Hugging Face's logo

hkivancoral
/
smids_10x_deit_small_sgd_0001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
hkivancoral commited on
Commit
a45c203
·
1 Parent(s): b0fe2c3

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_0001_fold2
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: 0.826955074875208
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_0001_fold2
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: 0.4097
36
+ - Accuracy: 0.8270
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
+ | 0.9968 | 1.0 | 750 | 1.0169 | 0.4659 |
69
+ | 0.9174 | 2.0 | 1500 | 0.9543 | 0.5308 |
70
+ | 0.8121 | 3.0 | 2250 | 0.8838 | 0.6273 |
71
+ | 0.7871 | 4.0 | 3000 | 0.8228 | 0.6522 |
72
+ | 0.691 | 5.0 | 3750 | 0.7665 | 0.6922 |
73
+ | 0.6733 | 6.0 | 4500 | 0.7184 | 0.7271 |
74
+ | 0.611 | 7.0 | 5250 | 0.6739 | 0.7488 |
75
+ | 0.5495 | 8.0 | 6000 | 0.6348 | 0.7537 |
76
+ | 0.5871 | 9.0 | 6750 | 0.6046 | 0.7587 |
77
+ | 0.5362 | 10.0 | 7500 | 0.5781 | 0.7754 |
78
+ | 0.5478 | 11.0 | 8250 | 0.5567 | 0.7754 |
79
+ | 0.5521 | 12.0 | 9000 | 0.5409 | 0.7804 |
80
+ | 0.475 | 13.0 | 9750 | 0.5265 | 0.7787 |
81
+ | 0.4124 | 14.0 | 10500 | 0.5147 | 0.7887 |
82
+ | 0.4689 | 15.0 | 11250 | 0.5048 | 0.7870 |
83
+ | 0.4042 | 16.0 | 12000 | 0.4956 | 0.7903 |
84
+ | 0.3787 | 17.0 | 12750 | 0.4873 | 0.7937 |
85
+ | 0.4203 | 18.0 | 13500 | 0.4799 | 0.7937 |
86
+ | 0.4173 | 19.0 | 14250 | 0.4729 | 0.7987 |
87
+ | 0.4444 | 20.0 | 15000 | 0.4676 | 0.8020 |
88
+ | 0.4225 | 21.0 | 15750 | 0.4619 | 0.8020 |
89
+ | 0.3886 | 22.0 | 16500 | 0.4572 | 0.8070 |
90
+ | 0.3882 | 23.0 | 17250 | 0.4523 | 0.8120 |
91
+ | 0.3793 | 24.0 | 18000 | 0.4484 | 0.8103 |
92
+ | 0.4027 | 25.0 | 18750 | 0.4443 | 0.8136 |
93
+ | 0.4864 | 26.0 | 19500 | 0.4411 | 0.8136 |
94
+ | 0.4229 | 27.0 | 20250 | 0.4378 | 0.8153 |
95
+ | 0.4258 | 28.0 | 21000 | 0.4349 | 0.8153 |
96
+ | 0.3905 | 29.0 | 21750 | 0.4322 | 0.8170 |
97
+ | 0.4099 | 30.0 | 22500 | 0.4297 | 0.8170 |
98
+ | 0.3721 | 31.0 | 23250 | 0.4276 | 0.8186 |
99
+ | 0.4104 | 32.0 | 24000 | 0.4255 | 0.8203 |
100
+ | 0.3815 | 33.0 | 24750 | 0.4237 | 0.8220 |
101
+ | 0.3966 | 34.0 | 25500 | 0.4218 | 0.8220 |
102
+ | 0.4057 | 35.0 | 26250 | 0.4202 | 0.8220 |
103
+ | 0.4004 | 36.0 | 27000 | 0.4187 | 0.8220 |
104
+ | 0.3921 | 37.0 | 27750 | 0.4174 | 0.8220 |
105
+ | 0.4046 | 38.0 | 28500 | 0.4161 | 0.8220 |
106
+ | 0.3819 | 39.0 | 29250 | 0.4149 | 0.8220 |
107
+ | 0.4626 | 40.0 | 30000 | 0.4139 | 0.8236 |
108
+ | 0.4062 | 41.0 | 30750 | 0.4130 | 0.8236 |
109
+ | 0.3793 | 42.0 | 31500 | 0.4123 | 0.8253 |
110
+ | 0.3246 | 43.0 | 32250 | 0.4116 | 0.8253 |
111
+ | 0.3382 | 44.0 | 33000 | 0.4110 | 0.8270 |
112
+ | 0.3636 | 45.0 | 33750 | 0.4106 | 0.8270 |
113
+ | 0.4008 | 46.0 | 34500 | 0.4102 | 0.8270 |
114
+ | 0.3708 | 47.0 | 35250 | 0.4099 | 0.8270 |
115
+ | 0.3436 | 48.0 | 36000 | 0.4098 | 0.8270 |
116
+ | 0.3738 | 49.0 | 36750 | 0.4097 | 0.8270 |
117
+ | 0.373 | 50.0 | 37500 | 0.4097 | 0.8270 |
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 sha256:5e58a286a1694194b99614ac896625a127c4b3b37c09cb24c8f9c9b013bff0b8
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796f7060f52ce982032d80238df5328a4e9ddd62b4c956e2b5d34541bb2b842b
3
  size 86735658