npayaresc commited on
Commit
6773b27
1 Parent(s): 5cc4559

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: 1.7699
20
+ - Answer: {'precision': 0.8906439854191981, 'recall': 0.8971848225214198, 'f1': 0.8939024390243904, 'number': 817}
21
+ - Header: {'precision': 0.6274509803921569, 'recall': 0.5378151260504201, 'f1': 0.579185520361991, 'number': 119}
22
+ - Question: {'precision': 0.8778359511343804, 'recall': 0.9340761374187558, 'f1': 0.9050832208726944, 'number': 1077}
23
+ - Overall Precision: 0.8706
24
+ - Overall Recall: 0.8957
25
+ - Overall F1: 0.8830
26
+ - Overall Accuracy: 0.7973
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
+ | 0.4312 | 10.53 | 200 | 0.9853 | {'precision': 0.8581818181818182, 'recall': 0.8665850673194615, 'f1': 0.8623629719853837, 'number': 817} | {'precision': 0.5625, 'recall': 0.5294117647058824, 'f1': 0.5454545454545455, 'number': 119} | {'precision': 0.8788706739526412, 'recall': 0.8960074280408542, 'f1': 0.8873563218390804, 'number': 1077} | 0.8531 | 0.8624 | 0.8577 | 0.8172 |
59
+ | 0.0478 | 21.05 | 400 | 1.2825 | {'precision': 0.8571428571428571, 'recall': 0.9033047735618115, 'f1': 0.8796185935637664, 'number': 817} | {'precision': 0.5136986301369864, 'recall': 0.6302521008403361, 'f1': 0.5660377358490567, 'number': 119} | {'precision': 0.8739650413983441, 'recall': 0.8820798514391829, 'f1': 0.878003696857671, 'number': 1077} | 0.8419 | 0.8758 | 0.8585 | 0.8026 |
60
+ | 0.0127 | 31.58 | 600 | 1.4791 | {'precision': 0.8568075117370892, 'recall': 0.8935128518971848, 'f1': 0.8747753145596165, 'number': 817} | {'precision': 0.5779816513761468, 'recall': 0.5294117647058824, 'f1': 0.5526315789473684, 'number': 119} | {'precision': 0.8909426987060998, 'recall': 0.8950789229340761, 'f1': 0.8930060213061601, 'number': 1077} | 0.8600 | 0.8728 | 0.8664 | 0.7957 |
61
+ | 0.0073 | 42.11 | 800 | 1.3846 | {'precision': 0.8853046594982079, 'recall': 0.9069767441860465, 'f1': 0.8960096735187424, 'number': 817} | {'precision': 0.5333333333333333, 'recall': 0.6050420168067226, 'f1': 0.5669291338582677, 'number': 119} | {'precision': 0.8932584269662921, 'recall': 0.8857938718662952, 'f1': 0.8895104895104896, 'number': 1077} | 0.8662 | 0.8778 | 0.8719 | 0.8142 |
62
+ | 0.0023 | 52.63 | 1000 | 1.5955 | {'precision': 0.8430034129692833, 'recall': 0.9069767441860465, 'f1': 0.8738207547169811, 'number': 817} | {'precision': 0.6190476190476191, 'recall': 0.5462184873949579, 'f1': 0.5803571428571429, 'number': 119} | {'precision': 0.8935574229691877, 'recall': 0.8885793871866295, 'f1': 0.8910614525139665, 'number': 1077} | 0.8579 | 0.8758 | 0.8668 | 0.7992 |
63
+ | 0.0023 | 63.16 | 1200 | 1.6214 | {'precision': 0.8955773955773956, 'recall': 0.8922888616891065, 'f1': 0.8939301042305334, 'number': 817} | {'precision': 0.5882352941176471, 'recall': 0.5882352941176471, 'f1': 0.5882352941176471, 'number': 119} | {'precision': 0.8841354723707665, 'recall': 0.9210770659238626, 'f1': 0.9022282855843565, 'number': 1077} | 0.8715 | 0.8897 | 0.8805 | 0.8057 |
64
+ | 0.0016 | 73.68 | 1400 | 1.8002 | {'precision': 0.8732394366197183, 'recall': 0.9106487148102815, 'f1': 0.8915518274415818, 'number': 817} | {'precision': 0.5765765765765766, 'recall': 0.5378151260504201, 'f1': 0.5565217391304348, 'number': 119} | {'precision': 0.8892921960072595, 'recall': 0.9099350046425255, 'f1': 0.8994951812758146, 'number': 1077} | 0.8659 | 0.8882 | 0.8769 | 0.7860 |
65
+ | 0.0013 | 84.21 | 1600 | 1.7699 | {'precision': 0.8906439854191981, 'recall': 0.8971848225214198, 'f1': 0.8939024390243904, 'number': 817} | {'precision': 0.6274509803921569, 'recall': 0.5378151260504201, 'f1': 0.579185520361991, 'number': 119} | {'precision': 0.8778359511343804, 'recall': 0.9340761374187558, 'f1': 0.9050832208726944, 'number': 1077} | 0.8706 | 0.8957 | 0.8830 | 0.7973 |
66
+ | 0.0008 | 94.74 | 1800 | 1.7824 | {'precision': 0.8733572281959379, 'recall': 0.8947368421052632, 'f1': 0.8839177750906893, 'number': 817} | {'precision': 0.616822429906542, 'recall': 0.5546218487394958, 'f1': 0.5840707964601769, 'number': 119} | {'precision': 0.8901996370235935, 'recall': 0.9108635097493036, 'f1': 0.9004130335016063, 'number': 1077} | 0.8690 | 0.8833 | 0.8761 | 0.8019 |
67
+ | 0.0005 | 105.26 | 2000 | 1.7894 | {'precision': 0.872791519434629, 'recall': 0.9069767441860465, 'f1': 0.8895558223289316, 'number': 817} | {'precision': 0.6036036036036037, 'recall': 0.5630252100840336, 'f1': 0.582608695652174, 'number': 119} | {'precision': 0.8931506849315068, 'recall': 0.9080779944289693, 'f1': 0.9005524861878452, 'number': 1077} | 0.8691 | 0.8872 | 0.8781 | 0.7940 |
68
+ | 0.0002 | 115.79 | 2200 | 1.8409 | {'precision': 0.8665893271461717, 'recall': 0.9143206854345165, 'f1': 0.8898153662894581, 'number': 817} | {'precision': 0.6296296296296297, 'recall': 0.5714285714285714, 'f1': 0.5991189427312775, 'number': 119} | {'precision': 0.8978644382544104, 'recall': 0.8978644382544104, 'f1': 0.8978644382544104, 'number': 1077} | 0.8705 | 0.8852 | 0.8778 | 0.7982 |
69
+ | 0.0002 | 126.32 | 2400 | 1.8311 | {'precision': 0.8709302325581395, 'recall': 0.9167686658506732, 'f1': 0.8932617769827073, 'number': 817} | {'precision': 0.6018518518518519, 'recall': 0.5462184873949579, 'f1': 0.5726872246696034, 'number': 119} | {'precision': 0.893953488372093, 'recall': 0.8922934076137419, 'f1': 0.8931226765799257, 'number': 1077} | 0.8688 | 0.8818 | 0.8752 | 0.7988 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.25.1
75
+ - Pytorch 1.12.1
76
+ - Datasets 2.7.1
77
+ - Tokenizers 0.13.2
logs/events.out.tfevents.1670426953.104-171-203-174.67561.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26e7099efd4f89c2feb7e058413d1689dac9cbf112da4ce636d04515558f03c6
3
- size 12052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2562cd5697262bc042759ff0da9c888573ff4dd535244731d6f8c515c3c8274
3
+ size 12406
logs/events.out.tfevents.1670432251.104-171-203-174.67561.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631cc87e7bc1742bf6821691dea316889edb8af566ffb825c62c9d4a7c0eff50
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 sha256:30fb79445a1d8b3691ec4ba933da1571a341f723f0732fb8a7e663dc651b8a86
3
  size 520818271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddab7893cf7a8da54e14add544c21da9904aec63ef63b75ffcdf863782a5f6a
3
  size 520818271
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