Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_adamax_0001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
a320d01
•
1 Parent(s): ed1f2d2

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_0001_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: 0.8735440931780366
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_0001_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: 0.8884
36
+ - Accuracy: 0.8735
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: 0.0001
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
+ | 0.4433 | 1.0 | 75 | 0.4087 | 0.8136 |
69
+ | 0.2718 | 2.0 | 150 | 0.3393 | 0.8636 |
70
+ | 0.1523 | 3.0 | 225 | 0.3549 | 0.8602 |
71
+ | 0.1126 | 4.0 | 300 | 0.4203 | 0.8785 |
72
+ | 0.1857 | 5.0 | 375 | 0.5016 | 0.8702 |
73
+ | 0.1676 | 6.0 | 450 | 0.6812 | 0.8403 |
74
+ | 0.0685 | 7.0 | 525 | 0.6011 | 0.8719 |
75
+ | 0.0238 | 8.0 | 600 | 0.6670 | 0.8686 |
76
+ | 0.0519 | 9.0 | 675 | 0.6013 | 0.8686 |
77
+ | 0.0386 | 10.0 | 750 | 0.7008 | 0.8719 |
78
+ | 0.0148 | 11.0 | 825 | 0.7193 | 0.8619 |
79
+ | 0.0007 | 12.0 | 900 | 0.7563 | 0.8752 |
80
+ | 0.0241 | 13.0 | 975 | 0.7693 | 0.8636 |
81
+ | 0.0307 | 14.0 | 1050 | 0.8760 | 0.8636 |
82
+ | 0.0115 | 15.0 | 1125 | 0.7808 | 0.8719 |
83
+ | 0.0035 | 16.0 | 1200 | 0.7588 | 0.8669 |
84
+ | 0.0001 | 17.0 | 1275 | 0.8971 | 0.8619 |
85
+ | 0.0102 | 18.0 | 1350 | 0.7909 | 0.8719 |
86
+ | 0.0001 | 19.0 | 1425 | 0.7984 | 0.8636 |
87
+ | 0.004 | 20.0 | 1500 | 0.8206 | 0.8669 |
88
+ | 0.0001 | 21.0 | 1575 | 0.8515 | 0.8752 |
89
+ | 0.0 | 22.0 | 1650 | 0.7887 | 0.8752 |
90
+ | 0.0 | 23.0 | 1725 | 0.9036 | 0.8719 |
91
+ | 0.0001 | 24.0 | 1800 | 0.8151 | 0.8735 |
92
+ | 0.0 | 25.0 | 1875 | 0.8674 | 0.8669 |
93
+ | 0.0 | 26.0 | 1950 | 0.8463 | 0.8702 |
94
+ | 0.0044 | 27.0 | 2025 | 0.8541 | 0.8669 |
95
+ | 0.0043 | 28.0 | 2100 | 0.8322 | 0.8669 |
96
+ | 0.002 | 29.0 | 2175 | 0.8405 | 0.8686 |
97
+ | 0.0043 | 30.0 | 2250 | 0.8433 | 0.8686 |
98
+ | 0.0034 | 31.0 | 2325 | 0.8353 | 0.8752 |
99
+ | 0.0 | 32.0 | 2400 | 0.8744 | 0.8702 |
100
+ | 0.0 | 33.0 | 2475 | 0.8688 | 0.8669 |
101
+ | 0.0 | 34.0 | 2550 | 0.8557 | 0.8669 |
102
+ | 0.0091 | 35.0 | 2625 | 0.8746 | 0.8669 |
103
+ | 0.0 | 36.0 | 2700 | 0.8586 | 0.8686 |
104
+ | 0.0 | 37.0 | 2775 | 0.8715 | 0.8702 |
105
+ | 0.0 | 38.0 | 2850 | 0.8844 | 0.8719 |
106
+ | 0.0019 | 39.0 | 2925 | 0.8957 | 0.8735 |
107
+ | 0.0 | 40.0 | 3000 | 0.8803 | 0.8752 |
108
+ | 0.0031 | 41.0 | 3075 | 0.8802 | 0.8752 |
109
+ | 0.0 | 42.0 | 3150 | 0.8828 | 0.8752 |
110
+ | 0.0026 | 43.0 | 3225 | 0.8803 | 0.8735 |
111
+ | 0.003 | 44.0 | 3300 | 0.8878 | 0.8752 |
112
+ | 0.0 | 45.0 | 3375 | 0.8894 | 0.8702 |
113
+ | 0.0 | 46.0 | 3450 | 0.8874 | 0.8735 |
114
+ | 0.0024 | 47.0 | 3525 | 0.8958 | 0.8752 |
115
+ | 0.0 | 48.0 | 3600 | 0.8893 | 0.8735 |
116
+ | 0.0023 | 49.0 | 3675 | 0.8880 | 0.8735 |
117
+ | 0.0021 | 50.0 | 3750 | 0.8884 | 0.8735 |
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 sha256:6c5eb940875774b5324dea58241e8e80ffa6bcf39235a7acc44b4e5b67b2013e
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a84596b3cb7f4bf099bee75f58a6ce7ecb8d90707c72dba81a2d942564e223
3
  size 22122692