Hugging Face's logo

hkivancoral
/
smids_3x_deit_base_sgd_00001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
67d3248
•
1 Parent(s): 08cf881

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-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_base_sgd_00001_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: 0.39600665557404324
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_base_sgd_00001_fold2
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.0800
36
+ - Accuracy: 0.3960
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: 1e-05
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
+ | 1.1076 | 1.0 | 225 | 1.1068 | 0.3378 |
69
+ | 1.1268 | 2.0 | 450 | 1.1056 | 0.3344 |
70
+ | 1.1054 | 3.0 | 675 | 1.1044 | 0.3378 |
71
+ | 1.1083 | 4.0 | 900 | 1.1032 | 0.3361 |
72
+ | 1.1053 | 5.0 | 1125 | 1.1021 | 0.3344 |
73
+ | 1.0996 | 6.0 | 1350 | 1.1010 | 0.3378 |
74
+ | 1.1167 | 7.0 | 1575 | 1.0999 | 0.3461 |
75
+ | 1.1117 | 8.0 | 1800 | 1.0989 | 0.3478 |
76
+ | 1.1001 | 9.0 | 2025 | 1.0979 | 0.3494 |
77
+ | 1.0985 | 10.0 | 2250 | 1.0970 | 0.3527 |
78
+ | 1.088 | 11.0 | 2475 | 1.0961 | 0.3561 |
79
+ | 1.1055 | 12.0 | 2700 | 1.0952 | 0.3594 |
80
+ | 1.1011 | 13.0 | 2925 | 1.0943 | 0.3661 |
81
+ | 1.0919 | 14.0 | 3150 | 1.0935 | 0.3727 |
82
+ | 1.097 | 15.0 | 3375 | 1.0927 | 0.3727 |
83
+ | 1.1083 | 16.0 | 3600 | 1.0919 | 0.3744 |
84
+ | 1.099 | 17.0 | 3825 | 1.0911 | 0.3727 |
85
+ | 1.0873 | 18.0 | 4050 | 1.0904 | 0.3710 |
86
+ | 1.0775 | 19.0 | 4275 | 1.0897 | 0.3694 |
87
+ | 1.1063 | 20.0 | 4500 | 1.0890 | 0.3677 |
88
+ | 1.0977 | 21.0 | 4725 | 1.0884 | 0.3710 |
89
+ | 1.0779 | 22.0 | 4950 | 1.0878 | 0.3727 |
90
+ | 1.0723 | 23.0 | 5175 | 1.0872 | 0.3694 |
91
+ | 1.0778 | 24.0 | 5400 | 1.0866 | 0.3727 |
92
+ | 1.0917 | 25.0 | 5625 | 1.0861 | 0.3727 |
93
+ | 1.0896 | 26.0 | 5850 | 1.0856 | 0.3744 |
94
+ | 1.0859 | 27.0 | 6075 | 1.0851 | 0.3760 |
95
+ | 1.0933 | 28.0 | 6300 | 1.0846 | 0.3760 |
96
+ | 1.0926 | 29.0 | 6525 | 1.0842 | 0.3794 |
97
+ | 1.0799 | 30.0 | 6750 | 1.0838 | 0.3810 |
98
+ | 1.0805 | 31.0 | 6975 | 1.0834 | 0.3827 |
99
+ | 1.078 | 32.0 | 7200 | 1.0830 | 0.3810 |
100
+ | 1.0795 | 33.0 | 7425 | 1.0827 | 0.3860 |
101
+ | 1.0907 | 34.0 | 7650 | 1.0823 | 0.3860 |
102
+ | 1.0893 | 35.0 | 7875 | 1.0820 | 0.3860 |
103
+ | 1.0658 | 36.0 | 8100 | 1.0818 | 0.3894 |
104
+ | 1.0887 | 37.0 | 8325 | 1.0815 | 0.3910 |
105
+ | 1.0779 | 38.0 | 8550 | 1.0813 | 0.3910 |
106
+ | 1.0768 | 39.0 | 8775 | 1.0810 | 0.3927 |
107
+ | 1.089 | 40.0 | 9000 | 1.0809 | 0.3927 |
108
+ | 1.0766 | 41.0 | 9225 | 1.0807 | 0.3927 |
109
+ | 1.0713 | 42.0 | 9450 | 1.0805 | 0.3927 |
110
+ | 1.0786 | 43.0 | 9675 | 1.0804 | 0.3927 |
111
+ | 1.0932 | 44.0 | 9900 | 1.0803 | 0.3927 |
112
+ | 1.0641 | 45.0 | 10125 | 1.0802 | 0.3943 |
113
+ | 1.0516 | 46.0 | 10350 | 1.0801 | 0.3943 |
114
+ | 1.0624 | 47.0 | 10575 | 1.0801 | 0.3960 |
115
+ | 1.0722 | 48.0 | 10800 | 1.0801 | 0.3960 |
116
+ | 1.0714 | 49.0 | 11025 | 1.0800 | 0.3960 |
117
+ | 1.0822 | 50.0 | 11250 | 1.0800 | 0.3960 |
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 sha256:1d5e9055ed495ac49df1d134d4acca480b20407648528c57e91bba180e9e8203
3
  size 343272234
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed99cbd576d5d45f7fed54c30f728d4577b82fe181c8edbd1e5c15a8f590e6ef
3
  size 343272234