romin23 commited on
Commit
43661b7
1 Parent(s): 1df84d7

End of training

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - funsd-layoutlmv3
7
+ model-index:
8
+ - name: lilt-form-read
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
+ # lilt-form-read
16
+
17
+ This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the funsd-layoutlmv3 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.7208
20
+ - Answer: {'precision': 0.8635321100917431, 'recall': 0.9216646266829865, 'f1': 0.8916518650088809, 'number': 817}
21
+ - Header: {'precision': 0.6813186813186813, 'recall': 0.5210084033613446, 'f1': 0.5904761904761905, 'number': 119}
22
+ - Question: {'precision': 0.9005424954792043, 'recall': 0.924791086350975, 'f1': 0.9125057260650481, 'number': 1077}
23
+ - Overall Precision: 0.8753
24
+ - Overall Recall: 0.8997
25
+ - Overall F1: 0.8873
26
+ - Overall Accuracy: 0.8077
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - training_steps: 2500
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
58
+ | 0.4555 | 10.53 | 200 | 0.9514 | {'precision': 0.8207440811724915, 'recall': 0.8910648714810282, 'f1': 0.8544600938967137, 'number': 817} | {'precision': 0.6233766233766234, 'recall': 0.40336134453781514, 'f1': 0.48979591836734687, 'number': 119} | {'precision': 0.8611825192802056, 'recall': 0.9331476323119777, 'f1': 0.8957219251336899, 'number': 1077} | 0.8358 | 0.8847 | 0.8596 | 0.7991 |
59
+ | 0.0457 | 21.05 | 400 | 1.4096 | {'precision': 0.8654088050314466, 'recall': 0.8421052631578947, 'f1': 0.8535980148883374, 'number': 817} | {'precision': 0.5833333333333334, 'recall': 0.5294117647058824, 'f1': 0.5550660792951542, 'number': 119} | {'precision': 0.8606837606837607, 'recall': 0.9350046425255338, 'f1': 0.8963061860258122, 'number': 1077} | 0.8480 | 0.8733 | 0.8605 | 0.7914 |
60
+ | 0.0144 | 31.58 | 600 | 1.4435 | {'precision': 0.8720095693779905, 'recall': 0.8922888616891065, 'f1': 0.8820326678765881, 'number': 817} | {'precision': 0.6428571428571429, 'recall': 0.5294117647058824, 'f1': 0.5806451612903226, 'number': 119} | {'precision': 0.8682581786030061, 'recall': 0.9117920148560817, 'f1': 0.8894927536231884, 'number': 1077} | 0.8591 | 0.8813 | 0.8700 | 0.8033 |
61
+ | 0.008 | 42.11 | 800 | 1.5197 | {'precision': 0.8660287081339713, 'recall': 0.8861689106487148, 'f1': 0.8759830611010284, 'number': 817} | {'precision': 0.5798319327731093, 'recall': 0.5798319327731093, 'f1': 0.5798319327731093, 'number': 119} | {'precision': 0.8838248436103664, 'recall': 0.9182915506035283, 'f1': 0.9007285974499089, 'number': 1077} | 0.8592 | 0.8852 | 0.8720 | 0.7921 |
62
+ | 0.0039 | 52.63 | 1000 | 1.4373 | {'precision': 0.8733727810650888, 'recall': 0.9033047735618115, 'f1': 0.888086642599278, 'number': 817} | {'precision': 0.6019417475728155, 'recall': 0.5210084033613446, 'f1': 0.5585585585585585, 'number': 119} | {'precision': 0.8854351687388987, 'recall': 0.9257195914577531, 'f1': 0.9051293690422152, 'number': 1077} | 0.8664 | 0.8927 | 0.8794 | 0.8096 |
63
+ | 0.0028 | 63.16 | 1200 | 1.7146 | {'precision': 0.8490351872871736, 'recall': 0.9155446756425949, 'f1': 0.8810365135453475, 'number': 817} | {'precision': 0.6941176470588235, 'recall': 0.4957983193277311, 'f1': 0.5784313725490197, 'number': 119} | {'precision': 0.8852313167259787, 'recall': 0.9238625812441968, 'f1': 0.9041344843253067, 'number': 1077} | 0.8622 | 0.8952 | 0.8784 | 0.7971 |
64
+ | 0.0022 | 73.68 | 1400 | 1.5638 | {'precision': 0.8608893956670467, 'recall': 0.9241126070991432, 'f1': 0.8913813459268004, 'number': 817} | {'precision': 0.6565656565656566, 'recall': 0.5462184873949579, 'f1': 0.5963302752293578, 'number': 119} | {'precision': 0.8993536472760849, 'recall': 0.904363974001857, 'f1': 0.9018518518518519, 'number': 1077} | 0.8713 | 0.8912 | 0.8811 | 0.8051 |
65
+ | 0.0009 | 84.21 | 1600 | 1.7113 | {'precision': 0.8682080924855491, 'recall': 0.9192166462668299, 'f1': 0.8929845422116528, 'number': 817} | {'precision': 0.65625, 'recall': 0.5294117647058824, 'f1': 0.586046511627907, 'number': 119} | {'precision': 0.9085027726432532, 'recall': 0.9127205199628597, 'f1': 0.9106067623899953, 'number': 1077} | 0.8796 | 0.8927 | 0.8861 | 0.8039 |
66
+ | 0.0009 | 94.74 | 1800 | 1.6397 | {'precision': 0.8767942583732058, 'recall': 0.8971848225214198, 'f1': 0.8868723532970357, 'number': 817} | {'precision': 0.6274509803921569, 'recall': 0.5378151260504201, 'f1': 0.579185520361991, 'number': 119} | {'precision': 0.898458748866727, 'recall': 0.9201485608170845, 'f1': 0.9091743119266055, 'number': 1077} | 0.8760 | 0.8882 | 0.8821 | 0.8042 |
67
+ | 0.0004 | 105.26 | 2000 | 1.7362 | {'precision': 0.8690614136732329, 'recall': 0.9179926560587516, 'f1': 0.8928571428571428, 'number': 817} | {'precision': 0.6458333333333334, 'recall': 0.5210084033613446, 'f1': 0.5767441860465117, 'number': 119} | {'precision': 0.8928892889288929, 'recall': 0.9210770659238626, 'f1': 0.9067641681901281, 'number': 1077} | 0.8715 | 0.8962 | 0.8837 | 0.8040 |
68
+ | 0.0003 | 115.79 | 2200 | 1.7208 | {'precision': 0.8635321100917431, 'recall': 0.9216646266829865, 'f1': 0.8916518650088809, 'number': 817} | {'precision': 0.6813186813186813, 'recall': 0.5210084033613446, 'f1': 0.5904761904761905, 'number': 119} | {'precision': 0.9005424954792043, 'recall': 0.924791086350975, 'f1': 0.9125057260650481, 'number': 1077} | 0.8753 | 0.8997 | 0.8873 | 0.8077 |
69
+ | 0.0002 | 126.32 | 2400 | 1.7281 | {'precision': 0.8819362455726092, 'recall': 0.9143206854345165, 'f1': 0.8978365384615384, 'number': 817} | {'precision': 0.6631578947368421, 'recall': 0.5294117647058824, 'f1': 0.5887850467289719, 'number': 119} | {'precision': 0.8917710196779964, 'recall': 0.9257195914577531, 'f1': 0.9084282460136676, 'number': 1077} | 0.8772 | 0.8977 | 0.8873 | 0.8060 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.25.1
75
+ - Pytorch 1.13.0+cu116
76
+ - Datasets 2.7.1
77
+ - Tokenizers 0.13.2
logs/events.out.tfevents.1671106667.8e5d4b60e0f3.375.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96344b2b54feca282f186c7b612bda7a82f3d69f115d3e83d36b1451a1c08e8
3
- size 4785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf8a53a0afa2ea6bda1bec00c8e5594a6f71cca319a382747816203d93dc582
3
+ size 12410
logs/events.out.tfevents.1671108048.8e5d4b60e0f3.375.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc60e6975dfb1e41521c2aa179888a1209cb3a8923d2cd3c445f10aaf91b210
3
+ size 544
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
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
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a550687f4fe2d96e33de9ab84c08849b05dce7e2f584507b40b09d871b58f9b
3
  size 520821201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869b2d6233f37f30ad5f767df40121a650dce5c029bed3c053a82b723facec74
3
  size 520821201
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
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "cls_token_box": [
20
+ 0,
21
+ 0,
22
+ 0,
23
+ 0
24
+ ],
25
+ "eos_token": {
26
+ "__type": "AddedToken",
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "errors": "replace",
34
+ "mask_token": {
35
+ "__type": "AddedToken",
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "model_max_length": 512,
43
+ "name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "processor_class": "LayoutLMv3Processor",
61
+ "sep_token": {
62
+ "__type": "AddedToken",
63
+ "content": "</s>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "special_tokens_map_file": null,
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
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff