Hugging Face's logo

hkivancoral
/
smids_5x_deit_small_adamax_0001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
371a4af
•
1 Parent(s): e2a9334

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_5x_deit_small_adamax_0001_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: 0.9131886477462438
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
+ # smids_5x_deit_small_adamax_0001_fold1
32
+
33
+ This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8826
36
+ - Accuracy: 0.9132
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: 0.0001
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
+ | 0.2523 | 1.0 | 751 | 0.2969 | 0.8781 |
69
+ | 0.098 | 2.0 | 1502 | 0.3056 | 0.9048 |
70
+ | 0.0879 | 3.0 | 2253 | 0.3755 | 0.9082 |
71
+ | 0.0112 | 4.0 | 3004 | 0.4946 | 0.9015 |
72
+ | 0.0331 | 5.0 | 3755 | 0.5182 | 0.9115 |
73
+ | 0.034 | 6.0 | 4506 | 0.6894 | 0.8982 |
74
+ | 0.0195 | 7.0 | 5257 | 0.5733 | 0.9082 |
75
+ | 0.0006 | 8.0 | 6008 | 0.6615 | 0.9065 |
76
+ | 0.0 | 9.0 | 6759 | 0.6188 | 0.9149 |
77
+ | 0.0001 | 10.0 | 7510 | 0.6672 | 0.9115 |
78
+ | 0.0153 | 11.0 | 8261 | 0.6447 | 0.9165 |
79
+ | 0.0 | 12.0 | 9012 | 0.7794 | 0.9098 |
80
+ | 0.0 | 13.0 | 9763 | 0.7124 | 0.9098 |
81
+ | 0.0 | 14.0 | 10514 | 0.7255 | 0.9082 |
82
+ | 0.0 | 15.0 | 11265 | 0.7805 | 0.9098 |
83
+ | 0.0 | 16.0 | 12016 | 0.8624 | 0.9048 |
84
+ | 0.0069 | 17.0 | 12767 | 0.7828 | 0.9115 |
85
+ | 0.0001 | 18.0 | 13518 | 0.7977 | 0.9032 |
86
+ | 0.0 | 19.0 | 14269 | 0.7469 | 0.9065 |
87
+ | 0.0001 | 20.0 | 15020 | 0.8490 | 0.9065 |
88
+ | 0.0 | 21.0 | 15771 | 0.7619 | 0.9098 |
89
+ | 0.0 | 22.0 | 16522 | 0.7972 | 0.9149 |
90
+ | 0.0 | 23.0 | 17273 | 0.7542 | 0.9199 |
91
+ | 0.0 | 24.0 | 18024 | 0.8510 | 0.9048 |
92
+ | 0.0 | 25.0 | 18775 | 0.8348 | 0.9082 |
93
+ | 0.0 | 26.0 | 19526 | 0.8141 | 0.9182 |
94
+ | 0.0 | 27.0 | 20277 | 0.8518 | 0.9115 |
95
+ | 0.0 | 28.0 | 21028 | 0.8281 | 0.9098 |
96
+ | 0.0044 | 29.0 | 21779 | 0.8328 | 0.9132 |
97
+ | 0.0 | 30.0 | 22530 | 0.8675 | 0.9149 |
98
+ | 0.0 | 31.0 | 23281 | 0.8219 | 0.9048 |
99
+ | 0.0 | 32.0 | 24032 | 0.8656 | 0.9065 |
100
+ | 0.0 | 33.0 | 24783 | 0.8259 | 0.9048 |
101
+ | 0.0 | 34.0 | 25534 | 0.8526 | 0.9082 |
102
+ | 0.0 | 35.0 | 26285 | 0.8439 | 0.9098 |
103
+ | 0.0 | 36.0 | 27036 | 0.8589 | 0.9115 |
104
+ | 0.0 | 37.0 | 27787 | 0.8573 | 0.9149 |
105
+ | 0.0 | 38.0 | 28538 | 0.8548 | 0.9149 |
106
+ | 0.0 | 39.0 | 29289 | 0.8558 | 0.9149 |
107
+ | 0.0 | 40.0 | 30040 | 0.8593 | 0.9149 |
108
+ | 0.0 | 41.0 | 30791 | 0.8680 | 0.9149 |
109
+ | 0.0 | 42.0 | 31542 | 0.8686 | 0.9149 |
110
+ | 0.0 | 43.0 | 32293 | 0.8703 | 0.9132 |
111
+ | 0.0 | 44.0 | 33044 | 0.8724 | 0.9132 |
112
+ | 0.0 | 45.0 | 33795 | 0.8746 | 0.9132 |
113
+ | 0.0 | 46.0 | 34546 | 0.8749 | 0.9132 |
114
+ | 0.0 | 47.0 | 35297 | 0.8795 | 0.9132 |
115
+ | 0.0 | 48.0 | 36048 | 0.8807 | 0.9132 |
116
+ | 0.0 | 49.0 | 36799 | 0.8817 | 0.9132 |
117
+ | 0.0 | 50.0 | 37550 | 0.8826 | 0.9132 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:008f2fb0220cc6c5de23e7a22514fcc648d73ef0ab581d1b76dd05e1a19ce558
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6895fc2f5d5b91681daa70cd3278704dd4f6ab251257910bb928d2138eccc3e
3
  size 86735658