Hugging Face's logo

hkivancoral
/
hushem_1x_deit_base_adamax_00001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
113ffce
•
1 Parent(s): 39f170c

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +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: hushem_1x_deit_base_adamax_00001_fold4
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: 0.7619047619047619
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
+ # hushem_1x_deit_base_adamax_00001_fold4
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: 0.5330
36
+ - Accuracy: 0.7619
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
+ | No log | 1.0 | 6 | 1.3484 | 0.2857 |
69
+ | 1.3393 | 2.0 | 12 | 1.3138 | 0.4524 |
70
+ | 1.3393 | 3.0 | 18 | 1.2772 | 0.4048 |
71
+ | 1.1604 | 4.0 | 24 | 1.2261 | 0.4524 |
72
+ | 1.014 | 5.0 | 30 | 1.1685 | 0.4762 |
73
+ | 1.014 | 6.0 | 36 | 1.1130 | 0.5476 |
74
+ | 0.8569 | 7.0 | 42 | 1.0641 | 0.5476 |
75
+ | 0.8569 | 8.0 | 48 | 1.0213 | 0.5476 |
76
+ | 0.7145 | 9.0 | 54 | 0.9685 | 0.5714 |
77
+ | 0.5812 | 10.0 | 60 | 0.9109 | 0.6190 |
78
+ | 0.5812 | 11.0 | 66 | 0.8739 | 0.6905 |
79
+ | 0.4645 | 12.0 | 72 | 0.8376 | 0.6667 |
80
+ | 0.4645 | 13.0 | 78 | 0.8046 | 0.6667 |
81
+ | 0.3784 | 14.0 | 84 | 0.7821 | 0.6667 |
82
+ | 0.308 | 15.0 | 90 | 0.7516 | 0.6905 |
83
+ | 0.308 | 16.0 | 96 | 0.7309 | 0.7143 |
84
+ | 0.2446 | 17.0 | 102 | 0.7113 | 0.7381 |
85
+ | 0.2446 | 18.0 | 108 | 0.6911 | 0.7143 |
86
+ | 0.2032 | 19.0 | 114 | 0.6782 | 0.6905 |
87
+ | 0.1713 | 20.0 | 120 | 0.6649 | 0.7381 |
88
+ | 0.1713 | 21.0 | 126 | 0.6459 | 0.7381 |
89
+ | 0.1338 | 22.0 | 132 | 0.6300 | 0.7143 |
90
+ | 0.1338 | 23.0 | 138 | 0.6291 | 0.7619 |
91
+ | 0.113 | 24.0 | 144 | 0.6105 | 0.8095 |
92
+ | 0.0989 | 25.0 | 150 | 0.5999 | 0.7619 |
93
+ | 0.0989 | 26.0 | 156 | 0.5962 | 0.7857 |
94
+ | 0.0793 | 27.0 | 162 | 0.5828 | 0.7619 |
95
+ | 0.0793 | 28.0 | 168 | 0.5775 | 0.7857 |
96
+ | 0.0704 | 29.0 | 174 | 0.5718 | 0.7857 |
97
+ | 0.0586 | 30.0 | 180 | 0.5598 | 0.7857 |
98
+ | 0.0586 | 31.0 | 186 | 0.5576 | 0.7857 |
99
+ | 0.0498 | 32.0 | 192 | 0.5530 | 0.7857 |
100
+ | 0.0498 | 33.0 | 198 | 0.5470 | 0.7857 |
101
+ | 0.0487 | 34.0 | 204 | 0.5432 | 0.7857 |
102
+ | 0.0426 | 35.0 | 210 | 0.5430 | 0.7619 |
103
+ | 0.0426 | 36.0 | 216 | 0.5406 | 0.7619 |
104
+ | 0.0394 | 37.0 | 222 | 0.5370 | 0.7619 |
105
+ | 0.0394 | 38.0 | 228 | 0.5337 | 0.7619 |
106
+ | 0.039 | 39.0 | 234 | 0.5328 | 0.7619 |
107
+ | 0.0365 | 40.0 | 240 | 0.5330 | 0.7619 |
108
+ | 0.0365 | 41.0 | 246 | 0.5331 | 0.7619 |
109
+ | 0.0366 | 42.0 | 252 | 0.5330 | 0.7619 |
110
+ | 0.0366 | 43.0 | 258 | 0.5330 | 0.7619 |
111
+ | 0.0347 | 44.0 | 264 | 0.5330 | 0.7619 |
112
+ | 0.0374 | 45.0 | 270 | 0.5330 | 0.7619 |
113
+ | 0.0374 | 46.0 | 276 | 0.5330 | 0.7619 |
114
+ | 0.0363 | 47.0 | 282 | 0.5330 | 0.7619 |
115
+ | 0.0363 | 48.0 | 288 | 0.5330 | 0.7619 |
116
+ | 0.0346 | 49.0 | 294 | 0.5330 | 0.7619 |
117
+ | 0.0366 | 50.0 | 300 | 0.5330 | 0.7619 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.14.7
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fdaf57b1654c86daca78d94f0cb3a4ce8395200ee50dbdcddd221e115cb6776
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf1bbe8e346974931e1b452dd3c80f36a0d731cdf0550305c31b516f74f951b
3
  size 343230128