Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_0001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
51d99ca
•
1 Parent(s): ee2da82

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_sgd_0001_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: 0.5916666666666667
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_sgd_0001_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: 0.8882
36
+ - Accuracy: 0.5917
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
+ | 1.2279 | 1.0 | 75 | 1.2828 | 0.36 |
69
+ | 1.1801 | 2.0 | 150 | 1.2204 | 0.3717 |
70
+ | 1.1425 | 3.0 | 225 | 1.1764 | 0.3733 |
71
+ | 1.1496 | 4.0 | 300 | 1.1467 | 0.3817 |
72
+ | 1.0862 | 5.0 | 375 | 1.1259 | 0.39 |
73
+ | 1.1317 | 6.0 | 450 | 1.1103 | 0.3983 |
74
+ | 1.0711 | 7.0 | 525 | 1.0972 | 0.4083 |
75
+ | 1.0717 | 8.0 | 600 | 1.0858 | 0.4167 |
76
+ | 1.0458 | 9.0 | 675 | 1.0754 | 0.42 |
77
+ | 1.0711 | 10.0 | 750 | 1.0656 | 0.425 |
78
+ | 1.0389 | 11.0 | 825 | 1.0563 | 0.4383 |
79
+ | 1.0272 | 12.0 | 900 | 1.0476 | 0.4467 |
80
+ | 1.0495 | 13.0 | 975 | 1.0393 | 0.4517 |
81
+ | 1.0448 | 14.0 | 1050 | 1.0308 | 0.4533 |
82
+ | 1.0339 | 15.0 | 1125 | 1.0229 | 0.4583 |
83
+ | 0.9744 | 16.0 | 1200 | 1.0150 | 0.4617 |
84
+ | 0.9857 | 17.0 | 1275 | 1.0069 | 0.47 |
85
+ | 1.0108 | 18.0 | 1350 | 0.9993 | 0.4717 |
86
+ | 0.9584 | 19.0 | 1425 | 0.9919 | 0.4717 |
87
+ | 0.9977 | 20.0 | 1500 | 0.9844 | 0.485 |
88
+ | 0.9787 | 21.0 | 1575 | 0.9775 | 0.49 |
89
+ | 0.9724 | 22.0 | 1650 | 0.9707 | 0.5067 |
90
+ | 0.9219 | 23.0 | 1725 | 0.9645 | 0.515 |
91
+ | 0.923 | 24.0 | 1800 | 0.9585 | 0.525 |
92
+ | 0.9224 | 25.0 | 1875 | 0.9527 | 0.5317 |
93
+ | 0.9312 | 26.0 | 1950 | 0.9470 | 0.5417 |
94
+ | 0.9161 | 27.0 | 2025 | 0.9417 | 0.5433 |
95
+ | 0.9574 | 28.0 | 2100 | 0.9369 | 0.5467 |
96
+ | 0.9255 | 29.0 | 2175 | 0.9322 | 0.5517 |
97
+ | 0.9146 | 30.0 | 2250 | 0.9278 | 0.555 |
98
+ | 0.9155 | 31.0 | 2325 | 0.9238 | 0.5617 |
99
+ | 0.856 | 32.0 | 2400 | 0.9200 | 0.565 |
100
+ | 0.9504 | 33.0 | 2475 | 0.9164 | 0.5717 |
101
+ | 0.9096 | 34.0 | 2550 | 0.9130 | 0.5783 |
102
+ | 0.8983 | 35.0 | 2625 | 0.9100 | 0.5817 |
103
+ | 0.8589 | 36.0 | 2700 | 0.9071 | 0.585 |
104
+ | 0.8916 | 37.0 | 2775 | 0.9044 | 0.5817 |
105
+ | 0.8984 | 38.0 | 2850 | 0.9020 | 0.585 |
106
+ | 0.8824 | 39.0 | 2925 | 0.8998 | 0.5867 |
107
+ | 0.8736 | 40.0 | 3000 | 0.8977 | 0.5867 |
108
+ | 0.8723 | 41.0 | 3075 | 0.8958 | 0.5883 |
109
+ | 0.8965 | 42.0 | 3150 | 0.8942 | 0.59 |
110
+ | 0.8854 | 43.0 | 3225 | 0.8928 | 0.59 |
111
+ | 0.8622 | 44.0 | 3300 | 0.8915 | 0.5917 |
112
+ | 0.8601 | 45.0 | 3375 | 0.8905 | 0.5917 |
113
+ | 0.8904 | 46.0 | 3450 | 0.8896 | 0.5917 |
114
+ | 0.8654 | 47.0 | 3525 | 0.8890 | 0.5917 |
115
+ | 0.8638 | 48.0 | 3600 | 0.8885 | 0.5917 |
116
+ | 0.8282 | 49.0 | 3675 | 0.8883 | 0.5917 |
117
+ | 0.8485 | 50.0 | 3750 | 0.8882 | 0.5917 |
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 sha256:51acb0876dfb3e2436c48da7a30c8607839168f1e6c53d1bb979729907af31d8
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82bb38eb9a331295c397ea5adfe2ce326e5ad2819838e0004b9eccc342f689ae
3
  size 22122692