Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_sgd_00001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
177b8c1
•
1 Parent(s): 11a97fe

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_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: 0.28888888888888886
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_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: 1.6463
36
+ - Accuracy: 0.2889
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
+ | 1.5609 | 1.0 | 27 | 1.6799 | 0.2667 |
69
+ | 1.5496 | 2.0 | 54 | 1.6782 | 0.2667 |
70
+ | 1.5787 | 3.0 | 81 | 1.6767 | 0.2667 |
71
+ | 1.5647 | 4.0 | 108 | 1.6752 | 0.2667 |
72
+ | 1.5195 | 5.0 | 135 | 1.6738 | 0.2667 |
73
+ | 1.5668 | 6.0 | 162 | 1.6723 | 0.2667 |
74
+ | 1.5392 | 7.0 | 189 | 1.6709 | 0.2667 |
75
+ | 1.5582 | 8.0 | 216 | 1.6695 | 0.2667 |
76
+ | 1.5313 | 9.0 | 243 | 1.6682 | 0.2667 |
77
+ | 1.5128 | 10.0 | 270 | 1.6669 | 0.2667 |
78
+ | 1.5483 | 11.0 | 297 | 1.6658 | 0.2667 |
79
+ | 1.4916 | 12.0 | 324 | 1.6646 | 0.2667 |
80
+ | 1.5319 | 13.0 | 351 | 1.6635 | 0.2667 |
81
+ | 1.5642 | 14.0 | 378 | 1.6625 | 0.2667 |
82
+ | 1.5157 | 15.0 | 405 | 1.6614 | 0.2667 |
83
+ | 1.5547 | 16.0 | 432 | 1.6604 | 0.2667 |
84
+ | 1.561 | 17.0 | 459 | 1.6595 | 0.2667 |
85
+ | 1.5198 | 18.0 | 486 | 1.6585 | 0.2667 |
86
+ | 1.5162 | 19.0 | 513 | 1.6577 | 0.2667 |
87
+ | 1.501 | 20.0 | 540 | 1.6568 | 0.2667 |
88
+ | 1.536 | 21.0 | 567 | 1.6560 | 0.2667 |
89
+ | 1.5261 | 22.0 | 594 | 1.6552 | 0.2667 |
90
+ | 1.5076 | 23.0 | 621 | 1.6545 | 0.2667 |
91
+ | 1.5241 | 24.0 | 648 | 1.6538 | 0.2667 |
92
+ | 1.519 | 25.0 | 675 | 1.6531 | 0.2667 |
93
+ | 1.5215 | 26.0 | 702 | 1.6525 | 0.2667 |
94
+ | 1.4834 | 27.0 | 729 | 1.6518 | 0.2667 |
95
+ | 1.52 | 28.0 | 756 | 1.6513 | 0.2667 |
96
+ | 1.5201 | 29.0 | 783 | 1.6507 | 0.2667 |
97
+ | 1.5274 | 30.0 | 810 | 1.6502 | 0.2667 |
98
+ | 1.5272 | 31.0 | 837 | 1.6498 | 0.2667 |
99
+ | 1.5239 | 32.0 | 864 | 1.6493 | 0.2667 |
100
+ | 1.4813 | 33.0 | 891 | 1.6489 | 0.2667 |
101
+ | 1.5127 | 34.0 | 918 | 1.6485 | 0.2889 |
102
+ | 1.5315 | 35.0 | 945 | 1.6482 | 0.2889 |
103
+ | 1.4986 | 36.0 | 972 | 1.6479 | 0.2889 |
104
+ | 1.5458 | 37.0 | 999 | 1.6476 | 0.2889 |
105
+ | 1.5577 | 38.0 | 1026 | 1.6473 | 0.2889 |
106
+ | 1.5374 | 39.0 | 1053 | 1.6471 | 0.2889 |
107
+ | 1.4671 | 40.0 | 1080 | 1.6469 | 0.2889 |
108
+ | 1.5237 | 41.0 | 1107 | 1.6467 | 0.2889 |
109
+ | 1.4934 | 42.0 | 1134 | 1.6466 | 0.2889 |
110
+ | 1.5479 | 43.0 | 1161 | 1.6465 | 0.2889 |
111
+ | 1.5299 | 44.0 | 1188 | 1.6464 | 0.2889 |
112
+ | 1.5139 | 45.0 | 1215 | 1.6463 | 0.2889 |
113
+ | 1.4949 | 46.0 | 1242 | 1.6463 | 0.2889 |
114
+ | 1.5114 | 47.0 | 1269 | 1.6463 | 0.2889 |
115
+ | 1.5095 | 48.0 | 1296 | 1.6463 | 0.2889 |
116
+ | 1.514 | 49.0 | 1323 | 1.6463 | 0.2889 |
117
+ | 1.4915 | 50.0 | 1350 | 1.6463 | 0.2889 |
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 sha256:38266736ef76727744a11d1fc99291978c16152a547cd45a1dc59eb7d222597f
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b92639a3a2e02136b0f6e1d63854a56bba2a9db66f679d9eaa0d124b33bddcc
3
  size 22123464