Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_00001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
92c4b1d
•
1 Parent(s): 86ad5e3

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_00001_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: 0.36833333333333335
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_00001_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: 1.1969
36
+ - Accuracy: 0.3683
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
+ | 1.2818 | 1.0 | 75 | 1.3526 | 0.35 |
69
+ | 1.2881 | 2.0 | 150 | 1.3438 | 0.35 |
70
+ | 1.2902 | 3.0 | 225 | 1.3353 | 0.3533 |
71
+ | 1.3491 | 4.0 | 300 | 1.3273 | 0.3517 |
72
+ | 1.2508 | 5.0 | 375 | 1.3195 | 0.355 |
73
+ | 1.2901 | 6.0 | 450 | 1.3122 | 0.355 |
74
+ | 1.2792 | 7.0 | 525 | 1.3053 | 0.3583 |
75
+ | 1.2973 | 8.0 | 600 | 1.2988 | 0.3583 |
76
+ | 1.3051 | 9.0 | 675 | 1.2924 | 0.3583 |
77
+ | 1.3668 | 10.0 | 750 | 1.2863 | 0.3583 |
78
+ | 1.2982 | 11.0 | 825 | 1.2805 | 0.3633 |
79
+ | 1.1991 | 12.0 | 900 | 1.2750 | 0.3617 |
80
+ | 1.2833 | 13.0 | 975 | 1.2699 | 0.3617 |
81
+ | 1.2768 | 14.0 | 1050 | 1.2648 | 0.36 |
82
+ | 1.2691 | 15.0 | 1125 | 1.2602 | 0.36 |
83
+ | 1.2029 | 16.0 | 1200 | 1.2557 | 0.3617 |
84
+ | 1.2189 | 17.0 | 1275 | 1.2513 | 0.3667 |
85
+ | 1.2814 | 18.0 | 1350 | 1.2472 | 0.3683 |
86
+ | 1.1777 | 19.0 | 1425 | 1.2435 | 0.37 |
87
+ | 1.2006 | 20.0 | 1500 | 1.2398 | 0.3683 |
88
+ | 1.3016 | 21.0 | 1575 | 1.2363 | 0.3717 |
89
+ | 1.2664 | 22.0 | 1650 | 1.2331 | 0.3683 |
90
+ | 1.1963 | 23.0 | 1725 | 1.2301 | 0.37 |
91
+ | 1.2239 | 24.0 | 1800 | 1.2272 | 0.37 |
92
+ | 1.1881 | 25.0 | 1875 | 1.2244 | 0.37 |
93
+ | 1.2397 | 26.0 | 1950 | 1.2219 | 0.3717 |
94
+ | 1.1817 | 27.0 | 2025 | 1.2194 | 0.3717 |
95
+ | 1.2303 | 28.0 | 2100 | 1.2172 | 0.3733 |
96
+ | 1.253 | 29.0 | 2175 | 1.2151 | 0.3733 |
97
+ | 1.1936 | 30.0 | 2250 | 1.2131 | 0.3733 |
98
+ | 1.2173 | 31.0 | 2325 | 1.2113 | 0.3733 |
99
+ | 1.153 | 32.0 | 2400 | 1.2096 | 0.3733 |
100
+ | 1.2175 | 33.0 | 2475 | 1.2080 | 0.3733 |
101
+ | 1.2243 | 34.0 | 2550 | 1.2065 | 0.3733 |
102
+ | 1.1302 | 35.0 | 2625 | 1.2052 | 0.3717 |
103
+ | 1.1855 | 36.0 | 2700 | 1.2040 | 0.37 |
104
+ | 1.1832 | 37.0 | 2775 | 1.2029 | 0.37 |
105
+ | 1.1866 | 38.0 | 2850 | 1.2019 | 0.365 |
106
+ | 1.2112 | 39.0 | 2925 | 1.2010 | 0.365 |
107
+ | 1.199 | 40.0 | 3000 | 1.2002 | 0.3667 |
108
+ | 1.1826 | 41.0 | 3075 | 1.1995 | 0.3667 |
109
+ | 1.2211 | 42.0 | 3150 | 1.1988 | 0.3683 |
110
+ | 1.2093 | 43.0 | 3225 | 1.1983 | 0.3683 |
111
+ | 1.2039 | 44.0 | 3300 | 1.1979 | 0.3683 |
112
+ | 1.1848 | 45.0 | 3375 | 1.1975 | 0.3683 |
113
+ | 1.2445 | 46.0 | 3450 | 1.1973 | 0.3683 |
114
+ | 1.1786 | 47.0 | 3525 | 1.1971 | 0.3683 |
115
+ | 1.1742 | 48.0 | 3600 | 1.1970 | 0.3683 |
116
+ | 1.1159 | 49.0 | 3675 | 1.1969 | 0.3683 |
117
+ | 1.1807 | 50.0 | 3750 | 1.1969 | 0.3683 |
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:b0be2337423e728137bfe6b4c40bdffd80258da0fc0d1b2c3a01cab7ac11173f
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a986e68f7706185777be68ab881a6991320c070ce1887f22050a21096b96b3
3
  size 22122692