Hugging Face's logo

hkivancoral
/
smids_3x_deit_small_adamax_001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
4b4efe2
•
1 Parent(s): 890964b

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_small_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: 0.8866666666666667
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_small_adamax_001_fold5
32
+
33
+ This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.9259
36
+ - Accuracy: 0.8867
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
+ | 0.5128 | 1.0 | 225 | 0.3960 | 0.845 |
69
+ | 0.2912 | 2.0 | 450 | 0.3545 | 0.855 |
70
+ | 0.2355 | 3.0 | 675 | 0.5138 | 0.8283 |
71
+ | 0.2322 | 4.0 | 900 | 0.3502 | 0.8567 |
72
+ | 0.1566 | 5.0 | 1125 | 0.4327 | 0.855 |
73
+ | 0.1654 | 6.0 | 1350 | 0.3396 | 0.8883 |
74
+ | 0.1711 | 7.0 | 1575 | 0.4306 | 0.8733 |
75
+ | 0.1936 | 8.0 | 1800 | 0.4649 | 0.8783 |
76
+ | 0.1252 | 9.0 | 2025 | 0.4662 | 0.875 |
77
+ | 0.0897 | 10.0 | 2250 | 0.4869 | 0.8767 |
78
+ | 0.0556 | 11.0 | 2475 | 0.4677 | 0.8883 |
79
+ | 0.117 | 12.0 | 2700 | 0.5865 | 0.8667 |
80
+ | 0.1159 | 13.0 | 2925 | 0.6366 | 0.87 |
81
+ | 0.0526 | 14.0 | 3150 | 0.5638 | 0.8917 |
82
+ | 0.0199 | 15.0 | 3375 | 0.6092 | 0.885 |
83
+ | 0.0105 | 16.0 | 3600 | 0.7275 | 0.8817 |
84
+ | 0.0173 | 17.0 | 3825 | 0.6827 | 0.8883 |
85
+ | 0.0471 | 18.0 | 4050 | 0.6845 | 0.87 |
86
+ | 0.0272 | 19.0 | 4275 | 0.6814 | 0.8933 |
87
+ | 0.0245 | 20.0 | 4500 | 0.7971 | 0.8767 |
88
+ | 0.0042 | 21.0 | 4725 | 0.7308 | 0.8867 |
89
+ | 0.0003 | 22.0 | 4950 | 0.8304 | 0.895 |
90
+ | 0.0001 | 23.0 | 5175 | 0.8296 | 0.8917 |
91
+ | 0.0235 | 24.0 | 5400 | 0.7781 | 0.88 |
92
+ | 0.0005 | 25.0 | 5625 | 0.8114 | 0.8833 |
93
+ | 0.0112 | 26.0 | 5850 | 0.8185 | 0.8833 |
94
+ | 0.0 | 27.0 | 6075 | 0.9165 | 0.8833 |
95
+ | 0.0034 | 28.0 | 6300 | 0.9111 | 0.8783 |
96
+ | 0.0037 | 29.0 | 6525 | 0.8969 | 0.8833 |
97
+ | 0.0001 | 30.0 | 6750 | 0.9635 | 0.8783 |
98
+ | 0.0 | 31.0 | 6975 | 0.8389 | 0.8933 |
99
+ | 0.0 | 32.0 | 7200 | 0.9477 | 0.8767 |
100
+ | 0.003 | 33.0 | 7425 | 0.8612 | 0.8917 |
101
+ | 0.0001 | 34.0 | 7650 | 0.8689 | 0.8983 |
102
+ | 0.0025 | 35.0 | 7875 | 0.8114 | 0.885 |
103
+ | 0.0 | 36.0 | 8100 | 0.8426 | 0.8867 |
104
+ | 0.0037 | 37.0 | 8325 | 0.8625 | 0.8833 |
105
+ | 0.0006 | 38.0 | 8550 | 0.8725 | 0.885 |
106
+ | 0.0 | 39.0 | 8775 | 0.8789 | 0.8833 |
107
+ | 0.0 | 40.0 | 9000 | 0.8405 | 0.885 |
108
+ | 0.0 | 41.0 | 9225 | 0.8737 | 0.8833 |
109
+ | 0.0 | 42.0 | 9450 | 0.9022 | 0.8867 |
110
+ | 0.003 | 43.0 | 9675 | 0.9115 | 0.8833 |
111
+ | 0.0 | 44.0 | 9900 | 0.9099 | 0.8867 |
112
+ | 0.0 | 45.0 | 10125 | 0.9104 | 0.8883 |
113
+ | 0.0 | 46.0 | 10350 | 0.9175 | 0.8867 |
114
+ | 0.0 | 47.0 | 10575 | 0.9200 | 0.8867 |
115
+ | 0.0 | 48.0 | 10800 | 0.9224 | 0.8867 |
116
+ | 0.0 | 49.0 | 11025 | 0.9241 | 0.8867 |
117
+ | 0.0 | 50.0 | 11250 | 0.9259 | 0.8867 |
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:fb0f25c97c63d7348f143d56a8cc6e82579343653d319b596d571f199fea9680
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e10d21e640f7ff3f172150849710585c07abfc185f216c152856e4ee7dcc918
3
  size 86735658