oec24 commited on
Commit
de04624
1 Parent(s): d940ea5

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-en-funsd
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-en-funsd
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: 1.6055
20
+ - Answer: {'precision': 0.8728323699421965, 'recall': 0.9241126070991432, 'f1': 0.8977407847800237, 'number': 817}
21
+ - Header: {'precision': 0.6, 'recall': 0.5042016806722689, 'f1': 0.547945205479452, 'number': 119}
22
+ - Question: {'precision': 0.9, 'recall': 0.9108635097493036, 'f1': 0.9053991693585604, 'number': 1077}
23
+ - Overall Precision: 0.8740
24
+ - Overall Recall: 0.8922
25
+ - Overall F1: 0.8830
26
+ - Overall Accuracy: 0.8022
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
+ | 0.4096 | 10.53 | 200 | 0.9947 | {'precision': 0.8293515358361775, 'recall': 0.8922888616891065, 'f1': 0.8596698113207547, 'number': 817} | {'precision': 0.5833333333333334, 'recall': 0.5294117647058824, 'f1': 0.5550660792951542, 'number': 119} | {'precision': 0.8858195211786372, 'recall': 0.89322191272052, 'f1': 0.8895053166897827, 'number': 1077} | 0.8461 | 0.8713 | 0.8585 | 0.8133 |
59
+ | 0.0451 | 21.05 | 400 | 1.4850 | {'precision': 0.8394495412844036, 'recall': 0.8959608323133414, 'f1': 0.866785079928952, 'number': 817} | {'precision': 0.6333333333333333, 'recall': 0.4789915966386555, 'f1': 0.5454545454545454, 'number': 119} | {'precision': 0.9026974951830443, 'recall': 0.8700092850510678, 'f1': 0.8860520094562647, 'number': 1077} | 0.863 | 0.8574 | 0.8602 | 0.7910 |
60
+ | 0.0147 | 31.58 | 600 | 1.5603 | {'precision': 0.8478260869565217, 'recall': 0.9069767441860465, 'f1': 0.8764044943820224, 'number': 817} | {'precision': 0.6336633663366337, 'recall': 0.5378151260504201, 'f1': 0.5818181818181819, 'number': 119} | {'precision': 0.8845807033363391, 'recall': 0.9108635097493036, 'f1': 0.8975297346752059, 'number': 1077} | 0.8570 | 0.8872 | 0.8719 | 0.7948 |
61
+ | 0.0077 | 42.11 | 800 | 1.7433 | {'precision': 0.8344444444444444, 'recall': 0.9192166462668299, 'f1': 0.8747815958066395, 'number': 817} | {'precision': 0.5596330275229358, 'recall': 0.5126050420168067, 'f1': 0.5350877192982455, 'number': 119} | {'precision': 0.9031954887218046, 'recall': 0.8922934076137419, 'f1': 0.897711349836525, 'number': 1077} | 0.8553 | 0.8808 | 0.8678 | 0.7910 |
62
+ | 0.004 | 52.63 | 1000 | 1.6055 | {'precision': 0.8728323699421965, 'recall': 0.9241126070991432, 'f1': 0.8977407847800237, 'number': 817} | {'precision': 0.6, 'recall': 0.5042016806722689, 'f1': 0.547945205479452, 'number': 119} | {'precision': 0.9, 'recall': 0.9108635097493036, 'f1': 0.9053991693585604, 'number': 1077} | 0.8740 | 0.8922 | 0.8830 | 0.8022 |
63
+ | 0.0021 | 63.16 | 1200 | 1.7317 | {'precision': 0.8688524590163934, 'recall': 0.9082007343941249, 'f1': 0.8880909634949131, 'number': 817} | {'precision': 0.5904761904761905, 'recall': 0.5210084033613446, 'f1': 0.5535714285714286, 'number': 119} | {'precision': 0.8847184986595175, 'recall': 0.9192200557103064, 'f1': 0.9016393442622952, 'number': 1077} | 0.8633 | 0.8912 | 0.8770 | 0.7979 |
64
+ | 0.0017 | 73.68 | 1400 | 1.7249 | {'precision': 0.8705463182897862, 'recall': 0.8971848225214198, 'f1': 0.8836648583484027, 'number': 817} | {'precision': 0.5555555555555556, 'recall': 0.5042016806722689, 'f1': 0.5286343612334802, 'number': 119} | {'precision': 0.8818181818181818, 'recall': 0.9006499535747446, 'f1': 0.891134588883785, 'number': 1077} | 0.86 | 0.8758 | 0.8678 | 0.8014 |
65
+ | 0.0012 | 84.21 | 1600 | 1.8716 | {'precision': 0.8679678530424799, 'recall': 0.9253365973072215, 'f1': 0.8957345971563981, 'number': 817} | {'precision': 0.5652173913043478, 'recall': 0.5462184873949579, 'f1': 0.5555555555555555, 'number': 119} | {'precision': 0.898320895522388, 'recall': 0.8941504178272981, 'f1': 0.8962308050255934, 'number': 1077} | 0.8669 | 0.8862 | 0.8764 | 0.7946 |
66
+ | 0.0006 | 94.74 | 1800 | 1.8381 | {'precision': 0.8563218390804598, 'recall': 0.9118727050183598, 'f1': 0.8832246591582691, 'number': 817} | {'precision': 0.6055045871559633, 'recall': 0.5546218487394958, 'f1': 0.5789473684210525, 'number': 119} | {'precision': 0.8931226765799256, 'recall': 0.8922934076137419, 'f1': 0.8927078495123084, 'number': 1077} | 0.8623 | 0.8803 | 0.8712 | 0.7954 |
67
+ | 0.0007 | 105.26 | 2000 | 1.7090 | {'precision': 0.8822115384615384, 'recall': 0.8984088127294981, 'f1': 0.8902365069739235, 'number': 817} | {'precision': 0.576271186440678, 'recall': 0.5714285714285714, 'f1': 0.5738396624472574, 'number': 119} | {'precision': 0.8811881188118812, 'recall': 0.9090064995357474, 'f1': 0.8948811700182815, 'number': 1077} | 0.8641 | 0.8847 | 0.8743 | 0.8122 |
68
+ | 0.0003 | 115.79 | 2200 | 1.7487 | {'precision': 0.8730723606168446, 'recall': 0.9008567931456548, 'f1': 0.8867469879518072, 'number': 817} | {'precision': 0.5645161290322581, 'recall': 0.5882352941176471, 'f1': 0.5761316872427984, 'number': 119} | {'precision': 0.8936755270394133, 'recall': 0.9052924791086351, 'f1': 0.8994464944649446, 'number': 1077} | 0.8654 | 0.8847 | 0.8750 | 0.8084 |
69
+ | 0.0002 | 126.32 | 2400 | 1.7644 | {'precision': 0.8686046511627907, 'recall': 0.9143206854345165, 'f1': 0.8908765652951699, 'number': 817} | {'precision': 0.5932203389830508, 'recall': 0.5882352941176471, 'f1': 0.5907172995780592, 'number': 119} | {'precision': 0.8961397058823529, 'recall': 0.9052924791086351, 'f1': 0.9006928406466513, 'number': 1077} | 0.8674 | 0.8902 | 0.8786 | 0.8091 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.29.2
75
+ - Pytorch 2.0.1+cu118
76
+ - Datasets 2.12.0
77
+ - Tokenizers 0.13.3
logs/events.out.tfevents.1684744893.13895c1888c2.2904.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08509ee43f60b01f82380dd7314025c1dab8e0d39cd7bb27cbba09676ab66a91
3
- size 11683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b81337f4cba0ba9a682ae29c393dc821ea9bc91ce3a302106d3975a3582c3b
3
+ size 12698
logs/events.out.tfevents.1684748673.13895c1888c2.2904.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93ef87923b5892399f61860c11305725a732ffe6f2c3450f1efb16d588bdd3f
3
+ size 592
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": "LayoutLMv3FeatureExtractor",
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:efd261d023f9b680242f4d225acf833cb3677e5f7db2cddfad474ab212ee6b26
3
  size 520821201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57dd3d65ddf929f3f3796ffeddfc47dc1e1cf666710fe3ce0819d01ee251ab80
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 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
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
+ "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
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
+ "unk_token": {
78
+ "__type": "AddedToken",
79
+ "content": "<unk>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false
84
+ }
85
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff