Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_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
3a1cd2c
•
1 Parent(s): 1fe27c1

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_1x_deit_tiny_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: 0.6666666666666666
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_tiny_adamax_00001_fold4
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: 0.8218
36
+ - Accuracy: 0.6667
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 | 1.3850 | 0.3333 |
69
+ | 1.4335 | 2.0 | 12 | 1.3341 | 0.3571 |
70
+ | 1.4335 | 3.0 | 18 | 1.2836 | 0.4286 |
71
+ | 1.2369 | 4.0 | 24 | 1.2256 | 0.5238 |
72
+ | 1.1106 | 5.0 | 30 | 1.1743 | 0.4762 |
73
+ | 1.1106 | 6.0 | 36 | 1.1379 | 0.5238 |
74
+ | 0.9897 | 7.0 | 42 | 1.1120 | 0.5952 |
75
+ | 0.9897 | 8.0 | 48 | 1.0871 | 0.6190 |
76
+ | 0.869 | 9.0 | 54 | 1.0617 | 0.5952 |
77
+ | 0.7919 | 10.0 | 60 | 1.0389 | 0.5952 |
78
+ | 0.7919 | 11.0 | 66 | 1.0206 | 0.5714 |
79
+ | 0.7005 | 12.0 | 72 | 1.0005 | 0.5714 |
80
+ | 0.7005 | 13.0 | 78 | 0.9876 | 0.5714 |
81
+ | 0.6273 | 14.0 | 84 | 0.9709 | 0.5952 |
82
+ | 0.5477 | 15.0 | 90 | 0.9546 | 0.5952 |
83
+ | 0.5477 | 16.0 | 96 | 0.9438 | 0.5714 |
84
+ | 0.4708 | 17.0 | 102 | 0.9277 | 0.5952 |
85
+ | 0.4708 | 18.0 | 108 | 0.9166 | 0.6190 |
86
+ | 0.4523 | 19.0 | 114 | 0.9086 | 0.6190 |
87
+ | 0.3797 | 20.0 | 120 | 0.9051 | 0.5952 |
88
+ | 0.3797 | 21.0 | 126 | 0.8956 | 0.6190 |
89
+ | 0.3458 | 22.0 | 132 | 0.8852 | 0.6190 |
90
+ | 0.3458 | 23.0 | 138 | 0.8841 | 0.6190 |
91
+ | 0.3057 | 24.0 | 144 | 0.8804 | 0.5952 |
92
+ | 0.2867 | 25.0 | 150 | 0.8683 | 0.6429 |
93
+ | 0.2867 | 26.0 | 156 | 0.8580 | 0.6667 |
94
+ | 0.2509 | 27.0 | 162 | 0.8515 | 0.6667 |
95
+ | 0.2509 | 28.0 | 168 | 0.8546 | 0.6429 |
96
+ | 0.2322 | 29.0 | 174 | 0.8500 | 0.6667 |
97
+ | 0.2064 | 30.0 | 180 | 0.8396 | 0.6667 |
98
+ | 0.2064 | 31.0 | 186 | 0.8363 | 0.6667 |
99
+ | 0.1928 | 32.0 | 192 | 0.8371 | 0.6667 |
100
+ | 0.1928 | 33.0 | 198 | 0.8332 | 0.6667 |
101
+ | 0.1767 | 34.0 | 204 | 0.8261 | 0.6667 |
102
+ | 0.1746 | 35.0 | 210 | 0.8249 | 0.6667 |
103
+ | 0.1746 | 36.0 | 216 | 0.8258 | 0.6667 |
104
+ | 0.1557 | 37.0 | 222 | 0.8248 | 0.6667 |
105
+ | 0.1557 | 38.0 | 228 | 0.8243 | 0.6667 |
106
+ | 0.1581 | 39.0 | 234 | 0.8225 | 0.6667 |
107
+ | 0.1477 | 40.0 | 240 | 0.8219 | 0.6667 |
108
+ | 0.1477 | 41.0 | 246 | 0.8217 | 0.6667 |
109
+ | 0.149 | 42.0 | 252 | 0.8218 | 0.6667 |
110
+ | 0.149 | 43.0 | 258 | 0.8218 | 0.6667 |
111
+ | 0.1403 | 44.0 | 264 | 0.8218 | 0.6667 |
112
+ | 0.146 | 45.0 | 270 | 0.8218 | 0.6667 |
113
+ | 0.146 | 46.0 | 276 | 0.8218 | 0.6667 |
114
+ | 0.1461 | 47.0 | 282 | 0.8218 | 0.6667 |
115
+ | 0.1461 | 48.0 | 288 | 0.8218 | 0.6667 |
116
+ | 0.1422 | 49.0 | 294 | 0.8218 | 0.6667 |
117
+ | 0.1494 | 50.0 | 300 | 0.8218 | 0.6667 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.0
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.14.6
125
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad9b8e8c39d04970b6a3dff43e59390b5e62307e142a420caee4bc30323d34b0
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ebbe7cd9c76723cbb0f3974fc2d6de0b2621f7dba84656e1b263077d9e1dcd
3
  size 22123464