Hugging Face's logo

billyprodev
/
layoutlm-funsd

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Model card Files
xet
 Metrics Community
billyprodev commited on
Commit
15f24bf
·
verified ·
1 Parent(s): 296de14

End of training

Browse files
Files changed (6) hide show
  1. README.md +80 -0
  2. model.safetensors +1 -1
  3. processor_config.json +14 -0
  4. runs/May02_20-15-42_81b4d1914131/events.out.tfevents.1777752942.81b4d1914131.4120.0 +2 -2
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +37 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/layoutlm-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: layoutlm-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
+ # layoutlm-funsd
16
+
17
+ This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6849
20
+ - Answer: {'precision': 0.7012987012987013, 'recall': 0.8009888751545118, 'f1': 0.7478361223312175, 'number': 809}
21
+ - Header: {'precision': 0.2949640287769784, 'recall': 0.3445378151260504, 'f1': 0.31782945736434104, 'number': 119}
22
+ - Question: {'precision': 0.7841918294849023, 'recall': 0.8291079812206573, 'f1': 0.8060246462802373, 'number': 1065}
23
+ - Overall Precision: 0.7181
24
+ - Overall Recall: 0.7888
25
+ - Overall F1: 0.7518
26
+ - Overall Accuracy: 0.8109
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: 3e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 15
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
+ | 1.8118 | 1.0 | 10 | 1.6165 | {'precision': 0.0053475935828877, 'recall': 0.003708281829419036, 'f1': 0.004379562043795621, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.1696969696969697, 'recall': 0.07887323943661972, 'f1': 0.10769230769230771, 'number': 1065} | 0.0824 | 0.0437 | 0.0571 | 0.3296 |
59
+ | 1.4873 | 2.0 | 20 | 1.2837 | {'precision': 0.2286302780638517, 'recall': 0.27441285537700866, 'f1': 0.24943820224719102, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.40404040404040403, 'recall': 0.48826291079812206, 'f1': 0.4421768707482993, 'number': 1065} | 0.3286 | 0.3723 | 0.3491 | 0.5988 |
60
+ | 1.1439 | 3.0 | 30 | 0.9604 | {'precision': 0.4777777777777778, 'recall': 0.5315203955500618, 'f1': 0.5032182562902282, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5338345864661654, 'recall': 0.6666666666666666, 'f1': 0.5929018789144049, 'number': 1065} | 0.5096 | 0.5720 | 0.5390 | 0.7009 |
61
+ | 0.8769 | 4.0 | 40 | 0.8082 | {'precision': 0.5680473372781065, 'recall': 0.7119901112484549, 'f1': 0.6319253976961053, 'number': 809} | {'precision': 0.17142857142857143, 'recall': 0.05042016806722689, 'f1': 0.07792207792207793, 'number': 119} | {'precision': 0.634046052631579, 'recall': 0.723943661971831, 'f1': 0.676019289785182, 'number': 1065} | 0.5974 | 0.6789 | 0.6355 | 0.7460 |
62
+ | 0.7067 | 5.0 | 50 | 0.7335 | {'precision': 0.6294363256784968, 'recall': 0.7453646477132262, 'f1': 0.6825127334465195, 'number': 809} | {'precision': 0.1875, 'recall': 0.12605042016806722, 'f1': 0.1507537688442211, 'number': 119} | {'precision': 0.6707818930041153, 'recall': 0.7652582159624414, 'f1': 0.7149122807017545, 'number': 1065} | 0.6360 | 0.7190 | 0.6750 | 0.7739 |
63
+ | 0.6007 | 6.0 | 60 | 0.7113 | {'precision': 0.6472361809045226, 'recall': 0.796044499381953, 'f1': 0.7139689578713968, 'number': 809} | {'precision': 0.18604651162790697, 'recall': 0.13445378151260504, 'f1': 0.15609756097560976, 'number': 119} | {'precision': 0.7309377738825592, 'recall': 0.7830985915492957, 'f1': 0.7561196736174071, 'number': 1065} | 0.6724 | 0.7496 | 0.7089 | 0.7808 |
64
+ | 0.5219 | 7.0 | 70 | 0.6749 | {'precision': 0.6618257261410788, 'recall': 0.788627935723115, 'f1': 0.7196841511562324, 'number': 809} | {'precision': 0.2066115702479339, 'recall': 0.21008403361344538, 'f1': 0.20833333333333334, 'number': 119} | {'precision': 0.726649528706084, 'recall': 0.7962441314553991, 'f1': 0.7598566308243728, 'number': 1065} | 0.6710 | 0.7582 | 0.7119 | 0.7955 |
65
+ | 0.4628 | 8.0 | 80 | 0.6588 | {'precision': 0.6902465166130761, 'recall': 0.796044499381953, 'f1': 0.7393800229621125, 'number': 809} | {'precision': 0.2608695652173913, 'recall': 0.25210084033613445, 'f1': 0.2564102564102564, 'number': 119} | {'precision': 0.7422852376980817, 'recall': 0.8356807511737089, 'f1': 0.7862190812720848, 'number': 1065} | 0.6960 | 0.7847 | 0.7377 | 0.8061 |
66
+ | 0.4095 | 9.0 | 90 | 0.6676 | {'precision': 0.6787941787941788, 'recall': 0.8071693448702101, 'f1': 0.7374364765669114, 'number': 809} | {'precision': 0.29357798165137616, 'recall': 0.2689075630252101, 'f1': 0.28070175438596495, 'number': 119} | {'precision': 0.769163763066202, 'recall': 0.8291079812206573, 'f1': 0.7980117487573429, 'number': 1065} | 0.7066 | 0.7868 | 0.7445 | 0.8060 |
67
+ | 0.3940 | 10.0 | 100 | 0.6780 | {'precision': 0.7039473684210527, 'recall': 0.7935723114956736, 'f1': 0.7460778617083091, 'number': 809} | {'precision': 0.288135593220339, 'recall': 0.2857142857142857, 'f1': 0.2869198312236287, 'number': 119} | {'precision': 0.7744165946413137, 'recall': 0.8413145539906103, 'f1': 0.8064806480648066, 'number': 1065} | 0.7188 | 0.7888 | 0.7522 | 0.8091 |
68
+ | 0.3427 | 11.0 | 110 | 0.6791 | {'precision': 0.7005347593582888, 'recall': 0.8096415327564895, 'f1': 0.7511467889908257, 'number': 809} | {'precision': 0.24025974025974026, 'recall': 0.31092436974789917, 'f1': 0.2710622710622711, 'number': 119} | {'precision': 0.7715780296425457, 'recall': 0.8309859154929577, 'f1': 0.8001808318264014, 'number': 1065} | 0.7053 | 0.7913 | 0.7458 | 0.8075 |
69
+ | 0.3233 | 12.0 | 120 | 0.6765 | {'precision': 0.6941176470588235, 'recall': 0.8022249690976514, 'f1': 0.7442660550458714, 'number': 809} | {'precision': 0.27049180327868855, 'recall': 0.2773109243697479, 'f1': 0.27385892116182575, 'number': 119} | {'precision': 0.7831111111111111, 'recall': 0.8272300469483568, 'f1': 0.8045662100456622, 'number': 1065} | 0.7163 | 0.7842 | 0.7487 | 0.8096 |
70
+ | 0.3056 | 13.0 | 130 | 0.6867 | {'precision': 0.6944745395449621, 'recall': 0.792336217552534, 'f1': 0.7401847575057737, 'number': 809} | {'precision': 0.2702702702702703, 'recall': 0.33613445378151263, 'f1': 0.299625468164794, 'number': 119} | {'precision': 0.7764192139737991, 'recall': 0.8347417840375587, 'f1': 0.8045248868778281, 'number': 1065} | 0.7085 | 0.7878 | 0.7460 | 0.8108 |
71
+ | 0.2898 | 14.0 | 140 | 0.6837 | {'precision': 0.6989130434782609, 'recall': 0.7948084054388134, 'f1': 0.7437825332562175, 'number': 809} | {'precision': 0.2887323943661972, 'recall': 0.3445378151260504, 'f1': 0.31417624521072796, 'number': 119} | {'precision': 0.7856510186005314, 'recall': 0.8328638497652582, 'f1': 0.8085688240656335, 'number': 1065} | 0.7170 | 0.7883 | 0.7510 | 0.8110 |
72
+ | 0.2827 | 15.0 | 150 | 0.6849 | {'precision': 0.7012987012987013, 'recall': 0.8009888751545118, 'f1': 0.7478361223312175, 'number': 809} | {'precision': 0.2949640287769784, 'recall': 0.3445378151260504, 'f1': 0.31782945736434104, 'number': 119} | {'precision': 0.7841918294849023, 'recall': 0.8291079812206573, 'f1': 0.8060246462802373, 'number': 1065} | 0.7181 | 0.7888 | 0.7518 | 0.8109 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 5.7.0
78
+ - Pytorch 2.10.0+cu128
79
+ - Datasets 4.0.0
80
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eff32bdd2dbbafdc9fdc9b73c51aac34153aa06c9460f5bfa4552ac80d4d46d
3
  size 450558212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1153ebd09ab95a9cd65c68a2a87d4ac61194e258ee00aaa92803e6755e27b104
3
  size 450558212
processor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "apply_ocr": false,
4
+ "do_resize": true,
5
+ "image_processor_type": "LayoutLMv2ImageProcessor",
6
+ "resample": 2,
7
+ "size": {
8
+ "height": 224,
9
+ "width": 224
10
+ },
11
+ "tesseract_config": ""
12
+ },
13
+ "processor_class": "LayoutLMv2Processor"
14
+ }
runs/May02_20-15-42_81b4d1914131/events.out.tfevents.1777752942.81b4d1914131.4120.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f786d03e3d4afc4b18fc761240066dafa58b59802bf68e0a79c8bb5b1197eb39
3
- size 14582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e552f68045fc522695f7b9b02e94530c9d7b019ff83fce82d84c0cc4be66ae63
3
+ size 15651
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "backend": "tokenizers",
4
+ "cls_token": "[CLS]",
5
+ "cls_token_box": [
6
+ 0,
7
+ 0,
8
+ 0,
9
+ 0
10
+ ],
11
+ "do_lower_case": true,
12
+ "is_local": false,
13
+ "local_files_only": false,
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 512,
16
+ "only_label_first_subword": true,
17
+ "pad_token": "[PAD]",
18
+ "pad_token_box": [
19
+ 0,
20
+ 0,
21
+ 0,
22
+ 0
23
+ ],
24
+ "pad_token_label": -100,
25
+ "processor_class": "LayoutLMv2Processor",
26
+ "sep_token": "[SEP]",
27
+ "sep_token_box": [
28
+ 1000,
29
+ 1000,
30
+ 1000,
31
+ 1000
32
+ ],
33
+ "strip_accents": null,
34
+ "tokenize_chinese_chars": true,
35
+ "tokenizer_class": "LayoutLMv2Tokenizer",
36
+ "unk_token": "[UNK]"
37
+ }