Hugging Face's logo

hkivancoral
/
smids_3x_deit_tiny_adamax_001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
2eb795b
•
1 Parent(s): ad8b573

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_fold5
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: 0.89
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_fold5
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: 0.9334
36
+ - Accuracy: 0.89
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
+ | 0.6273 | 1.0 | 225 | 0.4733 | 0.805 |
69
+ | 0.2977 | 2.0 | 450 | 0.3448 | 0.8733 |
70
+ | 0.3197 | 3.0 | 675 | 0.3620 | 0.88 |
71
+ | 0.2909 | 4.0 | 900 | 0.4019 | 0.8367 |
72
+ | 0.1808 | 5.0 | 1125 | 0.3972 | 0.8617 |
73
+ | 0.2005 | 6.0 | 1350 | 0.4622 | 0.8483 |
74
+ | 0.1408 | 7.0 | 1575 | 0.4696 | 0.8717 |
75
+ | 0.1502 | 8.0 | 1800 | 0.4332 | 0.8633 |
76
+ | 0.2129 | 9.0 | 2025 | 0.3925 | 0.8833 |
77
+ | 0.114 | 10.0 | 2250 | 0.4888 | 0.8733 |
78
+ | 0.1195 | 11.0 | 2475 | 0.4884 | 0.8717 |
79
+ | 0.1124 | 12.0 | 2700 | 0.4439 | 0.8733 |
80
+ | 0.0652 | 13.0 | 2925 | 0.6058 | 0.8633 |
81
+ | 0.0425 | 14.0 | 3150 | 0.5627 | 0.875 |
82
+ | 0.039 | 15.0 | 3375 | 0.5971 | 0.875 |
83
+ | 0.0795 | 16.0 | 3600 | 0.6169 | 0.8733 |
84
+ | 0.0453 | 17.0 | 3825 | 0.6835 | 0.875 |
85
+ | 0.0066 | 18.0 | 4050 | 0.7361 | 0.8783 |
86
+ | 0.1031 | 19.0 | 4275 | 0.7941 | 0.8717 |
87
+ | 0.0061 | 20.0 | 4500 | 0.7090 | 0.8733 |
88
+ | 0.0198 | 21.0 | 4725 | 0.7250 | 0.8783 |
89
+ | 0.0155 | 22.0 | 4950 | 0.7045 | 0.8917 |
90
+ | 0.023 | 23.0 | 5175 | 0.8046 | 0.8817 |
91
+ | 0.057 | 24.0 | 5400 | 0.7359 | 0.8817 |
92
+ | 0.0134 | 25.0 | 5625 | 0.7403 | 0.8867 |
93
+ | 0.0001 | 26.0 | 5850 | 0.7361 | 0.895 |
94
+ | 0.0011 | 27.0 | 6075 | 0.7945 | 0.8733 |
95
+ | 0.0014 | 28.0 | 6300 | 0.6928 | 0.8983 |
96
+ | 0.0133 | 29.0 | 6525 | 0.6789 | 0.895 |
97
+ | 0.0002 | 30.0 | 6750 | 0.7451 | 0.8967 |
98
+ | 0.0001 | 31.0 | 6975 | 0.7847 | 0.8867 |
99
+ | 0.0 | 32.0 | 7200 | 0.7580 | 0.8917 |
100
+ | 0.0043 | 33.0 | 7425 | 0.8908 | 0.8833 |
101
+ | 0.0 | 34.0 | 7650 | 0.7939 | 0.89 |
102
+ | 0.0034 | 35.0 | 7875 | 0.8753 | 0.8933 |
103
+ | 0.0 | 36.0 | 8100 | 0.8470 | 0.8867 |
104
+ | 0.0046 | 37.0 | 8325 | 0.9037 | 0.8867 |
105
+ | 0.0001 | 38.0 | 8550 | 0.8793 | 0.89 |
106
+ | 0.0 | 39.0 | 8775 | 0.8702 | 0.8917 |
107
+ | 0.0 | 40.0 | 9000 | 0.8835 | 0.8883 |
108
+ | 0.0 | 41.0 | 9225 | 0.9101 | 0.8883 |
109
+ | 0.0 | 42.0 | 9450 | 0.9070 | 0.8933 |
110
+ | 0.0037 | 43.0 | 9675 | 0.9025 | 0.8933 |
111
+ | 0.0 | 44.0 | 9900 | 0.9038 | 0.89 |
112
+ | 0.0 | 45.0 | 10125 | 0.9112 | 0.89 |
113
+ | 0.0 | 46.0 | 10350 | 0.9228 | 0.89 |
114
+ | 0.0 | 47.0 | 10575 | 0.9243 | 0.89 |
115
+ | 0.0 | 48.0 | 10800 | 0.9283 | 0.89 |
116
+ | 0.0 | 49.0 | 11025 | 0.9314 | 0.89 |
117
+ | 0.0 | 50.0 | 11250 | 0.9334 | 0.89 |
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 sha256:0499ed2055cdc3cffeb61ec724bcf7342d92e50355081e56af29b849e003b11a
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0660b5be4dab1a990abc8baa9e3275db4c8d5240e60106e436c4f38b40604378
3
  size 22167850