Hugging Face's logo

hkivancoral
/
smids_3x_beit_base_adamax_00001_fold3

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
90af8d9
•
1 Parent(s): a4b288b

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: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_beit_base_adamax_00001_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: 0.9066666666666666
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_beit_base_adamax_00001_fold3
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8012
36
+ - Accuracy: 0.9067
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
+ | 0.3558 | 1.0 | 225 | 0.2857 | 0.8817 |
69
+ | 0.2025 | 2.0 | 450 | 0.2548 | 0.9083 |
70
+ | 0.1598 | 3.0 | 675 | 0.2521 | 0.92 |
71
+ | 0.1219 | 4.0 | 900 | 0.2685 | 0.9067 |
72
+ | 0.1177 | 5.0 | 1125 | 0.2855 | 0.9167 |
73
+ | 0.0821 | 6.0 | 1350 | 0.3265 | 0.915 |
74
+ | 0.035 | 7.0 | 1575 | 0.3390 | 0.9133 |
75
+ | 0.0488 | 8.0 | 1800 | 0.3876 | 0.91 |
76
+ | 0.0333 | 9.0 | 2025 | 0.4069 | 0.9183 |
77
+ | 0.0137 | 10.0 | 2250 | 0.4823 | 0.895 |
78
+ | 0.0425 | 11.0 | 2475 | 0.4830 | 0.91 |
79
+ | 0.0131 | 12.0 | 2700 | 0.5278 | 0.9067 |
80
+ | 0.0362 | 13.0 | 2925 | 0.5365 | 0.91 |
81
+ | 0.0127 | 14.0 | 3150 | 0.5604 | 0.91 |
82
+ | 0.0059 | 15.0 | 3375 | 0.5988 | 0.9067 |
83
+ | 0.0457 | 16.0 | 3600 | 0.6291 | 0.8983 |
84
+ | 0.0096 | 17.0 | 3825 | 0.6121 | 0.905 |
85
+ | 0.0291 | 18.0 | 4050 | 0.6425 | 0.91 |
86
+ | 0.0279 | 19.0 | 4275 | 0.6328 | 0.9017 |
87
+ | 0.006 | 20.0 | 4500 | 0.7129 | 0.905 |
88
+ | 0.0195 | 21.0 | 4725 | 0.7320 | 0.9017 |
89
+ | 0.0002 | 22.0 | 4950 | 0.7512 | 0.9017 |
90
+ | 0.0352 | 23.0 | 5175 | 0.7248 | 0.9067 |
91
+ | 0.0032 | 24.0 | 5400 | 0.7414 | 0.9 |
92
+ | 0.0649 | 25.0 | 5625 | 0.7106 | 0.915 |
93
+ | 0.0454 | 26.0 | 5850 | 0.7165 | 0.91 |
94
+ | 0.0011 | 27.0 | 6075 | 0.7232 | 0.915 |
95
+ | 0.0041 | 28.0 | 6300 | 0.7095 | 0.9117 |
96
+ | 0.0099 | 29.0 | 6525 | 0.7308 | 0.9083 |
97
+ | 0.0129 | 30.0 | 6750 | 0.7895 | 0.9083 |
98
+ | 0.0212 | 31.0 | 6975 | 0.7650 | 0.91 |
99
+ | 0.0018 | 32.0 | 7200 | 0.7684 | 0.9083 |
100
+ | 0.0006 | 33.0 | 7425 | 0.7607 | 0.9133 |
101
+ | 0.0001 | 34.0 | 7650 | 0.7555 | 0.9117 |
102
+ | 0.0002 | 35.0 | 7875 | 0.7851 | 0.9083 |
103
+ | 0.0002 | 36.0 | 8100 | 0.7601 | 0.9117 |
104
+ | 0.0002 | 37.0 | 8325 | 0.7878 | 0.9083 |
105
+ | 0.0284 | 38.0 | 8550 | 0.7877 | 0.9083 |
106
+ | 0.0007 | 39.0 | 8775 | 0.7993 | 0.9067 |
107
+ | 0.002 | 40.0 | 9000 | 0.7969 | 0.91 |
108
+ | 0.0004 | 41.0 | 9225 | 0.8163 | 0.9083 |
109
+ | 0.0234 | 42.0 | 9450 | 0.7871 | 0.915 |
110
+ | 0.0006 | 43.0 | 9675 | 0.8006 | 0.9067 |
111
+ | 0.0004 | 44.0 | 9900 | 0.7989 | 0.9083 |
112
+ | 0.0007 | 45.0 | 10125 | 0.8058 | 0.9067 |
113
+ | 0.0174 | 46.0 | 10350 | 0.8151 | 0.9017 |
114
+ | 0.0003 | 47.0 | 10575 | 0.8093 | 0.9033 |
115
+ | 0.0 | 48.0 | 10800 | 0.8021 | 0.9067 |
116
+ | 0.0012 | 49.0 | 11025 | 0.8063 | 0.9067 |
117
+ | 0.0009 | 50.0 | 11250 | 0.8012 | 0.9067 |
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 sha256:7cfbfe01a5aac0570e851d9b14bf590198a2821546cab43f23422932afbb471e
3
  size 343133766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a82fdb8744105b6ad6fad0db50d32c1a2820b876bf730d7599204406ec51b6
3
  size 343133766