Hugging Face's logo

Gokulapriyan
/
vit-base-patch16-224-finetuned-main-gpu-20e-final

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Gokulapriyan commited on
Commit
76e46ab
•
1 Parent(s): ff107e7

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: vit-base-patch16-224-finetuned-main-gpu-20e-final
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: validation
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9909863945578231
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
+ # vit-base-patch16-224-finetuned-main-gpu-20e-final
31
+
32
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0285
35
+ - Accuracy: 0.9910
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: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
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
+ | 0.4852 | 1.0 | 551 | 0.4533 | 0.8042 |
70
+ | 0.3033 | 2.0 | 1102 | 0.2157 | 0.9157 |
71
+ | 0.2339 | 3.0 | 1653 | 0.1212 | 0.9534 |
72
+ | 0.1694 | 4.0 | 2204 | 0.1076 | 0.9603 |
73
+ | 0.1715 | 5.0 | 2755 | 0.0830 | 0.9692 |
74
+ | 0.1339 | 6.0 | 3306 | 0.0674 | 0.9762 |
75
+ | 0.1527 | 7.0 | 3857 | 0.0556 | 0.9791 |
76
+ | 0.1214 | 8.0 | 4408 | 0.0455 | 0.9832 |
77
+ | 0.1062 | 9.0 | 4959 | 0.0466 | 0.9829 |
78
+ | 0.0974 | 10.0 | 5510 | 0.0403 | 0.9849 |
79
+ | 0.0875 | 11.0 | 6061 | 0.0385 | 0.9860 |
80
+ | 0.0992 | 12.0 | 6612 | 0.0376 | 0.9870 |
81
+ | 0.065 | 13.0 | 7163 | 0.0392 | 0.9864 |
82
+ | 0.0775 | 14.0 | 7714 | 0.0344 | 0.9890 |
83
+ | 0.0544 | 15.0 | 8265 | 0.0362 | 0.9888 |
84
+ | 0.0584 | 16.0 | 8816 | 0.0422 | 0.9872 |
85
+ | 0.0722 | 17.0 | 9367 | 0.0314 | 0.9900 |
86
+ | 0.0765 | 18.0 | 9918 | 0.0313 | 0.9908 |
87
+ | 0.0696 | 19.0 | 10469 | 0.0297 | 0.9912 |
88
+ | 0.0596 | 20.0 | 11020 | 0.0285 | 0.9910 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.1
94
+ - Pytorch 1.13.1+cu116
95
+ - Datasets 2.10.1
96
+ - Tokenizers 0.13.2