Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_adamax_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
a94c1a8
·
1 Parent(s): 7114801

End of training

Browse files
Files changed (2) hide show
  1. README.md +54 -54
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5777777777777777
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 3.1828
36
- - Accuracy: 0.5778
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
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
@@ -65,56 +65,56 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | No log | 1.0 | 6 | 1.5039 | 0.2444 |
69
- | 1.9347 | 2.0 | 12 | 1.3951 | 0.2444 |
70
- | 1.9347 | 3.0 | 18 | 1.5970 | 0.2444 |
71
- | 1.3507 | 4.0 | 24 | 1.5883 | 0.2444 |
72
- | 1.2448 | 5.0 | 30 | 1.2899 | 0.3111 |
73
- | 1.2448 | 6.0 | 36 | 1.2061 | 0.3333 |
74
- | 1.0721 | 7.0 | 42 | 1.5421 | 0.4444 |
75
- | 1.0721 | 8.0 | 48 | 1.5331 | 0.2667 |
76
- | 1.0322 | 9.0 | 54 | 1.2467 | 0.4889 |
77
- | 1.0027 | 10.0 | 60 | 1.1754 | 0.4667 |
78
- | 1.0027 | 11.0 | 66 | 1.3260 | 0.4444 |
79
- | 0.8782 | 12.0 | 72 | 1.4220 | 0.3778 |
80
- | 0.8782 | 13.0 | 78 | 1.2909 | 0.3778 |
81
- | 0.9336 | 14.0 | 84 | 1.2228 | 0.3778 |
82
- | 0.8518 | 15.0 | 90 | 1.3127 | 0.4889 |
83
- | 0.8518 | 16.0 | 96 | 1.2461 | 0.5111 |
84
- | 0.6856 | 17.0 | 102 | 1.5495 | 0.5111 |
85
- | 0.6856 | 18.0 | 108 | 1.4003 | 0.4444 |
86
- | 0.6629 | 19.0 | 114 | 1.6481 | 0.5111 |
87
- | 0.6106 | 20.0 | 120 | 1.4665 | 0.5111 |
88
- | 0.6106 | 21.0 | 126 | 1.3091 | 0.4667 |
89
- | 0.5404 | 22.0 | 132 | 1.6995 | 0.5333 |
90
- | 0.5404 | 23.0 | 138 | 1.3819 | 0.4889 |
91
- | 0.6208 | 24.0 | 144 | 1.4295 | 0.4667 |
92
- | 0.3803 | 25.0 | 150 | 1.5233 | 0.4667 |
93
- | 0.3803 | 26.0 | 156 | 1.8157 | 0.5778 |
94
- | 0.3131 | 27.0 | 162 | 1.2837 | 0.5556 |
95
- | 0.3131 | 28.0 | 168 | 1.8123 | 0.5111 |
96
- | 0.2542 | 29.0 | 174 | 1.9185 | 0.5333 |
97
- | 0.1524 | 30.0 | 180 | 1.7784 | 0.6 |
98
- | 0.1524 | 31.0 | 186 | 2.2830 | 0.5333 |
99
- | 0.0946 | 32.0 | 192 | 2.4060 | 0.5556 |
100
- | 0.0946 | 33.0 | 198 | 2.8614 | 0.4889 |
101
- | 0.1333 | 34.0 | 204 | 2.7119 | 0.5333 |
102
- | 0.1824 | 35.0 | 210 | 2.7486 | 0.4667 |
103
- | 0.1824 | 36.0 | 216 | 2.8911 | 0.5556 |
104
- | 0.0482 | 37.0 | 222 | 2.9042 | 0.5556 |
105
- | 0.0482 | 38.0 | 228 | 2.8283 | 0.5778 |
106
- | 0.0366 | 39.0 | 234 | 3.0321 | 0.5778 |
107
- | 0.051 | 40.0 | 240 | 3.1410 | 0.5778 |
108
- | 0.051 | 41.0 | 246 | 3.1802 | 0.5778 |
109
- | 0.0414 | 42.0 | 252 | 3.1828 | 0.5778 |
110
- | 0.0414 | 43.0 | 258 | 3.1828 | 0.5778 |
111
- | 0.0218 | 44.0 | 264 | 3.1828 | 0.5778 |
112
- | 0.0134 | 45.0 | 270 | 3.1828 | 0.5778 |
113
- | 0.0134 | 46.0 | 276 | 3.1828 | 0.5778 |
114
- | 0.0227 | 47.0 | 282 | 3.1828 | 0.5778 |
115
- | 0.0227 | 48.0 | 288 | 3.1828 | 0.5778 |
116
- | 0.0135 | 49.0 | 294 | 3.1828 | 0.5778 |
117
- | 0.0221 | 50.0 | 300 | 3.1828 | 0.5778 |
118
 
119
 
120
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 1.6766
36
+ - Accuracy: 0.6
37
 
38
  ## Model description
39
 
 
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
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | No log | 1.0 | 6 | 1.3194 | 0.2889 |
69
+ | 1.3705 | 2.0 | 12 | 1.2766 | 0.3778 |
70
+ | 1.3705 | 3.0 | 18 | 1.3268 | 0.5333 |
71
+ | 0.7361 | 4.0 | 24 | 1.2927 | 0.5556 |
72
+ | 0.3404 | 5.0 | 30 | 1.3610 | 0.5556 |
73
+ | 0.3404 | 6.0 | 36 | 1.1429 | 0.5778 |
74
+ | 0.1188 | 7.0 | 42 | 1.5833 | 0.5333 |
75
+ | 0.1188 | 8.0 | 48 | 1.2765 | 0.6667 |
76
+ | 0.0229 | 9.0 | 54 | 1.4099 | 0.6222 |
77
+ | 0.0046 | 10.0 | 60 | 1.4395 | 0.6 |
78
+ | 0.0046 | 11.0 | 66 | 1.6161 | 0.5556 |
79
+ | 0.0013 | 12.0 | 72 | 1.5774 | 0.5778 |
80
+ | 0.0013 | 13.0 | 78 | 1.5201 | 0.6 |
81
+ | 0.0007 | 14.0 | 84 | 1.5608 | 0.6 |
82
+ | 0.0005 | 15.0 | 90 | 1.6187 | 0.5778 |
83
+ | 0.0005 | 16.0 | 96 | 1.6424 | 0.5778 |
84
+ | 0.0004 | 17.0 | 102 | 1.6470 | 0.5778 |
85
+ | 0.0004 | 18.0 | 108 | 1.6480 | 0.6 |
86
+ | 0.0003 | 19.0 | 114 | 1.6471 | 0.6 |
87
+ | 0.0003 | 20.0 | 120 | 1.6450 | 0.6 |
88
+ | 0.0003 | 21.0 | 126 | 1.6532 | 0.6 |
89
+ | 0.0003 | 22.0 | 132 | 1.6559 | 0.6 |
90
+ | 0.0003 | 23.0 | 138 | 1.6612 | 0.6 |
91
+ | 0.0003 | 24.0 | 144 | 1.6668 | 0.6 |
92
+ | 0.0002 | 25.0 | 150 | 1.6718 | 0.6 |
93
+ | 0.0002 | 26.0 | 156 | 1.6748 | 0.6 |
94
+ | 0.0002 | 27.0 | 162 | 1.6728 | 0.6 |
95
+ | 0.0002 | 28.0 | 168 | 1.6726 | 0.6 |
96
+ | 0.0002 | 29.0 | 174 | 1.6718 | 0.6 |
97
+ | 0.0002 | 30.0 | 180 | 1.6716 | 0.6 |
98
+ | 0.0002 | 31.0 | 186 | 1.6738 | 0.6 |
99
+ | 0.0002 | 32.0 | 192 | 1.6734 | 0.6 |
100
+ | 0.0002 | 33.0 | 198 | 1.6748 | 0.6 |
101
+ | 0.0002 | 34.0 | 204 | 1.6753 | 0.6 |
102
+ | 0.0002 | 35.0 | 210 | 1.6740 | 0.6 |
103
+ | 0.0002 | 36.0 | 216 | 1.6735 | 0.6 |
104
+ | 0.0002 | 37.0 | 222 | 1.6732 | 0.6 |
105
+ | 0.0002 | 38.0 | 228 | 1.6740 | 0.6 |
106
+ | 0.0002 | 39.0 | 234 | 1.6751 | 0.6 |
107
+ | 0.0002 | 40.0 | 240 | 1.6758 | 0.6 |
108
+ | 0.0002 | 41.0 | 246 | 1.6766 | 0.6 |
109
+ | 0.0002 | 42.0 | 252 | 1.6766 | 0.6 |
110
+ | 0.0002 | 43.0 | 258 | 1.6766 | 0.6 |
111
+ | 0.0002 | 44.0 | 264 | 1.6766 | 0.6 |
112
+ | 0.0002 | 45.0 | 270 | 1.6766 | 0.6 |
113
+ | 0.0002 | 46.0 | 276 | 1.6766 | 0.6 |
114
+ | 0.0002 | 47.0 | 282 | 1.6766 | 0.6 |
115
+ | 0.0002 | 48.0 | 288 | 1.6766 | 0.6 |
116
+ | 0.0002 | 49.0 | 294 | 1.6766 | 0.6 |
117
+ | 0.0002 | 50.0 | 300 | 1.6766 | 0.6 |
118
 
119
 
120
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e3a65f56826247199a6484f9cfbd1b890d22cf2145e0c272a6562d3de31ed14
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4354587da5b05a2ed5e77f0f365f73709a3f9dde0791b63366a6657cbad6644f
3
  size 22123464