Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
b2a35c2
·
1 Parent(s): 1d8da19

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +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_1x_deit_small_sgd_001_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: 0.8616666666666667
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_1x_deit_small_sgd_001_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: 0.3679
36
+ - Accuracy: 0.8617
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
+ | 0.9928 | 1.0 | 75 | 0.9393 | 0.6083 |
69
+ | 0.8712 | 2.0 | 150 | 0.8295 | 0.6433 |
70
+ | 0.7828 | 3.0 | 225 | 0.7388 | 0.7083 |
71
+ | 0.6696 | 4.0 | 300 | 0.6714 | 0.7567 |
72
+ | 0.6657 | 5.0 | 375 | 0.6202 | 0.7767 |
73
+ | 0.5692 | 6.0 | 450 | 0.5823 | 0.7883 |
74
+ | 0.568 | 7.0 | 525 | 0.5504 | 0.795 |
75
+ | 0.5196 | 8.0 | 600 | 0.5262 | 0.805 |
76
+ | 0.5314 | 9.0 | 675 | 0.5056 | 0.8167 |
77
+ | 0.4867 | 10.0 | 750 | 0.4885 | 0.8183 |
78
+ | 0.4734 | 11.0 | 825 | 0.4740 | 0.8183 |
79
+ | 0.4623 | 12.0 | 900 | 0.4619 | 0.8267 |
80
+ | 0.4683 | 13.0 | 975 | 0.4510 | 0.835 |
81
+ | 0.4153 | 14.0 | 1050 | 0.4430 | 0.8317 |
82
+ | 0.3992 | 15.0 | 1125 | 0.4360 | 0.8333 |
83
+ | 0.3763 | 16.0 | 1200 | 0.4269 | 0.845 |
84
+ | 0.3576 | 17.0 | 1275 | 0.4206 | 0.85 |
85
+ | 0.3638 | 18.0 | 1350 | 0.4146 | 0.845 |
86
+ | 0.3788 | 19.0 | 1425 | 0.4098 | 0.8433 |
87
+ | 0.333 | 20.0 | 1500 | 0.4060 | 0.85 |
88
+ | 0.3671 | 21.0 | 1575 | 0.4016 | 0.85 |
89
+ | 0.3178 | 22.0 | 1650 | 0.3983 | 0.8533 |
90
+ | 0.3335 | 23.0 | 1725 | 0.3950 | 0.8467 |
91
+ | 0.3527 | 24.0 | 1800 | 0.3923 | 0.8533 |
92
+ | 0.3211 | 25.0 | 1875 | 0.3897 | 0.8483 |
93
+ | 0.3209 | 26.0 | 1950 | 0.3876 | 0.855 |
94
+ | 0.2907 | 27.0 | 2025 | 0.3854 | 0.8517 |
95
+ | 0.3294 | 28.0 | 2100 | 0.3833 | 0.86 |
96
+ | 0.2805 | 29.0 | 2175 | 0.3818 | 0.8533 |
97
+ | 0.3183 | 30.0 | 2250 | 0.3799 | 0.855 |
98
+ | 0.2622 | 31.0 | 2325 | 0.3784 | 0.86 |
99
+ | 0.3165 | 32.0 | 2400 | 0.3771 | 0.86 |
100
+ | 0.2898 | 33.0 | 2475 | 0.3761 | 0.8617 |
101
+ | 0.2776 | 34.0 | 2550 | 0.3750 | 0.8617 |
102
+ | 0.2847 | 35.0 | 2625 | 0.3739 | 0.8633 |
103
+ | 0.2631 | 36.0 | 2700 | 0.3731 | 0.86 |
104
+ | 0.2584 | 37.0 | 2775 | 0.3723 | 0.8583 |
105
+ | 0.2889 | 38.0 | 2850 | 0.3718 | 0.8617 |
106
+ | 0.3213 | 39.0 | 2925 | 0.3709 | 0.8617 |
107
+ | 0.2873 | 40.0 | 3000 | 0.3704 | 0.865 |
108
+ | 0.284 | 41.0 | 3075 | 0.3700 | 0.865 |
109
+ | 0.2939 | 42.0 | 3150 | 0.3694 | 0.8633 |
110
+ | 0.3121 | 43.0 | 3225 | 0.3692 | 0.8633 |
111
+ | 0.2744 | 44.0 | 3300 | 0.3688 | 0.8617 |
112
+ | 0.2881 | 45.0 | 3375 | 0.3686 | 0.8617 |
113
+ | 0.302 | 46.0 | 3450 | 0.3683 | 0.8617 |
114
+ | 0.2645 | 47.0 | 3525 | 0.3682 | 0.8617 |
115
+ | 0.307 | 48.0 | 3600 | 0.3681 | 0.8617 |
116
+ | 0.2733 | 49.0 | 3675 | 0.3680 | 0.8617 |
117
+ | 0.2676 | 50.0 | 3750 | 0.3679 | 0.8617 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea3e41b43dc2e54fde10c158d2903540e00a117a2c333b5e3bf85d499ba5551a
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d99d51b2f9c330eeb9050f09427c79b0d6ceba7291fe490fb7deadc733e5877
3
  size 86690164