Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_rms_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
891ba53
·
1 Parent(s): aae55e0

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_5x_deit_tiny_rms_001_fold3
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: 0.6976744186046512
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_5x_deit_tiny_rms_001_fold3
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: 0.9822
36
+ - Accuracy: 0.6977
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
+ | 1.9654 | 1.0 | 28 | 2.6283 | 0.2558 |
69
+ | 1.5373 | 2.0 | 56 | 2.1986 | 0.2558 |
70
+ | 1.4995 | 3.0 | 84 | 1.6042 | 0.2558 |
71
+ | 1.4355 | 4.0 | 112 | 1.6838 | 0.2558 |
72
+ | 1.4504 | 5.0 | 140 | 1.5958 | 0.2326 |
73
+ | 1.4097 | 6.0 | 168 | 1.4017 | 0.2791 |
74
+ | 1.4297 | 7.0 | 196 | 1.5664 | 0.2326 |
75
+ | 1.4137 | 8.0 | 224 | 1.4485 | 0.2558 |
76
+ | 1.3745 | 9.0 | 252 | 1.2801 | 0.4186 |
77
+ | 1.2697 | 10.0 | 280 | 1.2764 | 0.3256 |
78
+ | 1.1321 | 11.0 | 308 | 1.5227 | 0.3256 |
79
+ | 1.1096 | 12.0 | 336 | 1.2384 | 0.3953 |
80
+ | 1.0727 | 13.0 | 364 | 1.1395 | 0.4884 |
81
+ | 1.0037 | 14.0 | 392 | 1.3856 | 0.3953 |
82
+ | 1.0402 | 15.0 | 420 | 1.1134 | 0.5116 |
83
+ | 1.0378 | 16.0 | 448 | 1.2506 | 0.4419 |
84
+ | 0.958 | 17.0 | 476 | 1.1080 | 0.4651 |
85
+ | 0.9953 | 18.0 | 504 | 1.2467 | 0.4884 |
86
+ | 0.9958 | 19.0 | 532 | 1.0807 | 0.5814 |
87
+ | 0.9467 | 20.0 | 560 | 1.1055 | 0.4186 |
88
+ | 0.9535 | 21.0 | 588 | 1.1974 | 0.5116 |
89
+ | 0.9184 | 22.0 | 616 | 1.1307 | 0.4186 |
90
+ | 0.9252 | 23.0 | 644 | 1.0833 | 0.5116 |
91
+ | 0.8662 | 24.0 | 672 | 1.1623 | 0.5349 |
92
+ | 0.8421 | 25.0 | 700 | 0.9575 | 0.5814 |
93
+ | 0.8602 | 26.0 | 728 | 1.1189 | 0.5581 |
94
+ | 0.923 | 27.0 | 756 | 1.3369 | 0.5116 |
95
+ | 0.8226 | 28.0 | 784 | 1.0806 | 0.6279 |
96
+ | 0.8183 | 29.0 | 812 | 1.2385 | 0.4186 |
97
+ | 0.801 | 30.0 | 840 | 0.8599 | 0.6744 |
98
+ | 0.7516 | 31.0 | 868 | 1.3471 | 0.4884 |
99
+ | 0.7555 | 32.0 | 896 | 1.0726 | 0.5814 |
100
+ | 0.7219 | 33.0 | 924 | 0.8253 | 0.6977 |
101
+ | 0.7341 | 34.0 | 952 | 0.9501 | 0.6744 |
102
+ | 0.7645 | 35.0 | 980 | 0.9024 | 0.6512 |
103
+ | 0.6775 | 36.0 | 1008 | 0.6982 | 0.6977 |
104
+ | 0.6942 | 37.0 | 1036 | 0.8138 | 0.6744 |
105
+ | 0.6421 | 38.0 | 1064 | 1.1443 | 0.6279 |
106
+ | 0.6108 | 39.0 | 1092 | 0.7170 | 0.6977 |
107
+ | 0.7595 | 40.0 | 1120 | 0.7538 | 0.6744 |
108
+ | 0.6409 | 41.0 | 1148 | 1.2761 | 0.5581 |
109
+ | 0.6168 | 42.0 | 1176 | 1.0481 | 0.6279 |
110
+ | 0.5155 | 43.0 | 1204 | 0.7647 | 0.7209 |
111
+ | 0.5674 | 44.0 | 1232 | 0.9942 | 0.6744 |
112
+ | 0.5763 | 45.0 | 1260 | 0.8142 | 0.6977 |
113
+ | 0.4817 | 46.0 | 1288 | 0.8614 | 0.6977 |
114
+ | 0.4723 | 47.0 | 1316 | 1.0386 | 0.6512 |
115
+ | 0.4863 | 48.0 | 1344 | 0.9689 | 0.7209 |
116
+ | 0.4909 | 49.0 | 1372 | 0.9822 | 0.6977 |
117
+ | 0.4786 | 50.0 | 1400 | 0.9822 | 0.6977 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d922cd732faf7b0fe8ded8f83909c089e11d2d87f54b1564d1cbc6e805d4c858
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e0a565fafb6fbbb518acc527a510df8c096cf68712961c642a1c265710a49e
3
  size 22123464