Hugging Face's logo

hkivancoral
/
smids_10x_deit_tiny_sgd_00001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
00d5e66
·
1 Parent(s): 5cad729

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_10x_deit_tiny_sgd_00001_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: 0.5074875207986689
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_tiny_sgd_00001_fold2
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: 0.9487
36
+ - Accuracy: 0.5075
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: 1e-05
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
+ | 1.3101 | 1.0 | 750 | 1.2862 | 0.3394 |
69
+ | 1.2651 | 2.0 | 1500 | 1.2316 | 0.3494 |
70
+ | 1.2534 | 3.0 | 2250 | 1.1915 | 0.3461 |
71
+ | 1.2051 | 4.0 | 3000 | 1.1627 | 0.3627 |
72
+ | 1.1704 | 5.0 | 3750 | 1.1422 | 0.3644 |
73
+ | 1.1559 | 6.0 | 4500 | 1.1266 | 0.3727 |
74
+ | 1.1314 | 7.0 | 5250 | 1.1140 | 0.3827 |
75
+ | 1.0917 | 8.0 | 6000 | 1.1032 | 0.3844 |
76
+ | 1.0985 | 9.0 | 6750 | 1.0936 | 0.4193 |
77
+ | 1.0734 | 10.0 | 7500 | 1.0847 | 0.4243 |
78
+ | 1.0397 | 11.0 | 8250 | 1.0764 | 0.4293 |
79
+ | 1.0584 | 12.0 | 9000 | 1.0685 | 0.4409 |
80
+ | 1.0692 | 13.0 | 9750 | 1.0611 | 0.4426 |
81
+ | 1.0127 | 14.0 | 10500 | 1.0540 | 0.4542 |
82
+ | 1.0605 | 15.0 | 11250 | 1.0471 | 0.4542 |
83
+ | 1.0197 | 16.0 | 12000 | 1.0406 | 0.4626 |
84
+ | 1.0472 | 17.0 | 12750 | 1.0344 | 0.4659 |
85
+ | 0.9868 | 18.0 | 13500 | 1.0285 | 0.4709 |
86
+ | 1.0498 | 19.0 | 14250 | 1.0228 | 0.4725 |
87
+ | 0.9916 | 20.0 | 15000 | 1.0174 | 0.4742 |
88
+ | 1.0032 | 21.0 | 15750 | 1.0122 | 0.4792 |
89
+ | 1.0262 | 22.0 | 16500 | 1.0073 | 0.4792 |
90
+ | 0.9732 | 23.0 | 17250 | 1.0026 | 0.4792 |
91
+ | 0.9627 | 24.0 | 18000 | 0.9981 | 0.4875 |
92
+ | 0.9933 | 25.0 | 18750 | 0.9939 | 0.4892 |
93
+ | 0.9645 | 26.0 | 19500 | 0.9898 | 0.4942 |
94
+ | 0.9413 | 27.0 | 20250 | 0.9860 | 0.4942 |
95
+ | 0.9502 | 28.0 | 21000 | 0.9824 | 0.4925 |
96
+ | 0.9622 | 29.0 | 21750 | 0.9790 | 0.4958 |
97
+ | 0.9399 | 30.0 | 22500 | 0.9758 | 0.4975 |
98
+ | 0.9259 | 31.0 | 23250 | 0.9728 | 0.4992 |
99
+ | 0.9425 | 32.0 | 24000 | 0.9700 | 0.5008 |
100
+ | 0.9657 | 33.0 | 24750 | 0.9673 | 0.5042 |
101
+ | 0.9537 | 34.0 | 25500 | 0.9649 | 0.5058 |
102
+ | 0.9361 | 35.0 | 26250 | 0.9627 | 0.5075 |
103
+ | 0.934 | 36.0 | 27000 | 0.9606 | 0.5092 |
104
+ | 0.927 | 37.0 | 27750 | 0.9587 | 0.5092 |
105
+ | 0.9435 | 38.0 | 28500 | 0.9570 | 0.5092 |
106
+ | 0.9139 | 39.0 | 29250 | 0.9555 | 0.5092 |
107
+ | 0.9394 | 40.0 | 30000 | 0.9541 | 0.5075 |
108
+ | 0.9635 | 41.0 | 30750 | 0.9529 | 0.5075 |
109
+ | 0.9447 | 42.0 | 31500 | 0.9519 | 0.5075 |
110
+ | 0.9124 | 43.0 | 32250 | 0.9510 | 0.5075 |
111
+ | 0.9404 | 44.0 | 33000 | 0.9503 | 0.5075 |
112
+ | 0.9374 | 45.0 | 33750 | 0.9497 | 0.5075 |
113
+ | 0.9103 | 46.0 | 34500 | 0.9493 | 0.5075 |
114
+ | 0.9609 | 47.0 | 35250 | 0.9490 | 0.5075 |
115
+ | 0.9309 | 48.0 | 36000 | 0.9488 | 0.5075 |
116
+ | 0.9307 | 49.0 | 36750 | 0.9487 | 0.5075 |
117
+ | 0.9119 | 50.0 | 37500 | 0.9487 | 0.5075 |
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 sha256:1591e806512eb1ed0ff2136f823c79e0b295b54cf199a819461984f8c165bbef
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842add4a68345e7d19e062529dd859c5c3c5f779c15ee52f9b10833000513b0a
3
  size 22167850