Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_adamax_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
c504a84
•
1 Parent(s): 33ea6ff

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +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_1x_deit_tiny_adamax_001_fold2
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: 0.8336106489184693
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_1x_deit_tiny_adamax_001_fold2
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: 1.3785
36
+ - Accuracy: 0.8336
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
+ | 0.8106 | 1.0 | 75 | 0.7856 | 0.5657 |
69
+ | 0.8289 | 2.0 | 150 | 0.7551 | 0.7121 |
70
+ | 0.6607 | 3.0 | 225 | 0.6595 | 0.7288 |
71
+ | 0.5966 | 4.0 | 300 | 0.5724 | 0.7671 |
72
+ | 0.5316 | 5.0 | 375 | 0.5404 | 0.7854 |
73
+ | 0.3929 | 6.0 | 450 | 0.5052 | 0.7970 |
74
+ | 0.407 | 7.0 | 525 | 0.4685 | 0.8303 |
75
+ | 0.3944 | 8.0 | 600 | 0.4515 | 0.8236 |
76
+ | 0.2836 | 9.0 | 675 | 0.4807 | 0.8070 |
77
+ | 0.2744 | 10.0 | 750 | 0.4423 | 0.8469 |
78
+ | 0.2808 | 11.0 | 825 | 0.4896 | 0.7953 |
79
+ | 0.152 | 12.0 | 900 | 0.5241 | 0.8319 |
80
+ | 0.1786 | 13.0 | 975 | 0.4922 | 0.8486 |
81
+ | 0.1372 | 14.0 | 1050 | 0.6687 | 0.8220 |
82
+ | 0.1982 | 15.0 | 1125 | 0.7505 | 0.8253 |
83
+ | 0.1651 | 16.0 | 1200 | 0.8354 | 0.8236 |
84
+ | 0.1906 | 17.0 | 1275 | 1.1129 | 0.7737 |
85
+ | 0.0899 | 18.0 | 1350 | 1.0319 | 0.8003 |
86
+ | 0.0875 | 19.0 | 1425 | 1.0962 | 0.7987 |
87
+ | 0.0186 | 20.0 | 1500 | 0.9631 | 0.8270 |
88
+ | 0.0742 | 21.0 | 1575 | 1.2547 | 0.7887 |
89
+ | 0.0229 | 22.0 | 1650 | 0.9476 | 0.8303 |
90
+ | 0.0161 | 23.0 | 1725 | 1.3651 | 0.8070 |
91
+ | 0.0097 | 24.0 | 1800 | 1.0596 | 0.8286 |
92
+ | 0.0082 | 25.0 | 1875 | 0.9954 | 0.8386 |
93
+ | 0.0036 | 26.0 | 1950 | 0.9671 | 0.8353 |
94
+ | 0.0205 | 27.0 | 2025 | 1.0817 | 0.8253 |
95
+ | 0.0109 | 28.0 | 2100 | 0.9995 | 0.8353 |
96
+ | 0.007 | 29.0 | 2175 | 1.1573 | 0.8369 |
97
+ | 0.0048 | 30.0 | 2250 | 1.2320 | 0.8303 |
98
+ | 0.0312 | 31.0 | 2325 | 1.1062 | 0.8453 |
99
+ | 0.0003 | 32.0 | 2400 | 1.3037 | 0.8436 |
100
+ | 0.0002 | 33.0 | 2475 | 1.2278 | 0.8403 |
101
+ | 0.0041 | 34.0 | 2550 | 1.3384 | 0.8286 |
102
+ | 0.0096 | 35.0 | 2625 | 1.3396 | 0.8303 |
103
+ | 0.0049 | 36.0 | 2700 | 1.3638 | 0.8403 |
104
+ | 0.0054 | 37.0 | 2775 | 1.3303 | 0.8303 |
105
+ | 0.0 | 38.0 | 2850 | 1.3273 | 0.8303 |
106
+ | 0.0017 | 39.0 | 2925 | 1.3584 | 0.8336 |
107
+ | 0.0 | 40.0 | 3000 | 1.3526 | 0.8319 |
108
+ | 0.0031 | 41.0 | 3075 | 1.3529 | 0.8303 |
109
+ | 0.0029 | 42.0 | 3150 | 1.3744 | 0.8336 |
110
+ | 0.0052 | 43.0 | 3225 | 1.3603 | 0.8319 |
111
+ | 0.0041 | 44.0 | 3300 | 1.3711 | 0.8336 |
112
+ | 0.0 | 45.0 | 3375 | 1.3741 | 0.8353 |
113
+ | 0.0002 | 46.0 | 3450 | 1.3699 | 0.8336 |
114
+ | 0.0029 | 47.0 | 3525 | 1.3797 | 0.8336 |
115
+ | 0.0 | 48.0 | 3600 | 1.3781 | 0.8336 |
116
+ | 0.0022 | 49.0 | 3675 | 1.3784 | 0.8336 |
117
+ | 0.0022 | 50.0 | 3750 | 1.3785 | 0.8336 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c27556f23d5c089d94a141aaaecc2a1e42002174280b92abb3c69f0df5ba3a3
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7ef20d42669b74d8d3b1b22804e3a0591b3c90fc24fdf5b4478d94fb6f00be
3
  size 22122692