Hugging Face's logo

hkivancoral
/
hushem_40x_deit_small_sgd_00001_fold3

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
0bd6186
•
1 Parent(s): a4aabf9

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: hushem_40x_deit_small_sgd_00001_fold3
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: 0.32558139534883723
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_40x_deit_small_sgd_00001_fold3
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: 1.3703
36
+ - Accuracy: 0.3256
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
+ | 1.8914 | 1.0 | 217 | 1.5805 | 0.2558 |
69
+ | 2.0178 | 2.0 | 434 | 1.5654 | 0.2558 |
70
+ | 2.0179 | 3.0 | 651 | 1.5510 | 0.2558 |
71
+ | 1.8888 | 4.0 | 868 | 1.5374 | 0.2558 |
72
+ | 1.872 | 5.0 | 1085 | 1.5245 | 0.2558 |
73
+ | 1.7831 | 6.0 | 1302 | 1.5124 | 0.2558 |
74
+ | 1.836 | 7.0 | 1519 | 1.5009 | 0.2558 |
75
+ | 1.8178 | 8.0 | 1736 | 1.4901 | 0.2558 |
76
+ | 1.7694 | 9.0 | 1953 | 1.4801 | 0.2326 |
77
+ | 1.7678 | 10.0 | 2170 | 1.4706 | 0.2326 |
78
+ | 1.659 | 11.0 | 2387 | 1.4618 | 0.2326 |
79
+ | 1.6239 | 12.0 | 2604 | 1.4536 | 0.2558 |
80
+ | 1.6882 | 13.0 | 2821 | 1.4460 | 0.2558 |
81
+ | 1.6748 | 14.0 | 3038 | 1.4391 | 0.2558 |
82
+ | 1.6892 | 15.0 | 3255 | 1.4327 | 0.2791 |
83
+ | 1.725 | 16.0 | 3472 | 1.4268 | 0.2791 |
84
+ | 1.6371 | 17.0 | 3689 | 1.4214 | 0.2791 |
85
+ | 1.6193 | 18.0 | 3906 | 1.4164 | 0.3256 |
86
+ | 1.6512 | 19.0 | 4123 | 1.4119 | 0.3256 |
87
+ | 1.6188 | 20.0 | 4340 | 1.4078 | 0.3256 |
88
+ | 1.643 | 21.0 | 4557 | 1.4041 | 0.3256 |
89
+ | 1.5803 | 22.0 | 4774 | 1.4006 | 0.3256 |
90
+ | 1.592 | 23.0 | 4991 | 1.3975 | 0.3256 |
91
+ | 1.5987 | 24.0 | 5208 | 1.3946 | 0.3256 |
92
+ | 1.566 | 25.0 | 5425 | 1.3921 | 0.3488 |
93
+ | 1.5574 | 26.0 | 5642 | 1.3897 | 0.3488 |
94
+ | 1.4978 | 27.0 | 5859 | 1.3876 | 0.3488 |
95
+ | 1.524 | 28.0 | 6076 | 1.3857 | 0.3488 |
96
+ | 1.5682 | 29.0 | 6293 | 1.3839 | 0.3488 |
97
+ | 1.5042 | 30.0 | 6510 | 1.3823 | 0.3488 |
98
+ | 1.5589 | 31.0 | 6727 | 1.3808 | 0.3023 |
99
+ | 1.5347 | 32.0 | 6944 | 1.3795 | 0.3023 |
100
+ | 1.5403 | 33.0 | 7161 | 1.3783 | 0.3023 |
101
+ | 1.5548 | 34.0 | 7378 | 1.3772 | 0.3023 |
102
+ | 1.5321 | 35.0 | 7595 | 1.3762 | 0.3023 |
103
+ | 1.5015 | 36.0 | 7812 | 1.3753 | 0.3023 |
104
+ | 1.4993 | 37.0 | 8029 | 1.3745 | 0.3023 |
105
+ | 1.4844 | 38.0 | 8246 | 1.3738 | 0.3023 |
106
+ | 1.5191 | 39.0 | 8463 | 1.3732 | 0.3023 |
107
+ | 1.515 | 40.0 | 8680 | 1.3726 | 0.3256 |
108
+ | 1.4957 | 41.0 | 8897 | 1.3721 | 0.3256 |
109
+ | 1.5585 | 42.0 | 9114 | 1.3717 | 0.3256 |
110
+ | 1.5037 | 43.0 | 9331 | 1.3713 | 0.3256 |
111
+ | 1.4828 | 44.0 | 9548 | 1.3710 | 0.3256 |
112
+ | 1.4967 | 45.0 | 9765 | 1.3708 | 0.3256 |
113
+ | 1.5387 | 46.0 | 9982 | 1.3706 | 0.3256 |
114
+ | 1.5118 | 47.0 | 10199 | 1.3705 | 0.3256 |
115
+ | 1.5073 | 48.0 | 10416 | 1.3704 | 0.3256 |
116
+ | 1.5166 | 49.0 | 10633 | 1.3703 | 0.3256 |
117
+ | 1.4994 | 50.0 | 10850 | 1.3703 | 0.3256 |
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 sha256:59a52809a4c16387b58c65661f9255dd6d437cfd98656265b76c4ccac33d4dea
3
  size 86737194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96aa83587d1d577c0ab4553697e4fc12ab109ac9d684a0febe3fa911aa8ce25f
3
  size 86737194