ashu1318 commited on
Commit
b0213fe
1 Parent(s): 0640a27

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: 1.8731
20
+ - Answer: {'precision': 0.8688915375446961, 'recall': 0.8922888616891065, 'f1': 0.8804347826086957, 'number': 817}
21
+ - Header: {'precision': 0.638095238095238, 'recall': 0.5630252100840336, 'f1': 0.5982142857142857, 'number': 119}
22
+ - Question: {'precision': 0.9105166051660517, 'recall': 0.9164345403899722, 'f1': 0.9134659879685332, 'number': 1077}
23
+ - Overall Precision: 0.8792
24
+ - Overall Recall: 0.8857
25
+ - Overall F1: 0.8825
26
+ - Overall Accuracy: 0.7976
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
+ | 0.4323 | 10.53 | 200 | 1.0423 | {'precision': 0.8369195922989807, 'recall': 0.9045287637698899, 'f1': 0.8694117647058823, 'number': 817} | {'precision': 0.5405405405405406, 'recall': 0.5042016806722689, 'f1': 0.5217391304347826, 'number': 119} | {'precision': 0.8869323447636701, 'recall': 0.8885793871866295, 'f1': 0.8877551020408162, 'number': 1077} | 0.8471 | 0.8723 | 0.8595 | 0.7981 |
59
+ | 0.045 | 21.05 | 400 | 1.2757 | {'precision': 0.8435374149659864, 'recall': 0.9106487148102815, 'f1': 0.8758092995879929, 'number': 817} | {'precision': 0.5795454545454546, 'recall': 0.42857142857142855, 'f1': 0.49275362318840576, 'number': 119} | {'precision': 0.8626943005181347, 'recall': 0.9275766016713092, 'f1': 0.8939597315436242, 'number': 1077} | 0.8430 | 0.8912 | 0.8665 | 0.8026 |
60
+ | 0.0133 | 31.58 | 600 | 1.4887 | {'precision': 0.8632075471698113, 'recall': 0.8959608323133414, 'f1': 0.8792792792792793, 'number': 817} | {'precision': 0.6020408163265306, 'recall': 0.4957983193277311, 'f1': 0.543778801843318, 'number': 119} | {'precision': 0.8791887125220459, 'recall': 0.9257195914577531, 'f1': 0.9018543645409318, 'number': 1077} | 0.8596 | 0.8882 | 0.8737 | 0.7983 |
61
+ | 0.0051 | 42.11 | 800 | 1.7382 | {'precision': 0.8601645123384254, 'recall': 0.8959608323133414, 'f1': 0.8776978417266187, 'number': 817} | {'precision': 0.5636363636363636, 'recall': 0.5210084033613446, 'f1': 0.5414847161572053, 'number': 119} | {'precision': 0.9032558139534884, 'recall': 0.9015784586815228, 'f1': 0.9024163568773235, 'number': 1077} | 0.8669 | 0.8768 | 0.8718 | 0.7925 |
62
+ | 0.004 | 52.63 | 1000 | 1.7599 | {'precision': 0.8307349665924276, 'recall': 0.9130966952264382, 'f1': 0.8699708454810495, 'number': 817} | {'precision': 0.6039603960396039, 'recall': 0.5126050420168067, 'f1': 0.5545454545454545, 'number': 119} | {'precision': 0.8939256572982774, 'recall': 0.9155060352831941, 'f1': 0.9045871559633027, 'number': 1077} | 0.8530 | 0.8907 | 0.8714 | 0.7941 |
63
+ | 0.002 | 63.16 | 1200 | 1.8409 | {'precision': 0.8312985571587126, 'recall': 0.9167686658506732, 'f1': 0.8719441210710128, 'number': 817} | {'precision': 0.6074766355140186, 'recall': 0.5462184873949579, 'f1': 0.575221238938053, 'number': 119} | {'precision': 0.8814949863263446, 'recall': 0.8978644382544104, 'f1': 0.8896044158233671, 'number': 1077} | 0.8461 | 0.8847 | 0.8650 | 0.7876 |
64
+ | 0.0013 | 73.68 | 1400 | 1.7795 | {'precision': 0.81445523193096, 'recall': 0.9241126070991432, 'f1': 0.8658256880733943, 'number': 817} | {'precision': 0.6237623762376238, 'recall': 0.5294117647058824, 'f1': 0.5727272727272728, 'number': 119} | {'precision': 0.888785046728972, 'recall': 0.883008356545961, 'f1': 0.8858872845831393, 'number': 1077} | 0.8432 | 0.8788 | 0.8606 | 0.7934 |
65
+ | 0.0011 | 84.21 | 1600 | 1.8386 | {'precision': 0.8338833883388339, 'recall': 0.9277845777233782, 'f1': 0.8783314020857474, 'number': 817} | {'precision': 0.6597938144329897, 'recall': 0.5378151260504201, 'f1': 0.5925925925925926, 'number': 119} | {'precision': 0.8943985307621671, 'recall': 0.904363974001857, 'f1': 0.8993536472760849, 'number': 1077} | 0.8573 | 0.8922 | 0.8744 | 0.7945 |
66
+ | 0.0048 | 94.74 | 1800 | 1.8664 | {'precision': 0.8589595375722543, 'recall': 0.9094247246022031, 'f1': 0.8834720570749108, 'number': 817} | {'precision': 0.6504854368932039, 'recall': 0.5630252100840336, 'f1': 0.6036036036036037, 'number': 119} | {'precision': 0.9003656307129799, 'recall': 0.914577530176416, 'f1': 0.9074159373560571, 'number': 1077} | 0.8705 | 0.8917 | 0.8810 | 0.7927 |
67
+ | 0.0004 | 105.26 | 2000 | 1.8672 | {'precision': 0.8634772462077013, 'recall': 0.9057527539779682, 'f1': 0.8841099163679809, 'number': 817} | {'precision': 0.7093023255813954, 'recall': 0.5126050420168067, 'f1': 0.5951219512195123, 'number': 119} | {'precision': 0.8923076923076924, 'recall': 0.9155060352831941, 'f1': 0.9037580201649862, 'number': 1077} | 0.8726 | 0.8877 | 0.8801 | 0.7953 |
68
+ | 0.0005 | 115.79 | 2200 | 1.8731 | {'precision': 0.8688915375446961, 'recall': 0.8922888616891065, 'f1': 0.8804347826086957, 'number': 817} | {'precision': 0.638095238095238, 'recall': 0.5630252100840336, 'f1': 0.5982142857142857, 'number': 119} | {'precision': 0.9105166051660517, 'recall': 0.9164345403899722, 'f1': 0.9134659879685332, 'number': 1077} | 0.8792 | 0.8857 | 0.8825 | 0.7976 |
69
+ | 0.0002 | 126.32 | 2400 | 1.9408 | {'precision': 0.8408071748878924, 'recall': 0.9179926560587516, 'f1': 0.8777062609713283, 'number': 817} | {'precision': 0.6310679611650486, 'recall': 0.5462184873949579, 'f1': 0.5855855855855856, 'number': 119} | {'precision': 0.9091760299625468, 'recall': 0.9015784586815228, 'f1': 0.9053613053613054, 'number': 1077} | 0.8657 | 0.8872 | 0.8763 | 0.7935 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.24.0
75
+ - Pytorch 1.12.1+cu113
76
+ - Datasets 2.7.1
77
+ - Tokenizers 0.13.2
logs/events.out.tfevents.1669657832.60f793e7d073.637.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5189ecb5297fa5e001d2a349966b37690dc59e108f47ea90ec3adf3e7293832
3
- size 4759
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b282ba9ab4b771f8e1d80aed4b4f531616fbe1f99569274faaccaab17a1b777
3
+ size 12384
logs/events.out.tfevents.1669659432.60f793e7d073.637.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2435ca44d7c7b9c9e9eeb96fa078c967f997f3efad71108db180ef791f5db7
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_normalize": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "ocr_lang": null,
17
+ "processor_class": "LayoutLMv3Processor",
18
+ "resample": 2,
19
+ "size": 224,
20
+ "tesseract_config": ""
21
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73d733879b6986a120538a9f28d9d4a6ad9eca640b49903b6be31f7398958e06
3
  size 520818271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec3e0bba0627df91200d23beb62387f9964ac2dd6415bf02da9b2f1f0ac27ba
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