Hugging Face's logo

pierreguillou
/
layout-xlm-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv2
object-detection
vision
Generated from Trainer
DocLayNet
LayoutXLM
COCO
PDF
IBM
Financial-Reports
Finance
Manuals
Scientific-Articles
Science
Laws
Law
Regulations
Patents
Government-Tenders
image-segmentation
Eval Results
Model card Files Metrics Community
1
pierreguillou commited on
Commit
3e240d7
·
1 Parent(s): 988833c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: layout-xlm-base-finetuned-DocLayNet-base_paragraphs_ml512-v6
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # layout-xlm-base-finetuned-DocLayNet-base_paragraphs_ml512-v6
19
+
20
+ This model is a fine-tuned version of [microsoft/layoutxlm-base](https://huggingface.co/microsoft/layoutxlm-base) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1796
23
+ - Precision: 0.8062
24
+ - Recall: 0.7441
25
+ - F1: 0.7739
26
+ - Accuracy: 0.9693
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: 2e-05
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 4
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
58
+ |:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|:---------:|:------:|
59
+ | No log | 0.11 | 200 | 0.8842 | 0.1066 | 0.4428 | 0.1154 | 0.0991 |
60
+ | No log | 0.21 | 400 | 0.9243 | 0.4440 | 0.3040 | 0.4548 | 0.4336 |
61
+ | 0.7241 | 0.32 | 600 | 0.9359 | 0.5544 | 0.2265 | 0.5330 | 0.5775 |
62
+ | 0.7241 | 0.43 | 800 | 0.9479 | 0.6015 | 0.2140 | 0.6013 | 0.6017 |
63
+ | 0.2343 | 0.53 | 1000 | 0.9402 | 0.6132 | 0.2852 | 0.6642 | 0.5695 |
64
+ | 0.2343 | 0.64 | 1200 | 0.9540 | 0.6604 | 0.1694 | 0.6565 | 0.6644 |
65
+ | 0.2343 | 0.75 | 1400 | 0.9354 | 0.6198 | 0.2308 | 0.5119 | 0.7854 |
66
+ | 0.1913 | 0.85 | 1600 | 0.9594 | 0.6590 | 0.1601 | 0.7190 | 0.6082 |
67
+ | 0.1913 | 0.96 | 1800 | 0.9541 | 0.6597 | 0.1671 | 0.5790 | 0.7664 |
68
+ | 0.1346 | 1.07 | 2000 | 0.9612 | 0.6986 | 0.1580 | 0.6838 | 0.7140 |
69
+ | 0.1346 | 1.17 | 2200 | 0.9597 | 0.6897 | 0.1423 | 0.6618 | 0.7200 |
70
+ | 0.1346 | 1.28 | 2400 | 0.9663 | 0.6980 | 0.1580 | 0.7490 | 0.6535 |
71
+ | 0.098 | 1.39 | 2600 | 0.9616 | 0.6800 | 0.1394 | 0.7044 | 0.6573 |
72
+ | 0.098 | 1.49 | 2800 | 0.9686 | 0.7251 | 0.1756 | 0.6893 | 0.7649 |
73
+ | 0.0999 | 1.6 | 3000 | 0.9636 | 0.6985 | 0.1542 | 0.7127 | 0.6848 |
74
+ | 0.0999 | 1.71 | 3200 | 0.9670 | 0.7097 | 0.1187 | 0.7538 | 0.6705 |
75
+ | 0.0999 | 1.81 | 3400 | 0.9585 | 0.7427 | 0.1793 | 0.7602 | 0.7260 |
76
+ | 0.0972 | 1.92 | 3600 | 0.9621 | 0.7189 | 0.1836 | 0.7576 | 0.6839 |
77
+ | 0.0972 | 2.03 | 3800 | 0.9642 | 0.7189 | 0.1465 | 0.7388 | 0.6999 |
78
+ | 0.0662 | 2.13 | 4000 | 0.9691 | 0.7450 | 0.1409 | 0.7615 | 0.7292 |
79
+ | 0.0662 | 2.24 | 4200 | 0.9615 | 0.7432 | 0.1720 | 0.7435 | 0.7429 |
80
+ | 0.0662 | 2.35 | 4400 | 0.9667 | 0.7338 | 0.1440 | 0.7469 | 0.7212 |
81
+ | 0.0581 | 2.45 | 4600 | 0.9657 | 0.7135 | 0.1928 | 0.7458 | 0.6839 |
82
+ | 0.0581 | 2.56 | 4800 | 0.9692 | 0.7378 | 0.1645 | 0.7467 | 0.7292 |
83
+ | 0.0538 | 2.67 | 5000 | 0.9656 | 0.7619 | 0.1517 | 0.7700 | 0.7541 |
84
+ | 0.0538 | 2.77 | 5200 | 0.9684 | 0.7728 | 0.1676 | 0.8227 | 0.7286 |
85
+ | 0.0538 | 2.88 | 5400 | 0.9725 | 0.7608 | 0.1277 | 0.7865 | 0.7367 |
86
+ | 0.0432 | 2.99 | 5600 | 0.9693 | 0.7784 | 0.1532 | 0.7891 | 0.7681 |
87
+ | 0.0432 | 3.09 | 5800 | 0.9692 | 0.7783 | 0.1701 | 0.8067 | 0.7519 |
88
+ | 0.0272 | 3.2 | 6000 | 0.9732 | 0.7798 | 0.1159 | 0.8072 | 0.7542 |
89
+ | 0.0272 | 3.3 | 6200 | 0.9720 | 0.7797 | 0.1835 | 0.7926 | 0.7672 |
90
+ | 0.0272 | 3.41 | 6400 | 0.9730 | 0.7894 | 0.1481 | 0.8183 | 0.7624 |
91
+ | 0.0274 | 3.52 | 6600 | 0.9686 | 0.7655 | 0.1552 | 0.7958 | 0.7373 |
92
+ | 0.0274 | 3.62 | 6800 | 0.9698 | 0.7724 | 0.1523 | 0.8068 | 0.7407 |
93
+ | 0.0246 | 3.73 | 7000 | 0.9691 | 0.7720 | 0.1673 | 0.7960 | 0.7493 |
94
+ | 0.0246 | 3.84 | 7200 | 0.9688 | 0.7695 | 0.1333 | 0.7986 | 0.7424 |
95
+ | 0.0246 | 3.94 | 7400 | 0.1796 | 0.8062 | 0.7441 | 0.7739 | 0.9693 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.27.3
101
+ - Pytorch 1.10.0+cu111
102
+ - Datasets 2.10.1
103
+ - Tokenizers 0.13.2