haronbenfaida commited on
Commit
d53cd36
1 Parent(s): 6d95936

layoutlmv3-finetuned-facturesv1

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: test
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # test
15
+
16
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.9442
19
+ - eval_precision: 0.8653
20
+ - eval_recall: 0.7740
21
+ - eval_f1: 0.8171
22
+ - eval_accuracy: 0.9284
23
+ - eval_runtime: 77.5017
24
+ - eval_samples_per_second: 18.064
25
+ - eval_steps_per_second: 4.516
26
+ - epoch: 1.7707
27
+ - step: 3807
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-06
47
+ - train_batch_size: 4
48
+ - eval_batch_size: 4
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - training_steps: 25000
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.41.2
57
+ - Pytorch 2.3.0+cu121
58
+ - Datasets 2.20.0
59
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "$",
18
+ "1": "Total",
19
+ "2": "Total in Words",
20
+ "3": "Invoice Date",
21
+ "4": "Due Date",
22
+ "5": "Send_to",
23
+ "6": "Seller name",
24
+ "7": "7",
25
+ "8": "Buyer",
26
+ "9": "Tax",
27
+ "10": "Table",
28
+ "11": "Logo",
29
+ "12": "Invoice Number",
30
+ "13": "O"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "input_size": 224,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "$": 0,
37
+ "7": 7,
38
+ "Buyer": 8,
39
+ "Due Date": 4,
40
+ "Invoice Date": 3,
41
+ "Invoice Number": 12,
42
+ "Logo": 11,
43
+ "O": 13,
44
+ "Seller name": 6,
45
+ "Send_to": 5,
46
+ "Table": 10,
47
+ "Tax": 9,
48
+ "Total": 1,
49
+ "Total in Words": 2
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_2d_position_embeddings": 1024,
53
+ "max_position_embeddings": 514,
54
+ "max_rel_2d_pos": 256,
55
+ "max_rel_pos": 128,
56
+ "model_type": "layoutlmv3",
57
+ "num_attention_heads": 12,
58
+ "num_channels": 3,
59
+ "num_hidden_layers": 12,
60
+ "pad_token_id": 1,
61
+ "patch_size": 16,
62
+ "rel_2d_pos_bins": 64,
63
+ "rel_pos_bins": 32,
64
+ "second_input_size": 112,
65
+ "shape_size": 128,
66
+ "text_embed": true,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.41.2",
69
+ "type_vocab_size": 1,
70
+ "visual_embed": true,
71
+ "vocab_size": 50265
72
+ }
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 sha256:565994510dba98ee8aec88d7eaa0cf6bd651d107fe4caddb64a63f6263e6b04f
3
+ size 503739664
preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "apply_ocr",
13
+ "ocr_lang",
14
+ "tesseract_config",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
+ "apply_ocr": false,
20
+ "do_normalize": true,
21
+ "do_rescale": true,
22
+ "do_resize": true,
23
+ "image_mean": [
24
+ 0.5,
25
+ 0.5,
26
+ 0.5
27
+ ],
28
+ "image_processor_type": "LayoutLMv3ImageProcessor",
29
+ "image_std": [
30
+ 0.5,
31
+ 0.5,
32
+ 0.5
33
+ ],
34
+ "ocr_lang": null,
35
+ "processor_class": "LayoutLMv3Processor",
36
+ "resample": 2,
37
+ "rescale_factor": 0.00392156862745098,
38
+ "size": {
39
+ "height": 224,
40
+ "width": 224
41
+ },
42
+ "tesseract_config": ""
43
+ }
runs/Jul12_16-00-40_3cf3c36cf330/events.out.tfevents.1720800041.3cf3c36cf330.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8ef176e4ae1fe7eeedecc560ea9212e4899fd81199eb8ce691697f6e7b227a
3
+ size 14311
runs/Jul12_16-37-52_3cf3c36cf330/events.out.tfevents.1720802277.3cf3c36cf330.517.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780ac3ad37303e5b584b635101248af8ec53c5fc03ea142a327a5e13e8486102
3
+ size 8642
runs/Jul12_16-37-52_3cf3c36cf330/events.out.tfevents.1720803233.3cf3c36cf330.517.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2791d4fcecc1b0385a55b7aa89ae21e4db741e26c907ef9b58c319dc0130b157
3
+ size 6198
runs/Jul12_16-55-25_3cf3c36cf330/events.out.tfevents.1720803331.3cf3c36cf330.517.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97e53520cd1834a490503efa49aeb04346ca9cbbd5db148c3a6e4f783a048293
3
+ size 11827
runs/Jul12_17-01-43_3cf3c36cf330/events.out.tfevents.1720803706.3cf3c36cf330.517.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ab9e5894ac0bdc3c1446e625284e18ede64f078b1ea1fa649a8a8d8ab11f9
3
+ size 7135
runs/Jul12_17-11-57_3cf3c36cf330/events.out.tfevents.1720804320.3cf3c36cf330.517.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f463fadf488e1b7d60d70b0ac706403afec2278f09f70e3f5a06b27bfaf251
3
+ size 25604
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543b335cdcaf92f91409dd6256e38e3f40e44ec74cd99f155c1aa622d2e7dcdb
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff