Hugging Face's logo

sxandie
/
nexon_jan_2023

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
sxandie commited on
Commit
62e4dde
•
1 Parent(s): bf01c2b

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
+ datasets:
6
+ - sroie
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: nexon_jan_2023
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: sroie
20
+ type: sroie
21
+ config: discharge
22
+ split: test
23
+ args: discharge
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.975609756097561
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9302325581395349
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9523809523809524
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9971428571428571
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
+ # nexon_jan_2023
43
+
44
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the sroie dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.0380
47
+ - Precision: 0.9756
48
+ - Recall: 0.9302
49
+ - F1: 0.9524
50
+ - Accuracy: 0.9971
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: 2
71
+ - eval_batch_size: 2
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - training_steps: 1500
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 16.67 | 100 | 0.1998 | 0.6286 | 0.5116 | 0.5641 | 0.9571 |
82
+ | No log | 33.33 | 200 | 0.0616 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
83
+ | No log | 50.0 | 300 | 0.0439 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
84
+ | No log | 66.67 | 400 | 0.0404 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
85
+ | 0.1151 | 83.33 | 500 | 0.0389 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
86
+ | 0.1151 | 100.0 | 600 | 0.0380 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
87
+ | 0.1151 | 116.67 | 700 | 0.0378 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
88
+ | 0.1151 | 133.33 | 800 | 0.0379 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
89
+ | 0.1151 | 150.0 | 900 | 0.0378 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
90
+ | 0.009 | 166.67 | 1000 | 0.0378 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
91
+ | 0.009 | 183.33 | 1100 | 0.0378 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
92
+ | 0.009 | 200.0 | 1200 | 0.0379 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
93
+ | 0.009 | 216.67 | 1300 | 0.0379 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
94
+ | 0.009 | 233.33 | 1400 | 0.0379 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
95
+ | 0.0064 | 250.0 | 1500 | 0.0380 | 0.9756 | 0.9302 | 0.9524 | 0.9971 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.27.0.dev0
101
+ - Pytorch 1.13.1+cu116
102
+ - Datasets 2.2.2
103
+ - Tokenizers 0.13.2