Hugging Face's logo

FrancisAnth
/
layoutlm-funsd

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Model card Files
xet
Metrics Community
FrancisAnth commited on
Commit
09b2e52
·
verified ·
1 Parent(s): 6ba85ba

End of training

Browse files
Files changed (7) hide show
  1. README.md +82 -0
  2. logs/events.out.tfevents.1738598697.4aff30dc3aef.1894.0 +2 -2
  3. preprocessor_config.json +13 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +81 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/layoutlm-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - funsd
9
+ model-index:
10
+ - name: layoutlm-funsd
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # layoutlm-funsd
18
+
19
+ This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7082
22
+ - Answer: {'precision': 0.7248322147651006, 'recall': 0.8009888751545118, 'f1': 0.7610099823840282, 'number': 809}
23
+ - Header: {'precision': 0.2962962962962963, 'recall': 0.33613445378151263, 'f1': 0.31496062992125984, 'number': 119}
24
+ - Question: {'precision': 0.7685589519650655, 'recall': 0.8262910798122066, 'f1': 0.7963800904977376, 'number': 1065}
25
+ - Overall Precision: 0.7213
26
+ - Overall Recall: 0.7868
27
+ - Overall F1: 0.7526
28
+ - Overall Accuracy: 0.8029
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 15
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
60
+ | 1.8006 | 1.0 | 10 | 1.6139 | {'precision': 0.017793594306049824, 'recall': 0.018541409147095178, 'f1': 0.018159806295399518, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.17797552836484984, 'recall': 0.15023474178403756, 'f1': 0.1629327902240326, 'number': 1065} | 0.1005 | 0.0878 | 0.0937 | 0.3573 |
61
+ | 1.4765 | 2.0 | 20 | 1.2915 | {'precision': 0.10949720670391061, 'recall': 0.1211372064276885, 'f1': 0.11502347417840375, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.40053404539385845, 'recall': 0.5633802816901409, 'f1': 0.46820132657042524, 'number': 1065} | 0.2917 | 0.3502 | 0.3183 | 0.5594 |
62
+ | 1.1259 | 3.0 | 30 | 0.9621 | {'precision': 0.4625641025641026, 'recall': 0.5574783683559951, 'f1': 0.5056053811659192, 'number': 809} | {'precision': 0.03571428571428571, 'recall': 0.008403361344537815, 'f1': 0.013605442176870748, 'number': 119} | {'precision': 0.5056980056980057, 'recall': 0.6666666666666666, 'f1': 0.5751316322397733, 'number': 1065} | 0.4828 | 0.5830 | 0.5282 | 0.6918 |
63
+ | 0.8531 | 4.0 | 40 | 0.7812 | {'precision': 0.5848861283643892, 'recall': 0.6983930778739185, 'f1': 0.6366197183098592, 'number': 809} | {'precision': 0.06944444444444445, 'recall': 0.04201680672268908, 'f1': 0.052356020942408384, 'number': 119} | {'precision': 0.6385642737896494, 'recall': 0.7183098591549296, 'f1': 0.6760936809544852, 'number': 1065} | 0.5970 | 0.6698 | 0.6314 | 0.7585 |
64
+ | 0.6752 | 5.0 | 50 | 0.7226 | {'precision': 0.6356589147286822, 'recall': 0.7095179233621756, 'f1': 0.6705607476635514, 'number': 809} | {'precision': 0.20930232558139536, 'recall': 0.15126050420168066, 'f1': 0.17560975609756097, 'number': 119} | {'precision': 0.6551193225558122, 'recall': 0.7990610328638498, 'f1': 0.7199661590524534, 'number': 1065} | 0.6307 | 0.7240 | 0.6741 | 0.7734 |
65
+ | 0.5812 | 6.0 | 60 | 0.6909 | {'precision': 0.6659459459459459, 'recall': 0.761433868974042, 'f1': 0.7104959630911187, 'number': 809} | {'precision': 0.16822429906542055, 'recall': 0.15126050420168066, 'f1': 0.1592920353982301, 'number': 119} | {'precision': 0.723874256584537, 'recall': 0.8, 'f1': 0.7600356824264051, 'number': 1065} | 0.6727 | 0.7456 | 0.7073 | 0.7815 |
66
+ | 0.5108 | 7.0 | 70 | 0.6653 | {'precision': 0.6673728813559322, 'recall': 0.7787391841779975, 'f1': 0.7187678265830005, 'number': 809} | {'precision': 0.23636363636363636, 'recall': 0.2184873949579832, 'f1': 0.22707423580786026, 'number': 119} | {'precision': 0.727810650887574, 'recall': 0.8084507042253521, 'f1': 0.7660142348754447, 'number': 1065} | 0.6781 | 0.7612 | 0.7173 | 0.7966 |
67
+ | 0.451 | 8.0 | 80 | 0.6639 | {'precision': 0.689989235737352, 'recall': 0.792336217552534, 'f1': 0.7376294591484466, 'number': 809} | {'precision': 0.23214285714285715, 'recall': 0.2184873949579832, 'f1': 0.22510822510822512, 'number': 119} | {'precision': 0.7385398981324278, 'recall': 0.8169014084507042, 'f1': 0.7757467677218011, 'number': 1065} | 0.6927 | 0.7712 | 0.7298 | 0.7994 |
68
+ | 0.3912 | 9.0 | 90 | 0.6756 | {'precision': 0.6998880179171333, 'recall': 0.7725587144622992, 'f1': 0.7344300822561693, 'number': 809} | {'precision': 0.26865671641791045, 'recall': 0.3025210084033613, 'f1': 0.2845849802371542, 'number': 119} | {'precision': 0.7476149176062445, 'recall': 0.8093896713615023, 'f1': 0.7772768259693417, 'number': 1065} | 0.6986 | 0.7642 | 0.7299 | 0.7965 |
69
+ | 0.3826 | 10.0 | 100 | 0.6725 | {'precision': 0.7037037037037037, 'recall': 0.7985166872682324, 'f1': 0.7481181239143023, 'number': 809} | {'precision': 0.2782608695652174, 'recall': 0.2689075630252101, 'f1': 0.2735042735042735, 'number': 119} | {'precision': 0.7555938037865749, 'recall': 0.8244131455399061, 'f1': 0.7885047148630445, 'number': 1065} | 0.7089 | 0.7807 | 0.7431 | 0.8015 |
70
+ | 0.3211 | 11.0 | 110 | 0.6932 | {'precision': 0.7253121452894438, 'recall': 0.7898640296662547, 'f1': 0.7562130177514793, 'number': 809} | {'precision': 0.29411764705882354, 'recall': 0.33613445378151263, 'f1': 0.3137254901960785, 'number': 119} | {'precision': 0.7652173913043478, 'recall': 0.8262910798122066, 'f1': 0.7945823927765238, 'number': 1065} | 0.7194 | 0.7822 | 0.7495 | 0.7991 |
71
+ | 0.3043 | 12.0 | 120 | 0.6975 | {'precision': 0.7150776053215078, 'recall': 0.7972805933250927, 'f1': 0.7539450613676213, 'number': 809} | {'precision': 0.3089430894308943, 'recall': 0.31932773109243695, 'f1': 0.3140495867768595, 'number': 119} | {'precision': 0.7671353251318102, 'recall': 0.819718309859155, 'f1': 0.7925556059918293, 'number': 1065} | 0.7194 | 0.7807 | 0.7488 | 0.8012 |
72
+ | 0.2903 | 13.0 | 130 | 0.7007 | {'precision': 0.7277777777777777, 'recall': 0.8096415327564895, 'f1': 0.7665301345816268, 'number': 809} | {'precision': 0.2992125984251969, 'recall': 0.31932773109243695, 'f1': 0.30894308943089427, 'number': 119} | {'precision': 0.7724077328646749, 'recall': 0.8253521126760563, 'f1': 0.7980027235587837, 'number': 1065} | 0.7261 | 0.7888 | 0.7561 | 0.8036 |
73
+ | 0.2664 | 14.0 | 140 | 0.7039 | {'precision': 0.7352941176470589, 'recall': 0.8034610630407911, 'f1': 0.7678676904902539, 'number': 809} | {'precision': 0.3, 'recall': 0.3277310924369748, 'f1': 0.3132530120481928, 'number': 119} | {'precision': 0.7682926829268293, 'recall': 0.828169014084507, 'f1': 0.7971079981924988, 'number': 1065} | 0.7266 | 0.7883 | 0.7562 | 0.8036 |
74
+ | 0.2683 | 15.0 | 150 | 0.7082 | {'precision': 0.7248322147651006, 'recall': 0.8009888751545118, 'f1': 0.7610099823840282, 'number': 809} | {'precision': 0.2962962962962963, 'recall': 0.33613445378151263, 'f1': 0.31496062992125984, 'number': 119} | {'precision': 0.7685589519650655, 'recall': 0.8262910798122066, 'f1': 0.7963800904977376, 'number': 1065} | 0.7213 | 0.7868 | 0.7526 | 0.8029 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.47.1
80
+ - Pytorch 2.5.1+cu124
81
+ - Datasets 3.2.0
82
+ - Tokenizers 0.21.0
logs/events.out.tfevents.1738598697.4aff30dc3aef.1894.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77a31f34065af4a0e64c386ec1743f9270e08f3ad1497999d62d13739a430afa
3
- size 15150
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0879af658443f7b37bdbee126c6bc84b4cdeadee1a6d54b9a0515fa443b05214
3
+ size 16219
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "image_processor_type": "LayoutLMv2ImageProcessor",
5
+ "ocr_lang": null,
6
+ "processor_class": "LayoutLMv2Processor",
7
+ "resample": 2,
8
+ "size": {
9
+ "height": 224,
10
+ "width": 224
11
+ },
12
+ "tesseract_config": ""
13
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "apply_ocr": false,
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "[CLS]",
48
+ "cls_token_box": [
49
+ 0,
50
+ 0,
51
+ 0,
52
+ 0
53
+ ],
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": true,
56
+ "extra_special_tokens": {},
57
+ "mask_token": "[MASK]",
58
+ "model_max_length": 512,
59
+ "never_split": null,
60
+ "only_label_first_subword": true,
61
+ "pad_token": "[PAD]",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
69
+ "processor_class": "LayoutLMv2Processor",
70
+ "sep_token": "[SEP]",
71
+ "sep_token_box": [
72
+ 1000,
73
+ 1000,
74
+ 1000,
75
+ 1000
76
+ ],
77
+ "strip_accents": null,
78
+ "tokenize_chinese_chars": true,
79
+ "tokenizer_class": "LayoutLMv2Tokenizer",
80
+ "unk_token": "[UNK]"
81
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff