Soulaimen commited on
Commit
b23163d
1 Parent(s): 16aa1dd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: swin-tiny-patch4-window7-224-bottom_cleaned_data-hpt
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: 0.9694041867954911
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
+ # swin-tiny-patch4-window7-224-bottom_cleaned_data-hpt
31
+
32
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0701
35
+ - Accuracy: 0.9694
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: 5e-05
55
+ - train_batch_size: 8
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 7
59
+ - total_train_batch_size: 56
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.01
63
+ - num_epochs: 10
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.4307 | 0.99 | 99 | 0.2332 | 0.9227 |
70
+ | 0.3425 | 2.0 | 199 | 0.1904 | 0.9404 |
71
+ | 0.29 | 3.0 | 299 | 0.1316 | 0.9388 |
72
+ | 0.2597 | 3.99 | 398 | 0.1158 | 0.9533 |
73
+ | 0.2638 | 4.99 | 498 | 0.0987 | 0.9614 |
74
+ | 0.209 | 6.0 | 598 | 0.0802 | 0.9710 |
75
+ | 0.1776 | 7.0 | 698 | 0.0838 | 0.9597 |
76
+ | 0.1776 | 7.99 | 797 | 0.0787 | 0.9694 |
77
+ | 0.1502 | 9.0 | 897 | 0.0797 | 0.9726 |
78
+ | 0.1402 | 9.93 | 990 | 0.0701 | 0.9694 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.28.1
84
+ - Pytorch 2.0.0+cu118
85
+ - Datasets 2.11.0
86
+ - Tokenizers 0.13.3