Hugging Face's logo

ddebnath
/
layoutlmv3-finetuned-invoice

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
ddebnath commited on
Commit
36c6b36
•
1 Parent(s): a6a79d4

Training in progress, step 500

Browse files
Files changed (14) hide show
  1. .gitignore +1 -0
  2. config.json +68 -0
  3. merges.txt +0 -0
  4. preprocessor_config.json +21 -0
  5. pytorch_model.bin +3 -0
  6. runs/Oct23_17-11-37_5f3ea45ed310/1666545126.6251264/events.out.tfevents.1666545126.5f3ea45ed310.1033.1 +3 -0
  7. runs/Oct23_17-11-37_5f3ea45ed310/events.out.tfevents.1666545126.5f3ea45ed310.1033.0 +3 -0
  8. runs/Oct23_17-13-42_5f3ea45ed310/1666545236.0511203/events.out.tfevents.1666545236.5f3ea45ed310.1033.3 +3 -0
  9. runs/Oct23_17-13-42_5f3ea45ed310/events.out.tfevents.1666545236.5f3ea45ed310.1033.2 +3 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +87 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
18
+ "1": "B-ABN",
19
+ "2": "B-BILLER",
20
+ "3": "B-BILLER_ADDRESS",
21
+ "4": "B-BILLER_POST_CODE",
22
+ "5": "B-DUE_DATE",
23
+ "6": "B-GST",
24
+ "7": "B-INVOICE_DATE",
25
+ "8": "B-INVOICE_NUMBER",
26
+ "9": "B-SUBTOTAL",
27
+ "10": "B-TOTAL",
28
+ "11": "I-BILLER_ADDRESS"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "input_size": 224,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "B-ABN": 1,
35
+ "B-BILLER": 2,
36
+ "B-BILLER_ADDRESS": 3,
37
+ "B-BILLER_POST_CODE": 4,
38
+ "B-DUE_DATE": 5,
39
+ "B-GST": 6,
40
+ "B-INVOICE_DATE": 7,
41
+ "B-INVOICE_NUMBER": 8,
42
+ "B-SUBTOTAL": 9,
43
+ "B-TOTAL": 10,
44
+ "I-BILLER_ADDRESS": 11,
45
+ "O": 0
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "max_2d_position_embeddings": 1024,
49
+ "max_position_embeddings": 514,
50
+ "max_rel_2d_pos": 256,
51
+ "max_rel_pos": 128,
52
+ "model_type": "layoutlmv3",
53
+ "num_attention_heads": 12,
54
+ "num_channels": 3,
55
+ "num_hidden_layers": 12,
56
+ "pad_token_id": 1,
57
+ "patch_size": 16,
58
+ "rel_2d_pos_bins": 64,
59
+ "rel_pos_bins": 32,
60
+ "second_input_size": 112,
61
+ "shape_size": 128,
62
+ "text_embed": true,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.23.1",
65
+ "type_vocab_size": 1,
66
+ "visual_embed": true,
67
+ "vocab_size": 50265
68
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "ocr_lang": null,
17
+ "processor_class": "LayoutLMv3Processor",
18
+ "resample": 2,
19
+ "size": 224,
20
+ "tesseract_config": ""
21
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31fac5ef546290d69707c7f5bc4ea060c7a6c7c20044e8e7aebfbd6111d6ddf6
3
+ size 503784271
runs/Oct23_17-11-37_5f3ea45ed310/1666545126.6251264/events.out.tfevents.1666545126.5f3ea45ed310.1033.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b37d8fa6a95a96680bdde7f065b7d960f18d08e7028f204b0cfa1ceadd0bae
3
+ size 5559
runs/Oct23_17-11-37_5f3ea45ed310/events.out.tfevents.1666545126.5f3ea45ed310.1033.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e6c76c1c894646abe5fe8fa5865ca0ec012bdbb09852052c1b2934285af1f00
3
+ size 4702
runs/Oct23_17-13-42_5f3ea45ed310/1666545236.0511203/events.out.tfevents.1666545236.5f3ea45ed310.1033.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c8d37c2ebfe21633960523733c0c06fde9db722a9f5cc248b3b203c3263ffb
3
+ size 5559
runs/Oct23_17-13-42_5f3ea45ed310/events.out.tfevents.1666545236.5f3ea45ed310.1033.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2948359e8577ce2f3ae45dbd0d5e617ee0120e2b08482aae56a4a245e5db97c
3
+ size 7210
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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "apply_ocr": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "name_or_path": "microsoft/layoutlmv3-base",
45
+ "only_label_first_subword": true,
46
+ "pad_token": {
47
+ "__type": "AddedToken",
48
+ "content": "<pad>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "pad_token_box": [
55
+ 0,
56
+ 0,
57
+ 0,
58
+ 0
59
+ ],
60
+ "pad_token_label": -100,
61
+ "processor_class": "LayoutLMv3Processor",
62
+ "sep_token": {
63
+ "__type": "AddedToken",
64
+ "content": "</s>",
65
+ "lstrip": false,
66
+ "normalized": true,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ },
70
+ "sep_token_box": [
71
+ 0,
72
+ 0,
73
+ 0,
74
+ 0
75
+ ],
76
+ "special_tokens_map_file": null,
77
+ "tokenizer_class": "LayoutLMv3Tokenizer",
78
+ "trim_offsets": true,
79
+ "unk_token": {
80
+ "__type": "AddedToken",
81
+ "content": "<unk>",
82
+ "lstrip": false,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ }
87
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e2f84dfd8aa839d21ef71ab63b40b713cf66e2b802b2fcc8725865683baf06
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff