ID>": 57575,
45
+ "<s_CGST_RATE>": 57573,
46
+ "<s_CGST_VALUE>": 57571,
47
+ "<s_CIN_ID>": 57595,
48
+ "<s_CIN_NO>": 57593,
49
+ "<s_CUSTOMER_NAME>": 57569,
50
+ "<s_CUSTOMER_PO_ID>": 57585,
51
+ "<s_CUSTOMER_PO_NO>": 57583,
52
+ "<s_GSTIN_ID>": 57567,
53
+ "<s_GSTIN_NO>": 57565,
54
+ "<s_GSTIN_SELL_ID>": 57563,
55
+ "<s_GSTIN_SELL_NO>": 57561,
56
+ "<s_IGST_ID>": 57591,
57
+ "<s_IGST_RATE>": 57559,
58
+ "<s_IGST_VALUE>": 57557,
59
+ "<s_INVOICE_DATE_ID>": 57555,
60
+ "<s_INVOICE_DATE_NO>": 57553,
61
+ "<s_INVOICE_ID>": 57551,
62
+ "<s_INVOICE_NO>": 57549,
63
+ "<s_MODE_OF_PAY_ID>": 57547,
64
+ "<s_MODE_OF_PAY_NO>": 57545,
65
+ "<s_REVERSE_CHARGE_ID>": 57587,
66
+ "<s_REVERSE_CHARGE_NO>": 57601,
67
+ "<s_SELL_ADD>": 57543,
68
+ "<s_SELL_PAN_ID>": 57581,
69
+ "<s_SELL_PAN_NO>": 57579,
70
+ "<s_SGST_ID>": 57541,
71
+ "<s_SGST_RATE>": 57539,
72
+ "<s_SGST_VALUE>": 57537,
73
+ "<s_SUBTOTAL_ID>": 57535,
74
+ "<s_SUBTOTAL_VALUE>": 57533,
75
+ "<s_TOTAL_ID>": 57531,
76
+ "<s_TOTAL_NO>": 57529,
77
+ "<s_VEHICLE_ID>": 57589,
78
+ "<s_VEHICLE_NO>": 57527,
79
+ "<s_VENDER_NAME>": 57525,
80
+ "<s_iitcdip>": 57523,
81
+ "<s_synthdog>": 57524,
82
+ "<sep/>": 57522
83
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_resize": true,
6
+ "do_thumbnail": true,
7
+ "feature_extractor_type": "DonutFeatureExtractor",
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "DonutProcessor",
19
+ "resample": 2,
20
+ "size": [
21
+ 720,
22
+ 960
23
+ ]
24
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69406369ecd59814a8c713424bb16266111a7c95314b78ed21e32df771fbc677
3
  size 809494907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da25948ed35e54e88d5b53ad6e02ecd3239ff8140fcb1ec0fab5aff2bc08df8a
3
  size 809494907
runs/Nov08_05-44-57_1fa4274a315b/events.out.tfevents.1667886317.1fa4274a315b.73.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2810a68d7c9b99a065eea8420fafe50a2914d2e7be885cb25bf729f0f68c9fd4
3
- size 8457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1b3dbd8c296986cc678de0147ee0aba033bc114b6c438503f2ab2b4cc63eb9
3
+ size 11009
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 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_VENDER_NAME>",
4
+ "</s_VENDER_NAME>",
5
+ "<s_VEHICLE_NO>",
6
+ "</s_VEHICLE_NO>",
7
+ "<s_VEHICLE_ID>",
8
+ "</s_VEHICLE_ID>",
9
+ "<s_TOTAL_NO>",
10
+ "</s_TOTAL_NO>",
11
+ "<s_TOTAL_ID>",
12
+ "</s_TOTAL_ID>",
13
+ "<s_SUBTOTAL_VALUE>",
14
+ "</s_SUBTOTAL_VALUE>",
15
+ "<s_SUBTOTAL_ID>",
16
+ "</s_SUBTOTAL_ID>",
17
+ "<s_SGST_VALUE>",
18
+ "</s_SGST_VALUE>",
19
+ "<s_SGST_RATE>",
20
+ "</s_SGST_RATE>",
21
+ "<s_SGST_ID>",
22
+ "</s_SGST_ID>",
23
+ "<s_SELL_PAN_NO>",
24
+ "</s_SELL_PAN_NO>",
25
+ "<s_SELL_PAN_ID>",
26
+ "</s_SELL_PAN_ID>",
27
+ "<s_SELL_ADD>",
28
+ "</s_SELL_ADD>",
29
+ "<s_REVERSE_CHARGE_NO>",
30
+ "</s_REVERSE_CHARGE_NO>",
31
+ "<s_REVERSE_CHARGE_ID>",
32
+ "</s_REVERSE_CHARGE_ID>",
33
+ "<s_INVOICE_NO>",
34
+ "</s_INVOICE_NO>",
35
+ "<s_INVOICE_ID>",
36
+ "</s_INVOICE_ID>",
37
+ "<s_INVOICE_DATE_NO>",
38
+ "</s_INVOICE_DATE_NO>",
39
+ "<s_INVOICE_DATE_ID>",
40
+ "</s_INVOICE_DATE_ID>",
41
+ "<s_GSTIN_SELL_NO>",
42
+ "</s_GSTIN_SELL_NO>",
43
+ "<s_GSTIN_SELL_ID>",
44
+ "</s_GSTIN_SELL_ID>",
45
+ "<s_GSTIN_NO>",
46
+ "</s_GSTIN_NO>",
47
+ "<s_GSTIN_ID>",
48
+ "</s_GSTIN_ID>",
49
+ "<s_CUSTOMER_PO_ID>",
50
+ "</s_CUSTOMER_PO_ID>",
51
+ "<s_CUSTOMER_NAME>",
52
+ "</s_CUSTOMER_NAME>",
53
+ "<s_CIN_NO>",
54
+ "</s_CIN_NO>",
55
+ "<s_CIN_ID>",
56
+ "</s_CIN_ID>",
57
+ "<s_CGST_VALUE>",
58
+ "</s_CGST_VALUE>",
59
+ "<s_CGST_RATE>",
60
+ "</s_CGST_RATE>",
61
+ "<s_CGST_ID>",
62
+ "</s_CGST_ID>",
63
+ "<s_BUY_ADD>",
64
+ "</s_BUY_ADD>",
65
+ "<s_IGST_VALUE>",
66
+ "</s_IGST_VALUE>",
67
+ "<s_IGST_ID>",
68
+ "</s_IGST_ID>",
69
+ "<s_BUY_PAN_NO>",
70
+ "</s_BUY_PAN_NO>",
71
+ "<s_BUY_PAN_ID>",
72
+ "</s_BUY_PAN_ID>",
73
+ "<s_IGST_RATE>",
74
+ "</s_IGST_RATE>",
75
+ "<s_MODE_OF_PAY_ID>",
76
+ "</s_MODE_OF_PAY_ID>",
77
+ "<s_CUSTOMER_PO_NO>",
78
+ "</s_CUSTOMER_PO_NO>",
79
+ "<s_MODE_OF_PAY_NO>",
80
+ "</s_MODE_OF_PAY_NO>",
81
+ "<s>",
82
+ "</s>"
83
+ ],
84
+ "bos_token": "<s>",
85
+ "cls_token": "<s>",
86
+ "eos_token": "</s>",
87
+ "mask_token": {
88
+ "content": "<mask>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ "pad_token": "<pad>",
95
+ "sep_token": "</s>",
96
+ "unk_token": "<unk>"
97
+ }
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
+ "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
+ "name_or_path": "Prem11100/donut-base-Label-studio",
14
+ "pad_token": "<pad>",
15
+ "processor_class": "DonutProcessor",
16
+ "sep_token": "</s>",
17
+ "sp_model_kwargs": {},
18
+ "special_tokens_map_file": null,
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }