jpino commited on
Commit
4facc45
1 Parent(s): 84b1d2f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - data_cedulas_layoutv3
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: layoutlmv3-finetuned-cedulas_v3
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: data_cedulas_layoutv3
20
+ type: data_cedulas_layoutv3
21
+ config: default
22
+ split: test
23
+ args: default
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.8991596638655462
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9067796610169492
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9029535864978903
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9816565809379728
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-cedulas_v3
43
+
44
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the data_cedulas_layoutv3 dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.0832
47
+ - Precision: 0.8992
48
+ - Recall: 0.9068
49
+ - F1: 0.9030
50
+ - Accuracy: 0.9817
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: 5e-06
70
+ - train_batch_size: 4
71
+ - eval_batch_size: 4
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - training_steps: 2500
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 3.12 | 250 | 0.7409 | 0.2850 | 0.2729 | 0.2788 | 0.8614 |
82
+ | 0.9048 | 6.25 | 500 | 0.3660 | 0.6222 | 0.6559 | 0.6386 | 0.9393 |
83
+ | 0.9048 | 9.38 | 750 | 0.2132 | 0.7492 | 0.7593 | 0.7542 | 0.9544 |
84
+ | 0.2923 | 12.5 | 1000 | 0.1467 | 0.7830 | 0.7949 | 0.7889 | 0.9661 |
85
+ | 0.2923 | 15.62 | 1250 | 0.1172 | 0.8114 | 0.8237 | 0.8175 | 0.9701 |
86
+ | 0.1445 | 18.75 | 1500 | 0.1013 | 0.8560 | 0.8763 | 0.8660 | 0.9766 |
87
+ | 0.1445 | 21.88 | 1750 | 0.0952 | 0.8811 | 0.8915 | 0.8863 | 0.9794 |
88
+ | 0.0956 | 25.0 | 2000 | 0.0876 | 0.8923 | 0.8983 | 0.8953 | 0.9807 |
89
+ | 0.0956 | 28.12 | 2250 | 0.0840 | 0.9005 | 0.9051 | 0.9028 | 0.9811 |
90
+ | 0.0766 | 31.25 | 2500 | 0.0832 | 0.8992 | 0.9068 | 0.9030 | 0.9817 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.29.2
96
+ - Pytorch 2.0.1+cu118
97
+ - Datasets 2.12.0
98
+ - Tokenizers 0.13.3