Hugging Face's logo

ahishamm
/
vit-base-binary-isic-sharpened-patch-16

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
ahishamm commited on
Commit
e75c43e
·
1 Parent(s): a901d24

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-base-binary-isic-sharpened-patch-16
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-base-binary-isic-sharpened-patch-16
19
+
20
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3894
23
+ - Accuracy: 0.9225
24
+ - Recall: 0.9225
25
+ - F1: 0.9225
26
+ - Precision: 0.9225
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
+ | 0.3281 | 0.09 | 100 | 0.4381 | 0.8183 | 0.8183 | 0.8183 | 0.8183 |
58
+ | 0.3212 | 0.18 | 200 | 0.3179 | 0.8503 | 0.8503 | 0.8503 | 0.8503 |
59
+ | 0.2864 | 0.28 | 300 | 0.3126 | 0.8655 | 0.8655 | 0.8655 | 0.8655 |
60
+ | 0.2692 | 0.37 | 400 | 0.3217 | 0.8599 | 0.8599 | 0.8599 | 0.8599 |
61
+ | 0.3195 | 0.46 | 500 | 0.3061 | 0.8694 | 0.8694 | 0.8694 | 0.8694 |
62
+ | 0.2095 | 0.55 | 600 | 0.2910 | 0.8669 | 0.8669 | 0.8669 | 0.8669 |
63
+ | 0.2168 | 0.65 | 700 | 0.3248 | 0.8730 | 0.8730 | 0.8730 | 0.8730 |
64
+ | 0.2288 | 0.74 | 800 | 0.3067 | 0.8553 | 0.8553 | 0.8553 | 0.8553 |
65
+ | 0.2521 | 0.83 | 900 | 0.2723 | 0.8689 | 0.8689 | 0.8689 | 0.8689 |
66
+ | 0.1953 | 0.92 | 1000 | 0.2729 | 0.8724 | 0.8724 | 0.8724 | 0.8724 |
67
+ | 0.2845 | 1.02 | 1100 | 0.4392 | 0.8666 | 0.8666 | 0.8666 | 0.8666 |
68
+ | 0.1484 | 1.11 | 1200 | 0.3031 | 0.8884 | 0.8884 | 0.8884 | 0.8884 |
69
+ | 0.153 | 1.2 | 1300 | 0.2849 | 0.8992 | 0.8992 | 0.8992 | 0.8992 |
70
+ | 0.1648 | 1.29 | 1400 | 0.2583 | 0.8912 | 0.8912 | 0.8912 | 0.8912 |
71
+ | 0.1627 | 1.39 | 1500 | 0.2706 | 0.8933 | 0.8933 | 0.8933 | 0.8933 |
72
+ | 0.0943 | 1.48 | 1600 | 0.2783 | 0.9034 | 0.9034 | 0.9034 | 0.9034 |
73
+ | 0.0624 | 1.57 | 1700 | 0.2921 | 0.8926 | 0.8926 | 0.8926 | 0.8926 |
74
+ | 0.12 | 1.66 | 1800 | 0.2915 | 0.9006 | 0.9006 | 0.9006 | 0.9006 |
75
+ | 0.0735 | 1.76 | 1900 | 0.3103 | 0.8897 | 0.8897 | 0.8897 | 0.8897 |
76
+ | 0.0609 | 1.85 | 2000 | 0.3382 | 0.8971 | 0.8971 | 0.8971 | 0.8971 |
77
+ | 0.1645 | 1.94 | 2100 | 0.2675 | 0.8901 | 0.8901 | 0.8901 | 0.8901 |
78
+ | 0.0839 | 2.03 | 2200 | 0.3941 | 0.8962 | 0.8962 | 0.8962 | 0.8962 |
79
+ | 0.0571 | 2.13 | 2300 | 0.3888 | 0.9047 | 0.9047 | 0.9047 | 0.9047 |
80
+ | 0.0929 | 2.22 | 2400 | 0.3773 | 0.9009 | 0.9009 | 0.9009 | 0.9009 |
81
+ | 0.0378 | 2.31 | 2500 | 0.4577 | 0.9029 | 0.9029 | 0.9029 | 0.9029 |
82
+ | 0.0085 | 2.4 | 2600 | 0.3183 | 0.9203 | 0.9203 | 0.9203 | 0.9203 |
83
+ | 0.06 | 2.5 | 2700 | 0.3548 | 0.9126 | 0.9126 | 0.9126 | 0.9126 |
84
+ | 0.0139 | 2.59 | 2800 | 0.3213 | 0.9198 | 0.9198 | 0.9198 | 0.9198 |
85
+ | 0.056 | 2.68 | 2900 | 0.3558 | 0.9131 | 0.9131 | 0.9131 | 0.9131 |
86
+ | 0.0433 | 2.77 | 3000 | 0.3101 | 0.9215 | 0.9215 | 0.9215 | 0.9215 |
87
+ | 0.0074 | 2.87 | 3100 | 0.3140 | 0.9176 | 0.9176 | 0.9176 | 0.9176 |
88
+ | 0.0216 | 2.96 | 3200 | 0.3657 | 0.9186 | 0.9186 | 0.9186 | 0.9186 |
89
+ | 0.0118 | 3.05 | 3300 | 0.3722 | 0.9195 | 0.9195 | 0.9195 | 0.9195 |
90
+ | 0.0014 | 3.14 | 3400 | 0.4089 | 0.9141 | 0.9141 | 0.9141 | 0.9141 |
91
+ | 0.001 | 3.23 | 3500 | 0.4045 | 0.9189 | 0.9189 | 0.9189 | 0.9189 |
92
+ | 0.0009 | 3.33 | 3600 | 0.3932 | 0.9230 | 0.9230 | 0.9230 | 0.9230 |
93
+ | 0.0009 | 3.42 | 3700 | 0.4257 | 0.9174 | 0.9174 | 0.9174 | 0.9174 |
94
+ | 0.03 | 3.51 | 3800 | 0.3981 | 0.9222 | 0.9222 | 0.9222 | 0.9222 |
95
+ | 0.0007 | 3.6 | 3900 | 0.4211 | 0.9189 | 0.9189 | 0.9189 | 0.9189 |
96
+ | 0.0494 | 3.7 | 4000 | 0.4029 | 0.9207 | 0.9207 | 0.9207 | 0.9207 |
97
+ | 0.0009 | 3.79 | 4100 | 0.3951 | 0.9226 | 0.9226 | 0.9226 | 0.9226 |
98
+ | 0.0319 | 3.88 | 4200 | 0.3944 | 0.9221 | 0.9221 | 0.9221 | 0.9221 |
99
+ | 0.0013 | 3.97 | 4300 | 0.3894 | 0.9225 | 0.9225 | 0.9225 | 0.9225 |
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