Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_adamax_00001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
bb01e27
·
1 Parent(s): faee41f

End of training

Browse files
Files changed (2) hide show
  1. README.md +52 -52
  2. model.safetensors +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.8979
36
  - Accuracy: 0.8293
37
 
38
  ## Model description
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0001
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
@@ -65,56 +65,56 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.89 | 1.0 | 28 | 0.6693 | 0.7073 |
69
- | 0.2735 | 2.0 | 56 | 0.4551 | 0.7805 |
70
- | 0.0858 | 3.0 | 84 | 0.6564 | 0.7561 |
71
- | 0.0113 | 4.0 | 112 | 0.7630 | 0.8537 |
72
- | 0.0078 | 5.0 | 140 | 0.5220 | 0.8049 |
73
- | 0.0013 | 6.0 | 168 | 0.8772 | 0.8049 |
74
- | 0.0003 | 7.0 | 196 | 0.7171 | 0.8293 |
75
- | 0.0002 | 8.0 | 224 | 0.7732 | 0.8537 |
76
- | 0.0001 | 9.0 | 252 | 0.7686 | 0.8537 |
77
- | 0.0001 | 10.0 | 280 | 0.7839 | 0.8537 |
78
- | 0.0001 | 11.0 | 308 | 0.7871 | 0.8537 |
79
- | 0.0001 | 12.0 | 336 | 0.7948 | 0.8537 |
80
- | 0.0001 | 13.0 | 364 | 0.8088 | 0.8537 |
81
- | 0.0001 | 14.0 | 392 | 0.8070 | 0.8537 |
82
- | 0.0001 | 15.0 | 420 | 0.8143 | 0.8537 |
83
- | 0.0001 | 16.0 | 448 | 0.8175 | 0.8537 |
84
- | 0.0001 | 17.0 | 476 | 0.8255 | 0.8537 |
85
- | 0.0001 | 18.0 | 504 | 0.8292 | 0.8537 |
86
- | 0.0001 | 19.0 | 532 | 0.8250 | 0.8537 |
87
- | 0.0001 | 20.0 | 560 | 0.8378 | 0.8537 |
88
- | 0.0001 | 21.0 | 588 | 0.8394 | 0.8537 |
89
- | 0.0001 | 22.0 | 616 | 0.8440 | 0.8293 |
90
- | 0.0001 | 23.0 | 644 | 0.8474 | 0.8293 |
91
- | 0.0 | 24.0 | 672 | 0.8547 | 0.8293 |
92
- | 0.0 | 25.0 | 700 | 0.8569 | 0.8293 |
93
- | 0.0 | 26.0 | 728 | 0.8563 | 0.8293 |
94
- | 0.0 | 27.0 | 756 | 0.8612 | 0.8293 |
95
- | 0.0 | 28.0 | 784 | 0.8649 | 0.8293 |
96
- | 0.0 | 29.0 | 812 | 0.8707 | 0.8293 |
97
- | 0.0 | 30.0 | 840 | 0.8644 | 0.8293 |
98
- | 0.0 | 31.0 | 868 | 0.8688 | 0.8293 |
99
- | 0.0 | 32.0 | 896 | 0.8737 | 0.8293 |
100
- | 0.0 | 33.0 | 924 | 0.8760 | 0.8293 |
101
- | 0.0 | 34.0 | 952 | 0.8808 | 0.8293 |
102
- | 0.0 | 35.0 | 980 | 0.8838 | 0.8293 |
103
- | 0.0 | 36.0 | 1008 | 0.8834 | 0.8293 |
104
- | 0.0 | 37.0 | 1036 | 0.8857 | 0.8293 |
105
- | 0.0 | 38.0 | 1064 | 0.8913 | 0.8293 |
106
- | 0.0 | 39.0 | 1092 | 0.8912 | 0.8293 |
107
- | 0.0 | 40.0 | 1120 | 0.8917 | 0.8293 |
108
- | 0.0 | 41.0 | 1148 | 0.8927 | 0.8293 |
109
- | 0.0 | 42.0 | 1176 | 0.8947 | 0.8293 |
110
- | 0.0 | 43.0 | 1204 | 0.8969 | 0.8293 |
111
- | 0.0 | 44.0 | 1232 | 0.8977 | 0.8293 |
112
- | 0.0 | 45.0 | 1260 | 0.8966 | 0.8293 |
113
- | 0.0 | 46.0 | 1288 | 0.8974 | 0.8293 |
114
- | 0.0 | 47.0 | 1316 | 0.8978 | 0.8293 |
115
- | 0.0 | 48.0 | 1344 | 0.8978 | 0.8293 |
116
- | 0.0 | 49.0 | 1372 | 0.8979 | 0.8293 |
117
- | 0.0 | 50.0 | 1400 | 0.8979 | 0.8293 |
118
 
119
 
120
  ### Framework versions
 
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: 1.0196
36
  - Accuracy: 0.8293
37
 
38
  ## Model description
 
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
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.3464 | 1.0 | 28 | 1.2206 | 0.4390 |
69
+ | 1.038 | 2.0 | 56 | 1.1163 | 0.4390 |
70
+ | 0.9036 | 3.0 | 84 | 1.0326 | 0.5122 |
71
+ | 0.7256 | 4.0 | 112 | 0.9850 | 0.4634 |
72
+ | 0.6091 | 5.0 | 140 | 0.9299 | 0.5366 |
73
+ | 0.5118 | 6.0 | 168 | 0.8096 | 0.6098 |
74
+ | 0.3976 | 7.0 | 196 | 0.8337 | 0.6341 |
75
+ | 0.2983 | 8.0 | 224 | 0.8361 | 0.6829 |
76
+ | 0.2464 | 9.0 | 252 | 0.7489 | 0.6829 |
77
+ | 0.1797 | 10.0 | 280 | 0.7126 | 0.7317 |
78
+ | 0.155 | 11.0 | 308 | 0.7190 | 0.7317 |
79
+ | 0.1087 | 12.0 | 336 | 0.7349 | 0.7561 |
80
+ | 0.0817 | 13.0 | 364 | 0.6756 | 0.7805 |
81
+ | 0.0808 | 14.0 | 392 | 0.7587 | 0.7561 |
82
+ | 0.0526 | 15.0 | 420 | 0.6534 | 0.7805 |
83
+ | 0.0415 | 16.0 | 448 | 0.7396 | 0.7805 |
84
+ | 0.0249 | 17.0 | 476 | 0.7772 | 0.8049 |
85
+ | 0.0224 | 18.0 | 504 | 0.7783 | 0.8049 |
86
+ | 0.016 | 19.0 | 532 | 0.8153 | 0.7805 |
87
+ | 0.0121 | 20.0 | 560 | 0.8052 | 0.8049 |
88
+ | 0.0082 | 21.0 | 588 | 0.8047 | 0.8049 |
89
+ | 0.0059 | 22.0 | 616 | 0.8544 | 0.8049 |
90
+ | 0.0042 | 23.0 | 644 | 0.9271 | 0.7805 |
91
+ | 0.0032 | 24.0 | 672 | 0.8999 | 0.8049 |
92
+ | 0.0029 | 25.0 | 700 | 0.9068 | 0.8293 |
93
+ | 0.0025 | 26.0 | 728 | 0.9094 | 0.8293 |
94
+ | 0.0022 | 27.0 | 756 | 0.9291 | 0.8293 |
95
+ | 0.0019 | 28.0 | 784 | 0.9347 | 0.8293 |
96
+ | 0.0016 | 29.0 | 812 | 0.9448 | 0.8293 |
97
+ | 0.0016 | 30.0 | 840 | 0.9586 | 0.8293 |
98
+ | 0.0015 | 31.0 | 868 | 0.9704 | 0.8293 |
99
+ | 0.0013 | 32.0 | 896 | 0.9735 | 0.8293 |
100
+ | 0.0013 | 33.0 | 924 | 0.9776 | 0.8293 |
101
+ | 0.0012 | 34.0 | 952 | 0.9829 | 0.8293 |
102
+ | 0.0011 | 35.0 | 980 | 0.9923 | 0.8293 |
103
+ | 0.0011 | 36.0 | 1008 | 0.9922 | 0.8293 |
104
+ | 0.001 | 37.0 | 1036 | 0.9983 | 0.8293 |
105
+ | 0.001 | 38.0 | 1064 | 1.0035 | 0.8293 |
106
+ | 0.0009 | 39.0 | 1092 | 0.9985 | 0.8293 |
107
+ | 0.0009 | 40.0 | 1120 | 1.0064 | 0.8293 |
108
+ | 0.0009 | 41.0 | 1148 | 1.0089 | 0.8293 |
109
+ | 0.0008 | 42.0 | 1176 | 1.0130 | 0.8293 |
110
+ | 0.0008 | 43.0 | 1204 | 1.0152 | 0.8293 |
111
+ | 0.0009 | 44.0 | 1232 | 1.0185 | 0.8293 |
112
+ | 0.0009 | 45.0 | 1260 | 1.0165 | 0.8293 |
113
+ | 0.0009 | 46.0 | 1288 | 1.0180 | 0.8293 |
114
+ | 0.0008 | 47.0 | 1316 | 1.0182 | 0.8293 |
115
+ | 0.0008 | 48.0 | 1344 | 1.0196 | 0.8293 |
116
+ | 0.0008 | 49.0 | 1372 | 1.0196 | 0.8293 |
117
+ | 0.0008 | 50.0 | 1400 | 1.0196 | 0.8293 |
118
 
119
 
120
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:028f4840ee787c64e5c232f202eadcf4604cf8a07ac95af0db555a4aaeaf3f1b
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6ae7fdee352cfb9c904c2a9cb75019031ec3290618bf195ba97215412574df
3
  size 22123464