Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_0001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
06a0108
•
1 Parent(s): 6620085

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_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: 0.6023294509151415
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_fold2
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: 0.8723
36
+ - Accuracy: 0.6023
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
+ | 1.2913 | 1.0 | 75 | 1.2725 | 0.3394 |
69
+ | 1.2246 | 2.0 | 150 | 1.2089 | 0.3444 |
70
+ | 1.1634 | 3.0 | 225 | 1.1639 | 0.3561 |
71
+ | 1.1405 | 4.0 | 300 | 1.1319 | 0.3661 |
72
+ | 1.1027 | 5.0 | 375 | 1.1096 | 0.3727 |
73
+ | 1.1314 | 6.0 | 450 | 1.0924 | 0.3960 |
74
+ | 1.1132 | 7.0 | 525 | 1.0784 | 0.4193 |
75
+ | 1.0729 | 8.0 | 600 | 1.0662 | 0.4359 |
76
+ | 1.064 | 9.0 | 675 | 1.0549 | 0.4526 |
77
+ | 1.0806 | 10.0 | 750 | 1.0450 | 0.4576 |
78
+ | 1.063 | 11.0 | 825 | 1.0356 | 0.4692 |
79
+ | 1.0489 | 12.0 | 900 | 1.0265 | 0.4792 |
80
+ | 1.0267 | 13.0 | 975 | 1.0180 | 0.4942 |
81
+ | 0.9878 | 14.0 | 1050 | 1.0096 | 0.5042 |
82
+ | 1.01 | 15.0 | 1125 | 1.0018 | 0.5058 |
83
+ | 0.9915 | 16.0 | 1200 | 0.9940 | 0.5092 |
84
+ | 0.9952 | 17.0 | 1275 | 0.9865 | 0.5158 |
85
+ | 1.0114 | 18.0 | 1350 | 0.9793 | 0.5258 |
86
+ | 1.0011 | 19.0 | 1425 | 0.9723 | 0.5308 |
87
+ | 0.9762 | 20.0 | 1500 | 0.9654 | 0.5358 |
88
+ | 1.0144 | 21.0 | 1575 | 0.9587 | 0.5408 |
89
+ | 0.9349 | 22.0 | 1650 | 0.9525 | 0.5507 |
90
+ | 0.9869 | 23.0 | 1725 | 0.9462 | 0.5557 |
91
+ | 0.9417 | 24.0 | 1800 | 0.9404 | 0.5591 |
92
+ | 0.9277 | 25.0 | 1875 | 0.9347 | 0.5591 |
93
+ | 0.9227 | 26.0 | 1950 | 0.9293 | 0.5707 |
94
+ | 0.9725 | 27.0 | 2025 | 0.9242 | 0.5674 |
95
+ | 0.9104 | 28.0 | 2100 | 0.9193 | 0.5691 |
96
+ | 0.9618 | 29.0 | 2175 | 0.9147 | 0.5774 |
97
+ | 0.8904 | 30.0 | 2250 | 0.9103 | 0.5824 |
98
+ | 0.9175 | 31.0 | 2325 | 0.9062 | 0.5840 |
99
+ | 0.916 | 32.0 | 2400 | 0.9024 | 0.5857 |
100
+ | 0.8843 | 33.0 | 2475 | 0.8990 | 0.5874 |
101
+ | 0.9346 | 34.0 | 2550 | 0.8956 | 0.5923 |
102
+ | 0.8711 | 35.0 | 2625 | 0.8924 | 0.5957 |
103
+ | 0.8808 | 36.0 | 2700 | 0.8897 | 0.5973 |
104
+ | 0.9043 | 37.0 | 2775 | 0.8870 | 0.5990 |
105
+ | 0.9738 | 38.0 | 2850 | 0.8847 | 0.5957 |
106
+ | 0.8643 | 39.0 | 2925 | 0.8826 | 0.5940 |
107
+ | 0.8918 | 40.0 | 3000 | 0.8806 | 0.5957 |
108
+ | 0.9135 | 41.0 | 3075 | 0.8789 | 0.5973 |
109
+ | 0.9187 | 42.0 | 3150 | 0.8773 | 0.5973 |
110
+ | 0.8721 | 43.0 | 3225 | 0.8760 | 0.5973 |
111
+ | 0.9047 | 44.0 | 3300 | 0.8749 | 0.5990 |
112
+ | 0.8511 | 45.0 | 3375 | 0.8740 | 0.6007 |
113
+ | 0.8649 | 46.0 | 3450 | 0.8732 | 0.6007 |
114
+ | 0.8917 | 47.0 | 3525 | 0.8727 | 0.6023 |
115
+ | 0.8901 | 48.0 | 3600 | 0.8724 | 0.6023 |
116
+ | 0.883 | 49.0 | 3675 | 0.8723 | 0.6023 |
117
+ | 0.8823 | 50.0 | 3750 | 0.8723 | 0.6023 |
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 sha256:20492cb90369bcc5b6cb117fd79d3ce39293fcb87fb7ae8ee7bc8db5751247cf
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64f5a0c961056abb4bf39fae44574e30294ce96fb99f1d8f46d5f3936b1a577
3
  size 22122692