Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_sgd_00001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
0e3b392
•
1 Parent(s): 56e8bcd

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_sgd_00001_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: 0.27906976744186046
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_sgd_00001_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: 1.6587
36
+ - Accuracy: 0.2791
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
+ | 1.5526 | 1.0 | 28 | 1.7069 | 0.2791 |
69
+ | 1.5173 | 2.0 | 56 | 1.7047 | 0.2791 |
70
+ | 1.5161 | 3.0 | 84 | 1.7025 | 0.2791 |
71
+ | 1.5055 | 4.0 | 112 | 1.7004 | 0.2791 |
72
+ | 1.4587 | 5.0 | 140 | 1.6983 | 0.2791 |
73
+ | 1.5199 | 6.0 | 168 | 1.6963 | 0.2791 |
74
+ | 1.5621 | 7.0 | 196 | 1.6943 | 0.2791 |
75
+ | 1.5165 | 8.0 | 224 | 1.6925 | 0.2791 |
76
+ | 1.5226 | 9.0 | 252 | 1.6906 | 0.2791 |
77
+ | 1.4955 | 10.0 | 280 | 1.6889 | 0.2791 |
78
+ | 1.5136 | 11.0 | 308 | 1.6873 | 0.2791 |
79
+ | 1.5328 | 12.0 | 336 | 1.6856 | 0.2791 |
80
+ | 1.4996 | 13.0 | 364 | 1.6840 | 0.2791 |
81
+ | 1.5073 | 14.0 | 392 | 1.6824 | 0.2791 |
82
+ | 1.566 | 15.0 | 420 | 1.6809 | 0.2791 |
83
+ | 1.501 | 16.0 | 448 | 1.6795 | 0.2791 |
84
+ | 1.4781 | 17.0 | 476 | 1.6780 | 0.2791 |
85
+ | 1.5327 | 18.0 | 504 | 1.6766 | 0.2791 |
86
+ | 1.4922 | 19.0 | 532 | 1.6753 | 0.2791 |
87
+ | 1.5682 | 20.0 | 560 | 1.6741 | 0.2791 |
88
+ | 1.4804 | 21.0 | 588 | 1.6729 | 0.2791 |
89
+ | 1.4661 | 22.0 | 616 | 1.6719 | 0.2791 |
90
+ | 1.5385 | 23.0 | 644 | 1.6708 | 0.2791 |
91
+ | 1.4844 | 24.0 | 672 | 1.6698 | 0.2791 |
92
+ | 1.583 | 25.0 | 700 | 1.6688 | 0.2791 |
93
+ | 1.4741 | 26.0 | 728 | 1.6678 | 0.2791 |
94
+ | 1.4816 | 27.0 | 756 | 1.6669 | 0.2791 |
95
+ | 1.4922 | 28.0 | 784 | 1.6662 | 0.2791 |
96
+ | 1.5132 | 29.0 | 812 | 1.6654 | 0.2791 |
97
+ | 1.4828 | 30.0 | 840 | 1.6647 | 0.2791 |
98
+ | 1.4775 | 31.0 | 868 | 1.6640 | 0.2791 |
99
+ | 1.4969 | 32.0 | 896 | 1.6634 | 0.2791 |
100
+ | 1.5111 | 33.0 | 924 | 1.6627 | 0.2791 |
101
+ | 1.4897 | 34.0 | 952 | 1.6621 | 0.2791 |
102
+ | 1.485 | 35.0 | 980 | 1.6616 | 0.2791 |
103
+ | 1.5295 | 36.0 | 1008 | 1.6612 | 0.2791 |
104
+ | 1.4993 | 37.0 | 1036 | 1.6607 | 0.2791 |
105
+ | 1.4874 | 38.0 | 1064 | 1.6603 | 0.2791 |
106
+ | 1.5091 | 39.0 | 1092 | 1.6600 | 0.2791 |
107
+ | 1.4861 | 40.0 | 1120 | 1.6597 | 0.2791 |
108
+ | 1.5191 | 41.0 | 1148 | 1.6595 | 0.2791 |
109
+ | 1.4786 | 42.0 | 1176 | 1.6593 | 0.2791 |
110
+ | 1.4918 | 43.0 | 1204 | 1.6591 | 0.2791 |
111
+ | 1.5394 | 44.0 | 1232 | 1.6589 | 0.2791 |
112
+ | 1.4962 | 45.0 | 1260 | 1.6588 | 0.2791 |
113
+ | 1.4846 | 46.0 | 1288 | 1.6588 | 0.2791 |
114
+ | 1.4732 | 47.0 | 1316 | 1.6587 | 0.2791 |
115
+ | 1.4909 | 48.0 | 1344 | 1.6587 | 0.2791 |
116
+ | 1.4794 | 49.0 | 1372 | 1.6587 | 0.2791 |
117
+ | 1.4677 | 50.0 | 1400 | 1.6587 | 0.2791 |
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:c008b615bb90290ba01928b76789cc1af0bc78c8244fb4694cdf796f342d0b35
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d978afaaaaf15fe4adb5a6e32c771754d2a1f1a0f86d3dbd042ccdf717321922
3
  size 22123464