Hugging Face's logo

hkivancoral
/
smids_3x_deit_base_adamax_00001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
09dc79d
•
1 Parent(s): 842492d

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-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_base_adamax_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: 0.8818635607321131
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_base_adamax_00001_fold2
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.7483
36
+ - Accuracy: 0.8819
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
+ | 0.2908 | 1.0 | 225 | 0.3519 | 0.8469 |
69
+ | 0.2412 | 2.0 | 450 | 0.3425 | 0.8652 |
70
+ | 0.1561 | 3.0 | 675 | 0.3113 | 0.8752 |
71
+ | 0.1722 | 4.0 | 900 | 0.3333 | 0.8819 |
72
+ | 0.0793 | 5.0 | 1125 | 0.3397 | 0.8869 |
73
+ | 0.0512 | 6.0 | 1350 | 0.3703 | 0.8902 |
74
+ | 0.0408 | 7.0 | 1575 | 0.3948 | 0.8869 |
75
+ | 0.0153 | 8.0 | 1800 | 0.4474 | 0.8852 |
76
+ | 0.0036 | 9.0 | 2025 | 0.5055 | 0.8819 |
77
+ | 0.0009 | 10.0 | 2250 | 0.5138 | 0.8918 |
78
+ | 0.0011 | 11.0 | 2475 | 0.5776 | 0.8752 |
79
+ | 0.0004 | 12.0 | 2700 | 0.6002 | 0.8785 |
80
+ | 0.0004 | 13.0 | 2925 | 0.6053 | 0.8819 |
81
+ | 0.0002 | 14.0 | 3150 | 0.6097 | 0.8918 |
82
+ | 0.0002 | 15.0 | 3375 | 0.6366 | 0.8819 |
83
+ | 0.0001 | 16.0 | 3600 | 0.6507 | 0.8819 |
84
+ | 0.0042 | 17.0 | 3825 | 0.6732 | 0.8869 |
85
+ | 0.0001 | 18.0 | 4050 | 0.6626 | 0.8852 |
86
+ | 0.0001 | 19.0 | 4275 | 0.6800 | 0.8885 |
87
+ | 0.0001 | 20.0 | 4500 | 0.6886 | 0.8852 |
88
+ | 0.0001 | 21.0 | 4725 | 0.7001 | 0.8819 |
89
+ | 0.0001 | 22.0 | 4950 | 0.7256 | 0.8869 |
90
+ | 0.008 | 23.0 | 5175 | 0.7472 | 0.8918 |
91
+ | 0.0001 | 24.0 | 5400 | 0.7160 | 0.8835 |
92
+ | 0.0075 | 25.0 | 5625 | 0.7354 | 0.8852 |
93
+ | 0.0001 | 26.0 | 5850 | 0.7213 | 0.8819 |
94
+ | 0.0001 | 27.0 | 6075 | 0.7101 | 0.8835 |
95
+ | 0.0 | 28.0 | 6300 | 0.7245 | 0.8819 |
96
+ | 0.0001 | 29.0 | 6525 | 0.7475 | 0.8869 |
97
+ | 0.0058 | 30.0 | 6750 | 0.7235 | 0.8852 |
98
+ | 0.0 | 31.0 | 6975 | 0.7151 | 0.8852 |
99
+ | 0.0 | 32.0 | 7200 | 0.7303 | 0.8852 |
100
+ | 0.0 | 33.0 | 7425 | 0.7353 | 0.8835 |
101
+ | 0.0 | 34.0 | 7650 | 0.7337 | 0.8835 |
102
+ | 0.0 | 35.0 | 7875 | 0.7550 | 0.8835 |
103
+ | 0.0034 | 36.0 | 8100 | 0.7409 | 0.8885 |
104
+ | 0.0 | 37.0 | 8325 | 0.7323 | 0.8769 |
105
+ | 0.0 | 38.0 | 8550 | 0.7381 | 0.8835 |
106
+ | 0.0026 | 39.0 | 8775 | 0.7392 | 0.8819 |
107
+ | 0.0 | 40.0 | 9000 | 0.7428 | 0.8819 |
108
+ | 0.0 | 41.0 | 9225 | 0.7496 | 0.8835 |
109
+ | 0.0 | 42.0 | 9450 | 0.7433 | 0.8835 |
110
+ | 0.0 | 43.0 | 9675 | 0.7393 | 0.8852 |
111
+ | 0.0 | 44.0 | 9900 | 0.7435 | 0.8835 |
112
+ | 0.0 | 45.0 | 10125 | 0.7479 | 0.8835 |
113
+ | 0.0 | 46.0 | 10350 | 0.7454 | 0.8835 |
114
+ | 0.0 | 47.0 | 10575 | 0.7458 | 0.8802 |
115
+ | 0.0 | 48.0 | 10800 | 0.7464 | 0.8819 |
116
+ | 0.0037 | 49.0 | 11025 | 0.7477 | 0.8835 |
117
+ | 0.0037 | 50.0 | 11250 | 0.7483 | 0.8819 |
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:ead3522fd63978476e7bff87c0173172cb34e7ebff56fb1a4970ca328a422899
3
  size 343272234
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a230dffb2c4fe45376180a150a53cac4407136d491de57ad594e16e5d8aa935f
3
  size 343272234