Hugging Face's logo

sudo-s
/
exper3_mesum5

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sudo-s commited on
Commit
5a797b4
•
1 Parent(s): 400ca1c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: exper3_mesum5
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # exper3_mesum5
16
+
17
+ 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 None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6397
20
+ - Accuracy: 0.8385
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 8
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 3.895 | 0.23 | 100 | 3.8276 | 0.1935 |
53
+ | 3.1174 | 0.47 | 200 | 3.1217 | 0.3107 |
54
+ | 2.6 | 0.7 | 300 | 2.5399 | 0.4207 |
55
+ | 2.256 | 0.93 | 400 | 2.1767 | 0.5160 |
56
+ | 1.5441 | 1.16 | 500 | 1.8086 | 0.5852 |
57
+ | 1.3834 | 1.4 | 600 | 1.5565 | 0.6325 |
58
+ | 1.1995 | 1.63 | 700 | 1.3339 | 0.6763 |
59
+ | 1.0845 | 1.86 | 800 | 1.3299 | 0.6533 |
60
+ | 0.6472 | 2.09 | 900 | 1.0679 | 0.7219 |
61
+ | 0.5948 | 2.33 | 1000 | 1.0286 | 0.7124 |
62
+ | 0.5565 | 2.56 | 1100 | 0.9595 | 0.7284 |
63
+ | 0.4879 | 2.79 | 1200 | 0.8915 | 0.7420 |
64
+ | 0.2816 | 3.02 | 1300 | 0.8159 | 0.7763 |
65
+ | 0.2412 | 3.26 | 1400 | 0.7766 | 0.7911 |
66
+ | 0.2015 | 3.49 | 1500 | 0.7850 | 0.7828 |
67
+ | 0.274 | 3.72 | 1600 | 0.7361 | 0.7935 |
68
+ | 0.1244 | 3.95 | 1700 | 0.7299 | 0.7911 |
69
+ | 0.0794 | 4.19 | 1800 | 0.7441 | 0.7846 |
70
+ | 0.0915 | 4.42 | 1900 | 0.7614 | 0.7941 |
71
+ | 0.0817 | 4.65 | 2000 | 0.7310 | 0.8012 |
72
+ | 0.0561 | 4.88 | 2100 | 0.7222 | 0.8065 |
73
+ | 0.0165 | 5.12 | 2200 | 0.7515 | 0.8059 |
74
+ | 0.0168 | 5.35 | 2300 | 0.6687 | 0.8213 |
75
+ | 0.0212 | 5.58 | 2400 | 0.6671 | 0.8249 |
76
+ | 0.0389 | 5.81 | 2500 | 0.6893 | 0.8278 |
77
+ | 0.0087 | 6.05 | 2600 | 0.6839 | 0.8260 |
78
+ | 0.0087 | 6.28 | 2700 | 0.6412 | 0.8320 |
79
+ | 0.0077 | 6.51 | 2800 | 0.6366 | 0.8367 |
80
+ | 0.0065 | 6.74 | 2900 | 0.6697 | 0.8272 |
81
+ | 0.0061 | 6.98 | 3000 | 0.6510 | 0.8349 |
82
+ | 0.0185 | 7.21 | 3100 | 0.6452 | 0.8367 |
83
+ | 0.0059 | 7.44 | 3200 | 0.6426 | 0.8379 |
84
+ | 0.0062 | 7.67 | 3300 | 0.6398 | 0.8379 |
85
+ | 0.0315 | 7.91 | 3400 | 0.6397 | 0.8385 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.20.1
91
+ - Pytorch 1.12.0+cu113
92
+ - Datasets 2.3.2
93
+ - Tokenizers 0.12.1