tkazusa commited on
Commit
664dd09
1 Parent(s): 1aeca06

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: 1.3685
20
+ - Answer: {'precision': 0.8654073199527745, 'recall': 0.8971848225214198, 'f1': 0.8810096153846154, 'number': 817}
21
+ - Header: {'precision': 0.6041666666666666, 'recall': 0.48739495798319327, 'f1': 0.5395348837209302, 'number': 119}
22
+ - Question: {'precision': 0.8660245183887916, 'recall': 0.9182915506035283, 'f1': 0.8913925191527715, 'number': 1077}
23
+ - Overall Precision: 0.8537
24
+ - Overall Recall: 0.8843
25
+ - Overall F1: 0.8687
26
+ - Overall Accuracy: 0.8073
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
+ | 0.4208 | 10.53 | 200 | 0.9422 | {'precision': 0.8501742160278746, 'recall': 0.8959608323133414, 'f1': 0.872467222884386, 'number': 817} | {'precision': 0.47580645161290325, 'recall': 0.4957983193277311, 'f1': 0.48559670781893005, 'number': 119} | {'precision': 0.8847884788478848, 'recall': 0.9127205199628597, 'f1': 0.8985374771480805, 'number': 1077} | 0.8464 | 0.8813 | 0.8635 | 0.8109 |
59
+ | 0.043 | 21.05 | 400 | 1.3865 | {'precision': 0.8387096774193549, 'recall': 0.9228886168910648, 'f1': 0.8787878787878787, 'number': 817} | {'precision': 0.5423728813559322, 'recall': 0.5378151260504201, 'f1': 0.540084388185654, 'number': 119} | {'precision': 0.8985507246376812, 'recall': 0.8635097493036211, 'f1': 0.8806818181818181, 'number': 1077} | 0.8519 | 0.8684 | 0.8600 | 0.7941 |
60
+ | 0.0126 | 31.58 | 600 | 1.3685 | {'precision': 0.8654073199527745, 'recall': 0.8971848225214198, 'f1': 0.8810096153846154, 'number': 817} | {'precision': 0.6041666666666666, 'recall': 0.48739495798319327, 'f1': 0.5395348837209302, 'number': 119} | {'precision': 0.8660245183887916, 'recall': 0.9182915506035283, 'f1': 0.8913925191527715, 'number': 1077} | 0.8537 | 0.8843 | 0.8687 | 0.8073 |
61
+ | 0.006 | 42.11 | 800 | 1.6230 | {'precision': 0.8476977567886659, 'recall': 0.8788249694002448, 'f1': 0.8629807692307692, 'number': 817} | {'precision': 0.6, 'recall': 0.4789915966386555, 'f1': 0.5327102803738317, 'number': 119} | {'precision': 0.872207327971403, 'recall': 0.9062209842154132, 'f1': 0.8888888888888888, 'number': 1077} | 0.8496 | 0.8698 | 0.8596 | 0.7927 |
62
+ | 0.005 | 52.63 | 1000 | 1.5735 | {'precision': 0.8246392896781354, 'recall': 0.9094247246022031, 'f1': 0.8649592549476135, 'number': 817} | {'precision': 0.5897435897435898, 'recall': 0.5798319327731093, 'f1': 0.5847457627118645, 'number': 119} | {'precision': 0.8932316491897044, 'recall': 0.8700092850510678, 'f1': 0.8814675446848542, 'number': 1077} | 0.8462 | 0.8689 | 0.8574 | 0.7970 |
63
+ | 0.0025 | 63.16 | 1200 | 1.6481 | {'precision': 0.8327721661054994, 'recall': 0.9082007343941249, 'f1': 0.8688524590163934, 'number': 817} | {'precision': 0.5688073394495413, 'recall': 0.5210084033613446, 'f1': 0.543859649122807, 'number': 119} | {'precision': 0.9084778420038536, 'recall': 0.8755803156917363, 'f1': 0.8917257683215132, 'number': 1077} | 0.8572 | 0.8679 | 0.8625 | 0.7981 |
64
+ | 0.002 | 73.68 | 1400 | 1.5911 | {'precision': 0.8459743290548425, 'recall': 0.8873929008567931, 'f1': 0.8661887694145758, 'number': 817} | {'precision': 0.6122448979591837, 'recall': 0.5042016806722689, 'f1': 0.5529953917050692, 'number': 119} | {'precision': 0.8736462093862816, 'recall': 0.8987929433611885, 'f1': 0.8860411899313502, 'number': 1077} | 0.8497 | 0.8708 | 0.8602 | 0.8120 |
65
+ | 0.0009 | 84.21 | 1600 | 1.6905 | {'precision': 0.8041575492341356, 'recall': 0.8996328029375765, 'f1': 0.8492201039861352, 'number': 817} | {'precision': 0.6020408163265306, 'recall': 0.4957983193277311, 'f1': 0.543778801843318, 'number': 119} | {'precision': 0.900375939849624, 'recall': 0.8895078922934077, 'f1': 0.8949089210649229, 'number': 1077} | 0.8439 | 0.8703 | 0.8569 | 0.7985 |
66
+ | 0.0007 | 94.74 | 1800 | 1.7006 | {'precision': 0.8256467941507312, 'recall': 0.8984088127294981, 'f1': 0.8604923798358733, 'number': 817} | {'precision': 0.5573770491803278, 'recall': 0.5714285714285714, 'f1': 0.5643153526970954, 'number': 119} | {'precision': 0.8952830188679245, 'recall': 0.8811513463324049, 'f1': 0.888160973327094, 'number': 1077} | 0.8455 | 0.8698 | 0.8575 | 0.7981 |
67
+ | 0.0002 | 105.26 | 2000 | 1.6531 | {'precision': 0.8352402745995423, 'recall': 0.8935128518971848, 'f1': 0.8633944411590775, 'number': 817} | {'precision': 0.5784313725490197, 'recall': 0.4957983193277311, 'f1': 0.5339366515837104, 'number': 119} | {'precision': 0.8848987108655617, 'recall': 0.8922934076137419, 'f1': 0.888580674988442, 'number': 1077} | 0.8487 | 0.8693 | 0.8589 | 0.8140 |
68
+ | 0.0002 | 115.79 | 2200 | 1.6520 | {'precision': 0.8342857142857143, 'recall': 0.8935128518971848, 'f1': 0.8628841607565011, 'number': 817} | {'precision': 0.625, 'recall': 0.5462184873949579, 'f1': 0.5829596412556054, 'number': 119} | {'precision': 0.8868445262189513, 'recall': 0.8950789229340761, 'f1': 0.8909426987060998, 'number': 1077} | 0.8514 | 0.8738 | 0.8625 | 0.8153 |
69
+ | 0.0003 | 126.32 | 2400 | 1.6411 | {'precision': 0.830316742081448, 'recall': 0.8984088127294981, 'f1': 0.8630217519106408, 'number': 817} | {'precision': 0.6055045871559633, 'recall': 0.5546218487394958, 'f1': 0.5789473684210525, 'number': 119} | {'precision': 0.8976744186046511, 'recall': 0.8960074280408542, 'f1': 0.8968401486988847, 'number': 1077} | 0.8535 | 0.8768 | 0.8650 | 0.8183 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.25.1
75
+ - Pytorch 1.13.0+cu117
76
+ - Datasets 2.7.1
77
+ - Tokenizers 0.13.2
logs/events.out.tfevents.1670420416.ip-172-31-89-140.47049.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48c16107a76639166ae04f29b35a07248d1fe2a69bf4b1d731cd598eb6c1e7f7
3
- size 12052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95bc868eebbf57164fe3811391ca19625d868021f2222ad1c7e4215dac16faf
3
+ size 12406
logs/events.out.tfevents.1670422059.ip-172-31-89-140.47049.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1464611ce0950ec8a991ff9271372c69bba62abd5fa66ee7f808b2524f4cc320
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 sha256:384ea75195a978ee74f05c51f5b9c4c199cd205eb2370fd7a8601dd8a331170f
3
  size 520821201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93937c5a44cee634451fa465d5e087a3876c27c0f8b403e94621f30d1d1cfc01
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