Hugging Face's logo

pabloma09
/
layoutlm-funsd

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
pabloma09 commited on
Commit
d16d42c
·
1 Parent(s): 4989065

Training in progress, epoch 1

Browse files
Files changed (11) hide show
  1. README.md +81 -0
  2. config.json +44 -0
  3. logs/events.out.tfevents.1703150256.DESKTOP-HA84SVN.2677.0 +3 -0
  4. logs/events.out.tfevents.1703159383.DESKTOP-HA84SVN.4393.0 +3 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +14 -0
  7. special_tokens_map.json +37 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +80 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/layoutlm-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - funsd
8
+ model-index:
9
+ - name: layoutlm-funsd
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # layoutlm-funsd
17
+
18
+ This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7001
21
+ - Answer: {'precision': 0.7016574585635359, 'recall': 0.7849196538936959, 'f1': 0.7409568261376897, 'number': 809}
22
+ - Header: {'precision': 0.3115942028985507, 'recall': 0.36134453781512604, 'f1': 0.3346303501945525, 'number': 119}
23
+ - Question: {'precision': 0.7809439002671416, 'recall': 0.8234741784037559, 'f1': 0.8016453382084096, 'number': 1065}
24
+ - Overall Precision: 0.7179
25
+ - Overall Recall: 0.7802
26
+ - Overall F1: 0.7478
27
+ - Overall Accuracy: 0.8048
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 3e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 15
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
59
+ | 1.7703 | 1.0 | 10 | 1.5577 | {'precision': 0.02032913843175218, 'recall': 0.02595797280593325, 'f1': 0.02280130293159609, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.1728395061728395, 'recall': 0.17089201877934274, 'f1': 0.17186024551463644, 'number': 1065} | 0.0973 | 0.1019 | 0.0995 | 0.3886 |
60
+ | 1.3909 | 2.0 | 20 | 1.1804 | {'precision': 0.2391304347826087, 'recall': 0.20395550061804696, 'f1': 0.22014676450967313, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4996186117467582, 'recall': 0.6150234741784038, 'f1': 0.5513468013468013, 'number': 1065} | 0.4098 | 0.4114 | 0.4106 | 0.6136 |
61
+ | 1.045 | 3.0 | 30 | 0.9199 | {'precision': 0.5039018952062431, 'recall': 0.5587144622991347, 'f1': 0.5298944900351701, 'number': 809} | {'precision': 0.025, 'recall': 0.008403361344537815, 'f1': 0.012578616352201259, 'number': 119} | {'precision': 0.5976095617529881, 'recall': 0.704225352112676, 'f1': 0.6465517241379312, 'number': 1065} | 0.5488 | 0.6036 | 0.5749 | 0.7203 |
62
+ | 0.7906 | 4.0 | 40 | 0.7703 | {'precision': 0.6037735849056604, 'recall': 0.7119901112484549, 'f1': 0.6534316505955757, 'number': 809} | {'precision': 0.20833333333333334, 'recall': 0.12605042016806722, 'f1': 0.15706806282722513, 'number': 119} | {'precision': 0.6666666666666666, 'recall': 0.7812206572769953, 'f1': 0.719412019022914, 'number': 1065} | 0.6258 | 0.7140 | 0.6670 | 0.7687 |
63
+ | 0.635 | 5.0 | 50 | 0.7374 | {'precision': 0.6146179401993356, 'recall': 0.6860321384425216, 'f1': 0.6483644859813085, 'number': 809} | {'precision': 0.2976190476190476, 'recall': 0.21008403361344538, 'f1': 0.24630541871921183, 'number': 119} | {'precision': 0.6959349593495935, 'recall': 0.8037558685446009, 'f1': 0.7459694989106754, 'number': 1065} | 0.6477 | 0.7205 | 0.6822 | 0.7712 |
64
+ | 0.5475 | 6.0 | 60 | 0.6925 | {'precision': 0.6453305351521511, 'recall': 0.7601977750309024, 'f1': 0.6980703745743474, 'number': 809} | {'precision': 0.2542372881355932, 'recall': 0.25210084033613445, 'f1': 0.25316455696202533, 'number': 119} | {'precision': 0.7153589315525877, 'recall': 0.8046948356807512, 'f1': 0.7574016791869199, 'number': 1065} | 0.6620 | 0.7536 | 0.7048 | 0.7865 |
65
+ | 0.4876 | 7.0 | 70 | 0.6876 | {'precision': 0.649740932642487, 'recall': 0.7750309023485785, 'f1': 0.7068771138669674, 'number': 809} | {'precision': 0.26732673267326734, 'recall': 0.226890756302521, 'f1': 0.24545454545454548, 'number': 119} | {'precision': 0.7449249779346867, 'recall': 0.7924882629107981, 'f1': 0.7679708826205641, 'number': 1065} | 0.6812 | 0.7516 | 0.7147 | 0.7952 |
66
+ | 0.4438 | 8.0 | 80 | 0.6672 | {'precision': 0.6842684268426843, 'recall': 0.7688504326328801, 'f1': 0.7240977881257276, 'number': 809} | {'precision': 0.26717557251908397, 'recall': 0.29411764705882354, 'f1': 0.28, 'number': 119} | {'precision': 0.7534602076124568, 'recall': 0.8178403755868544, 'f1': 0.7843313822602431, 'number': 1065} | 0.6958 | 0.7667 | 0.7295 | 0.8040 |
67
+ | 0.3708 | 9.0 | 90 | 0.6684 | {'precision': 0.6832779623477298, 'recall': 0.7626699629171817, 'f1': 0.7207943925233644, 'number': 809} | {'precision': 0.2549019607843137, 'recall': 0.3277310924369748, 'f1': 0.286764705882353, 'number': 119} | {'precision': 0.7547660311958405, 'recall': 0.8178403755868544, 'f1': 0.7850383055430372, 'number': 1065} | 0.6910 | 0.7662 | 0.7266 | 0.8003 |
68
+ | 0.3433 | 10.0 | 100 | 0.6779 | {'precision': 0.6833514689880305, 'recall': 0.7762669962917181, 'f1': 0.7268518518518517, 'number': 809} | {'precision': 0.29411764705882354, 'recall': 0.29411764705882354, 'f1': 0.29411764705882354, 'number': 119} | {'precision': 0.7772887323943662, 'recall': 0.8291079812206573, 'f1': 0.8023625624716039, 'number': 1065} | 0.7111 | 0.7757 | 0.7420 | 0.8084 |
69
+ | 0.3173 | 11.0 | 110 | 0.6856 | {'precision': 0.6939890710382514, 'recall': 0.7849196538936959, 'f1': 0.7366589327146172, 'number': 809} | {'precision': 0.3089430894308943, 'recall': 0.31932773109243695, 'f1': 0.3140495867768595, 'number': 119} | {'precision': 0.7876895628902766, 'recall': 0.8291079812206573, 'f1': 0.807868252516011, 'number': 1065} | 0.7207 | 0.7807 | 0.7495 | 0.8103 |
70
+ | 0.2951 | 12.0 | 120 | 0.6854 | {'precision': 0.6961883408071748, 'recall': 0.7676143386897404, 'f1': 0.7301587301587301, 'number': 809} | {'precision': 0.2986111111111111, 'recall': 0.36134453781512604, 'f1': 0.32699619771863114, 'number': 119} | {'precision': 0.7908438061041293, 'recall': 0.8272300469483568, 'f1': 0.8086278109224414, 'number': 1065} | 0.7186 | 0.7752 | 0.7458 | 0.8061 |
71
+ | 0.2819 | 13.0 | 130 | 0.6966 | {'precision': 0.6995661605206074, 'recall': 0.7972805933250927, 'f1': 0.7452339688041594, 'number': 809} | {'precision': 0.3, 'recall': 0.35294117647058826, 'f1': 0.3243243243243243, 'number': 119} | {'precision': 0.7793594306049823, 'recall': 0.8225352112676056, 'f1': 0.8003654636820466, 'number': 1065} | 0.7150 | 0.7842 | 0.7480 | 0.8056 |
72
+ | 0.2653 | 14.0 | 140 | 0.7000 | {'precision': 0.6970033296337403, 'recall': 0.7762669962917181, 'f1': 0.7345029239766083, 'number': 809} | {'precision': 0.30714285714285716, 'recall': 0.36134453781512604, 'f1': 0.33204633204633205, 'number': 119} | {'precision': 0.7908025247971145, 'recall': 0.8234741784037559, 'f1': 0.8068077276908925, 'number': 1065} | 0.72 | 0.7767 | 0.7473 | 0.8057 |
73
+ | 0.2662 | 15.0 | 150 | 0.7001 | {'precision': 0.7016574585635359, 'recall': 0.7849196538936959, 'f1': 0.7409568261376897, 'number': 809} | {'precision': 0.3115942028985507, 'recall': 0.36134453781512604, 'f1': 0.3346303501945525, 'number': 119} | {'precision': 0.7809439002671416, 'recall': 0.8234741784037559, 'f1': 0.8016453382084096, 'number': 1065} | 0.7179 | 0.7802 | 0.7478 | 0.8048 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.36.2
79
+ - Pytorch 2.1.2
80
+ - Datasets 2.15.0
81
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlm-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-HEADER",
13
+ "2": "I-HEADER",
14
+ "3": "B-QUESTION",
15
+ "4": "I-QUESTION",
16
+ "5": "B-ANSWER",
17
+ "6": "I-ANSWER"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "B-ANSWER": 5,
23
+ "B-HEADER": 1,
24
+ "B-QUESTION": 3,
25
+ "I-ANSWER": 6,
26
+ "I-HEADER": 2,
27
+ "I-QUESTION": 4,
28
+ "O": 0
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_2d_position_embeddings": 1024,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "layoutlm",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 30522
44
+ }
logs/events.out.tfevents.1703150256.DESKTOP-HA84SVN.2677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1a510b8c50e11a9e5eb6e5ad5c6ed817c4f57789f42b042fc901e77bf3a3e4
3
+ size 14729
logs/events.out.tfevents.1703159383.DESKTOP-HA84SVN.4393.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2628a267a12b9973619b2797a3664f7f5465c6050312a7f89e66eef9965fed9b
3
+ size 5253
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b72efb027050fa918cc60dc88f028aa13913352a9a59485310c9227ef76193
3
+ size 450558212
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "LayoutLMv2FeatureExtractor",
5
+ "image_processor_type": "LayoutLMv2ImageProcessor",
6
+ "ocr_lang": null,
7
+ "processor_class": "LayoutLMv2Processor",
8
+ "resample": 2,
9
+ "size": {
10
+ "height": 224,
11
+ "width": 224
12
+ },
13
+ "tesseract_config": ""
14
+ }
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 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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
+ "mask_token": "[MASK]",
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv2Processor",
69
+ "sep_token": "[SEP]",
70
+ "sep_token_box": [
71
+ 1000,
72
+ 1000,
73
+ 1000,
74
+ 1000
75
+ ],
76
+ "strip_accents": null,
77
+ "tokenize_chinese_chars": true,
78
+ "tokenizer_class": "LayoutLMv2Tokenizer",
79
+ "unk_token": "[UNK]"
80
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496cdc98bd97b69e26b61b75e57108b3ab8f568934ff5478c2cab003032ae00d
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff