Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_adamax_00001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
88ba0e6
·
1 Parent(s): 2da7788

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: smids_1x_deit_tiny_adamax_00001_fold2
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: 0.8535773710482529
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_1x_deit_tiny_adamax_00001_fold2
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: 0.9040
36
+ - Accuracy: 0.8536
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
+ | 0.7328 | 1.0 | 75 | 0.6585 | 0.7321 |
69
+ | 0.4509 | 2.0 | 150 | 0.4910 | 0.7903 |
70
+ | 0.3653 | 3.0 | 225 | 0.4211 | 0.8253 |
71
+ | 0.2986 | 4.0 | 300 | 0.4104 | 0.8353 |
72
+ | 0.2809 | 5.0 | 375 | 0.3830 | 0.8336 |
73
+ | 0.2519 | 6.0 | 450 | 0.3604 | 0.8502 |
74
+ | 0.2227 | 7.0 | 525 | 0.3681 | 0.8552 |
75
+ | 0.2223 | 8.0 | 600 | 0.3795 | 0.8419 |
76
+ | 0.1548 | 9.0 | 675 | 0.3730 | 0.8552 |
77
+ | 0.1857 | 10.0 | 750 | 0.3841 | 0.8602 |
78
+ | 0.1291 | 11.0 | 825 | 0.3934 | 0.8602 |
79
+ | 0.08 | 12.0 | 900 | 0.4226 | 0.8552 |
80
+ | 0.0831 | 13.0 | 975 | 0.4456 | 0.8486 |
81
+ | 0.0574 | 14.0 | 1050 | 0.5173 | 0.8436 |
82
+ | 0.0548 | 15.0 | 1125 | 0.4816 | 0.8602 |
83
+ | 0.051 | 16.0 | 1200 | 0.5112 | 0.8569 |
84
+ | 0.0349 | 17.0 | 1275 | 0.5235 | 0.8536 |
85
+ | 0.0192 | 18.0 | 1350 | 0.5709 | 0.8502 |
86
+ | 0.027 | 19.0 | 1425 | 0.6300 | 0.8453 |
87
+ | 0.0409 | 20.0 | 1500 | 0.6458 | 0.8502 |
88
+ | 0.009 | 21.0 | 1575 | 0.6679 | 0.8552 |
89
+ | 0.0172 | 22.0 | 1650 | 0.6845 | 0.8519 |
90
+ | 0.0015 | 23.0 | 1725 | 0.7310 | 0.8552 |
91
+ | 0.0059 | 24.0 | 1800 | 0.7388 | 0.8552 |
92
+ | 0.0018 | 25.0 | 1875 | 0.7514 | 0.8569 |
93
+ | 0.0008 | 26.0 | 1950 | 0.7646 | 0.8552 |
94
+ | 0.0024 | 27.0 | 2025 | 0.7898 | 0.8569 |
95
+ | 0.0185 | 28.0 | 2100 | 0.7969 | 0.8519 |
96
+ | 0.0012 | 29.0 | 2175 | 0.8175 | 0.8619 |
97
+ | 0.003 | 30.0 | 2250 | 0.8189 | 0.8536 |
98
+ | 0.0009 | 31.0 | 2325 | 0.8193 | 0.8569 |
99
+ | 0.0003 | 32.0 | 2400 | 0.8343 | 0.8602 |
100
+ | 0.0006 | 33.0 | 2475 | 0.8317 | 0.8586 |
101
+ | 0.0003 | 34.0 | 2550 | 0.8413 | 0.8536 |
102
+ | 0.026 | 35.0 | 2625 | 0.8594 | 0.8519 |
103
+ | 0.0003 | 36.0 | 2700 | 0.8747 | 0.8519 |
104
+ | 0.0002 | 37.0 | 2775 | 0.8582 | 0.8536 |
105
+ | 0.0003 | 38.0 | 2850 | 0.8927 | 0.8536 |
106
+ | 0.0067 | 39.0 | 2925 | 0.8896 | 0.8519 |
107
+ | 0.0002 | 40.0 | 3000 | 0.8915 | 0.8536 |
108
+ | 0.003 | 41.0 | 3075 | 0.8737 | 0.8586 |
109
+ | 0.0003 | 42.0 | 3150 | 0.9065 | 0.8519 |
110
+ | 0.0159 | 43.0 | 3225 | 0.8958 | 0.8552 |
111
+ | 0.0007 | 44.0 | 3300 | 0.8969 | 0.8519 |
112
+ | 0.0002 | 45.0 | 3375 | 0.9007 | 0.8519 |
113
+ | 0.0002 | 46.0 | 3450 | 0.9037 | 0.8536 |
114
+ | 0.007 | 47.0 | 3525 | 0.9095 | 0.8536 |
115
+ | 0.0002 | 48.0 | 3600 | 0.9035 | 0.8536 |
116
+ | 0.0057 | 49.0 | 3675 | 0.9034 | 0.8536 |
117
+ | 0.0097 | 50.0 | 3750 | 0.9040 | 0.8536 |
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 sha256:768aed57e6614984df32716d84d828ed1f9b418e7e9e3f4321ca2bc641c7fb77
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0217aa5dd43dd2b68ec8ce96f082c9c7d2f5341f266ff153e94dbde402a256
3
  size 22122692