Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_rms_lr001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
63e871d
·
1 Parent(s): a1c59ab

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_rms_lr001_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: 0.4523809523809524
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_rms_lr001_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: 1.1726
36
+ - Accuracy: 0.4524
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: 0.001
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 | 5.8408 | 0.2619 |
69
+ | 4.7138 | 2.0 | 12 | 1.8632 | 0.2381 |
70
+ | 4.7138 | 3.0 | 18 | 1.9369 | 0.2619 |
71
+ | 1.8439 | 4.0 | 24 | 1.7584 | 0.2381 |
72
+ | 1.6449 | 5.0 | 30 | 1.4723 | 0.2619 |
73
+ | 1.6449 | 6.0 | 36 | 1.7187 | 0.2381 |
74
+ | 1.5171 | 7.0 | 42 | 1.4960 | 0.2381 |
75
+ | 1.5171 | 8.0 | 48 | 1.3962 | 0.2619 |
76
+ | 1.4701 | 9.0 | 54 | 1.4942 | 0.2619 |
77
+ | 1.4652 | 10.0 | 60 | 1.3642 | 0.2381 |
78
+ | 1.4652 | 11.0 | 66 | 1.4490 | 0.2619 |
79
+ | 1.4547 | 12.0 | 72 | 1.1912 | 0.4524 |
80
+ | 1.4547 | 13.0 | 78 | 1.4737 | 0.2857 |
81
+ | 1.3944 | 14.0 | 84 | 1.2170 | 0.4286 |
82
+ | 1.3536 | 15.0 | 90 | 1.3540 | 0.2381 |
83
+ | 1.3536 | 16.0 | 96 | 1.0819 | 0.6190 |
84
+ | 1.2835 | 17.0 | 102 | 1.1640 | 0.4286 |
85
+ | 1.2835 | 18.0 | 108 | 1.2309 | 0.3333 |
86
+ | 1.306 | 19.0 | 114 | 1.3288 | 0.2857 |
87
+ | 1.2522 | 20.0 | 120 | 1.4561 | 0.2857 |
88
+ | 1.2522 | 21.0 | 126 | 1.0774 | 0.4762 |
89
+ | 1.2491 | 22.0 | 132 | 1.1807 | 0.4286 |
90
+ | 1.2491 | 23.0 | 138 | 1.1668 | 0.3810 |
91
+ | 1.1882 | 24.0 | 144 | 1.2075 | 0.4286 |
92
+ | 1.2028 | 25.0 | 150 | 1.2635 | 0.3333 |
93
+ | 1.2028 | 26.0 | 156 | 1.1653 | 0.3810 |
94
+ | 1.1822 | 27.0 | 162 | 1.1741 | 0.4048 |
95
+ | 1.1822 | 28.0 | 168 | 1.4014 | 0.2619 |
96
+ | 1.1086 | 29.0 | 174 | 1.0259 | 0.5476 |
97
+ | 1.1111 | 30.0 | 180 | 1.1225 | 0.5238 |
98
+ | 1.1111 | 31.0 | 186 | 1.1813 | 0.5 |
99
+ | 1.0458 | 32.0 | 192 | 1.1678 | 0.4286 |
100
+ | 1.0458 | 33.0 | 198 | 1.1915 | 0.4048 |
101
+ | 1.1348 | 34.0 | 204 | 1.3148 | 0.5 |
102
+ | 0.9776 | 35.0 | 210 | 1.0082 | 0.5238 |
103
+ | 0.9776 | 36.0 | 216 | 0.9144 | 0.6190 |
104
+ | 0.9456 | 37.0 | 222 | 1.0677 | 0.4762 |
105
+ | 0.9456 | 38.0 | 228 | 1.0695 | 0.5238 |
106
+ | 0.8714 | 39.0 | 234 | 1.1982 | 0.4762 |
107
+ | 0.8643 | 40.0 | 240 | 1.1143 | 0.4048 |
108
+ | 0.8643 | 41.0 | 246 | 1.1270 | 0.4524 |
109
+ | 0.7971 | 42.0 | 252 | 1.1726 | 0.4524 |
110
+ | 0.7971 | 43.0 | 258 | 1.1726 | 0.4524 |
111
+ | 0.7662 | 44.0 | 264 | 1.1726 | 0.4524 |
112
+ | 0.7801 | 45.0 | 270 | 1.1726 | 0.4524 |
113
+ | 0.7801 | 46.0 | 276 | 1.1726 | 0.4524 |
114
+ | 0.7773 | 47.0 | 282 | 1.1726 | 0.4524 |
115
+ | 0.7773 | 48.0 | 288 | 1.1726 | 0.4524 |
116
+ | 0.7728 | 49.0 | 294 | 1.1726 | 0.4524 |
117
+ | 0.7828 | 50.0 | 300 | 1.1726 | 0.4524 |
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 sha256:7f6f0b72fa542be615981577c3d68b2fa0f9975bbf78d253581a005563d18795
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1152909c7dc96f3ce2c01078984d9cbdeaa71fa49f3d8db2fd2dc0e70cc74dc6
3
  size 22123464