Hugging Face's logo

hkivancoral
/
smids_5x_deit_tiny_sgd_0001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
644cf4c
•
1 Parent(s): 610fc75

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_5x_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: 0.8216666666666667
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_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: 0.4623
36
+ - Accuracy: 0.8217
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
+ | 1.1763 | 1.0 | 375 | 1.1547 | 0.3917 |
69
+ | 1.0966 | 2.0 | 750 | 1.0897 | 0.42 |
70
+ | 1.0223 | 3.0 | 1125 | 1.0444 | 0.46 |
71
+ | 0.9886 | 4.0 | 1500 | 1.0052 | 0.4917 |
72
+ | 0.9546 | 5.0 | 1875 | 0.9693 | 0.515 |
73
+ | 0.932 | 6.0 | 2250 | 0.9344 | 0.54 |
74
+ | 0.8619 | 7.0 | 2625 | 0.9000 | 0.57 |
75
+ | 0.857 | 8.0 | 3000 | 0.8647 | 0.5967 |
76
+ | 0.8079 | 9.0 | 3375 | 0.8304 | 0.62 |
77
+ | 0.7619 | 10.0 | 3750 | 0.7976 | 0.645 |
78
+ | 0.7316 | 11.0 | 4125 | 0.7657 | 0.665 |
79
+ | 0.6666 | 12.0 | 4500 | 0.7355 | 0.68 |
80
+ | 0.6961 | 13.0 | 4875 | 0.7078 | 0.69 |
81
+ | 0.6607 | 14.0 | 5250 | 0.6819 | 0.7083 |
82
+ | 0.6448 | 15.0 | 5625 | 0.6579 | 0.725 |
83
+ | 0.6031 | 16.0 | 6000 | 0.6371 | 0.7333 |
84
+ | 0.633 | 17.0 | 6375 | 0.6195 | 0.7433 |
85
+ | 0.6177 | 18.0 | 6750 | 0.6022 | 0.7533 |
86
+ | 0.5854 | 19.0 | 7125 | 0.5875 | 0.765 |
87
+ | 0.5213 | 20.0 | 7500 | 0.5748 | 0.77 |
88
+ | 0.5296 | 21.0 | 7875 | 0.5628 | 0.7833 |
89
+ | 0.5226 | 22.0 | 8250 | 0.5527 | 0.7917 |
90
+ | 0.5777 | 23.0 | 8625 | 0.5439 | 0.795 |
91
+ | 0.5616 | 24.0 | 9000 | 0.5354 | 0.8017 |
92
+ | 0.5254 | 25.0 | 9375 | 0.5279 | 0.8067 |
93
+ | 0.5443 | 26.0 | 9750 | 0.5213 | 0.8067 |
94
+ | 0.5349 | 27.0 | 10125 | 0.5152 | 0.8133 |
95
+ | 0.5476 | 28.0 | 10500 | 0.5090 | 0.8133 |
96
+ | 0.5198 | 29.0 | 10875 | 0.5041 | 0.815 |
97
+ | 0.4665 | 30.0 | 11250 | 0.4997 | 0.8167 |
98
+ | 0.5013 | 31.0 | 11625 | 0.4955 | 0.8167 |
99
+ | 0.5242 | 32.0 | 12000 | 0.4917 | 0.8167 |
100
+ | 0.5162 | 33.0 | 12375 | 0.4881 | 0.8167 |
101
+ | 0.5094 | 34.0 | 12750 | 0.4847 | 0.815 |
102
+ | 0.4537 | 35.0 | 13125 | 0.4817 | 0.8167 |
103
+ | 0.4056 | 36.0 | 13500 | 0.4788 | 0.8167 |
104
+ | 0.4566 | 37.0 | 13875 | 0.4763 | 0.8167 |
105
+ | 0.4864 | 38.0 | 14250 | 0.4740 | 0.8183 |
106
+ | 0.4572 | 39.0 | 14625 | 0.4721 | 0.82 |
107
+ | 0.5272 | 40.0 | 15000 | 0.4702 | 0.82 |
108
+ | 0.4662 | 41.0 | 15375 | 0.4685 | 0.82 |
109
+ | 0.4598 | 42.0 | 15750 | 0.4671 | 0.82 |
110
+ | 0.4764 | 43.0 | 16125 | 0.4660 | 0.82 |
111
+ | 0.4497 | 44.0 | 16500 | 0.4650 | 0.82 |
112
+ | 0.4734 | 45.0 | 16875 | 0.4641 | 0.82 |
113
+ | 0.4953 | 46.0 | 17250 | 0.4634 | 0.82 |
114
+ | 0.4817 | 47.0 | 17625 | 0.4629 | 0.8217 |
115
+ | 0.4691 | 48.0 | 18000 | 0.4625 | 0.8217 |
116
+ | 0.4502 | 49.0 | 18375 | 0.4623 | 0.8217 |
117
+ | 0.4257 | 50.0 | 18750 | 0.4623 | 0.8217 |
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 sha256:5e6f5d5af702c68268b925828b0c9963af422892731722947936f2bbc9800b68
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902a749cabd571f60962c8ce0a4353b3be678fd4e086c65585db93048604ba25
3
  size 22167850