Hugging Face's logo

hkivancoral
/
hushem_5x_deit_small_rms_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
b48690c
·
1 Parent(s): 230c19f

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_deit_small_rms_001_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: 0.6585365853658537
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
+ # hushem_5x_deit_small_rms_001_fold5
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: 1.2275
36
+ - Accuracy: 0.6585
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: 0.001
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
+ | 1.7524 | 1.0 | 28 | 1.5298 | 0.2439 |
69
+ | 1.4312 | 2.0 | 56 | 1.4291 | 0.2683 |
70
+ | 1.3924 | 3.0 | 84 | 1.4059 | 0.2927 |
71
+ | 1.4173 | 4.0 | 112 | 1.3938 | 0.2683 |
72
+ | 1.3939 | 5.0 | 140 | 1.3790 | 0.2683 |
73
+ | 1.3863 | 6.0 | 168 | 1.4164 | 0.2439 |
74
+ | 1.3865 | 7.0 | 196 | 1.3790 | 0.2683 |
75
+ | 1.394 | 8.0 | 224 | 1.3790 | 0.2683 |
76
+ | 1.3883 | 9.0 | 252 | 1.4097 | 0.2683 |
77
+ | 1.3472 | 10.0 | 280 | 1.2478 | 0.4390 |
78
+ | 1.3905 | 11.0 | 308 | 1.2068 | 0.3902 |
79
+ | 1.1031 | 12.0 | 336 | 1.2038 | 0.4390 |
80
+ | 1.1503 | 13.0 | 364 | 1.0846 | 0.4634 |
81
+ | 1.2064 | 14.0 | 392 | 1.1395 | 0.4146 |
82
+ | 1.1249 | 15.0 | 420 | 1.1544 | 0.4146 |
83
+ | 1.1285 | 16.0 | 448 | 1.0714 | 0.4634 |
84
+ | 1.1149 | 17.0 | 476 | 0.9771 | 0.6098 |
85
+ | 1.0493 | 18.0 | 504 | 0.9974 | 0.4634 |
86
+ | 0.9938 | 19.0 | 532 | 0.9792 | 0.5366 |
87
+ | 1.0212 | 20.0 | 560 | 0.9949 | 0.5854 |
88
+ | 0.9943 | 21.0 | 588 | 1.0078 | 0.5366 |
89
+ | 1.0044 | 22.0 | 616 | 0.9007 | 0.5366 |
90
+ | 1.0661 | 23.0 | 644 | 1.2742 | 0.4878 |
91
+ | 0.9523 | 24.0 | 672 | 0.9851 | 0.6829 |
92
+ | 0.8733 | 25.0 | 700 | 0.9430 | 0.5854 |
93
+ | 0.8075 | 26.0 | 728 | 0.9660 | 0.6585 |
94
+ | 0.9128 | 27.0 | 756 | 0.9161 | 0.7561 |
95
+ | 0.8898 | 28.0 | 784 | 0.8767 | 0.7073 |
96
+ | 0.8051 | 29.0 | 812 | 0.8174 | 0.6829 |
97
+ | 0.8328 | 30.0 | 840 | 0.8077 | 0.6585 |
98
+ | 0.81 | 31.0 | 868 | 0.7911 | 0.6585 |
99
+ | 0.7372 | 32.0 | 896 | 1.0262 | 0.6585 |
100
+ | 0.7641 | 33.0 | 924 | 1.0698 | 0.5854 |
101
+ | 0.7745 | 34.0 | 952 | 0.8530 | 0.6829 |
102
+ | 0.7037 | 35.0 | 980 | 1.0106 | 0.6585 |
103
+ | 0.7449 | 36.0 | 1008 | 0.8975 | 0.7073 |
104
+ | 0.7391 | 37.0 | 1036 | 0.9607 | 0.6829 |
105
+ | 0.7447 | 38.0 | 1064 | 1.0096 | 0.6585 |
106
+ | 0.7043 | 39.0 | 1092 | 1.0986 | 0.7073 |
107
+ | 0.6379 | 40.0 | 1120 | 1.0787 | 0.6829 |
108
+ | 0.6476 | 41.0 | 1148 | 1.0057 | 0.6829 |
109
+ | 0.5799 | 42.0 | 1176 | 1.1714 | 0.6341 |
110
+ | 0.5954 | 43.0 | 1204 | 1.1356 | 0.6829 |
111
+ | 0.6189 | 44.0 | 1232 | 1.1609 | 0.6829 |
112
+ | 0.5672 | 45.0 | 1260 | 1.1726 | 0.6829 |
113
+ | 0.5115 | 46.0 | 1288 | 1.2388 | 0.6829 |
114
+ | 0.4522 | 47.0 | 1316 | 1.2273 | 0.6829 |
115
+ | 0.4728 | 48.0 | 1344 | 1.2290 | 0.6585 |
116
+ | 0.4195 | 49.0 | 1372 | 1.2275 | 0.6585 |
117
+ | 0.4871 | 50.0 | 1400 | 1.2275 | 0.6585 |
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 sha256:6cf5f18f3d66fb8937d116185ee8f37d76b18e74adacd5945eff0e8f6f6e99f8
3
  size 86691704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2fd3e2d6790bc049278f9241cbcc77e54ab577df7fb9af5f1a1060264d53be
3
  size 86691704