Hugging Face's logo

hkivancoral
/
smids_5x_deit_tiny_adamax_001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
b0ddcd3
•
1 Parent(s): 838c691

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_5x_deit_tiny_adamax_001_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: 0.8901830282861897
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_5x_deit_tiny_adamax_001_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: 1.1513
36
+ - Accuracy: 0.8902
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
+ | 0.3758 | 1.0 | 375 | 0.3275 | 0.8619 |
69
+ | 0.3244 | 2.0 | 750 | 0.4328 | 0.8403 |
70
+ | 0.3305 | 3.0 | 1125 | 0.3559 | 0.8586 |
71
+ | 0.2057 | 4.0 | 1500 | 0.3484 | 0.8752 |
72
+ | 0.2037 | 5.0 | 1875 | 0.3334 | 0.8918 |
73
+ | 0.109 | 6.0 | 2250 | 0.3396 | 0.8869 |
74
+ | 0.1296 | 7.0 | 2625 | 0.4274 | 0.8719 |
75
+ | 0.1447 | 8.0 | 3000 | 0.4555 | 0.8569 |
76
+ | 0.0656 | 9.0 | 3375 | 0.4650 | 0.8869 |
77
+ | 0.0303 | 10.0 | 3750 | 0.5987 | 0.8602 |
78
+ | 0.0379 | 11.0 | 4125 | 0.5753 | 0.8835 |
79
+ | 0.0368 | 12.0 | 4500 | 0.6264 | 0.8669 |
80
+ | 0.0495 | 13.0 | 4875 | 0.6979 | 0.8569 |
81
+ | 0.0376 | 14.0 | 5250 | 0.7442 | 0.8636 |
82
+ | 0.0604 | 15.0 | 5625 | 0.8422 | 0.8636 |
83
+ | 0.0353 | 16.0 | 6000 | 0.7521 | 0.8852 |
84
+ | 0.0761 | 17.0 | 6375 | 0.7920 | 0.8752 |
85
+ | 0.004 | 18.0 | 6750 | 1.0354 | 0.8702 |
86
+ | 0.0148 | 19.0 | 7125 | 0.7279 | 0.8785 |
87
+ | 0.0237 | 20.0 | 7500 | 0.7424 | 0.8735 |
88
+ | 0.0011 | 21.0 | 7875 | 0.7919 | 0.8802 |
89
+ | 0.0017 | 22.0 | 8250 | 0.8106 | 0.8918 |
90
+ | 0.0086 | 23.0 | 8625 | 0.8451 | 0.8735 |
91
+ | 0.0037 | 24.0 | 9000 | 0.8674 | 0.8735 |
92
+ | 0.0002 | 25.0 | 9375 | 0.8393 | 0.8869 |
93
+ | 0.0036 | 26.0 | 9750 | 0.8897 | 0.8902 |
94
+ | 0.0019 | 27.0 | 10125 | 0.8685 | 0.8885 |
95
+ | 0.0 | 28.0 | 10500 | 0.8366 | 0.8902 |
96
+ | 0.0007 | 29.0 | 10875 | 0.9524 | 0.8985 |
97
+ | 0.0002 | 30.0 | 11250 | 0.9036 | 0.8918 |
98
+ | 0.0073 | 31.0 | 11625 | 0.9747 | 0.8935 |
99
+ | 0.0057 | 32.0 | 12000 | 0.9823 | 0.8885 |
100
+ | 0.0116 | 33.0 | 12375 | 0.9806 | 0.8935 |
101
+ | 0.0 | 34.0 | 12750 | 1.0179 | 0.8885 |
102
+ | 0.0 | 35.0 | 13125 | 1.0978 | 0.8785 |
103
+ | 0.0 | 36.0 | 13500 | 0.9957 | 0.8852 |
104
+ | 0.0 | 37.0 | 13875 | 1.0261 | 0.8902 |
105
+ | 0.0 | 38.0 | 14250 | 1.0512 | 0.8885 |
106
+ | 0.0 | 39.0 | 14625 | 1.0513 | 0.8902 |
107
+ | 0.0035 | 40.0 | 15000 | 1.0782 | 0.8902 |
108
+ | 0.0 | 41.0 | 15375 | 1.0839 | 0.8885 |
109
+ | 0.0032 | 42.0 | 15750 | 1.1078 | 0.8885 |
110
+ | 0.0027 | 43.0 | 16125 | 1.1099 | 0.8902 |
111
+ | 0.0028 | 44.0 | 16500 | 1.1218 | 0.8902 |
112
+ | 0.0032 | 45.0 | 16875 | 1.1207 | 0.8885 |
113
+ | 0.0 | 46.0 | 17250 | 1.1330 | 0.8885 |
114
+ | 0.0059 | 47.0 | 17625 | 1.1405 | 0.8885 |
115
+ | 0.0 | 48.0 | 18000 | 1.1472 | 0.8885 |
116
+ | 0.0026 | 49.0 | 18375 | 1.1507 | 0.8885 |
117
+ | 0.0022 | 50.0 | 18750 | 1.1513 | 0.8902 |
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 sha256:3944ba9ffcf20a7ea4bbee51e3f4e181009d1e7286dea4ca59cfa0f700b38376
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bfbc9eab17a5cefe7d35ec477b1d6016695084c08560d097945a8df009229d
3
  size 22167850