Hugging Face's logo

sudo-s
/
exper_batch_8_e4

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
sudo-s commited on
Commit
f130495
·
1 Parent(s): 3958ca9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: exper_batch_8_e4
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
+ # exper_batch_8_e4
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: 0.3353
20
+ - Accuracy: 0.9183
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: 8
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: 4
46
+ - mixed_precision_training: Apex, opt level O1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 4.2251 | 0.08 | 100 | 4.1508 | 0.1203 |
53
+ | 3.4942 | 0.16 | 200 | 3.5566 | 0.2082 |
54
+ | 3.2871 | 0.23 | 300 | 3.0942 | 0.3092 |
55
+ | 2.7273 | 0.31 | 400 | 2.8338 | 0.3308 |
56
+ | 2.4984 | 0.39 | 500 | 2.4860 | 0.4341 |
57
+ | 2.3423 | 0.47 | 600 | 2.2201 | 0.4796 |
58
+ | 1.8785 | 0.55 | 700 | 2.1890 | 0.4653 |
59
+ | 1.8012 | 0.63 | 800 | 1.9901 | 0.4865 |
60
+ | 1.7236 | 0.7 | 900 | 1.6821 | 0.5736 |
61
+ | 1.4949 | 0.78 | 1000 | 1.5422 | 0.6083 |
62
+ | 1.5573 | 0.86 | 1100 | 1.5436 | 0.6110 |
63
+ | 1.3241 | 0.94 | 1200 | 1.4077 | 0.6207 |
64
+ | 1.0773 | 1.02 | 1300 | 1.1417 | 0.6916 |
65
+ | 0.7935 | 1.1 | 1400 | 1.1194 | 0.6931 |
66
+ | 0.7677 | 1.17 | 1500 | 1.0727 | 0.7167 |
67
+ | 0.9468 | 1.25 | 1600 | 1.0707 | 0.7136 |
68
+ | 0.7563 | 1.33 | 1700 | 0.9427 | 0.7390 |
69
+ | 0.8471 | 1.41 | 1800 | 0.8906 | 0.7571 |
70
+ | 0.9998 | 1.49 | 1900 | 0.8098 | 0.7845 |
71
+ | 0.6039 | 1.57 | 2000 | 0.7244 | 0.8034 |
72
+ | 0.7052 | 1.64 | 2100 | 0.7881 | 0.7953 |
73
+ | 0.6753 | 1.72 | 2200 | 0.7458 | 0.7926 |
74
+ | 0.3758 | 1.8 | 2300 | 0.6987 | 0.8022 |
75
+ | 0.4985 | 1.88 | 2400 | 0.6286 | 0.8265 |
76
+ | 0.4122 | 1.96 | 2500 | 0.5949 | 0.8358 |
77
+ | 0.1286 | 2.04 | 2600 | 0.5691 | 0.8385 |
78
+ | 0.1989 | 2.11 | 2700 | 0.5535 | 0.8389 |
79
+ | 0.3304 | 2.19 | 2800 | 0.5261 | 0.8520 |
80
+ | 0.3415 | 2.27 | 2900 | 0.5504 | 0.8477 |
81
+ | 0.4066 | 2.35 | 3000 | 0.5418 | 0.8497 |
82
+ | 0.1208 | 2.43 | 3100 | 0.5156 | 0.8612 |
83
+ | 0.1668 | 2.51 | 3200 | 0.5655 | 0.8539 |
84
+ | 0.0727 | 2.58 | 3300 | 0.4971 | 0.8658 |
85
+ | 0.0929 | 2.66 | 3400 | 0.4962 | 0.8635 |
86
+ | 0.0678 | 2.74 | 3500 | 0.4903 | 0.8670 |
87
+ | 0.1212 | 2.82 | 3600 | 0.4357 | 0.8867 |
88
+ | 0.1579 | 2.9 | 3700 | 0.4642 | 0.8739 |
89
+ | 0.2625 | 2.98 | 3800 | 0.3994 | 0.8951 |
90
+ | 0.024 | 3.05 | 3900 | 0.3953 | 0.8971 |
91
+ | 0.0696 | 3.13 | 4000 | 0.3883 | 0.9056 |
92
+ | 0.0169 | 3.21 | 4100 | 0.3755 | 0.9086 |
93
+ | 0.023 | 3.29 | 4200 | 0.3685 | 0.9109 |
94
+ | 0.0337 | 3.37 | 4300 | 0.3623 | 0.9109 |
95
+ | 0.0123 | 3.45 | 4400 | 0.3647 | 0.9067 |
96
+ | 0.0159 | 3.52 | 4500 | 0.3630 | 0.9082 |
97
+ | 0.0154 | 3.6 | 4600 | 0.3522 | 0.9094 |
98
+ | 0.0112 | 3.68 | 4700 | 0.3439 | 0.9163 |
99
+ | 0.0219 | 3.76 | 4800 | 0.3404 | 0.9194 |
100
+ | 0.0183 | 3.84 | 4900 | 0.3371 | 0.9183 |
101
+ | 0.0103 | 3.92 | 5000 | 0.3362 | 0.9183 |
102
+ | 0.0357 | 3.99 | 5100 | 0.3353 | 0.9183 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.19.4
108
+ - Pytorch 1.5.1
109
+ - Datasets 2.3.2
110
+ - Tokenizers 0.12.1