Hugging Face's logo

hkivancoral
/
hushem_40x_deit_small_sgd_0001_fold3

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
fde01af
•
1 Parent(s): 8274a48

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_0001_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: 0.5813953488372093
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_0001_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: 1.0466
36
+ - Accuracy: 0.5814
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
+ | 1.6887 | 1.0 | 217 | 1.4610 | 0.2558 |
69
+ | 1.5962 | 2.0 | 434 | 1.3845 | 0.3488 |
70
+ | 1.5124 | 3.0 | 651 | 1.3560 | 0.3721 |
71
+ | 1.442 | 4.0 | 868 | 1.3419 | 0.3721 |
72
+ | 1.41 | 5.0 | 1085 | 1.3313 | 0.3488 |
73
+ | 1.3709 | 6.0 | 1302 | 1.3218 | 0.3721 |
74
+ | 1.3157 | 7.0 | 1519 | 1.3125 | 0.3721 |
75
+ | 1.3328 | 8.0 | 1736 | 1.3039 | 0.3488 |
76
+ | 1.3107 | 9.0 | 1953 | 1.2950 | 0.3488 |
77
+ | 1.2568 | 10.0 | 2170 | 1.2861 | 0.3488 |
78
+ | 1.2226 | 11.0 | 2387 | 1.2769 | 0.3256 |
79
+ | 1.198 | 12.0 | 2604 | 1.2671 | 0.3256 |
80
+ | 1.232 | 13.0 | 2821 | 1.2570 | 0.3488 |
81
+ | 1.1803 | 14.0 | 3038 | 1.2472 | 0.3488 |
82
+ | 1.214 | 15.0 | 3255 | 1.2376 | 0.3488 |
83
+ | 1.208 | 16.0 | 3472 | 1.2274 | 0.3953 |
84
+ | 1.1406 | 17.0 | 3689 | 1.2176 | 0.3953 |
85
+ | 1.1243 | 18.0 | 3906 | 1.2072 | 0.3953 |
86
+ | 1.1316 | 19.0 | 4123 | 1.1970 | 0.4884 |
87
+ | 1.1119 | 20.0 | 4340 | 1.1873 | 0.4884 |
88
+ | 1.117 | 21.0 | 4557 | 1.1775 | 0.5116 |
89
+ | 1.0609 | 22.0 | 4774 | 1.1681 | 0.5116 |
90
+ | 1.0751 | 23.0 | 4991 | 1.1588 | 0.5581 |
91
+ | 1.058 | 24.0 | 5208 | 1.1499 | 0.5581 |
92
+ | 1.0301 | 25.0 | 5425 | 1.1417 | 0.5581 |
93
+ | 1.089 | 26.0 | 5642 | 1.1338 | 0.5581 |
94
+ | 0.9909 | 27.0 | 5859 | 1.1255 | 0.5814 |
95
+ | 0.9932 | 28.0 | 6076 | 1.1180 | 0.5814 |
96
+ | 1.026 | 29.0 | 6293 | 1.1110 | 0.5814 |
97
+ | 1.0236 | 30.0 | 6510 | 1.1044 | 0.5814 |
98
+ | 1.0169 | 31.0 | 6727 | 1.0980 | 0.5814 |
99
+ | 1.0049 | 32.0 | 6944 | 1.0921 | 0.5814 |
100
+ | 1.0261 | 33.0 | 7161 | 1.0868 | 0.5814 |
101
+ | 0.994 | 34.0 | 7378 | 1.0819 | 0.5814 |
102
+ | 0.9887 | 35.0 | 7595 | 1.0769 | 0.5581 |
103
+ | 1.0137 | 36.0 | 7812 | 1.0725 | 0.5581 |
104
+ | 0.9359 | 37.0 | 8029 | 1.0687 | 0.5581 |
105
+ | 0.9531 | 38.0 | 8246 | 1.0651 | 0.5581 |
106
+ | 0.9682 | 39.0 | 8463 | 1.0620 | 0.5581 |
107
+ | 0.9947 | 40.0 | 8680 | 1.0590 | 0.5581 |
108
+ | 0.9063 | 41.0 | 8897 | 1.0565 | 0.5581 |
109
+ | 1.0195 | 42.0 | 9114 | 1.0543 | 0.5581 |
110
+ | 0.966 | 43.0 | 9331 | 1.0523 | 0.5581 |
111
+ | 0.9409 | 44.0 | 9548 | 1.0506 | 0.5581 |
112
+ | 0.9327 | 45.0 | 9765 | 1.0492 | 0.5581 |
113
+ | 0.9575 | 46.0 | 9982 | 1.0481 | 0.5814 |
114
+ | 0.9627 | 47.0 | 10199 | 1.0474 | 0.5814 |
115
+ | 0.9553 | 48.0 | 10416 | 1.0469 | 0.5814 |
116
+ | 0.9631 | 49.0 | 10633 | 1.0467 | 0.5814 |
117
+ | 0.944 | 50.0 | 10850 | 1.0466 | 0.5814 |
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:d93304d28ae5c3ff4154f5825a1189178eaf43a42408e2fc0ab2b551f660a3cd
3
  size 86737194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869f0d62f0a7c32da350dd84d404d9d1934b898bb7a3fb4fdc38e9e1a7862bf4
3
  size 86737194