Hugging Face's logo

ahishamm
/
vit-large-binary-isic-patch-32

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
ahishamm commited on
Commit
75ea51b
·
1 Parent(s): c080abb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - recall
8
+ - f1
9
+ - precision
10
+ model-index:
11
+ - name: vit-large-binary-isic-patch-32
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
+ # vit-large-binary-isic-patch-32
19
+
20
+ This model is a fine-tuned version of [google/vit-large-patch32-224-in21k](https://huggingface.co/google/vit-large-patch32-224-in21k) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4923
23
+ - Accuracy: 0.9059
24
+ - Recall: 0.9059
25
+ - F1: 0.9059
26
+ - Precision: 0.9059
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: 0.0002
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 4
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
57
+ | 0.3606 | 0.09 | 100 | 0.3225 | 0.8123 | 0.8123 | 0.8123 | 0.8123 |
58
+ | 0.2867 | 0.19 | 200 | 0.3654 | 0.8565 | 0.8565 | 0.8565 | 0.8565 |
59
+ | 0.3359 | 0.28 | 300 | 0.3051 | 0.8502 | 0.8502 | 0.8502 | 0.8502 |
60
+ | 0.2825 | 0.37 | 400 | 0.3576 | 0.8588 | 0.8588 | 0.8588 | 0.8588 |
61
+ | 0.2438 | 0.46 | 500 | 0.3043 | 0.8620 | 0.8620 | 0.8620 | 0.8620 |
62
+ | 0.1465 | 0.56 | 600 | 0.2791 | 0.8798 | 0.8798 | 0.8798 | 0.8798 |
63
+ | 0.2318 | 0.65 | 700 | 0.2816 | 0.8629 | 0.8629 | 0.8629 | 0.8629 |
64
+ | 0.1846 | 0.74 | 800 | 0.2479 | 0.8913 | 0.8913 | 0.8913 | 0.8913 |
65
+ | 0.1451 | 0.84 | 900 | 0.3232 | 0.8829 | 0.8829 | 0.8829 | 0.8829 |
66
+ | 0.1157 | 0.93 | 1000 | 0.2799 | 0.8767 | 0.8767 | 0.8767 | 0.8767 |
67
+ | 0.1175 | 1.02 | 1100 | 0.3236 | 0.8697 | 0.8697 | 0.8697 | 0.8697 |
68
+ | 0.2015 | 1.12 | 1200 | 0.3056 | 0.8706 | 0.8706 | 0.8706 | 0.8706 |
69
+ | 0.0627 | 1.21 | 1300 | 0.3160 | 0.8757 | 0.8757 | 0.8757 | 0.8757 |
70
+ | 0.0842 | 1.3 | 1400 | 0.3299 | 0.8908 | 0.8908 | 0.8908 | 0.8908 |
71
+ | 0.0617 | 1.39 | 1500 | 0.3353 | 0.8847 | 0.8847 | 0.8847 | 0.8847 |
72
+ | 0.1919 | 1.49 | 1600 | 0.3421 | 0.8630 | 0.8630 | 0.8630 | 0.8630 |
73
+ | 0.1212 | 1.58 | 1700 | 0.4301 | 0.8693 | 0.8693 | 0.8693 | 0.8693 |
74
+ | 0.1012 | 1.67 | 1800 | 0.3352 | 0.8799 | 0.8799 | 0.8799 | 0.8799 |
75
+ | 0.0622 | 1.77 | 1900 | 0.3272 | 0.8881 | 0.8881 | 0.8881 | 0.8881 |
76
+ | 0.0733 | 1.86 | 2000 | 0.2903 | 0.8867 | 0.8867 | 0.8867 | 0.8867 |
77
+ | 0.0293 | 1.95 | 2100 | 0.2772 | 0.9031 | 0.9031 | 0.9031 | 0.9031 |
78
+ | 0.0305 | 2.04 | 2200 | 0.3218 | 0.8929 | 0.8929 | 0.8929 | 0.8929 |
79
+ | 0.034 | 2.14 | 2300 | 0.4207 | 0.8915 | 0.8915 | 0.8915 | 0.8915 |
80
+ | 0.0113 | 2.23 | 2400 | 0.4193 | 0.8948 | 0.8948 | 0.8948 | 0.8948 |
81
+ | 0.0071 | 2.32 | 2500 | 0.4372 | 0.8908 | 0.8908 | 0.8908 | 0.8908 |
82
+ | 0.0074 | 2.42 | 2600 | 0.4253 | 0.9009 | 0.9009 | 0.9009 | 0.9009 |
83
+ | 0.079 | 2.51 | 2700 | 0.3814 | 0.9012 | 0.9012 | 0.9012 | 0.9012 |
84
+ | 0.0407 | 2.6 | 2800 | 0.3968 | 0.9071 | 0.9071 | 0.9071 | 0.9071 |
85
+ | 0.0096 | 2.7 | 2900 | 0.4318 | 0.9047 | 0.9047 | 0.9047 | 0.9047 |
86
+ | 0.052 | 2.79 | 3000 | 0.4112 | 0.8986 | 0.8986 | 0.8986 | 0.8986 |
87
+ | 0.0075 | 2.88 | 3100 | 0.4231 | 0.9021 | 0.9021 | 0.9021 | 0.9021 |
88
+ | 0.0183 | 2.97 | 3200 | 0.4106 | 0.8963 | 0.8963 | 0.8963 | 0.8963 |
89
+ | 0.0134 | 3.07 | 3300 | 0.4210 | 0.9031 | 0.9031 | 0.9031 | 0.9031 |
90
+ | 0.0387 | 3.16 | 3400 | 0.4336 | 0.9042 | 0.9042 | 0.9042 | 0.9042 |
91
+ | 0.001 | 3.25 | 3500 | 0.4679 | 0.8988 | 0.8988 | 0.8988 | 0.8988 |
92
+ | 0.0292 | 3.35 | 3600 | 0.4691 | 0.8976 | 0.8976 | 0.8976 | 0.8976 |
93
+ | 0.0109 | 3.44 | 3700 | 0.4713 | 0.9061 | 0.9061 | 0.9061 | 0.9061 |
94
+ | 0.0007 | 3.53 | 3800 | 0.4842 | 0.9062 | 0.9062 | 0.9062 | 0.9062 |
95
+ | 0.0023 | 3.62 | 3900 | 0.4973 | 0.9042 | 0.9042 | 0.9042 | 0.9042 |
96
+ | 0.0039 | 3.72 | 4000 | 0.4994 | 0.9043 | 0.9043 | 0.9043 | 0.9043 |
97
+ | 0.0005 | 3.81 | 4100 | 0.4907 | 0.9059 | 0.9059 | 0.9059 | 0.9059 |
98
+ | 0.0005 | 3.9 | 4200 | 0.4919 | 0.9058 | 0.9058 | 0.9058 | 0.9058 |
99
+ | 0.0432 | 4.0 | 4300 | 0.4923 | 0.9059 | 0.9059 | 0.9059 | 0.9059 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.30.2
105
+ - Pytorch 2.0.1+cu118
106
+ - Datasets 2.13.1
107
+ - Tokenizers 0.13.3