Hugging Face's logo

hkivancoral
/
smids_5x_deit_small_sgd_00001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
924297f
•
1 Parent(s): 2c76be0

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_sgd_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: 0.5108153078202995
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_sgd_00001_fold2
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: 0.9907
36
+ - Accuracy: 0.5108
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
+ | 1.0998 | 1.0 | 375 | 1.0701 | 0.4260 |
69
+ | 1.0872 | 2.0 | 750 | 1.0668 | 0.4276 |
70
+ | 1.0721 | 3.0 | 1125 | 1.0636 | 0.4343 |
71
+ | 1.068 | 4.0 | 1500 | 1.0604 | 0.4343 |
72
+ | 1.0595 | 5.0 | 1875 | 1.0573 | 0.4376 |
73
+ | 1.0368 | 6.0 | 2250 | 1.0542 | 0.4409 |
74
+ | 1.0324 | 7.0 | 2625 | 1.0513 | 0.4493 |
75
+ | 1.0454 | 8.0 | 3000 | 1.0484 | 0.4526 |
76
+ | 1.0424 | 9.0 | 3375 | 1.0456 | 0.4509 |
77
+ | 1.0256 | 10.0 | 3750 | 1.0428 | 0.4559 |
78
+ | 1.0778 | 11.0 | 4125 | 1.0401 | 0.4559 |
79
+ | 1.0323 | 12.0 | 4500 | 1.0375 | 0.4592 |
80
+ | 1.0063 | 13.0 | 4875 | 1.0349 | 0.4626 |
81
+ | 1.0266 | 14.0 | 5250 | 1.0324 | 0.4642 |
82
+ | 1.0153 | 15.0 | 5625 | 1.0299 | 0.4659 |
83
+ | 1.0 | 16.0 | 6000 | 1.0276 | 0.4692 |
84
+ | 1.0251 | 17.0 | 6375 | 1.0253 | 0.4692 |
85
+ | 1.0305 | 18.0 | 6750 | 1.0231 | 0.4725 |
86
+ | 1.0097 | 19.0 | 7125 | 1.0209 | 0.4725 |
87
+ | 1.02 | 20.0 | 7500 | 1.0189 | 0.4725 |
88
+ | 0.9981 | 21.0 | 7875 | 1.0168 | 0.4775 |
89
+ | 0.9952 | 22.0 | 8250 | 1.0149 | 0.4775 |
90
+ | 1.007 | 23.0 | 8625 | 1.0131 | 0.4859 |
91
+ | 1.0141 | 24.0 | 9000 | 1.0113 | 0.4875 |
92
+ | 1.0041 | 25.0 | 9375 | 1.0095 | 0.4875 |
93
+ | 1.0032 | 26.0 | 9750 | 1.0079 | 0.4875 |
94
+ | 1.0112 | 27.0 | 10125 | 1.0064 | 0.4875 |
95
+ | 0.9862 | 28.0 | 10500 | 1.0049 | 0.4892 |
96
+ | 0.9745 | 29.0 | 10875 | 1.0035 | 0.4892 |
97
+ | 0.9881 | 30.0 | 11250 | 1.0022 | 0.4925 |
98
+ | 0.9936 | 31.0 | 11625 | 1.0009 | 0.4908 |
99
+ | 0.9959 | 32.0 | 12000 | 0.9998 | 0.4892 |
100
+ | 0.9804 | 33.0 | 12375 | 0.9987 | 0.4875 |
101
+ | 0.9795 | 34.0 | 12750 | 0.9977 | 0.4958 |
102
+ | 0.9724 | 35.0 | 13125 | 0.9967 | 0.4975 |
103
+ | 0.9957 | 36.0 | 13500 | 0.9958 | 0.4992 |
104
+ | 0.9651 | 37.0 | 13875 | 0.9950 | 0.5025 |
105
+ | 0.9869 | 38.0 | 14250 | 0.9943 | 0.5042 |
106
+ | 0.9664 | 39.0 | 14625 | 0.9937 | 0.5075 |
107
+ | 0.9769 | 40.0 | 15000 | 0.9931 | 0.5092 |
108
+ | 0.9473 | 41.0 | 15375 | 0.9926 | 0.5108 |
109
+ | 0.9911 | 42.0 | 15750 | 0.9921 | 0.5108 |
110
+ | 0.9625 | 43.0 | 16125 | 0.9917 | 0.5108 |
111
+ | 0.9689 | 44.0 | 16500 | 0.9914 | 0.5108 |
112
+ | 0.9736 | 45.0 | 16875 | 0.9912 | 0.5108 |
113
+ | 0.9789 | 46.0 | 17250 | 0.9910 | 0.5108 |
114
+ | 0.9732 | 47.0 | 17625 | 0.9908 | 0.5108 |
115
+ | 0.9789 | 48.0 | 18000 | 0.9907 | 0.5108 |
116
+ | 0.987 | 49.0 | 18375 | 0.9907 | 0.5108 |
117
+ | 1.0128 | 50.0 | 18750 | 0.9907 | 0.5108 |
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 sha256:30dc0b7527547934ed2a2805916485d2506f5e02ea27cae2fbd970b2adc595fd
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fbed703d6667900e4317dfbbebfbb4a93963873e7c58f1e99bc23015704b44
3
  size 86735658