Hugging Face's logo

hkivancoral
/
smids_10x_deit_small_sgd_00001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
1447e64
•
1 Parent(s): e9fd38a

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: smids_10x_deit_small_sgd_00001_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: 0.5590682196339434
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_10x_deit_small_sgd_00001_fold2
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: 0.9349
36
+ - Accuracy: 0.5591
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
+ | 1.0693 | 1.0 | 750 | 1.0692 | 0.4293 |
69
+ | 1.0584 | 2.0 | 1500 | 1.0648 | 0.4343 |
70
+ | 1.0342 | 3.0 | 2250 | 1.0600 | 0.4376 |
71
+ | 1.0374 | 4.0 | 3000 | 1.0551 | 0.4443 |
72
+ | 1.028 | 5.0 | 3750 | 1.0500 | 0.4459 |
73
+ | 1.0131 | 6.0 | 4500 | 1.0451 | 0.4476 |
74
+ | 1.022 | 7.0 | 5250 | 1.0402 | 0.4459 |
75
+ | 1.0192 | 8.0 | 6000 | 1.0354 | 0.4526 |
76
+ | 1.0168 | 9.0 | 6750 | 1.0306 | 0.4576 |
77
+ | 0.9985 | 10.0 | 7500 | 1.0259 | 0.4592 |
78
+ | 0.9898 | 11.0 | 8250 | 1.0213 | 0.4609 |
79
+ | 1.0116 | 12.0 | 9000 | 1.0168 | 0.4642 |
80
+ | 0.9986 | 13.0 | 9750 | 1.0125 | 0.4659 |
81
+ | 0.9818 | 14.0 | 10500 | 1.0083 | 0.4759 |
82
+ | 0.9837 | 15.0 | 11250 | 1.0041 | 0.4809 |
83
+ | 0.9601 | 16.0 | 12000 | 1.0001 | 0.4809 |
84
+ | 0.9572 | 17.0 | 12750 | 0.9961 | 0.4809 |
85
+ | 0.9406 | 18.0 | 13500 | 0.9923 | 0.4859 |
86
+ | 0.9621 | 19.0 | 14250 | 0.9887 | 0.4892 |
87
+ | 0.9467 | 20.0 | 15000 | 0.9850 | 0.4925 |
88
+ | 0.9691 | 21.0 | 15750 | 0.9816 | 0.4992 |
89
+ | 0.9406 | 22.0 | 16500 | 0.9782 | 0.5008 |
90
+ | 0.9223 | 23.0 | 17250 | 0.9750 | 0.5058 |
91
+ | 0.9127 | 24.0 | 18000 | 0.9718 | 0.5075 |
92
+ | 0.9371 | 25.0 | 18750 | 0.9688 | 0.5141 |
93
+ | 0.9589 | 26.0 | 19500 | 0.9659 | 0.5175 |
94
+ | 0.9189 | 27.0 | 20250 | 0.9631 | 0.5208 |
95
+ | 0.9249 | 28.0 | 21000 | 0.9605 | 0.5258 |
96
+ | 0.927 | 29.0 | 21750 | 0.9580 | 0.5275 |
97
+ | 0.9378 | 30.0 | 22500 | 0.9556 | 0.5308 |
98
+ | 0.8829 | 31.0 | 23250 | 0.9533 | 0.5308 |
99
+ | 0.931 | 32.0 | 24000 | 0.9512 | 0.5341 |
100
+ | 0.9197 | 33.0 | 24750 | 0.9492 | 0.5374 |
101
+ | 0.9032 | 34.0 | 25500 | 0.9474 | 0.5374 |
102
+ | 0.9 | 35.0 | 26250 | 0.9457 | 0.5391 |
103
+ | 0.8939 | 36.0 | 27000 | 0.9442 | 0.5441 |
104
+ | 0.9276 | 37.0 | 27750 | 0.9427 | 0.5458 |
105
+ | 0.8712 | 38.0 | 28500 | 0.9414 | 0.5458 |
106
+ | 0.9222 | 39.0 | 29250 | 0.9402 | 0.5458 |
107
+ | 0.8913 | 40.0 | 30000 | 0.9392 | 0.5474 |
108
+ | 0.8879 | 41.0 | 30750 | 0.9383 | 0.5474 |
109
+ | 0.8851 | 42.0 | 31500 | 0.9375 | 0.5541 |
110
+ | 0.8777 | 43.0 | 32250 | 0.9368 | 0.5541 |
111
+ | 0.8945 | 44.0 | 33000 | 0.9362 | 0.5541 |
112
+ | 0.8708 | 45.0 | 33750 | 0.9358 | 0.5574 |
113
+ | 0.9082 | 46.0 | 34500 | 0.9354 | 0.5591 |
114
+ | 0.9028 | 47.0 | 35250 | 0.9352 | 0.5591 |
115
+ | 0.8903 | 48.0 | 36000 | 0.9350 | 0.5591 |
116
+ | 0.8994 | 49.0 | 36750 | 0.9349 | 0.5591 |
117
+ | 0.9183 | 50.0 | 37500 | 0.9349 | 0.5591 |
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 sha256:5e4bf230f8a79f46bb5222a19f19f816a7030edaf1e1935dcd6b8707545ab614
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f65c7888b284fd954d0db2fa7e67e8ce8e1d4cf9bd89fb6d6a578de5c3212f
3
  size 86735658