Hugging Face's logo

hkivancoral
/
smids_10x_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
6d2572c
•
1 Parent(s): bbcf754

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_10x_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: 0.8948247078464107
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_10x_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: 1.1377
36
+ - Accuracy: 0.8948
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
+ | 0.387 | 1.0 | 751 | 0.3856 | 0.8447 |
69
+ | 0.2275 | 2.0 | 1502 | 0.3799 | 0.8497 |
70
+ | 0.1732 | 3.0 | 2253 | 0.3628 | 0.8898 |
71
+ | 0.1418 | 4.0 | 3004 | 0.3720 | 0.8848 |
72
+ | 0.1851 | 5.0 | 3755 | 0.4163 | 0.8497 |
73
+ | 0.1168 | 6.0 | 4506 | 0.4228 | 0.8915 |
74
+ | 0.1217 | 7.0 | 5257 | 0.4050 | 0.8965 |
75
+ | 0.0972 | 8.0 | 6008 | 0.4659 | 0.8881 |
76
+ | 0.0717 | 9.0 | 6759 | 0.4692 | 0.8848 |
77
+ | 0.0615 | 10.0 | 7510 | 0.5939 | 0.8748 |
78
+ | 0.0582 | 11.0 | 8261 | 0.5202 | 0.8898 |
79
+ | 0.0569 | 12.0 | 9012 | 0.5681 | 0.8982 |
80
+ | 0.0142 | 13.0 | 9763 | 0.7223 | 0.8815 |
81
+ | 0.0849 | 14.0 | 10514 | 0.6292 | 0.8948 |
82
+ | 0.0289 | 15.0 | 11265 | 0.7113 | 0.8898 |
83
+ | 0.0438 | 16.0 | 12016 | 0.6702 | 0.8982 |
84
+ | 0.0561 | 17.0 | 12767 | 0.7629 | 0.8765 |
85
+ | 0.0013 | 18.0 | 13518 | 0.7639 | 0.8865 |
86
+ | 0.0173 | 19.0 | 14269 | 0.6756 | 0.8965 |
87
+ | 0.0044 | 20.0 | 15020 | 0.7365 | 0.8965 |
88
+ | 0.013 | 21.0 | 15771 | 0.8044 | 0.8831 |
89
+ | 0.0056 | 22.0 | 16522 | 0.7938 | 0.8915 |
90
+ | 0.0006 | 23.0 | 17273 | 0.8954 | 0.8848 |
91
+ | 0.0157 | 24.0 | 18024 | 0.8083 | 0.8998 |
92
+ | 0.0002 | 25.0 | 18775 | 0.8156 | 0.8965 |
93
+ | 0.0001 | 26.0 | 19526 | 0.8204 | 0.8982 |
94
+ | 0.0087 | 27.0 | 20277 | 0.8556 | 0.8948 |
95
+ | 0.0001 | 28.0 | 21028 | 0.8189 | 0.9048 |
96
+ | 0.0132 | 29.0 | 21779 | 0.8401 | 0.9065 |
97
+ | 0.0001 | 30.0 | 22530 | 0.9274 | 0.8915 |
98
+ | 0.0 | 31.0 | 23281 | 0.9668 | 0.8965 |
99
+ | 0.0153 | 32.0 | 24032 | 0.9746 | 0.8932 |
100
+ | 0.0 | 33.0 | 24783 | 1.0269 | 0.8881 |
101
+ | 0.0 | 34.0 | 25534 | 1.0125 | 0.8948 |
102
+ | 0.0 | 35.0 | 26285 | 1.0419 | 0.8898 |
103
+ | 0.0003 | 36.0 | 27036 | 1.0764 | 0.8898 |
104
+ | 0.0 | 37.0 | 27787 | 1.0824 | 0.8915 |
105
+ | 0.0 | 38.0 | 28538 | 1.0882 | 0.8898 |
106
+ | 0.0 | 39.0 | 29289 | 1.0563 | 0.8932 |
107
+ | 0.0 | 40.0 | 30040 | 1.0771 | 0.8915 |
108
+ | 0.0 | 41.0 | 30791 | 1.0705 | 0.8948 |
109
+ | 0.0 | 42.0 | 31542 | 1.0752 | 0.8932 |
110
+ | 0.0 | 43.0 | 32293 | 1.1011 | 0.8948 |
111
+ | 0.0 | 44.0 | 33044 | 1.1049 | 0.8948 |
112
+ | 0.0 | 45.0 | 33795 | 1.1132 | 0.8948 |
113
+ | 0.0 | 46.0 | 34546 | 1.1208 | 0.8965 |
114
+ | 0.0 | 47.0 | 35297 | 1.1280 | 0.8948 |
115
+ | 0.0 | 48.0 | 36048 | 1.1328 | 0.8948 |
116
+ | 0.0 | 49.0 | 36799 | 1.1361 | 0.8948 |
117
+ | 0.0 | 50.0 | 37550 | 1.1377 | 0.8948 |
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 sha256:04477c9a033f750ec874125caa1583a7fd06dff1178bb3ff3f71079ea38fbc28
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1819246d27830094e6ec33764dacdbc4f8fb8a1d5fe0c7391355abd38651c2ff
3
  size 22167850