Hugging Face's logo

wuru330
/
378A1_results

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Model card Files
xet
 Community
1
wuru330 commited on
Commit
c7a150f
·
1 Parent(s): 33fd6d4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: 378A1_results
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
+ # 378A1_results
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 an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4492
20
+ - Accuracy: 0.9014
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: 5e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.2401 | 1.0 | 37 | 1.0427 | 0.6582 |
55
+ | 0.669 | 2.0 | 74 | 0.5486 | 0.8418 |
56
+ | 0.4662 | 3.0 | 111 | 0.4012 | 0.8690 |
57
+ | 0.3211 | 4.0 | 148 | 0.5338 | 0.7942 |
58
+ | 0.2136 | 5.0 | 185 | 0.3189 | 0.8861 |
59
+ | 0.1626 | 6.0 | 222 | 0.4406 | 0.8435 |
60
+ | 0.1042 | 7.0 | 259 | 0.3812 | 0.8741 |
61
+ | 0.0688 | 8.0 | 296 | 0.3501 | 0.8946 |
62
+ | 0.0425 | 9.0 | 333 | 0.3845 | 0.8912 |
63
+ | 0.0586 | 10.0 | 370 | 0.3640 | 0.8980 |
64
+ | 0.0276 | 11.0 | 407 | 0.3708 | 0.9031 |
65
+ | 0.0342 | 12.0 | 444 | 0.3862 | 0.9082 |
66
+ | 0.0251 | 13.0 | 481 | 0.5206 | 0.8776 |
67
+ | 0.0209 | 14.0 | 518 | 0.4078 | 0.8929 |
68
+ | 0.0173 | 15.0 | 555 | 0.4168 | 0.8895 |
69
+ | 0.0159 | 16.0 | 592 | 0.4108 | 0.8997 |
70
+ | 0.0151 | 17.0 | 629 | 0.4176 | 0.9014 |
71
+ | 0.014 | 18.0 | 666 | 0.4228 | 0.9014 |
72
+ | 0.0131 | 19.0 | 703 | 0.4266 | 0.9014 |
73
+ | 0.0125 | 20.0 | 740 | 0.4301 | 0.9014 |
74
+ | 0.012 | 21.0 | 777 | 0.4339 | 0.9014 |
75
+ | 0.0115 | 22.0 | 814 | 0.4372 | 0.9014 |
76
+ | 0.0111 | 23.0 | 851 | 0.4401 | 0.9014 |
77
+ | 0.0107 | 24.0 | 888 | 0.4424 | 0.9014 |
78
+ | 0.0101 | 25.0 | 925 | 0.4444 | 0.9014 |
79
+ | 0.01 | 26.0 | 962 | 0.4461 | 0.9014 |
80
+ | 0.01 | 27.0 | 999 | 0.4475 | 0.9014 |
81
+ | 0.0099 | 28.0 | 1036 | 0.4485 | 0.9014 |
82
+ | 0.0097 | 29.0 | 1073 | 0.4490 | 0.9014 |
83
+ | 0.0097 | 30.0 | 1110 | 0.4492 | 0.9014 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.30.2
89
+ - Pytorch 2.0.1+cu117
90
+ - Datasets 2.13.1
91
+ - Tokenizers 0.13.3