Farideh commited on
Commit
e45b9fa
·
1 Parent(s): 3154bcb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: dataset_model2
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.8797595190380761
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # dataset_model2
31
+
32
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.5350
35
+ - Accuracy: 0.8798
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0001
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 64
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 20
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.1141 | 0.99 | 62 | 0.4707 | 0.8647 |
70
+ | 0.1098 | 1.99 | 124 | 0.4876 | 0.8597 |
71
+ | 0.1444 | 2.99 | 186 | 0.4651 | 0.8647 |
72
+ | 0.1088 | 3.99 | 248 | 0.5397 | 0.8527 |
73
+ | 0.1404 | 4.99 | 310 | 0.4794 | 0.8727 |
74
+ | 0.0656 | 5.99 | 372 | 0.5637 | 0.8507 |
75
+ | 0.1126 | 6.99 | 434 | 0.5318 | 0.8597 |
76
+ | 0.099 | 7.99 | 496 | 0.5522 | 0.8597 |
77
+ | 0.0501 | 8.99 | 558 | 0.5654 | 0.8667 |
78
+ | 0.0878 | 9.99 | 620 | 0.5915 | 0.8517 |
79
+ | 0.0594 | 10.99 | 682 | 0.5846 | 0.8717 |
80
+ | 0.0562 | 11.99 | 744 | 0.5191 | 0.8778 |
81
+ | 0.0554 | 12.99 | 806 | 0.5425 | 0.8717 |
82
+ | 0.0368 | 13.99 | 868 | 0.5725 | 0.8778 |
83
+ | 0.0415 | 14.99 | 930 | 0.5790 | 0.8637 |
84
+ | 0.0208 | 15.99 | 992 | 0.5319 | 0.8788 |
85
+ | 0.026 | 16.99 | 1054 | 0.5622 | 0.8677 |
86
+ | 0.0307 | 17.99 | 1116 | 0.5129 | 0.8878 |
87
+ | 0.015 | 18.99 | 1178 | 0.5508 | 0.8768 |
88
+ | 0.0263 | 19.99 | 1240 | 0.5350 | 0.8798 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.0.dev0
94
+ - Pytorch 1.13.0+cu117
95
+ - Datasets 2.7.1
96
+ - Tokenizers 0.13.2