dwitidibyajyoti commited on
Commit
d1dff75
1 Parent(s): c9b9e0a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: test
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # test
20
+
21
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.2843
24
+ - Precision: 0.4118
25
+ - Recall: 0.8235
26
+ - F1: 0.5490
27
+ - Accuracy: 0.9485
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: 1e-05
47
+ - train_batch_size: 2
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - training_steps: 1000
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 8.33 | 100 | 0.6271 | 0.1864 | 0.6471 | 0.2895 | 0.8757 |
59
+ | No log | 16.67 | 200 | 0.1736 | 0.52 | 0.7647 | 0.6190 | 0.9734 |
60
+ | No log | 25.0 | 300 | 0.1302 | 0.5714 | 0.9412 | 0.7111 | 0.9734 |
61
+ | No log | 33.33 | 400 | 0.2835 | 0.5333 | 0.9412 | 0.6809 | 0.9556 |
62
+ | 0.287 | 41.67 | 500 | 0.0924 | 0.4828 | 0.8235 | 0.6087 | 0.9805 |
63
+ | 0.287 | 50.0 | 600 | 0.2594 | 0.4412 | 0.8824 | 0.5882 | 0.9485 |
64
+ | 0.287 | 58.33 | 700 | 0.3172 | 0.4412 | 0.8824 | 0.5882 | 0.9467 |
65
+ | 0.287 | 66.67 | 800 | 0.2447 | 0.4545 | 0.8824 | 0.6 | 0.9520 |
66
+ | 0.287 | 75.0 | 900 | 0.2941 | 0.4118 | 0.8235 | 0.5490 | 0.9485 |
67
+ | 0.013 | 83.33 | 1000 | 0.2843 | 0.4118 | 0.8235 | 0.5490 | 0.9485 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.34.0.dev0
73
+ - Pytorch 2.0.1+cu118
74
+ - Datasets 2.14.5
75
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "E-VALUE",
18
+ "1": "I-IGNORE",
19
+ "2": "S-KEY",
20
+ "3": "E-IGNORE",
21
+ "4": "S-IGNORE",
22
+ "5": "S-VALUE",
23
+ "6": "I-VALUE",
24
+ "7": "B-IGNORE",
25
+ "8": "B-VALUE",
26
+ "9": "B-TABLE",
27
+ "10": "O",
28
+ "11": "I-TABLE",
29
+ "12": "E-TABLE"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "input_size": 224,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "B-IGNORE": 7,
36
+ "B-TABLE": 9,
37
+ "B-VALUE": 8,
38
+ "E-IGNORE": 3,
39
+ "E-TABLE": 12,
40
+ "E-VALUE": 0,
41
+ "I-IGNORE": 1,
42
+ "I-TABLE": 11,
43
+ "I-VALUE": 6,
44
+ "O": 10,
45
+ "S-IGNORE": 4,
46
+ "S-KEY": 2,
47
+ "S-VALUE": 5
48
+ },
49
+ "layer_norm_eps": 1e-05,
50
+ "max_2d_position_embeddings": 1024,
51
+ "max_position_embeddings": 514,
52
+ "max_rel_2d_pos": 256,
53
+ "max_rel_pos": 128,
54
+ "model_type": "layoutlmv3",
55
+ "num_attention_heads": 12,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 12,
58
+ "pad_token_id": 1,
59
+ "patch_size": 16,
60
+ "rel_2d_pos_bins": 64,
61
+ "rel_pos_bins": 32,
62
+ "second_input_size": 112,
63
+ "shape_size": 128,
64
+ "text_embed": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.34.0.dev0",
67
+ "type_vocab_size": 1,
68
+ "visual_embed": true,
69
+ "vocab_size": 50265
70
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "ocr_lang": null,
19
+ "processor_class": "LayoutLMv3Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 224,
24
+ "width": 224
25
+ },
26
+ "tesseract_config": ""
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c064517ba665e0a3c468193ff19cb0e7c0a014af212427239790794c136a4e3
3
+ size 503784749
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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
13
+ "cls_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "cls_token_box": [
22
+ 0,
23
+ 0,
24
+ 0,
25
+ 0
26
+ ],
27
+ "eos_token": {
28
+ "__type": "AddedToken",
29
+ "content": "</s>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "errors": "replace",
36
+ "mask_token": {
37
+ "__type": "AddedToken",
38
+ "content": "<mask>",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "model_max_length": 512,
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
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": {
79
+ "__type": "AddedToken",
80
+ "content": "<unk>",
81
+ "lstrip": false,
82
+ "normalized": true,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52512162a88483c3279f95df4cded9402de0e4a32111b20a2b0d2735a7919fb3
3
+ size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff