Hugging Face's logo

hkivancoral
/
smids_3x_deit_tiny_adamax_001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
23c5bcb
•
1 Parent(s): 823ae55

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_tiny_adamax_001_fold1
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8881469115191987
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # smids_3x_deit_tiny_adamax_001_fold1
32
+
33
+ This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.9854
36
+ - Accuracy: 0.8881
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.001
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 50
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 0.5438 | 1.0 | 226 | 0.3644 | 0.8564 |
69
+ | 0.3633 | 2.0 | 452 | 0.4295 | 0.8197 |
70
+ | 0.3319 | 3.0 | 678 | 0.3479 | 0.8798 |
71
+ | 0.2911 | 4.0 | 904 | 0.5122 | 0.7863 |
72
+ | 0.2297 | 5.0 | 1130 | 0.4447 | 0.8497 |
73
+ | 0.2355 | 6.0 | 1356 | 0.4870 | 0.8664 |
74
+ | 0.1726 | 7.0 | 1582 | 0.3746 | 0.8815 |
75
+ | 0.1516 | 8.0 | 1808 | 0.4061 | 0.8881 |
76
+ | 0.1399 | 9.0 | 2034 | 0.4165 | 0.8664 |
77
+ | 0.2099 | 10.0 | 2260 | 0.5285 | 0.8481 |
78
+ | 0.0642 | 11.0 | 2486 | 0.5850 | 0.8664 |
79
+ | 0.0496 | 12.0 | 2712 | 0.6577 | 0.8598 |
80
+ | 0.0572 | 13.0 | 2938 | 0.7482 | 0.8581 |
81
+ | 0.0345 | 14.0 | 3164 | 0.6445 | 0.8865 |
82
+ | 0.0353 | 15.0 | 3390 | 0.5804 | 0.8715 |
83
+ | 0.0492 | 16.0 | 3616 | 0.6578 | 0.8781 |
84
+ | 0.0534 | 17.0 | 3842 | 0.6841 | 0.8731 |
85
+ | 0.0164 | 18.0 | 4068 | 0.9341 | 0.8698 |
86
+ | 0.0478 | 19.0 | 4294 | 0.7274 | 0.8664 |
87
+ | 0.0375 | 20.0 | 4520 | 0.6850 | 0.8748 |
88
+ | 0.0043 | 21.0 | 4746 | 0.7649 | 0.8765 |
89
+ | 0.0174 | 22.0 | 4972 | 0.6718 | 0.8815 |
90
+ | 0.0185 | 23.0 | 5198 | 0.6797 | 0.8881 |
91
+ | 0.0071 | 24.0 | 5424 | 0.7435 | 0.8748 |
92
+ | 0.02 | 25.0 | 5650 | 0.7499 | 0.8731 |
93
+ | 0.0164 | 26.0 | 5876 | 0.7820 | 0.8898 |
94
+ | 0.001 | 27.0 | 6102 | 0.7752 | 0.8748 |
95
+ | 0.0009 | 28.0 | 6328 | 0.7790 | 0.8865 |
96
+ | 0.0 | 29.0 | 6554 | 0.8379 | 0.8865 |
97
+ | 0.0001 | 30.0 | 6780 | 0.8656 | 0.8965 |
98
+ | 0.0 | 31.0 | 7006 | 0.8923 | 0.8898 |
99
+ | 0.0 | 32.0 | 7232 | 0.8769 | 0.8898 |
100
+ | 0.0034 | 33.0 | 7458 | 0.9027 | 0.8915 |
101
+ | 0.0 | 34.0 | 7684 | 0.8621 | 0.8932 |
102
+ | 0.0 | 35.0 | 7910 | 0.8883 | 0.8898 |
103
+ | 0.0 | 36.0 | 8136 | 0.8819 | 0.8932 |
104
+ | 0.0 | 37.0 | 8362 | 0.9354 | 0.8881 |
105
+ | 0.0 | 38.0 | 8588 | 0.9191 | 0.8898 |
106
+ | 0.0 | 39.0 | 8814 | 0.9615 | 0.8881 |
107
+ | 0.0 | 40.0 | 9040 | 0.9125 | 0.8948 |
108
+ | 0.0034 | 41.0 | 9266 | 0.9410 | 0.8865 |
109
+ | 0.0034 | 42.0 | 9492 | 0.9578 | 0.8915 |
110
+ | 0.0 | 43.0 | 9718 | 0.9813 | 0.8881 |
111
+ | 0.0 | 44.0 | 9944 | 0.9641 | 0.8865 |
112
+ | 0.0 | 45.0 | 10170 | 0.9746 | 0.8865 |
113
+ | 0.0 | 46.0 | 10396 | 0.9611 | 0.8881 |
114
+ | 0.0 | 47.0 | 10622 | 0.9737 | 0.8865 |
115
+ | 0.0 | 48.0 | 10848 | 0.9767 | 0.8881 |
116
+ | 0.0 | 49.0 | 11074 | 0.9830 | 0.8881 |
117
+ | 0.0 | 50.0 | 11300 | 0.9854 | 0.8881 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33671efcc56b8dd3d7dd8533336c37a537f6a90214a3c6417689ba1df2ac27dd
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb868d9df23ebaa05885da13be27e64f0d7d43a540466ba916662e04cdbdb429
3
  size 22167850