Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_rms_lr001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
677efc4
·
1 Parent(s): 2eec58e

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_fold5
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: 0.5365853658536586
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_fold5
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: 1.0599
36
+ - Accuracy: 0.5366
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 | 2.6067 | 0.2439 |
69
+ | 4.0909 | 2.0 | 12 | 1.8085 | 0.2439 |
70
+ | 4.0909 | 3.0 | 18 | 1.7809 | 0.2439 |
71
+ | 2.0948 | 4.0 | 24 | 1.7586 | 0.2439 |
72
+ | 1.6719 | 5.0 | 30 | 1.5135 | 0.2439 |
73
+ | 1.6719 | 6.0 | 36 | 1.7849 | 0.2683 |
74
+ | 1.5694 | 7.0 | 42 | 1.4636 | 0.3902 |
75
+ | 1.5694 | 8.0 | 48 | 1.4809 | 0.2683 |
76
+ | 1.519 | 9.0 | 54 | 1.3587 | 0.3415 |
77
+ | 1.5241 | 10.0 | 60 | 1.3823 | 0.2439 |
78
+ | 1.5241 | 11.0 | 66 | 1.3645 | 0.3415 |
79
+ | 1.4557 | 12.0 | 72 | 1.2525 | 0.3659 |
80
+ | 1.4557 | 13.0 | 78 | 1.2955 | 0.3171 |
81
+ | 1.3674 | 14.0 | 84 | 1.3174 | 0.3415 |
82
+ | 1.3868 | 15.0 | 90 | 1.2787 | 0.3415 |
83
+ | 1.3868 | 16.0 | 96 | 1.6408 | 0.2683 |
84
+ | 1.3152 | 17.0 | 102 | 1.2750 | 0.3171 |
85
+ | 1.3152 | 18.0 | 108 | 1.0560 | 0.5366 |
86
+ | 1.2693 | 19.0 | 114 | 1.3256 | 0.4878 |
87
+ | 1.2554 | 20.0 | 120 | 1.3190 | 0.3902 |
88
+ | 1.2554 | 21.0 | 126 | 1.2498 | 0.3902 |
89
+ | 1.1813 | 22.0 | 132 | 1.2514 | 0.3902 |
90
+ | 1.1813 | 23.0 | 138 | 1.0907 | 0.5366 |
91
+ | 1.1113 | 24.0 | 144 | 1.2821 | 0.3415 |
92
+ | 1.1728 | 25.0 | 150 | 1.1433 | 0.4878 |
93
+ | 1.1728 | 26.0 | 156 | 1.0143 | 0.5366 |
94
+ | 1.1037 | 27.0 | 162 | 0.9542 | 0.5854 |
95
+ | 1.1037 | 28.0 | 168 | 1.1443 | 0.5122 |
96
+ | 1.0914 | 29.0 | 174 | 1.0904 | 0.4878 |
97
+ | 1.1385 | 30.0 | 180 | 1.1995 | 0.4146 |
98
+ | 1.1385 | 31.0 | 186 | 0.9746 | 0.6098 |
99
+ | 1.0636 | 32.0 | 192 | 1.1104 | 0.4634 |
100
+ | 1.0636 | 33.0 | 198 | 0.9890 | 0.6098 |
101
+ | 1.0129 | 34.0 | 204 | 1.2113 | 0.3902 |
102
+ | 0.999 | 35.0 | 210 | 1.0001 | 0.6098 |
103
+ | 0.999 | 36.0 | 216 | 1.0972 | 0.5122 |
104
+ | 0.9802 | 37.0 | 222 | 1.1639 | 0.4390 |
105
+ | 0.9802 | 38.0 | 228 | 1.0730 | 0.5122 |
106
+ | 0.9625 | 39.0 | 234 | 1.0471 | 0.4878 |
107
+ | 0.9424 | 40.0 | 240 | 1.0692 | 0.5366 |
108
+ | 0.9424 | 41.0 | 246 | 1.0654 | 0.5366 |
109
+ | 0.9521 | 42.0 | 252 | 1.0599 | 0.5366 |
110
+ | 0.9521 | 43.0 | 258 | 1.0599 | 0.5366 |
111
+ | 0.9184 | 44.0 | 264 | 1.0599 | 0.5366 |
112
+ | 0.9335 | 45.0 | 270 | 1.0599 | 0.5366 |
113
+ | 0.9335 | 46.0 | 276 | 1.0599 | 0.5366 |
114
+ | 0.9251 | 47.0 | 282 | 1.0599 | 0.5366 |
115
+ | 0.9251 | 48.0 | 288 | 1.0599 | 0.5366 |
116
+ | 0.9168 | 49.0 | 294 | 1.0599 | 0.5366 |
117
+ | 0.8964 | 50.0 | 300 | 1.0599 | 0.5366 |
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 sha256:50618c7819373ac3367dae6af2f11931c4ab5a201e025566a321de50c072db8f
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf917e40f57c947d888bd61c2299a83577f364e3e09fddc27aebaabcd2b88854
3
  size 22123464