Hugging Face's logo

ahishamm
/
vit-large-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
4370805
·
1 Parent(s): cf404b3

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-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-large-binary-isic-sharpened-patch-16
19
+
20
+ This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3398
23
+ - Accuracy: 0.8708
24
+ - Recall: 0.8708
25
+ - F1: 0.8708
26
+ - Precision: 0.8708
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
+ | 0.5213 | 0.09 | 100 | 0.4459 | 0.7638 | 0.7638 | 0.7638 | 0.7638 |
58
+ | 0.4388 | 0.18 | 200 | 0.5329 | 0.7869 | 0.7869 | 0.7869 | 0.7869 |
59
+ | 0.4157 | 0.28 | 300 | 0.4438 | 0.7713 | 0.7713 | 0.7713 | 0.7713 |
60
+ | 0.4578 | 0.37 | 400 | 0.4327 | 0.7652 | 0.7652 | 0.7652 | 0.7652 |
61
+ | 0.4322 | 0.46 | 500 | 0.4179 | 0.7897 | 0.7897 | 0.7897 | 0.7897 |
62
+ | 0.4258 | 0.55 | 600 | 0.4319 | 0.7979 | 0.7979 | 0.7979 | 0.7979 |
63
+ | 0.3156 | 0.65 | 700 | 0.4470 | 0.7729 | 0.7729 | 0.7729 | 0.7729 |
64
+ | 0.449 | 0.74 | 800 | 0.4223 | 0.8036 | 0.8036 | 0.8036 | 0.8036 |
65
+ | 0.464 | 0.83 | 900 | 0.4304 | 0.7814 | 0.7814 | 0.7814 | 0.7814 |
66
+ | 0.2522 | 0.92 | 1000 | 0.4755 | 0.8069 | 0.8069 | 0.8069 | 0.8069 |
67
+ | 0.3268 | 1.02 | 1100 | 0.3678 | 0.8119 | 0.8119 | 0.8119 | 0.8119 |
68
+ | 0.3374 | 1.11 | 1200 | 0.3609 | 0.8324 | 0.8324 | 0.8324 | 0.8324 |
69
+ | 0.3814 | 1.2 | 1300 | 0.3524 | 0.8393 | 0.8393 | 0.8393 | 0.8393 |
70
+ | 0.4162 | 1.29 | 1400 | 0.3600 | 0.8314 | 0.8314 | 0.8314 | 0.8314 |
71
+ | 0.3096 | 1.39 | 1500 | 0.3537 | 0.8405 | 0.8405 | 0.8405 | 0.8405 |
72
+ | 0.285 | 1.48 | 1600 | 0.3812 | 0.8234 | 0.8234 | 0.8234 | 0.8234 |
73
+ | 0.3039 | 1.57 | 1700 | 0.4491 | 0.8259 | 0.8259 | 0.8259 | 0.8259 |
74
+ | 0.3026 | 1.66 | 1800 | 0.3793 | 0.8155 | 0.8155 | 0.8155 | 0.8155 |
75
+ | 0.2304 | 1.76 | 1900 | 0.3488 | 0.8175 | 0.8175 | 0.8175 | 0.8175 |
76
+ | 0.2454 | 1.85 | 2000 | 0.3442 | 0.8357 | 0.8357 | 0.8357 | 0.8357 |
77
+ | 0.314 | 1.94 | 2100 | 0.3470 | 0.8370 | 0.8370 | 0.8370 | 0.8370 |
78
+ | 0.3015 | 2.03 | 2200 | 0.3263 | 0.8501 | 0.8501 | 0.8501 | 0.8501 |
79
+ | 0.2595 | 2.13 | 2300 | 0.3540 | 0.8425 | 0.8425 | 0.8425 | 0.8425 |
80
+ | 0.2901 | 2.22 | 2400 | 0.3567 | 0.8578 | 0.8578 | 0.8578 | 0.8578 |
81
+ | 0.1825 | 2.31 | 2500 | 0.2934 | 0.8585 | 0.8585 | 0.8585 | 0.8585 |
82
+ | 0.2558 | 2.4 | 2600 | 0.3281 | 0.8378 | 0.8378 | 0.8378 | 0.8378 |
83
+ | 0.2553 | 2.5 | 2700 | 0.3869 | 0.8306 | 0.8306 | 0.8306 | 0.8306 |
84
+ | 0.1911 | 2.59 | 2800 | 0.3586 | 0.8341 | 0.8341 | 0.8341 | 0.8341 |
85
+ | 0.1705 | 2.68 | 2900 | 0.3363 | 0.8576 | 0.8576 | 0.8576 | 0.8576 |
86
+ | 0.2686 | 2.77 | 3000 | 0.3378 | 0.8535 | 0.8535 | 0.8535 | 0.8535 |
87
+ | 0.2136 | 2.87 | 3100 | 0.3312 | 0.8676 | 0.8676 | 0.8676 | 0.8676 |
88
+ | 0.1913 | 2.96 | 3200 | 0.3305 | 0.8560 | 0.8560 | 0.8560 | 0.8560 |
89
+ | 0.3307 | 3.05 | 3300 | 0.3613 | 0.8675 | 0.8675 | 0.8675 | 0.8675 |
90
+ | 0.2204 | 3.14 | 3400 | 0.3567 | 0.8652 | 0.8652 | 0.8652 | 0.8652 |
91
+ | 0.2149 | 3.23 | 3500 | 0.3178 | 0.8706 | 0.8706 | 0.8706 | 0.8706 |
92
+ | 0.1389 | 3.33 | 3600 | 0.3123 | 0.8706 | 0.8706 | 0.8706 | 0.8706 |
93
+ | 0.1567 | 3.42 | 3700 | 0.3374 | 0.8669 | 0.8669 | 0.8669 | 0.8669 |
94
+ | 0.1871 | 3.51 | 3800 | 0.3450 | 0.8701 | 0.8701 | 0.8701 | 0.8701 |
95
+ | 0.1616 | 3.6 | 3900 | 0.3870 | 0.8608 | 0.8608 | 0.8608 | 0.8608 |
96
+ | 0.1582 | 3.7 | 4000 | 0.3490 | 0.8656 | 0.8656 | 0.8656 | 0.8656 |
97
+ | 0.1199 | 3.79 | 4100 | 0.3408 | 0.8684 | 0.8684 | 0.8684 | 0.8684 |
98
+ | 0.1563 | 3.88 | 4200 | 0.3498 | 0.8669 | 0.8669 | 0.8669 | 0.8669 |
99
+ | 0.1544 | 3.97 | 4300 | 0.3398 | 0.8708 | 0.8708 | 0.8708 | 0.8708 |
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