Hugging Face's logo

rajistics
/
layoutlmv3-finetuned-cord_500

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
rajistics commited on
Commit
8d690de
·
1 Parent(s): aa37588

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - cord-layoutlmv3
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: layoutlmv3-finetuned-cord_500
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: cord-layoutlmv3
20
+ type: cord-layoutlmv3
21
+ config: cord
22
+ split: train
23
+ args: cord
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.9509293680297398
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9573353293413174
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9541215964192465
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9609507640067911
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # layoutlmv3-finetuned-cord_500
43
+
44
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.2339
47
+ - Precision: 0.9509
48
+ - Recall: 0.9573
49
+ - F1: 0.9541
50
+ - Accuracy: 0.9610
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 1e-05
70
+ - train_batch_size: 5
71
+ - eval_batch_size: 5
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - training_steps: 4000
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 2.5 | 250 | 0.9950 | 0.7114 | 0.7784 | 0.7434 | 0.7903 |
82
+ | 1.3831 | 5.0 | 500 | 0.5152 | 0.8483 | 0.8787 | 0.8632 | 0.8816 |
83
+ | 1.3831 | 7.5 | 750 | 0.3683 | 0.9013 | 0.9154 | 0.9083 | 0.9240 |
84
+ | 0.3551 | 10.0 | 1000 | 0.3051 | 0.9201 | 0.9304 | 0.9252 | 0.9363 |
85
+ | 0.3551 | 12.5 | 1250 | 0.2636 | 0.9375 | 0.9424 | 0.9399 | 0.9457 |
86
+ | 0.1562 | 15.0 | 1500 | 0.2498 | 0.9385 | 0.9476 | 0.9430 | 0.9508 |
87
+ | 0.1562 | 17.5 | 1750 | 0.2380 | 0.9414 | 0.9499 | 0.9456 | 0.9559 |
88
+ | 0.0863 | 20.0 | 2000 | 0.2355 | 0.9400 | 0.9491 | 0.9445 | 0.9542 |
89
+ | 0.0863 | 22.5 | 2250 | 0.2268 | 0.9451 | 0.9536 | 0.9493 | 0.9601 |
90
+ | 0.0512 | 25.0 | 2500 | 0.2277 | 0.9429 | 0.9513 | 0.9471 | 0.9588 |
91
+ | 0.0512 | 27.5 | 2750 | 0.2315 | 0.9473 | 0.9551 | 0.9512 | 0.9593 |
92
+ | 0.0358 | 30.0 | 3000 | 0.2294 | 0.9509 | 0.9573 | 0.9541 | 0.9605 |
93
+ | 0.0358 | 32.5 | 3250 | 0.2330 | 0.9458 | 0.9543 | 0.9501 | 0.9593 |
94
+ | 0.028 | 35.0 | 3500 | 0.2374 | 0.9487 | 0.9558 | 0.9523 | 0.9597 |
95
+ | 0.028 | 37.5 | 3750 | 0.2374 | 0.9501 | 0.9558 | 0.9530 | 0.9593 |
96
+ | 0.0244 | 40.0 | 4000 | 0.2339 | 0.9509 | 0.9573 | 0.9541 | 0.9610 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.21.2
102
+ - Pytorch 1.12.1+cu113
103
+ - Datasets 2.4.0
104
+ - Tokenizers 0.12.1