Hugging Face's logo

sudo-s
/
exper_batch_16_e8

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sudo-s commited on
Commit
e7ba6d9
•
1 Parent(s): c68e1c8

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_16_e8
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_16_e8
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: 0.3952
20
+ - Accuracy: 0.9129
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: Apex, opt level O1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 3.8115 | 0.16 | 100 | 3.7948 | 0.1862 |
53
+ | 3.1194 | 0.31 | 200 | 3.0120 | 0.3281 |
54
+ | 2.3703 | 0.47 | 300 | 2.4791 | 0.4426 |
55
+ | 2.07 | 0.63 | 400 | 2.1720 | 0.5 |
56
+ | 1.6847 | 0.78 | 500 | 1.7291 | 0.5956 |
57
+ | 1.3821 | 0.94 | 600 | 1.4777 | 0.6299 |
58
+ | 0.9498 | 1.1 | 700 | 1.2935 | 0.6681 |
59
+ | 0.8741 | 1.25 | 800 | 1.1353 | 0.7051 |
60
+ | 0.8875 | 1.41 | 900 | 0.9951 | 0.7448 |
61
+ | 0.7233 | 1.56 | 1000 | 0.9265 | 0.7487 |
62
+ | 0.6696 | 1.72 | 1100 | 0.8660 | 0.7625 |
63
+ | 0.7364 | 1.88 | 1200 | 0.8710 | 0.7579 |
64
+ | 0.3933 | 2.03 | 1300 | 0.7162 | 0.8038 |
65
+ | 0.3443 | 2.19 | 1400 | 0.6305 | 0.8300 |
66
+ | 0.3376 | 2.35 | 1500 | 0.6273 | 0.8315 |
67
+ | 0.3071 | 2.5 | 1600 | 0.5988 | 0.8319 |
68
+ | 0.2863 | 2.66 | 1700 | 0.6731 | 0.8153 |
69
+ | 0.3017 | 2.82 | 1800 | 0.6042 | 0.8315 |
70
+ | 0.2382 | 2.97 | 1900 | 0.5118 | 0.8712 |
71
+ | 0.1578 | 3.13 | 2000 | 0.4917 | 0.8736 |
72
+ | 0.1794 | 3.29 | 2100 | 0.5302 | 0.8631 |
73
+ | 0.1093 | 3.44 | 2200 | 0.5035 | 0.8635 |
74
+ | 0.1076 | 3.6 | 2300 | 0.5186 | 0.8674 |
75
+ | 0.1219 | 3.76 | 2400 | 0.4723 | 0.8801 |
76
+ | 0.1017 | 3.91 | 2500 | 0.5132 | 0.8712 |
77
+ | 0.0351 | 4.07 | 2600 | 0.4709 | 0.8728 |
78
+ | 0.0295 | 4.23 | 2700 | 0.4674 | 0.8824 |
79
+ | 0.0416 | 4.38 | 2800 | 0.4836 | 0.8805 |
80
+ | 0.0386 | 4.54 | 2900 | 0.4663 | 0.8828 |
81
+ | 0.0392 | 4.69 | 3000 | 0.4003 | 0.8990 |
82
+ | 0.0383 | 4.85 | 3100 | 0.4187 | 0.8948 |
83
+ | 0.0624 | 5.01 | 3200 | 0.4460 | 0.8874 |
84
+ | 0.0188 | 5.16 | 3300 | 0.4169 | 0.9029 |
85
+ | 0.0174 | 5.32 | 3400 | 0.4098 | 0.8951 |
86
+ | 0.0257 | 5.48 | 3500 | 0.4289 | 0.8951 |
87
+ | 0.0123 | 5.63 | 3600 | 0.4295 | 0.9029 |
88
+ | 0.0052 | 5.79 | 3700 | 0.4395 | 0.8994 |
89
+ | 0.0081 | 5.95 | 3800 | 0.4217 | 0.9082 |
90
+ | 0.0032 | 6.1 | 3900 | 0.4216 | 0.9056 |
91
+ | 0.0033 | 6.26 | 4000 | 0.4113 | 0.9082 |
92
+ | 0.0024 | 6.42 | 4100 | 0.4060 | 0.9102 |
93
+ | 0.0022 | 6.57 | 4200 | 0.4067 | 0.9090 |
94
+ | 0.0031 | 6.73 | 4300 | 0.4005 | 0.9113 |
95
+ | 0.0021 | 6.89 | 4400 | 0.4008 | 0.9129 |
96
+ | 0.0021 | 7.04 | 4500 | 0.3967 | 0.9113 |
97
+ | 0.0043 | 7.2 | 4600 | 0.3960 | 0.9121 |
98
+ | 0.0022 | 7.36 | 4700 | 0.3962 | 0.9125 |
99
+ | 0.0021 | 7.51 | 4800 | 0.3992 | 0.9121 |
100
+ | 0.002 | 7.67 | 4900 | 0.3951 | 0.9129 |
101
+ | 0.0023 | 7.82 | 5000 | 0.3952 | 0.9125 |
102
+ | 0.0021 | 7.98 | 5100 | 0.3952 | 0.9129 |
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