Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
13109b6
·
1 Parent(s): 3bf3b2b

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: smids_1x_deit_tiny_sgd_001_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: 0.8433333333333334
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_tiny_sgd_001_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: 0.3753
36
+ - Accuracy: 0.8433
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
+ | 1.1 | 1.0 | 75 | 1.0685 | 0.46 |
69
+ | 0.9367 | 2.0 | 150 | 0.9646 | 0.5417 |
70
+ | 0.8514 | 3.0 | 225 | 0.8770 | 0.6067 |
71
+ | 0.8379 | 4.0 | 300 | 0.8018 | 0.6683 |
72
+ | 0.6855 | 5.0 | 375 | 0.7375 | 0.715 |
73
+ | 0.6563 | 6.0 | 450 | 0.6796 | 0.7433 |
74
+ | 0.6233 | 7.0 | 525 | 0.6334 | 0.7633 |
75
+ | 0.5422 | 8.0 | 600 | 0.5966 | 0.7817 |
76
+ | 0.5439 | 9.0 | 675 | 0.5698 | 0.795 |
77
+ | 0.5302 | 10.0 | 750 | 0.5521 | 0.795 |
78
+ | 0.503 | 11.0 | 825 | 0.5277 | 0.8083 |
79
+ | 0.4486 | 12.0 | 900 | 0.5133 | 0.8083 |
80
+ | 0.4811 | 13.0 | 975 | 0.4988 | 0.8133 |
81
+ | 0.4014 | 14.0 | 1050 | 0.4857 | 0.815 |
82
+ | 0.3711 | 15.0 | 1125 | 0.4759 | 0.8217 |
83
+ | 0.4033 | 16.0 | 1200 | 0.4684 | 0.8167 |
84
+ | 0.4414 | 17.0 | 1275 | 0.4593 | 0.8233 |
85
+ | 0.3659 | 18.0 | 1350 | 0.4514 | 0.8233 |
86
+ | 0.3656 | 19.0 | 1425 | 0.4448 | 0.8233 |
87
+ | 0.4021 | 20.0 | 1500 | 0.4388 | 0.825 |
88
+ | 0.4189 | 21.0 | 1575 | 0.4325 | 0.8267 |
89
+ | 0.3524 | 22.0 | 1650 | 0.4276 | 0.8283 |
90
+ | 0.356 | 23.0 | 1725 | 0.4217 | 0.8283 |
91
+ | 0.3419 | 24.0 | 1800 | 0.4174 | 0.835 |
92
+ | 0.3528 | 25.0 | 1875 | 0.4128 | 0.83 |
93
+ | 0.3819 | 26.0 | 1950 | 0.4110 | 0.8233 |
94
+ | 0.3203 | 27.0 | 2025 | 0.4057 | 0.835 |
95
+ | 0.3243 | 28.0 | 2100 | 0.4027 | 0.8333 |
96
+ | 0.3594 | 29.0 | 2175 | 0.3998 | 0.835 |
97
+ | 0.3291 | 30.0 | 2250 | 0.3976 | 0.84 |
98
+ | 0.3185 | 31.0 | 2325 | 0.3939 | 0.84 |
99
+ | 0.3337 | 32.0 | 2400 | 0.3916 | 0.8383 |
100
+ | 0.3127 | 33.0 | 2475 | 0.3899 | 0.8367 |
101
+ | 0.3111 | 34.0 | 2550 | 0.3887 | 0.835 |
102
+ | 0.3206 | 35.0 | 2625 | 0.3862 | 0.8383 |
103
+ | 0.3237 | 36.0 | 2700 | 0.3848 | 0.845 |
104
+ | 0.2644 | 37.0 | 2775 | 0.3830 | 0.85 |
105
+ | 0.3198 | 38.0 | 2850 | 0.3820 | 0.845 |
106
+ | 0.3031 | 39.0 | 2925 | 0.3811 | 0.8417 |
107
+ | 0.2823 | 40.0 | 3000 | 0.3801 | 0.8433 |
108
+ | 0.2812 | 41.0 | 3075 | 0.3793 | 0.8417 |
109
+ | 0.3147 | 42.0 | 3150 | 0.3783 | 0.8417 |
110
+ | 0.2862 | 43.0 | 3225 | 0.3776 | 0.845 |
111
+ | 0.2684 | 44.0 | 3300 | 0.3773 | 0.8433 |
112
+ | 0.306 | 45.0 | 3375 | 0.3765 | 0.8467 |
113
+ | 0.2738 | 46.0 | 3450 | 0.3761 | 0.845 |
114
+ | 0.2493 | 47.0 | 3525 | 0.3758 | 0.8433 |
115
+ | 0.2906 | 48.0 | 3600 | 0.3756 | 0.8433 |
116
+ | 0.2971 | 49.0 | 3675 | 0.3754 | 0.8433 |
117
+ | 0.2597 | 50.0 | 3750 | 0.3753 | 0.8433 |
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:f7b7de8ea2c14df7772ac5e3e8f6bf77587d89f155d88bd42a329c51cde558f1
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f952edebc1bd6fe350fcf2c22cd8d8af8cb0f24200f84c72632ac1ae502b6bc
3
  size 22122692