Hugging Face's logo

hkivancoral
/
smids_10x_deit_tiny_adamax_001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
3380f34
•
1 Parent(s): 6af12ec

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_10x_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: 0.915
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_10x_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: 0.8586
36
+ - Accuracy: 0.915
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
+ | 0.3782 | 1.0 | 750 | 0.3344 | 0.8667 |
69
+ | 0.2904 | 2.0 | 1500 | 0.3574 | 0.8483 |
70
+ | 0.2048 | 3.0 | 2250 | 0.3230 | 0.8817 |
71
+ | 0.2 | 4.0 | 3000 | 0.3479 | 0.8933 |
72
+ | 0.2233 | 5.0 | 3750 | 0.3431 | 0.8883 |
73
+ | 0.1334 | 6.0 | 4500 | 0.3350 | 0.9017 |
74
+ | 0.1268 | 7.0 | 5250 | 0.3335 | 0.8967 |
75
+ | 0.077 | 8.0 | 6000 | 0.4549 | 0.8883 |
76
+ | 0.0723 | 9.0 | 6750 | 0.3771 | 0.9067 |
77
+ | 0.0426 | 10.0 | 7500 | 0.4455 | 0.9017 |
78
+ | 0.0977 | 11.0 | 8250 | 0.4334 | 0.9067 |
79
+ | 0.0237 | 12.0 | 9000 | 0.5437 | 0.9 |
80
+ | 0.0358 | 13.0 | 9750 | 0.5148 | 0.885 |
81
+ | 0.0032 | 14.0 | 10500 | 0.6045 | 0.9083 |
82
+ | 0.0293 | 15.0 | 11250 | 0.6394 | 0.8933 |
83
+ | 0.0156 | 16.0 | 12000 | 0.6836 | 0.89 |
84
+ | 0.0548 | 17.0 | 12750 | 0.5770 | 0.9017 |
85
+ | 0.0127 | 18.0 | 13500 | 0.6663 | 0.8983 |
86
+ | 0.0203 | 19.0 | 14250 | 0.6791 | 0.905 |
87
+ | 0.0154 | 20.0 | 15000 | 0.6990 | 0.905 |
88
+ | 0.0128 | 21.0 | 15750 | 0.7251 | 0.9017 |
89
+ | 0.0003 | 22.0 | 16500 | 0.7324 | 0.8933 |
90
+ | 0.0024 | 23.0 | 17250 | 0.7123 | 0.9017 |
91
+ | 0.0015 | 24.0 | 18000 | 0.6502 | 0.9133 |
92
+ | 0.0109 | 25.0 | 18750 | 0.6676 | 0.9117 |
93
+ | 0.0004 | 26.0 | 19500 | 0.6984 | 0.9033 |
94
+ | 0.0105 | 27.0 | 20250 | 0.8181 | 0.8967 |
95
+ | 0.0029 | 28.0 | 21000 | 0.7764 | 0.9 |
96
+ | 0.0304 | 29.0 | 21750 | 0.7986 | 0.8967 |
97
+ | 0.008 | 30.0 | 22500 | 0.8233 | 0.895 |
98
+ | 0.0008 | 31.0 | 23250 | 0.8494 | 0.9033 |
99
+ | 0.0 | 32.0 | 24000 | 0.8041 | 0.91 |
100
+ | 0.0 | 33.0 | 24750 | 0.8842 | 0.9167 |
101
+ | 0.0 | 34.0 | 25500 | 0.7437 | 0.9233 |
102
+ | 0.0 | 35.0 | 26250 | 0.7405 | 0.925 |
103
+ | 0.0 | 36.0 | 27000 | 0.7962 | 0.9083 |
104
+ | 0.0059 | 37.0 | 27750 | 0.7867 | 0.9233 |
105
+ | 0.0 | 38.0 | 28500 | 0.8151 | 0.92 |
106
+ | 0.0 | 39.0 | 29250 | 0.8010 | 0.91 |
107
+ | 0.0 | 40.0 | 30000 | 0.8483 | 0.9133 |
108
+ | 0.0 | 41.0 | 30750 | 0.8225 | 0.9167 |
109
+ | 0.0 | 42.0 | 31500 | 0.8207 | 0.9167 |
110
+ | 0.0 | 43.0 | 32250 | 0.8290 | 0.915 |
111
+ | 0.0 | 44.0 | 33000 | 0.8408 | 0.915 |
112
+ | 0.0 | 45.0 | 33750 | 0.8374 | 0.9183 |
113
+ | 0.0 | 46.0 | 34500 | 0.8446 | 0.9167 |
114
+ | 0.0 | 47.0 | 35250 | 0.8518 | 0.915 |
115
+ | 0.0 | 48.0 | 36000 | 0.8526 | 0.915 |
116
+ | 0.0 | 49.0 | 36750 | 0.8568 | 0.9167 |
117
+ | 0.0 | 50.0 | 37500 | 0.8586 | 0.915 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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 sha256:9f6d982c51f080374512465f96f866e74c197d4949621ed8a3c08912eb5a7aa0
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75ef49ea37f6c2ba6469ad75d7b30559e08eb7b4ebf4538ae02cbd1b8db7c97
3
  size 22167850