Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_sgd_0001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
b09fe1d
•
1 Parent(s): 7b0816d

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_deit_tiny_sgd_0001_fold3
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: 0.2558139534883721
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
+ # hushem_5x_deit_tiny_sgd_0001_fold3
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: 1.4406
36
+ - Accuracy: 0.2558
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
+ | 1.5476 | 1.0 | 28 | 1.6881 | 0.2791 |
69
+ | 1.5009 | 2.0 | 56 | 1.6672 | 0.2791 |
70
+ | 1.493 | 3.0 | 84 | 1.6491 | 0.2791 |
71
+ | 1.4757 | 4.0 | 112 | 1.6326 | 0.2791 |
72
+ | 1.4183 | 5.0 | 140 | 1.6168 | 0.2791 |
73
+ | 1.4727 | 6.0 | 168 | 1.6027 | 0.2791 |
74
+ | 1.5064 | 7.0 | 196 | 1.5899 | 0.2791 |
75
+ | 1.4575 | 8.0 | 224 | 1.5786 | 0.2791 |
76
+ | 1.4566 | 9.0 | 252 | 1.5679 | 0.3023 |
77
+ | 1.4332 | 10.0 | 280 | 1.5586 | 0.3023 |
78
+ | 1.4461 | 11.0 | 308 | 1.5502 | 0.3023 |
79
+ | 1.4527 | 12.0 | 336 | 1.5422 | 0.3023 |
80
+ | 1.4102 | 13.0 | 364 | 1.5344 | 0.3023 |
81
+ | 1.4234 | 14.0 | 392 | 1.5271 | 0.3023 |
82
+ | 1.4638 | 15.0 | 420 | 1.5205 | 0.3023 |
83
+ | 1.4171 | 16.0 | 448 | 1.5148 | 0.3023 |
84
+ | 1.3787 | 17.0 | 476 | 1.5087 | 0.2791 |
85
+ | 1.4195 | 18.0 | 504 | 1.5032 | 0.2791 |
86
+ | 1.3909 | 19.0 | 532 | 1.4981 | 0.3256 |
87
+ | 1.4469 | 20.0 | 560 | 1.4935 | 0.3023 |
88
+ | 1.382 | 21.0 | 588 | 1.4891 | 0.3023 |
89
+ | 1.3548 | 22.0 | 616 | 1.4852 | 0.3023 |
90
+ | 1.4115 | 23.0 | 644 | 1.4815 | 0.3023 |
91
+ | 1.3595 | 24.0 | 672 | 1.4779 | 0.2791 |
92
+ | 1.4648 | 25.0 | 700 | 1.4744 | 0.2791 |
93
+ | 1.3584 | 26.0 | 728 | 1.4712 | 0.2791 |
94
+ | 1.3694 | 27.0 | 756 | 1.4682 | 0.2791 |
95
+ | 1.3704 | 28.0 | 784 | 1.4656 | 0.2791 |
96
+ | 1.3747 | 29.0 | 812 | 1.4631 | 0.2791 |
97
+ | 1.3528 | 30.0 | 840 | 1.4609 | 0.2791 |
98
+ | 1.3372 | 31.0 | 868 | 1.4586 | 0.2791 |
99
+ | 1.3782 | 32.0 | 896 | 1.4565 | 0.2791 |
100
+ | 1.3746 | 33.0 | 924 | 1.4545 | 0.2791 |
101
+ | 1.3597 | 34.0 | 952 | 1.4525 | 0.2791 |
102
+ | 1.3491 | 35.0 | 980 | 1.4509 | 0.2791 |
103
+ | 1.3872 | 36.0 | 1008 | 1.4493 | 0.2791 |
104
+ | 1.3595 | 37.0 | 1036 | 1.4478 | 0.2791 |
105
+ | 1.3401 | 38.0 | 1064 | 1.4465 | 0.2791 |
106
+ | 1.3573 | 39.0 | 1092 | 1.4454 | 0.2791 |
107
+ | 1.3488 | 40.0 | 1120 | 1.4444 | 0.2791 |
108
+ | 1.3842 | 41.0 | 1148 | 1.4435 | 0.2791 |
109
+ | 1.3433 | 42.0 | 1176 | 1.4428 | 0.2558 |
110
+ | 1.3592 | 43.0 | 1204 | 1.4421 | 0.2558 |
111
+ | 1.3773 | 44.0 | 1232 | 1.4415 | 0.2558 |
112
+ | 1.3285 | 45.0 | 1260 | 1.4411 | 0.2558 |
113
+ | 1.3374 | 46.0 | 1288 | 1.4408 | 0.2558 |
114
+ | 1.3383 | 47.0 | 1316 | 1.4407 | 0.2558 |
115
+ | 1.3567 | 48.0 | 1344 | 1.4406 | 0.2558 |
116
+ | 1.3494 | 49.0 | 1372 | 1.4406 | 0.2558 |
117
+ | 1.2617 | 50.0 | 1400 | 1.4406 | 0.2558 |
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 sha256:25d042c4654dc4edda76c0352de34f66ff9d6460d2a04f4a3fc4952aad4dde6b
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ca76f2b3ac3647281bb51e0495fd002dc0e857e33a7207350ad693b9a2da06
3
  size 22123464