Hugging Face's logo

hkivancoral
/
smids_3x_deit_tiny_rms_001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
60ba2dd
•
1 Parent(s): 7ac5827

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_rms_001_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: 0.8036605657237936
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_rms_001_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: 1.9828
36
+ - Accuracy: 0.8037
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
+ | 0.8903 | 1.0 | 225 | 0.8221 | 0.5707 |
69
+ | 0.8376 | 2.0 | 450 | 0.7917 | 0.6023 |
70
+ | 0.7073 | 3.0 | 675 | 0.7643 | 0.5790 |
71
+ | 0.7158 | 4.0 | 900 | 0.7590 | 0.6506 |
72
+ | 0.6892 | 5.0 | 1125 | 0.7293 | 0.6506 |
73
+ | 0.6685 | 6.0 | 1350 | 0.6489 | 0.6755 |
74
+ | 0.606 | 7.0 | 1575 | 0.5908 | 0.7471 |
75
+ | 0.6652 | 8.0 | 1800 | 0.5586 | 0.7537 |
76
+ | 0.6311 | 9.0 | 2025 | 0.5971 | 0.7504 |
77
+ | 0.5645 | 10.0 | 2250 | 0.5700 | 0.7571 |
78
+ | 0.6575 | 11.0 | 2475 | 0.6329 | 0.7338 |
79
+ | 0.5727 | 12.0 | 2700 | 0.5598 | 0.7521 |
80
+ | 0.5704 | 13.0 | 2925 | 0.5359 | 0.7754 |
81
+ | 0.5215 | 14.0 | 3150 | 0.5587 | 0.7571 |
82
+ | 0.583 | 15.0 | 3375 | 0.5430 | 0.7787 |
83
+ | 0.5848 | 16.0 | 3600 | 0.5789 | 0.7255 |
84
+ | 0.5726 | 17.0 | 3825 | 0.5236 | 0.7854 |
85
+ | 0.489 | 18.0 | 4050 | 0.4992 | 0.8003 |
86
+ | 0.4753 | 19.0 | 4275 | 0.5863 | 0.7621 |
87
+ | 0.5263 | 20.0 | 4500 | 0.5219 | 0.7704 |
88
+ | 0.4735 | 21.0 | 4725 | 0.4900 | 0.7970 |
89
+ | 0.5712 | 22.0 | 4950 | 0.5240 | 0.8070 |
90
+ | 0.5071 | 23.0 | 5175 | 0.5142 | 0.7854 |
91
+ | 0.5079 | 24.0 | 5400 | 0.5416 | 0.7887 |
92
+ | 0.4923 | 25.0 | 5625 | 0.5063 | 0.8053 |
93
+ | 0.3927 | 26.0 | 5850 | 0.5633 | 0.7870 |
94
+ | 0.3745 | 27.0 | 6075 | 0.6375 | 0.7621 |
95
+ | 0.3879 | 28.0 | 6300 | 0.5787 | 0.7787 |
96
+ | 0.3817 | 29.0 | 6525 | 0.5796 | 0.7887 |
97
+ | 0.3478 | 30.0 | 6750 | 0.5474 | 0.8070 |
98
+ | 0.3866 | 31.0 | 6975 | 0.5776 | 0.7920 |
99
+ | 0.3993 | 32.0 | 7200 | 0.5703 | 0.8103 |
100
+ | 0.2926 | 33.0 | 7425 | 0.6089 | 0.7970 |
101
+ | 0.2772 | 34.0 | 7650 | 0.6185 | 0.8020 |
102
+ | 0.2754 | 35.0 | 7875 | 0.6777 | 0.7854 |
103
+ | 0.2402 | 36.0 | 8100 | 0.7422 | 0.7870 |
104
+ | 0.2412 | 37.0 | 8325 | 0.7873 | 0.7754 |
105
+ | 0.2165 | 38.0 | 8550 | 0.8318 | 0.8070 |
106
+ | 0.1829 | 39.0 | 8775 | 0.8522 | 0.7920 |
107
+ | 0.1669 | 40.0 | 9000 | 0.9913 | 0.7903 |
108
+ | 0.135 | 41.0 | 9225 | 1.0029 | 0.8003 |
109
+ | 0.1443 | 42.0 | 9450 | 1.0999 | 0.7987 |
110
+ | 0.0893 | 43.0 | 9675 | 1.2541 | 0.8020 |
111
+ | 0.0533 | 44.0 | 9900 | 1.3854 | 0.8003 |
112
+ | 0.065 | 45.0 | 10125 | 1.6713 | 0.7754 |
113
+ | 0.0332 | 46.0 | 10350 | 1.6089 | 0.8003 |
114
+ | 0.0177 | 47.0 | 10575 | 1.8304 | 0.7920 |
115
+ | 0.0017 | 48.0 | 10800 | 1.9277 | 0.7937 |
116
+ | 0.0154 | 49.0 | 11025 | 1.9904 | 0.8053 |
117
+ | 0.0079 | 50.0 | 11250 | 1.9828 | 0.8037 |
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 sha256:19f919479ab27522b3cdf3da129eec3b41f755a33f52e42468ee3414f207e208
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf1a7b06c3c5f42da463b46217f064b48def423a8693a3937412d52d5196ea1
3
  size 22167850