Hugging Face's logo

ahishamm
/
vit-base-binary-isic-sharpened-patch-32

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
ahishamm commited on
Commit
5459c7b
·
1 Parent(s): 7beb4df

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-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-base-binary-isic-sharpened-patch-32
19
+
20
+ This model is a fine-tuned version of [google/vit-base-patch32-224-in21k](https://huggingface.co/google/vit-base-patch32-224-in21k) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3471
23
+ - Accuracy: 0.9264
24
+ - Recall: 0.9264
25
+ - F1: 0.9264
26
+ - Precision: 0.9264
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
+ | 0.3258 | 0.09 | 100 | 0.4318 | 0.7799 | 0.7799 | 0.7799 | 0.7799 |
58
+ | 0.3002 | 0.18 | 200 | 0.3273 | 0.8511 | 0.8511 | 0.8511 | 0.8511 |
59
+ | 0.3154 | 0.28 | 300 | 0.3165 | 0.8507 | 0.8507 | 0.8507 | 0.8507 |
60
+ | 0.412 | 0.37 | 400 | 0.3700 | 0.8547 | 0.8547 | 0.8547 | 0.8547 |
61
+ | 0.3264 | 0.46 | 500 | 0.2831 | 0.8635 | 0.8635 | 0.8635 | 0.8635 |
62
+ | 0.2851 | 0.55 | 600 | 0.3020 | 0.8520 | 0.8520 | 0.8520 | 0.8520 |
63
+ | 0.2582 | 0.65 | 700 | 0.3071 | 0.8385 | 0.8385 | 0.8385 | 0.8385 |
64
+ | 0.2376 | 0.74 | 800 | 0.3013 | 0.8579 | 0.8579 | 0.8579 | 0.8579 |
65
+ | 0.2635 | 0.83 | 900 | 0.2909 | 0.8544 | 0.8544 | 0.8544 | 0.8544 |
66
+ | 0.2837 | 0.92 | 1000 | 0.3623 | 0.8216 | 0.8216 | 0.8216 | 0.8216 |
67
+ | 0.2036 | 1.02 | 1100 | 0.2985 | 0.8763 | 0.8763 | 0.8763 | 0.8763 |
68
+ | 0.1586 | 1.11 | 1200 | 0.2620 | 0.8934 | 0.8934 | 0.8934 | 0.8934 |
69
+ | 0.1914 | 1.2 | 1300 | 0.2995 | 0.8799 | 0.8799 | 0.8799 | 0.8799 |
70
+ | 0.1604 | 1.29 | 1400 | 0.3001 | 0.8839 | 0.8839 | 0.8839 | 0.8839 |
71
+ | 0.1788 | 1.39 | 1500 | 0.3013 | 0.8883 | 0.8883 | 0.8883 | 0.8883 |
72
+ | 0.1975 | 1.48 | 1600 | 0.3369 | 0.8816 | 0.8816 | 0.8816 | 0.8816 |
73
+ | 0.1228 | 1.57 | 1700 | 0.3014 | 0.8835 | 0.8835 | 0.8835 | 0.8835 |
74
+ | 0.1982 | 1.66 | 1800 | 0.3094 | 0.8957 | 0.8957 | 0.8957 | 0.8957 |
75
+ | 0.1602 | 1.76 | 1900 | 0.3523 | 0.8717 | 0.8717 | 0.8717 | 0.8717 |
76
+ | 0.0748 | 1.85 | 2000 | 0.3154 | 0.8889 | 0.8889 | 0.8889 | 0.8889 |
77
+ | 0.1385 | 1.94 | 2100 | 0.2992 | 0.8885 | 0.8885 | 0.8885 | 0.8885 |
78
+ | 0.0977 | 2.03 | 2200 | 0.2889 | 0.8913 | 0.8913 | 0.8913 | 0.8913 |
79
+ | 0.1028 | 2.13 | 2300 | 0.2842 | 0.8967 | 0.8967 | 0.8967 | 0.8967 |
80
+ | 0.1025 | 2.22 | 2400 | 0.2997 | 0.8966 | 0.8966 | 0.8966 | 0.8966 |
81
+ | 0.0482 | 2.31 | 2500 | 0.3410 | 0.9043 | 0.9043 | 0.9043 | 0.9043 |
82
+ | 0.1243 | 2.4 | 2600 | 0.3357 | 0.9044 | 0.9044 | 0.9044 | 0.9044 |
83
+ | 0.0591 | 2.5 | 2700 | 0.3079 | 0.9076 | 0.9076 | 0.9076 | 0.9076 |
84
+ | 0.0324 | 2.59 | 2800 | 0.3434 | 0.9148 | 0.9148 | 0.9148 | 0.9148 |
85
+ | 0.0677 | 2.68 | 2900 | 0.3156 | 0.9083 | 0.9083 | 0.9083 | 0.9083 |
86
+ | 0.0397 | 2.77 | 3000 | 0.3390 | 0.9124 | 0.9124 | 0.9124 | 0.9124 |
87
+ | 0.0103 | 2.87 | 3100 | 0.3102 | 0.9106 | 0.9106 | 0.9106 | 0.9106 |
88
+ | 0.0359 | 2.96 | 3200 | 0.2847 | 0.9134 | 0.9134 | 0.9134 | 0.9134 |
89
+ | 0.0073 | 3.05 | 3300 | 0.4039 | 0.9077 | 0.9077 | 0.9077 | 0.9077 |
90
+ | 0.0156 | 3.14 | 3400 | 0.3630 | 0.9100 | 0.9100 | 0.9100 | 0.9100 |
91
+ | 0.003 | 3.23 | 3500 | 0.3671 | 0.9143 | 0.9143 | 0.9143 | 0.9143 |
92
+ | 0.0262 | 3.33 | 3600 | 0.3538 | 0.9152 | 0.9152 | 0.9152 | 0.9152 |
93
+ | 0.0035 | 3.42 | 3700 | 0.3822 | 0.9150 | 0.9150 | 0.9150 | 0.9150 |
94
+ | 0.0441 | 3.51 | 3800 | 0.3571 | 0.9188 | 0.9188 | 0.9188 | 0.9188 |
95
+ | 0.0017 | 3.6 | 3900 | 0.3793 | 0.9157 | 0.9157 | 0.9157 | 0.9157 |
96
+ | 0.0471 | 3.7 | 4000 | 0.3491 | 0.9213 | 0.9213 | 0.9213 | 0.9213 |
97
+ | 0.0018 | 3.79 | 4100 | 0.3486 | 0.9238 | 0.9238 | 0.9238 | 0.9238 |
98
+ | 0.0405 | 3.88 | 4200 | 0.3478 | 0.9248 | 0.9248 | 0.9248 | 0.9248 |
99
+ | 0.0231 | 3.97 | 4300 | 0.3471 | 0.9264 | 0.9264 | 0.9264 | 0.9264 |
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