Hugging Face's logo

hkivancoral
/
smids_5x_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
f72156e
•
1 Parent(s): 513edb5

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_5x_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_5x_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: 1.0852
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
+ | 0.3838 | 1.0 | 376 | 0.3847 | 0.8447 |
69
+ | 0.2562 | 2.0 | 752 | 0.3563 | 0.8531 |
70
+ | 0.358 | 3.0 | 1128 | 0.3978 | 0.8481 |
71
+ | 0.2712 | 4.0 | 1504 | 0.3777 | 0.8614 |
72
+ | 0.2293 | 5.0 | 1880 | 0.3817 | 0.8598 |
73
+ | 0.1996 | 6.0 | 2256 | 0.3240 | 0.8748 |
74
+ | 0.2119 | 7.0 | 2632 | 0.3780 | 0.8881 |
75
+ | 0.1466 | 8.0 | 3008 | 0.4634 | 0.8664 |
76
+ | 0.0956 | 9.0 | 3384 | 0.4489 | 0.8798 |
77
+ | 0.0653 | 10.0 | 3760 | 0.4510 | 0.8765 |
78
+ | 0.0885 | 11.0 | 4136 | 0.5890 | 0.8798 |
79
+ | 0.0566 | 12.0 | 4512 | 0.6272 | 0.8715 |
80
+ | 0.1127 | 13.0 | 4888 | 0.6122 | 0.8731 |
81
+ | 0.0185 | 14.0 | 5264 | 0.8487 | 0.8681 |
82
+ | 0.043 | 15.0 | 5640 | 0.8403 | 0.8865 |
83
+ | 0.0368 | 16.0 | 6016 | 0.6238 | 0.8865 |
84
+ | 0.01 | 17.0 | 6392 | 0.7868 | 0.8848 |
85
+ | 0.0149 | 18.0 | 6768 | 0.7885 | 0.8965 |
86
+ | 0.0123 | 19.0 | 7144 | 0.7935 | 0.8865 |
87
+ | 0.0229 | 20.0 | 7520 | 0.7435 | 0.8932 |
88
+ | 0.0082 | 21.0 | 7896 | 0.7843 | 0.8915 |
89
+ | 0.0106 | 22.0 | 8272 | 0.8710 | 0.8815 |
90
+ | 0.0143 | 23.0 | 8648 | 0.7822 | 0.8881 |
91
+ | 0.0003 | 24.0 | 9024 | 0.8293 | 0.8898 |
92
+ | 0.0003 | 25.0 | 9400 | 0.7682 | 0.8831 |
93
+ | 0.0066 | 26.0 | 9776 | 0.8030 | 0.8865 |
94
+ | 0.0001 | 27.0 | 10152 | 0.8738 | 0.8948 |
95
+ | 0.0001 | 28.0 | 10528 | 0.7680 | 0.9082 |
96
+ | 0.0061 | 29.0 | 10904 | 0.8259 | 0.8982 |
97
+ | 0.0071 | 30.0 | 11280 | 0.9741 | 0.8965 |
98
+ | 0.0001 | 31.0 | 11656 | 0.9083 | 0.8998 |
99
+ | 0.0 | 32.0 | 12032 | 0.9246 | 0.9048 |
100
+ | 0.0 | 33.0 | 12408 | 0.9790 | 0.8915 |
101
+ | 0.0 | 34.0 | 12784 | 0.9209 | 0.8998 |
102
+ | 0.0 | 35.0 | 13160 | 0.9253 | 0.8998 |
103
+ | 0.0 | 36.0 | 13536 | 0.9520 | 0.8982 |
104
+ | 0.0 | 37.0 | 13912 | 0.9297 | 0.8932 |
105
+ | 0.0 | 38.0 | 14288 | 1.0047 | 0.8948 |
106
+ | 0.0 | 39.0 | 14664 | 1.0348 | 0.8915 |
107
+ | 0.0 | 40.0 | 15040 | 1.0205 | 0.8915 |
108
+ | 0.0 | 41.0 | 15416 | 1.0309 | 0.8948 |
109
+ | 0.0 | 42.0 | 15792 | 1.0254 | 0.8948 |
110
+ | 0.0 | 43.0 | 16168 | 1.0375 | 0.8948 |
111
+ | 0.0 | 44.0 | 16544 | 1.0541 | 0.8915 |
112
+ | 0.0 | 45.0 | 16920 | 1.0544 | 0.8915 |
113
+ | 0.003 | 46.0 | 17296 | 1.0646 | 0.8898 |
114
+ | 0.0 | 47.0 | 17672 | 1.0720 | 0.8898 |
115
+ | 0.0 | 48.0 | 18048 | 1.0767 | 0.8881 |
116
+ | 0.0 | 49.0 | 18424 | 1.0809 | 0.8881 |
117
+ | 0.0022 | 50.0 | 18800 | 1.0852 | 0.8881 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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 sha256:7cd29201e77cc9389d4cd9a5871fd88a3d589e1f9dee5c861bfb2231114b50d4
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d1adbbf3ab68f9e48a8639a3aa0333b5bd255ed3f92a41ee5c81011f073d62
3
  size 22167850