Hugging Face's logo

hkivancoral
/
smids_3x_deit_tiny_adamax_001_fold3

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
6c9cdc8
•
1 Parent(s): d45a88b

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_3x_deit_tiny_adamax_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: 0.905
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_3x_deit_tiny_adamax_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: 0.9948
36
+ - Accuracy: 0.905
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
+ | 0.542 | 1.0 | 225 | 0.4548 | 0.81 |
69
+ | 0.3403 | 2.0 | 450 | 0.3948 | 0.8633 |
70
+ | 0.3018 | 3.0 | 675 | 0.3258 | 0.88 |
71
+ | 0.2181 | 4.0 | 900 | 0.3725 | 0.8583 |
72
+ | 0.2784 | 5.0 | 1125 | 0.3487 | 0.8667 |
73
+ | 0.2253 | 6.0 | 1350 | 0.3694 | 0.87 |
74
+ | 0.1182 | 7.0 | 1575 | 0.4281 | 0.8683 |
75
+ | 0.1479 | 8.0 | 1800 | 0.4669 | 0.8683 |
76
+ | 0.127 | 9.0 | 2025 | 0.3858 | 0.88 |
77
+ | 0.1437 | 10.0 | 2250 | 0.6727 | 0.825 |
78
+ | 0.1318 | 11.0 | 2475 | 0.5423 | 0.8583 |
79
+ | 0.1039 | 12.0 | 2700 | 0.5755 | 0.8717 |
80
+ | 0.0315 | 13.0 | 2925 | 0.6762 | 0.8633 |
81
+ | 0.0565 | 14.0 | 3150 | 0.6056 | 0.8833 |
82
+ | 0.0169 | 15.0 | 3375 | 0.6739 | 0.8667 |
83
+ | 0.0394 | 16.0 | 3600 | 0.7747 | 0.87 |
84
+ | 0.051 | 17.0 | 3825 | 0.7121 | 0.8817 |
85
+ | 0.0214 | 18.0 | 4050 | 0.7547 | 0.88 |
86
+ | 0.0367 | 19.0 | 4275 | 0.7020 | 0.8583 |
87
+ | 0.0574 | 20.0 | 4500 | 0.7090 | 0.8783 |
88
+ | 0.016 | 21.0 | 4725 | 0.8561 | 0.87 |
89
+ | 0.0011 | 22.0 | 4950 | 0.6767 | 0.8783 |
90
+ | 0.0009 | 23.0 | 5175 | 0.6981 | 0.89 |
91
+ | 0.0024 | 24.0 | 5400 | 0.8528 | 0.8717 |
92
+ | 0.0185 | 25.0 | 5625 | 0.7739 | 0.8833 |
93
+ | 0.0018 | 26.0 | 5850 | 0.9050 | 0.875 |
94
+ | 0.0011 | 27.0 | 6075 | 0.8197 | 0.8767 |
95
+ | 0.0199 | 28.0 | 6300 | 0.8264 | 0.8833 |
96
+ | 0.0076 | 29.0 | 6525 | 0.8894 | 0.895 |
97
+ | 0.0073 | 30.0 | 6750 | 0.8362 | 0.9 |
98
+ | 0.004 | 31.0 | 6975 | 0.8565 | 0.9033 |
99
+ | 0.0 | 32.0 | 7200 | 0.9512 | 0.8967 |
100
+ | 0.0 | 33.0 | 7425 | 0.8488 | 0.895 |
101
+ | 0.0 | 34.0 | 7650 | 0.8884 | 0.9033 |
102
+ | 0.0 | 35.0 | 7875 | 1.0628 | 0.8917 |
103
+ | 0.0 | 36.0 | 8100 | 0.8726 | 0.9017 |
104
+ | 0.0029 | 37.0 | 8325 | 0.9056 | 0.9067 |
105
+ | 0.0 | 38.0 | 8550 | 0.9531 | 0.9033 |
106
+ | 0.0 | 39.0 | 8775 | 0.9541 | 0.905 |
107
+ | 0.0 | 40.0 | 9000 | 0.9488 | 0.905 |
108
+ | 0.0 | 41.0 | 9225 | 0.9370 | 0.9083 |
109
+ | 0.0 | 42.0 | 9450 | 0.9567 | 0.9067 |
110
+ | 0.0 | 43.0 | 9675 | 0.9765 | 0.9033 |
111
+ | 0.0 | 44.0 | 9900 | 0.9911 | 0.9017 |
112
+ | 0.0 | 45.0 | 10125 | 0.9807 | 0.905 |
113
+ | 0.0 | 46.0 | 10350 | 0.9732 | 0.9083 |
114
+ | 0.0026 | 47.0 | 10575 | 0.9856 | 0.905 |
115
+ | 0.0 | 48.0 | 10800 | 0.9870 | 0.905 |
116
+ | 0.0 | 49.0 | 11025 | 0.9903 | 0.905 |
117
+ | 0.0 | 50.0 | 11250 | 0.9948 | 0.905 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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 sha256:92464ded9fee3cec8674f3b2342a554771e10b3a17573fcbc255ce780e6be1ab
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71c63b8ee7ea0a0badb090abc143fb93e0556214e28ec086d00902e0f256fd0
3
  size 22167850