Hugging Face's logo

hkivancoral
/
smids_3x_deit_small_sgd_0001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
fbbe2bd
•
1 Parent(s): a8ececd

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_sgd_0001_fold4
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: 0.7783333333333333
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_sgd_0001_fold4
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: 0.5687
36
+ - Accuracy: 0.7783
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: 0.0001
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
+ | 1.0247 | 1.0 | 225 | 1.0422 | 0.45 |
69
+ | 1.0237 | 2.0 | 450 | 1.0174 | 0.4883 |
70
+ | 0.9838 | 3.0 | 675 | 0.9928 | 0.52 |
71
+ | 0.9769 | 4.0 | 900 | 0.9683 | 0.555 |
72
+ | 0.9529 | 5.0 | 1125 | 0.9446 | 0.5867 |
73
+ | 0.9169 | 6.0 | 1350 | 0.9209 | 0.6017 |
74
+ | 0.9264 | 7.0 | 1575 | 0.8980 | 0.6083 |
75
+ | 0.9011 | 8.0 | 1800 | 0.8753 | 0.6267 |
76
+ | 0.8821 | 9.0 | 2025 | 0.8542 | 0.63 |
77
+ | 0.8381 | 10.0 | 2250 | 0.8337 | 0.66 |
78
+ | 0.8339 | 11.0 | 2475 | 0.8147 | 0.6683 |
79
+ | 0.8391 | 12.0 | 2700 | 0.7963 | 0.6833 |
80
+ | 0.8165 | 13.0 | 2925 | 0.7789 | 0.6933 |
81
+ | 0.736 | 14.0 | 3150 | 0.7623 | 0.7083 |
82
+ | 0.7819 | 15.0 | 3375 | 0.7468 | 0.725 |
83
+ | 0.7441 | 16.0 | 3600 | 0.7323 | 0.72 |
84
+ | 0.7169 | 17.0 | 3825 | 0.7189 | 0.7333 |
85
+ | 0.7451 | 18.0 | 4050 | 0.7062 | 0.7383 |
86
+ | 0.7048 | 19.0 | 4275 | 0.6943 | 0.74 |
87
+ | 0.6589 | 20.0 | 4500 | 0.6832 | 0.745 |
88
+ | 0.6884 | 21.0 | 4725 | 0.6730 | 0.7433 |
89
+ | 0.7041 | 22.0 | 4950 | 0.6635 | 0.745 |
90
+ | 0.6833 | 23.0 | 5175 | 0.6547 | 0.75 |
91
+ | 0.6669 | 24.0 | 5400 | 0.6465 | 0.7533 |
92
+ | 0.6608 | 25.0 | 5625 | 0.6391 | 0.7517 |
93
+ | 0.6311 | 26.0 | 5850 | 0.6322 | 0.7567 |
94
+ | 0.6676 | 27.0 | 6075 | 0.6258 | 0.7583 |
95
+ | 0.6172 | 28.0 | 6300 | 0.6199 | 0.7617 |
96
+ | 0.6339 | 29.0 | 6525 | 0.6146 | 0.765 |
97
+ | 0.6134 | 30.0 | 6750 | 0.6096 | 0.7717 |
98
+ | 0.6169 | 31.0 | 6975 | 0.6051 | 0.775 |
99
+ | 0.5976 | 32.0 | 7200 | 0.6008 | 0.7767 |
100
+ | 0.601 | 33.0 | 7425 | 0.5969 | 0.7767 |
101
+ | 0.6016 | 34.0 | 7650 | 0.5933 | 0.78 |
102
+ | 0.5916 | 35.0 | 7875 | 0.5900 | 0.78 |
103
+ | 0.6147 | 36.0 | 8100 | 0.5870 | 0.78 |
104
+ | 0.5896 | 37.0 | 8325 | 0.5843 | 0.78 |
105
+ | 0.5987 | 38.0 | 8550 | 0.5818 | 0.78 |
106
+ | 0.5562 | 39.0 | 8775 | 0.5795 | 0.78 |
107
+ | 0.6128 | 40.0 | 9000 | 0.5775 | 0.7817 |
108
+ | 0.5635 | 41.0 | 9225 | 0.5757 | 0.78 |
109
+ | 0.6047 | 42.0 | 9450 | 0.5742 | 0.78 |
110
+ | 0.5584 | 43.0 | 9675 | 0.5728 | 0.78 |
111
+ | 0.628 | 44.0 | 9900 | 0.5716 | 0.78 |
112
+ | 0.5798 | 45.0 | 10125 | 0.5707 | 0.7783 |
113
+ | 0.583 | 46.0 | 10350 | 0.5699 | 0.7783 |
114
+ | 0.5729 | 47.0 | 10575 | 0.5694 | 0.7783 |
115
+ | 0.5825 | 48.0 | 10800 | 0.5690 | 0.7783 |
116
+ | 0.6044 | 49.0 | 11025 | 0.5688 | 0.7783 |
117
+ | 0.5946 | 50.0 | 11250 | 0.5687 | 0.7783 |
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 sha256:21bd5c377b6b9ecf26c7336e1af688f910eb1efbef238506ff8f6f3cc5ccdd20
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde4d79e07702e90113fad76db02c4d87eedda5077c1b3fa76aedab0f4d61e28
3
  size 86735658