Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_adamax_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
259291f
•
1 Parent(s): 0779b0d

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_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: 0.7209302325581395
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_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: 1.8507
36
+ - Accuracy: 0.7209
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
+ | 1.4597 | 1.0 | 28 | 1.3552 | 0.3256 |
69
+ | 1.2609 | 2.0 | 56 | 0.9015 | 0.6744 |
70
+ | 1.1559 | 3.0 | 84 | 2.3181 | 0.3256 |
71
+ | 1.0822 | 4.0 | 112 | 1.6592 | 0.4186 |
72
+ | 1.0553 | 5.0 | 140 | 0.9222 | 0.4651 |
73
+ | 0.9651 | 6.0 | 168 | 0.7306 | 0.7442 |
74
+ | 0.9771 | 7.0 | 196 | 0.7827 | 0.6279 |
75
+ | 0.9016 | 8.0 | 224 | 0.9874 | 0.5581 |
76
+ | 0.8187 | 9.0 | 252 | 1.0233 | 0.5349 |
77
+ | 0.8405 | 10.0 | 280 | 0.6414 | 0.7674 |
78
+ | 0.7808 | 11.0 | 308 | 0.6637 | 0.6977 |
79
+ | 0.8152 | 12.0 | 336 | 0.5374 | 0.8605 |
80
+ | 0.8044 | 13.0 | 364 | 0.5684 | 0.7442 |
81
+ | 0.7275 | 14.0 | 392 | 0.6622 | 0.8140 |
82
+ | 0.6931 | 15.0 | 420 | 0.7767 | 0.7209 |
83
+ | 0.691 | 16.0 | 448 | 0.5520 | 0.7674 |
84
+ | 0.7585 | 17.0 | 476 | 0.6770 | 0.7674 |
85
+ | 0.6303 | 18.0 | 504 | 0.6834 | 0.7442 |
86
+ | 0.6578 | 19.0 | 532 | 0.7776 | 0.6977 |
87
+ | 0.4934 | 20.0 | 560 | 1.1067 | 0.7442 |
88
+ | 0.5397 | 21.0 | 588 | 0.7250 | 0.7674 |
89
+ | 0.5586 | 22.0 | 616 | 0.9824 | 0.6047 |
90
+ | 0.4808 | 23.0 | 644 | 0.9582 | 0.7442 |
91
+ | 0.4823 | 24.0 | 672 | 0.9114 | 0.6279 |
92
+ | 0.4124 | 25.0 | 700 | 1.1614 | 0.7209 |
93
+ | 0.3991 | 26.0 | 728 | 1.3579 | 0.6279 |
94
+ | 0.5138 | 27.0 | 756 | 1.5915 | 0.6512 |
95
+ | 0.3857 | 28.0 | 784 | 0.6799 | 0.8140 |
96
+ | 0.3797 | 29.0 | 812 | 1.1771 | 0.7907 |
97
+ | 0.3781 | 30.0 | 840 | 0.9809 | 0.7674 |
98
+ | 0.3225 | 31.0 | 868 | 0.7120 | 0.8140 |
99
+ | 0.3017 | 32.0 | 896 | 0.9984 | 0.7674 |
100
+ | 0.2468 | 33.0 | 924 | 1.0271 | 0.7674 |
101
+ | 0.1651 | 34.0 | 952 | 1.2194 | 0.7674 |
102
+ | 0.254 | 35.0 | 980 | 1.2984 | 0.7907 |
103
+ | 0.1644 | 36.0 | 1008 | 1.3708 | 0.7674 |
104
+ | 0.1972 | 37.0 | 1036 | 1.6461 | 0.7209 |
105
+ | 0.1252 | 38.0 | 1064 | 1.8473 | 0.7442 |
106
+ | 0.1252 | 39.0 | 1092 | 1.5823 | 0.7209 |
107
+ | 0.4334 | 40.0 | 1120 | 1.7311 | 0.7209 |
108
+ | 0.1029 | 41.0 | 1148 | 1.7390 | 0.7674 |
109
+ | 0.0992 | 42.0 | 1176 | 1.6959 | 0.7907 |
110
+ | 0.0993 | 43.0 | 1204 | 1.9237 | 0.7442 |
111
+ | 0.0435 | 44.0 | 1232 | 1.8569 | 0.7442 |
112
+ | 0.054 | 45.0 | 1260 | 1.8007 | 0.7907 |
113
+ | 0.0678 | 46.0 | 1288 | 1.8496 | 0.7442 |
114
+ | 0.0576 | 47.0 | 1316 | 1.8145 | 0.7442 |
115
+ | 0.0232 | 48.0 | 1344 | 1.8497 | 0.7209 |
116
+ | 0.0393 | 49.0 | 1372 | 1.8507 | 0.7209 |
117
+ | 0.0213 | 50.0 | 1400 | 1.8507 | 0.7209 |
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 sha256:569f0d604b2bd0b79ec79062fc44d934e6199b6ee734ca09bd062323eebf9fca
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9961984b8bbff30e748f47a0e910bbab7896cbe594cf50b7745f41b45aa6573d
3
  size 22123464