Hugging Face's logo

hkivancoral
/
smids_10x_deit_small_sgd_001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
a85e255
•
1 Parent(s): f9c2448

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_10x_deit_small_sgd_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: 0.9015025041736227
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_small_sgd_001_fold1
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: 0.2862
36
+ - Accuracy: 0.9015
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
+ | 0.5539 | 1.0 | 751 | 0.5690 | 0.7763 |
69
+ | 0.3867 | 2.0 | 1502 | 0.4456 | 0.8314 |
70
+ | 0.3236 | 3.0 | 2253 | 0.3927 | 0.8497 |
71
+ | 0.259 | 4.0 | 3004 | 0.3726 | 0.8514 |
72
+ | 0.3099 | 5.0 | 3755 | 0.3487 | 0.8598 |
73
+ | 0.2986 | 6.0 | 4506 | 0.3416 | 0.8715 |
74
+ | 0.2728 | 7.0 | 5257 | 0.3260 | 0.8731 |
75
+ | 0.2249 | 8.0 | 6008 | 0.3188 | 0.8781 |
76
+ | 0.2673 | 9.0 | 6759 | 0.3155 | 0.8848 |
77
+ | 0.2491 | 10.0 | 7510 | 0.3089 | 0.8848 |
78
+ | 0.2349 | 11.0 | 8261 | 0.3099 | 0.8881 |
79
+ | 0.2513 | 12.0 | 9012 | 0.3016 | 0.8898 |
80
+ | 0.2098 | 13.0 | 9763 | 0.3061 | 0.8898 |
81
+ | 0.1606 | 14.0 | 10514 | 0.3022 | 0.8881 |
82
+ | 0.1914 | 15.0 | 11265 | 0.2955 | 0.8881 |
83
+ | 0.2039 | 16.0 | 12016 | 0.2953 | 0.8898 |
84
+ | 0.2821 | 17.0 | 12767 | 0.2940 | 0.8965 |
85
+ | 0.1703 | 18.0 | 13518 | 0.2962 | 0.8915 |
86
+ | 0.2178 | 19.0 | 14269 | 0.2905 | 0.8965 |
87
+ | 0.1883 | 20.0 | 15020 | 0.2902 | 0.8998 |
88
+ | 0.13 | 21.0 | 15771 | 0.2893 | 0.8948 |
89
+ | 0.1613 | 22.0 | 16522 | 0.2875 | 0.8982 |
90
+ | 0.1627 | 23.0 | 17273 | 0.2879 | 0.8948 |
91
+ | 0.2201 | 24.0 | 18024 | 0.2853 | 0.8998 |
92
+ | 0.2067 | 25.0 | 18775 | 0.2893 | 0.8965 |
93
+ | 0.1982 | 26.0 | 19526 | 0.2860 | 0.8982 |
94
+ | 0.1922 | 27.0 | 20277 | 0.2854 | 0.8998 |
95
+ | 0.2065 | 28.0 | 21028 | 0.2873 | 0.8948 |
96
+ | 0.1663 | 29.0 | 21779 | 0.2836 | 0.9032 |
97
+ | 0.1637 | 30.0 | 22530 | 0.2824 | 0.9032 |
98
+ | 0.1216 | 31.0 | 23281 | 0.2840 | 0.8998 |
99
+ | 0.2073 | 32.0 | 24032 | 0.2863 | 0.9065 |
100
+ | 0.1694 | 33.0 | 24783 | 0.2888 | 0.8965 |
101
+ | 0.1525 | 34.0 | 25534 | 0.2882 | 0.8982 |
102
+ | 0.1562 | 35.0 | 26285 | 0.2864 | 0.9032 |
103
+ | 0.1612 | 36.0 | 27036 | 0.2821 | 0.9032 |
104
+ | 0.2418 | 37.0 | 27787 | 0.2832 | 0.9015 |
105
+ | 0.138 | 38.0 | 28538 | 0.2859 | 0.9032 |
106
+ | 0.0832 | 39.0 | 29289 | 0.2853 | 0.8998 |
107
+ | 0.1792 | 40.0 | 30040 | 0.2866 | 0.9015 |
108
+ | 0.1296 | 41.0 | 30791 | 0.2848 | 0.9032 |
109
+ | 0.1436 | 42.0 | 31542 | 0.2863 | 0.9032 |
110
+ | 0.1676 | 43.0 | 32293 | 0.2864 | 0.9015 |
111
+ | 0.129 | 44.0 | 33044 | 0.2863 | 0.9015 |
112
+ | 0.1268 | 45.0 | 33795 | 0.2864 | 0.9015 |
113
+ | 0.182 | 46.0 | 34546 | 0.2870 | 0.8998 |
114
+ | 0.0802 | 47.0 | 35297 | 0.2872 | 0.9015 |
115
+ | 0.1369 | 48.0 | 36048 | 0.2866 | 0.9015 |
116
+ | 0.1294 | 49.0 | 36799 | 0.2861 | 0.9015 |
117
+ | 0.1488 | 50.0 | 37550 | 0.2862 | 0.9015 |
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:aa42654abb27f5c726be7e6b63ab1419976978aeb32b0453c451165b9f1004b0
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62c88431d79b158daf3c2749d91cf8fe9f38b25da07fd25694c59fba19b7c22
3
  size 86735658