Hugging Face's logo

hkivancoral
/
hushem_40x_deit_base_sgd_001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
b722c6d
·
1 Parent(s): 1757364

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-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_40x_deit_base_sgd_001_fold4
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: 0.9285714285714286
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_base_sgd_001_fold4
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2186
36
+ - Accuracy: 0.9286
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
+ | 1.2742 | 1.0 | 219 | 1.3421 | 0.4286 |
69
+ | 1.1364 | 2.0 | 438 | 1.2693 | 0.4048 |
70
+ | 0.9912 | 3.0 | 657 | 1.1701 | 0.5238 |
71
+ | 0.8292 | 4.0 | 876 | 1.0493 | 0.6429 |
72
+ | 0.7771 | 5.0 | 1095 | 0.9148 | 0.7143 |
73
+ | 0.6956 | 6.0 | 1314 | 0.8048 | 0.7381 |
74
+ | 0.519 | 7.0 | 1533 | 0.7062 | 0.8095 |
75
+ | 0.5042 | 8.0 | 1752 | 0.6401 | 0.7857 |
76
+ | 0.4397 | 9.0 | 1971 | 0.5785 | 0.8333 |
77
+ | 0.3933 | 10.0 | 2190 | 0.5338 | 0.8571 |
78
+ | 0.341 | 11.0 | 2409 | 0.4959 | 0.8810 |
79
+ | 0.3345 | 12.0 | 2628 | 0.4569 | 0.8810 |
80
+ | 0.2949 | 13.0 | 2847 | 0.4265 | 0.9048 |
81
+ | 0.2608 | 14.0 | 3066 | 0.3999 | 0.9286 |
82
+ | 0.2368 | 15.0 | 3285 | 0.3796 | 0.9286 |
83
+ | 0.2257 | 16.0 | 3504 | 0.3614 | 0.9286 |
84
+ | 0.232 | 17.0 | 3723 | 0.3430 | 0.9286 |
85
+ | 0.1928 | 18.0 | 3942 | 0.3249 | 0.9286 |
86
+ | 0.1804 | 19.0 | 4161 | 0.3144 | 0.9286 |
87
+ | 0.1542 | 20.0 | 4380 | 0.3019 | 0.9048 |
88
+ | 0.1333 | 21.0 | 4599 | 0.2915 | 0.9286 |
89
+ | 0.1333 | 22.0 | 4818 | 0.2894 | 0.9048 |
90
+ | 0.1178 | 23.0 | 5037 | 0.2746 | 0.9286 |
91
+ | 0.1098 | 24.0 | 5256 | 0.2771 | 0.9048 |
92
+ | 0.1099 | 25.0 | 5475 | 0.2649 | 0.9048 |
93
+ | 0.0836 | 26.0 | 5694 | 0.2732 | 0.9048 |
94
+ | 0.0751 | 27.0 | 5913 | 0.2625 | 0.9048 |
95
+ | 0.0745 | 28.0 | 6132 | 0.2608 | 0.9048 |
96
+ | 0.0826 | 29.0 | 6351 | 0.2526 | 0.9048 |
97
+ | 0.079 | 30.0 | 6570 | 0.2463 | 0.9286 |
98
+ | 0.0659 | 31.0 | 6789 | 0.2439 | 0.9048 |
99
+ | 0.0738 | 32.0 | 7008 | 0.2422 | 0.9286 |
100
+ | 0.0683 | 33.0 | 7227 | 0.2335 | 0.9286 |
101
+ | 0.0674 | 34.0 | 7446 | 0.2343 | 0.9048 |
102
+ | 0.0633 | 35.0 | 7665 | 0.2311 | 0.9048 |
103
+ | 0.0608 | 36.0 | 7884 | 0.2259 | 0.9286 |
104
+ | 0.0543 | 37.0 | 8103 | 0.2239 | 0.9286 |
105
+ | 0.0444 | 38.0 | 8322 | 0.2256 | 0.9286 |
106
+ | 0.0496 | 39.0 | 8541 | 0.2255 | 0.9286 |
107
+ | 0.0513 | 40.0 | 8760 | 0.2253 | 0.9286 |
108
+ | 0.0449 | 41.0 | 8979 | 0.2226 | 0.9286 |
109
+ | 0.0449 | 42.0 | 9198 | 0.2216 | 0.9286 |
110
+ | 0.0549 | 43.0 | 9417 | 0.2202 | 0.9286 |
111
+ | 0.0488 | 44.0 | 9636 | 0.2213 | 0.9286 |
112
+ | 0.0437 | 45.0 | 9855 | 0.2208 | 0.9286 |
113
+ | 0.0362 | 46.0 | 10074 | 0.2201 | 0.9286 |
114
+ | 0.0622 | 47.0 | 10293 | 0.2188 | 0.9286 |
115
+ | 0.0546 | 48.0 | 10512 | 0.2185 | 0.9286 |
116
+ | 0.0472 | 49.0 | 10731 | 0.2186 | 0.9286 |
117
+ | 0.0581 | 50.0 | 10950 | 0.2186 | 0.9286 |
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:f89fa6d88a0ad5464fbe2dc41b664750570d223f31ded3a1f114a8118ae9ceda
3
  size 343275306
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fef3e8851b436693e175589d4c347412d0f0fee02c319bf10343bf01f4829d0
3
  size 343275306