Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_rms_lr0001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
7b886c5
·
1 Parent(s): 6d920a5

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_lr0001_fold1
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: 0.5777777777777777
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_lr0001_fold1
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: 3.0724
36
+ - Accuracy: 0.5778
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: 0.0001
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 | 1.7581 | 0.2444 |
69
+ | 2.2176 | 2.0 | 12 | 1.4575 | 0.2444 |
70
+ | 2.2176 | 3.0 | 18 | 1.4070 | 0.2444 |
71
+ | 1.4625 | 4.0 | 24 | 1.4089 | 0.2444 |
72
+ | 1.4303 | 5.0 | 30 | 1.4530 | 0.2667 |
73
+ | 1.4303 | 6.0 | 36 | 1.3605 | 0.3778 |
74
+ | 1.3759 | 7.0 | 42 | 1.4068 | 0.3778 |
75
+ | 1.3759 | 8.0 | 48 | 1.3279 | 0.2889 |
76
+ | 1.3199 | 9.0 | 54 | 1.5997 | 0.2444 |
77
+ | 1.2335 | 10.0 | 60 | 1.5834 | 0.2444 |
78
+ | 1.2335 | 11.0 | 66 | 1.6144 | 0.3333 |
79
+ | 1.0406 | 12.0 | 72 | 1.1266 | 0.5111 |
80
+ | 1.0406 | 13.0 | 78 | 1.6894 | 0.3556 |
81
+ | 0.851 | 14.0 | 84 | 1.8080 | 0.4444 |
82
+ | 0.5856 | 15.0 | 90 | 2.0552 | 0.3778 |
83
+ | 0.5856 | 16.0 | 96 | 1.3379 | 0.4889 |
84
+ | 0.3402 | 17.0 | 102 | 1.4787 | 0.4889 |
85
+ | 0.3402 | 18.0 | 108 | 2.2439 | 0.4222 |
86
+ | 0.233 | 19.0 | 114 | 1.7239 | 0.4889 |
87
+ | 0.1016 | 20.0 | 120 | 2.5401 | 0.4222 |
88
+ | 0.1016 | 21.0 | 126 | 1.5433 | 0.5778 |
89
+ | 0.0994 | 22.0 | 132 | 1.8891 | 0.5333 |
90
+ | 0.0994 | 23.0 | 138 | 1.9405 | 0.4889 |
91
+ | 0.0839 | 24.0 | 144 | 1.5418 | 0.5778 |
92
+ | 0.0282 | 25.0 | 150 | 2.4010 | 0.5778 |
93
+ | 0.0282 | 26.0 | 156 | 2.6175 | 0.5778 |
94
+ | 0.0011 | 27.0 | 162 | 2.7024 | 0.5778 |
95
+ | 0.0011 | 28.0 | 168 | 2.7954 | 0.5778 |
96
+ | 0.0007 | 29.0 | 174 | 2.8362 | 0.5778 |
97
+ | 0.0006 | 30.0 | 180 | 2.8852 | 0.5778 |
98
+ | 0.0006 | 31.0 | 186 | 2.9050 | 0.5778 |
99
+ | 0.0005 | 32.0 | 192 | 2.9414 | 0.5778 |
100
+ | 0.0005 | 33.0 | 198 | 2.9746 | 0.5778 |
101
+ | 0.0005 | 34.0 | 204 | 2.9947 | 0.5778 |
102
+ | 0.0004 | 35.0 | 210 | 3.0141 | 0.5778 |
103
+ | 0.0004 | 36.0 | 216 | 3.0300 | 0.5778 |
104
+ | 0.0004 | 37.0 | 222 | 3.0447 | 0.5778 |
105
+ | 0.0004 | 38.0 | 228 | 3.0565 | 0.5778 |
106
+ | 0.0003 | 39.0 | 234 | 3.0642 | 0.5778 |
107
+ | 0.0003 | 40.0 | 240 | 3.0696 | 0.5778 |
108
+ | 0.0003 | 41.0 | 246 | 3.0717 | 0.5778 |
109
+ | 0.0003 | 42.0 | 252 | 3.0724 | 0.5778 |
110
+ | 0.0003 | 43.0 | 258 | 3.0724 | 0.5778 |
111
+ | 0.0003 | 44.0 | 264 | 3.0724 | 0.5778 |
112
+ | 0.0003 | 45.0 | 270 | 3.0724 | 0.5778 |
113
+ | 0.0003 | 46.0 | 276 | 3.0724 | 0.5778 |
114
+ | 0.0003 | 47.0 | 282 | 3.0724 | 0.5778 |
115
+ | 0.0003 | 48.0 | 288 | 3.0724 | 0.5778 |
116
+ | 0.0003 | 49.0 | 294 | 3.0724 | 0.5778 |
117
+ | 0.0003 | 50.0 | 300 | 3.0724 | 0.5778 |
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 sha256:29b306b724bd9ed2f6fb1dbcb6f43e0b257683a5fa77dd34962819576eba40f6
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522f6273820ca00f890d0f1a6f77ceb4e9fa16d2394dff8d33cf5873a78cd991
3
  size 22123464