riteshbehera857 commited on
Commit
71d10e6
1 Parent(s): bc77ae9

layoutlmv3-model-ubiai-finetuned

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-sa-4.0
4
+ base_model: microsoft/layoutlmv3-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: output
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
+ # output
16
+
17
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.0733
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 5 | 1.4124 |
51
+ | 1.9095 | 2.0 | 10 | 1.1362 |
52
+ | 1.9095 | 3.0 | 15 | 1.0733 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.44.2
58
+ - Pytorch 2.4.1+cu121
59
+ - Datasets 3.0.1
60
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-base",
3
+ "architectures": [
4
+ "LayoutLMv3ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 128,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "B-B-ADDRESS",
18
+ "1": "B-B-NAME",
19
+ "2": "B-INVOICE NO",
20
+ "3": "B-ORDER DATE",
21
+ "4": "B-ORDER ID",
22
+ "5": "B-S-ADDRESS",
23
+ "6": "B-S-NAME",
24
+ "7": "B-TOTAL GROSS",
25
+ "8": "E-B-ADDRESS",
26
+ "9": "E-B-NAME",
27
+ "10": "E-INVOICE NO",
28
+ "11": "E-ORDER DATE",
29
+ "12": "E-ORDER ID",
30
+ "13": "E-S-ADDRESS",
31
+ "14": "E-S-NAME",
32
+ "15": "E-TOTAL GROSS",
33
+ "16": "I-B-ADDRESS",
34
+ "17": "I-B-NAME",
35
+ "18": "I-INVOICE NO",
36
+ "19": "I-ORDER DATE",
37
+ "20": "I-S-ADDRESS",
38
+ "21": "I-S-NAME",
39
+ "22": "I-TOTAL GROSS",
40
+ "23": "O",
41
+ "24": "S-B-ADDRESS",
42
+ "25": "S-B-NAME",
43
+ "26": "S-GST NO",
44
+ "27": "S-INVOICE NO",
45
+ "28": "S-ORDER DATE",
46
+ "29": "S-ORDER ID",
47
+ "30": "S-S-ADDRESS",
48
+ "31": "S-S-NAME",
49
+ "32": "S-TOTAL GROSS"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "input_size": 224,
53
+ "intermediate_size": 3072,
54
+ "label2id": {
55
+ "B-B-ADDRESS": 0,
56
+ "B-B-NAME": 1,
57
+ "B-INVOICE NO": 2,
58
+ "B-ORDER DATE": 3,
59
+ "B-ORDER ID": 4,
60
+ "B-S-ADDRESS": 5,
61
+ "B-S-NAME": 6,
62
+ "B-TOTAL GROSS": 7,
63
+ "E-B-ADDRESS": 8,
64
+ "E-B-NAME": 9,
65
+ "E-INVOICE NO": 10,
66
+ "E-ORDER DATE": 11,
67
+ "E-ORDER ID": 12,
68
+ "E-S-ADDRESS": 13,
69
+ "E-S-NAME": 14,
70
+ "E-TOTAL GROSS": 15,
71
+ "I-B-ADDRESS": 16,
72
+ "I-B-NAME": 17,
73
+ "I-INVOICE NO": 18,
74
+ "I-ORDER DATE": 19,
75
+ "I-S-ADDRESS": 20,
76
+ "I-S-NAME": 21,
77
+ "I-TOTAL GROSS": 22,
78
+ "O": 23,
79
+ "S-B-ADDRESS": 24,
80
+ "S-B-NAME": 25,
81
+ "S-GST NO": 26,
82
+ "S-INVOICE NO": 27,
83
+ "S-ORDER DATE": 28,
84
+ "S-ORDER ID": 29,
85
+ "S-S-ADDRESS": 30,
86
+ "S-S-NAME": 31,
87
+ "S-TOTAL GROSS": 32
88
+ },
89
+ "layer_norm_eps": 1e-05,
90
+ "max_2d_position_embeddings": 1024,
91
+ "max_position_embeddings": 514,
92
+ "max_rel_2d_pos": 256,
93
+ "max_rel_pos": 128,
94
+ "model_type": "layoutlmv3",
95
+ "num_attention_heads": 12,
96
+ "num_channels": 3,
97
+ "num_hidden_layers": 12,
98
+ "pad_token_id": 1,
99
+ "patch_size": 16,
100
+ "rel_2d_pos_bins": 64,
101
+ "rel_pos_bins": 32,
102
+ "second_input_size": 112,
103
+ "shape_size": 128,
104
+ "text_embed": true,
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.44.2",
107
+ "type_vocab_size": 1,
108
+ "visual_embed": true,
109
+ "vocab_size": 50265
110
+ }
eval_split/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bc189d383a12d8cdb4b9daa684c2f99682cfb89bdd9e236dd658feefe22c13
3
+ size 3180592
eval_split/dataset_info.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "pixel_values": {
6
+ "shape": [
7
+ 3,
8
+ 224,
9
+ 224
10
+ ],
11
+ "dtype": "float32",
12
+ "_type": "Array3D"
13
+ },
14
+ "input_ids": {
15
+ "feature": {
16
+ "dtype": "int64",
17
+ "_type": "Value"
18
+ },
19
+ "_type": "Sequence"
20
+ },
21
+ "attention_mask": {
22
+ "feature": {
23
+ "dtype": "int64",
24
+ "_type": "Value"
25
+ },
26
+ "_type": "Sequence"
27
+ },
28
+ "bbox": {
29
+ "shape": [
30
+ 512,
31
+ 4
32
+ ],
33
+ "dtype": "int64",
34
+ "_type": "Array2D"
35
+ },
36
+ "labels": {
37
+ "feature": {
38
+ "names": [
39
+ "B-B-ADDRESS",
40
+ "B-B-NAME",
41
+ "B-INVOICE NO",
42
+ "B-ORDER DATE",
43
+ "B-ORDER ID",
44
+ "B-S-ADDRESS",
45
+ "B-S-NAME",
46
+ "B-TOTAL GROSS",
47
+ "E-B-ADDRESS",
48
+ "E-B-NAME",
49
+ "E-INVOICE NO",
50
+ "E-ORDER DATE",
51
+ "E-ORDER ID",
52
+ "E-S-ADDRESS",
53
+ "E-S-NAME",
54
+ "E-TOTAL GROSS",
55
+ "I-B-ADDRESS",
56
+ "I-B-NAME",
57
+ "I-INVOICE NO",
58
+ "I-ORDER DATE",
59
+ "I-S-ADDRESS",
60
+ "I-S-NAME",
61
+ "I-TOTAL GROSS",
62
+ "O",
63
+ "S-B-ADDRESS",
64
+ "S-B-NAME",
65
+ "S-GST NO",
66
+ "S-INVOICE NO",
67
+ "S-ORDER DATE",
68
+ "S-ORDER ID",
69
+ "S-S-ADDRESS",
70
+ "S-S-NAME",
71
+ "S-TOTAL GROSS"
72
+ ],
73
+ "_type": "ClassLabel"
74
+ },
75
+ "_type": "Sequence"
76
+ }
77
+ },
78
+ "homepage": "",
79
+ "license": ""
80
+ }
eval_split/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "5eb40daa1a2ed827",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": "torch",
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
final_model/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-base",
3
+ "architectures": [
4
+ "LayoutLMv3ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 128,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "B-B-ADDRESS",
18
+ "1": "B-B-NAME",
19
+ "2": "B-INVOICE NO",
20
+ "3": "B-ORDER DATE",
21
+ "4": "B-ORDER ID",
22
+ "5": "B-S-ADDRESS",
23
+ "6": "B-S-NAME",
24
+ "7": "B-TOTAL GROSS",
25
+ "8": "E-B-ADDRESS",
26
+ "9": "E-B-NAME",
27
+ "10": "E-INVOICE NO",
28
+ "11": "E-ORDER DATE",
29
+ "12": "E-ORDER ID",
30
+ "13": "E-S-ADDRESS",
31
+ "14": "E-S-NAME",
32
+ "15": "E-TOTAL GROSS",
33
+ "16": "I-B-ADDRESS",
34
+ "17": "I-B-NAME",
35
+ "18": "I-INVOICE NO",
36
+ "19": "I-ORDER DATE",
37
+ "20": "I-S-ADDRESS",
38
+ "21": "I-S-NAME",
39
+ "22": "I-TOTAL GROSS",
40
+ "23": "O",
41
+ "24": "S-B-ADDRESS",
42
+ "25": "S-B-NAME",
43
+ "26": "S-GST NO",
44
+ "27": "S-INVOICE NO",
45
+ "28": "S-ORDER DATE",
46
+ "29": "S-ORDER ID",
47
+ "30": "S-S-ADDRESS",
48
+ "31": "S-S-NAME",
49
+ "32": "S-TOTAL GROSS"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "input_size": 224,
53
+ "intermediate_size": 3072,
54
+ "label2id": {
55
+ "B-B-ADDRESS": 0,
56
+ "B-B-NAME": 1,
57
+ "B-INVOICE NO": 2,
58
+ "B-ORDER DATE": 3,
59
+ "B-ORDER ID": 4,
60
+ "B-S-ADDRESS": 5,
61
+ "B-S-NAME": 6,
62
+ "B-TOTAL GROSS": 7,
63
+ "E-B-ADDRESS": 8,
64
+ "E-B-NAME": 9,
65
+ "E-INVOICE NO": 10,
66
+ "E-ORDER DATE": 11,
67
+ "E-ORDER ID": 12,
68
+ "E-S-ADDRESS": 13,
69
+ "E-S-NAME": 14,
70
+ "E-TOTAL GROSS": 15,
71
+ "I-B-ADDRESS": 16,
72
+ "I-B-NAME": 17,
73
+ "I-INVOICE NO": 18,
74
+ "I-ORDER DATE": 19,
75
+ "I-S-ADDRESS": 20,
76
+ "I-S-NAME": 21,
77
+ "I-TOTAL GROSS": 22,
78
+ "O": 23,
79
+ "S-B-ADDRESS": 24,
80
+ "S-B-NAME": 25,
81
+ "S-GST NO": 26,
82
+ "S-INVOICE NO": 27,
83
+ "S-ORDER DATE": 28,
84
+ "S-ORDER ID": 29,
85
+ "S-S-ADDRESS": 30,
86
+ "S-S-NAME": 31,
87
+ "S-TOTAL GROSS": 32
88
+ },
89
+ "layer_norm_eps": 1e-05,
90
+ "max_2d_position_embeddings": 1024,
91
+ "max_position_embeddings": 514,
92
+ "max_rel_2d_pos": 256,
93
+ "max_rel_pos": 128,
94
+ "model_type": "layoutlmv3",
95
+ "num_attention_heads": 12,
96
+ "num_channels": 3,
97
+ "num_hidden_layers": 12,
98
+ "pad_token_id": 1,
99
+ "patch_size": 16,
100
+ "rel_2d_pos_bins": 64,
101
+ "rel_pos_bins": 32,
102
+ "second_input_size": 112,
103
+ "shape_size": 128,
104
+ "text_embed": true,
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.44.2",
107
+ "type_vocab_size": 1,
108
+ "visual_embed": true,
109
+ "vocab_size": 50265
110
+ }
final_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
final_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6f341224aa5cbe9c685024f73ba51419820067b6f8c0928a695ec8df3d06f2
3
+ size 503798108
final_model/preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3ImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
final_model/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
final_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model/tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "apply_ocr": false,
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "cls_token_box": [
50
+ 0,
51
+ 0,
52
+ 0,
53
+ 0
54
+ ],
55
+ "eos_token": "</s>",
56
+ "errors": "replace",
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "<pad>",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv3Processor",
69
+ "sep_token": "</s>",
70
+ "sep_token_box": [
71
+ 0,
72
+ 0,
73
+ 0,
74
+ 0
75
+ ],
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": "<unk>"
79
+ }
final_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa351a10f8633d65ac423e224ef40bde28d717f12012d48652090b3b1dd00dd
3
+ size 5176
final_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
logs/events.out.tfevents.1727935696.fd5c96f7bbba.4005.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c7e50f2cc696e77f2d5d66d383a93483ee2bad466f9c4d98115c6c7e28b94e
3
+ size 8106
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6f341224aa5cbe9c685024f73ba51419820067b6f8c0928a695ec8df3d06f2
3
+ size 503798108
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3ImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
raw_data/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "test"]}
raw_data/test/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83677a728308497f631f37b81559627800bafe5440b5e1bcc2c244e97d77fe74
3
+ size 3154720
raw_data/test/dataset_info.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "id": {
6
+ "dtype": "string",
7
+ "_type": "Value"
8
+ },
9
+ "tokens": {
10
+ "feature": {
11
+ "dtype": "string",
12
+ "_type": "Value"
13
+ },
14
+ "_type": "Sequence"
15
+ },
16
+ "bboxes": {
17
+ "feature": {
18
+ "feature": {
19
+ "dtype": "int64",
20
+ "_type": "Value"
21
+ },
22
+ "_type": "Sequence"
23
+ },
24
+ "_type": "Sequence"
25
+ },
26
+ "ner_tags": {
27
+ "feature": {
28
+ "names": [
29
+ "B-B-ADDRESS",
30
+ "B-B-NAME",
31
+ "B-INVOICE NO",
32
+ "B-ORDER DATE",
33
+ "B-ORDER ID",
34
+ "B-S-ADDRESS",
35
+ "B-S-NAME",
36
+ "B-TOTAL GROSS",
37
+ "E-B-ADDRESS",
38
+ "E-B-NAME",
39
+ "E-INVOICE NO",
40
+ "E-ORDER DATE",
41
+ "E-ORDER ID",
42
+ "E-S-ADDRESS",
43
+ "E-S-NAME",
44
+ "E-TOTAL GROSS",
45
+ "I-B-ADDRESS",
46
+ "I-B-NAME",
47
+ "I-INVOICE NO",
48
+ "I-ORDER DATE",
49
+ "I-S-ADDRESS",
50
+ "I-S-NAME",
51
+ "I-TOTAL GROSS",
52
+ "O",
53
+ "S-B-ADDRESS",
54
+ "S-B-NAME",
55
+ "S-GST NO",
56
+ "S-INVOICE NO",
57
+ "S-ORDER DATE",
58
+ "S-ORDER ID",
59
+ "S-S-ADDRESS",
60
+ "S-S-NAME",
61
+ "S-TOTAL GROSS"
62
+ ],
63
+ "_type": "ClassLabel"
64
+ },
65
+ "_type": "Sequence"
66
+ },
67
+ "image": {
68
+ "_type": "Image"
69
+ }
70
+ },
71
+ "homepage": "",
72
+ "license": ""
73
+ }
raw_data/test/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "a2942ffa2c2ed7a4",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
raw_data/train/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5402ffcf0465c0691f7db53bd0ac48770ee423b0b710240a84a131d0b6f90f3e
3
+ size 23227744
raw_data/train/dataset_info.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "id": {
6
+ "dtype": "string",
7
+ "_type": "Value"
8
+ },
9
+ "tokens": {
10
+ "feature": {
11
+ "dtype": "string",
12
+ "_type": "Value"
13
+ },
14
+ "_type": "Sequence"
15
+ },
16
+ "bboxes": {
17
+ "feature": {
18
+ "feature": {
19
+ "dtype": "int64",
20
+ "_type": "Value"
21
+ },
22
+ "_type": "Sequence"
23
+ },
24
+ "_type": "Sequence"
25
+ },
26
+ "ner_tags": {
27
+ "feature": {
28
+ "names": [
29
+ "B-B-ADDRESS",
30
+ "B-B-NAME",
31
+ "B-INVOICE NO",
32
+ "B-ORDER DATE",
33
+ "B-ORDER ID",
34
+ "B-S-ADDRESS",
35
+ "B-S-NAME",
36
+ "B-TOTAL GROSS",
37
+ "E-B-ADDRESS",
38
+ "E-B-NAME",
39
+ "E-INVOICE NO",
40
+ "E-ORDER DATE",
41
+ "E-ORDER ID",
42
+ "E-S-ADDRESS",
43
+ "E-S-NAME",
44
+ "E-TOTAL GROSS",
45
+ "I-B-ADDRESS",
46
+ "I-B-NAME",
47
+ "I-INVOICE NO",
48
+ "I-ORDER DATE",
49
+ "I-S-ADDRESS",
50
+ "I-S-NAME",
51
+ "I-TOTAL GROSS",
52
+ "O",
53
+ "S-B-ADDRESS",
54
+ "S-B-NAME",
55
+ "S-GST NO",
56
+ "S-INVOICE NO",
57
+ "S-ORDER DATE",
58
+ "S-ORDER ID",
59
+ "S-S-ADDRESS",
60
+ "S-S-NAME",
61
+ "S-TOTAL GROSS"
62
+ ],
63
+ "_type": "ClassLabel"
64
+ },
65
+ "_type": "Sequence"
66
+ },
67
+ "image": {
68
+ "_type": "Image"
69
+ }
70
+ },
71
+ "homepage": "",
72
+ "license": ""
73
+ }
raw_data/train/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "99d2edbb60741c1e",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "apply_ocr": false,
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "cls_token_box": [
50
+ 0,
51
+ 0,
52
+ 0,
53
+ 0
54
+ ],
55
+ "eos_token": "</s>",
56
+ "errors": "replace",
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "<pad>",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv3Processor",
69
+ "sep_token": "</s>",
70
+ "sep_token_box": [
71
+ 0,
72
+ 0,
73
+ 0,
74
+ 0
75
+ ],
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": "<unk>"
79
+ }
train_split/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61367ca40e0bfddf7ff3793b41f081a9825103a809b2924b2c9c77f764c0895
3
+ size 24153832
train_split/dataset_info.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "pixel_values": {
6
+ "shape": [
7
+ 3,
8
+ 224,
9
+ 224
10
+ ],
11
+ "dtype": "float32",
12
+ "_type": "Array3D"
13
+ },
14
+ "input_ids": {
15
+ "feature": {
16
+ "dtype": "int64",
17
+ "_type": "Value"
18
+ },
19
+ "_type": "Sequence"
20
+ },
21
+ "attention_mask": {
22
+ "feature": {
23
+ "dtype": "int64",
24
+ "_type": "Value"
25
+ },
26
+ "_type": "Sequence"
27
+ },
28
+ "bbox": {
29
+ "shape": [
30
+ 512,
31
+ 4
32
+ ],
33
+ "dtype": "int64",
34
+ "_type": "Array2D"
35
+ },
36
+ "labels": {
37
+ "feature": {
38
+ "names": [
39
+ "B-B-ADDRESS",
40
+ "B-B-NAME",
41
+ "B-INVOICE NO",
42
+ "B-ORDER DATE",
43
+ "B-ORDER ID",
44
+ "B-S-ADDRESS",
45
+ "B-S-NAME",
46
+ "B-TOTAL GROSS",
47
+ "E-B-ADDRESS",
48
+ "E-B-NAME",
49
+ "E-INVOICE NO",
50
+ "E-ORDER DATE",
51
+ "E-ORDER ID",
52
+ "E-S-ADDRESS",
53
+ "E-S-NAME",
54
+ "E-TOTAL GROSS",
55
+ "I-B-ADDRESS",
56
+ "I-B-NAME",
57
+ "I-INVOICE NO",
58
+ "I-ORDER DATE",
59
+ "I-S-ADDRESS",
60
+ "I-S-NAME",
61
+ "I-TOTAL GROSS",
62
+ "O",
63
+ "S-B-ADDRESS",
64
+ "S-B-NAME",
65
+ "S-GST NO",
66
+ "S-INVOICE NO",
67
+ "S-ORDER DATE",
68
+ "S-ORDER ID",
69
+ "S-S-ADDRESS",
70
+ "S-S-NAME",
71
+ "S-TOTAL GROSS"
72
+ ],
73
+ "_type": "ClassLabel"
74
+ },
75
+ "_type": "Sequence"
76
+ }
77
+ },
78
+ "homepage": "",
79
+ "license": ""
80
+ }
train_split/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "839eea11a8c38e17",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": "torch",
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa351a10f8633d65ac423e224ef40bde28d717f12012d48652090b3b1dd00dd
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff