Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_adamax_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
87bdc5e
•
1 Parent(s): 8d80c8d

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_adamax_001_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: 0.6585365853658537
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_adamax_001_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: 2.7115
36
+ - Accuracy: 0.6585
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
+ | 1.4348 | 1.0 | 28 | 1.3734 | 0.2439 |
69
+ | 1.3624 | 2.0 | 56 | 1.4229 | 0.2683 |
70
+ | 1.1348 | 3.0 | 84 | 1.1315 | 0.3902 |
71
+ | 0.9863 | 4.0 | 112 | 1.0099 | 0.6829 |
72
+ | 0.9002 | 5.0 | 140 | 0.8153 | 0.7317 |
73
+ | 0.8747 | 6.0 | 168 | 0.8078 | 0.7317 |
74
+ | 0.7431 | 7.0 | 196 | 0.8202 | 0.7073 |
75
+ | 0.7236 | 8.0 | 224 | 0.6730 | 0.7073 |
76
+ | 0.7214 | 9.0 | 252 | 0.7811 | 0.6829 |
77
+ | 0.7661 | 10.0 | 280 | 0.8373 | 0.6341 |
78
+ | 0.6997 | 11.0 | 308 | 0.7829 | 0.7073 |
79
+ | 0.5964 | 12.0 | 336 | 0.9580 | 0.5366 |
80
+ | 0.601 | 13.0 | 364 | 0.8593 | 0.6341 |
81
+ | 0.4989 | 14.0 | 392 | 0.8291 | 0.7317 |
82
+ | 0.484 | 15.0 | 420 | 0.8268 | 0.7317 |
83
+ | 0.3579 | 16.0 | 448 | 0.8735 | 0.6585 |
84
+ | 0.3201 | 17.0 | 476 | 1.3019 | 0.6341 |
85
+ | 0.2054 | 18.0 | 504 | 1.2022 | 0.6829 |
86
+ | 0.2162 | 19.0 | 532 | 1.3723 | 0.6098 |
87
+ | 0.2359 | 20.0 | 560 | 2.1538 | 0.5854 |
88
+ | 0.1213 | 21.0 | 588 | 1.4495 | 0.6829 |
89
+ | 0.1657 | 22.0 | 616 | 1.5861 | 0.6341 |
90
+ | 0.2091 | 23.0 | 644 | 1.3652 | 0.6585 |
91
+ | 0.0692 | 24.0 | 672 | 1.7622 | 0.6585 |
92
+ | 0.1092 | 25.0 | 700 | 2.0505 | 0.6585 |
93
+ | 0.0584 | 26.0 | 728 | 2.2675 | 0.5610 |
94
+ | 0.0661 | 27.0 | 756 | 1.7051 | 0.7073 |
95
+ | 0.0353 | 28.0 | 784 | 1.9468 | 0.6585 |
96
+ | 0.0164 | 29.0 | 812 | 2.4092 | 0.6341 |
97
+ | 0.0019 | 30.0 | 840 | 2.7744 | 0.6585 |
98
+ | 0.0033 | 31.0 | 868 | 3.2900 | 0.5610 |
99
+ | 0.0105 | 32.0 | 896 | 2.4900 | 0.5854 |
100
+ | 0.0008 | 33.0 | 924 | 2.5105 | 0.6341 |
101
+ | 0.0047 | 34.0 | 952 | 2.0758 | 0.7073 |
102
+ | 0.0004 | 35.0 | 980 | 2.7140 | 0.6585 |
103
+ | 0.0 | 36.0 | 1008 | 2.9025 | 0.6585 |
104
+ | 0.0013 | 37.0 | 1036 | 2.6654 | 0.6585 |
105
+ | 0.0 | 38.0 | 1064 | 2.6558 | 0.6829 |
106
+ | 0.0 | 39.0 | 1092 | 2.6667 | 0.6585 |
107
+ | 0.0 | 40.0 | 1120 | 2.6779 | 0.6585 |
108
+ | 0.0 | 41.0 | 1148 | 2.6850 | 0.6585 |
109
+ | 0.0 | 42.0 | 1176 | 2.6917 | 0.6585 |
110
+ | 0.0 | 43.0 | 1204 | 2.6986 | 0.6585 |
111
+ | 0.0 | 44.0 | 1232 | 2.7032 | 0.6585 |
112
+ | 0.0 | 45.0 | 1260 | 2.7065 | 0.6585 |
113
+ | 0.0 | 46.0 | 1288 | 2.7090 | 0.6585 |
114
+ | 0.0 | 47.0 | 1316 | 2.7107 | 0.6585 |
115
+ | 0.0 | 48.0 | 1344 | 2.7115 | 0.6585 |
116
+ | 0.0 | 49.0 | 1372 | 2.7115 | 0.6585 |
117
+ | 0.0 | 50.0 | 1400 | 2.7115 | 0.6585 |
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:b026547ae74d6c14fb897549793d5cb123701c954c9ddce97696b555180e9832
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3235e818f4d0ed43cf3d509532493d038846e02048e70cb7ff59b19760da864
3
  size 22123464