Hugging Face's logo

samitizerxu
/
large-algae-vit-rgb

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
samitizerxu commited on
Commit
e800ad0
·
1 Parent(s): abf3d28

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -24
README.md CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # large-algae-vit-rgb
16
 
17
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.9150
20
- - Accuracy: 0.6227
21
 
22
  ## Model description
23
 
@@ -45,32 +45,42 @@ The following hyperparameters were used during training:
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: 20
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.1433 | 1.0 | 120 | 1.0966 | 0.5575 |
55
- | 1.0507 | 2.0 | 240 | 1.0357 | 0.5857 |
56
- | 1.0104 | 3.0 | 360 | 1.0168 | 0.5921 |
57
- | 1.0353 | 4.0 | 480 | 1.0345 | 0.5857 |
58
- | 0.9629 | 5.0 | 600 | 0.9839 | 0.6015 |
59
- | 0.9684 | 6.0 | 720 | 0.9672 | 0.6068 |
60
- | 0.9727 | 7.0 | 840 | 0.9590 | 0.6133 |
61
- | 0.9626 | 8.0 | 960 | 0.9426 | 0.6127 |
62
- | 0.9857 | 9.0 | 1080 | 0.9669 | 0.6080 |
63
- | 0.9321 | 10.0 | 1200 | 0.9397 | 0.6109 |
64
- | 0.9052 | 11.0 | 1320 | 0.9402 | 0.6021 |
65
- | 0.9457 | 12.0 | 1440 | 0.9181 | 0.6215 |
66
- | 0.9101 | 13.0 | 1560 | 0.9350 | 0.6185 |
67
- | 0.8772 | 14.0 | 1680 | 0.9537 | 0.6050 |
68
- | 0.8865 | 15.0 | 1800 | 0.9257 | 0.6127 |
69
- | 0.8454 | 16.0 | 1920 | 0.9160 | 0.6215 |
70
- | 0.8909 | 17.0 | 2040 | 0.9154 | 0.6138 |
71
- | 0.8473 | 18.0 | 2160 | 0.9096 | 0.6185 |
72
- | 0.8979 | 19.0 | 2280 | 0.9150 | 0.6227 |
73
- | 0.8337 | 20.0 | 2400 | 0.9113 | 0.6221 |
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
14
 
15
  # large-algae-vit-rgb
16
 
17
+ This model is a fine-tuned version of [samitizerxu/large-algae-vit-rgb](https://huggingface.co/samitizerxu/large-algae-vit-rgb) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1659
20
+ - Accuracy: 0.5798
21
 
22
  ## Model description
23
 
 
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
+ | 1.2115 | 1.0 | 120 | 0.9078 | 0.6315 |
55
+ | 1.1249 | 2.0 | 240 | 0.9217 | 0.6320 |
56
+ | 1.1385 | 3.0 | 360 | 0.9518 | 0.6180 |
57
+ | 1.1347 | 4.0 | 480 | 1.0201 | 0.6068 |
58
+ | 1.1358 | 5.0 | 600 | 1.0801 | 0.5892 |
59
+ | 1.098 | 6.0 | 720 | 1.0932 | 0.5851 |
60
+ | 1.0882 | 7.0 | 840 | 1.0347 | 0.6033 |
61
+ | 1.0688 | 8.0 | 960 | 1.0403 | 0.6056 |
62
+ | 1.0863 | 9.0 | 1080 | 1.0466 | 0.6009 |
63
+ | 1.1253 | 10.0 | 1200 | 1.2308 | 0.5511 |
64
+ | 1.0393 | 11.0 | 1320 | 1.1434 | 0.5869 |
65
+ | 1.0749 | 12.0 | 1440 | 1.2155 | 0.5622 |
66
+ | 1.0433 | 13.0 | 1560 | 1.2466 | 0.5522 |
67
+ | 1.0141 | 14.0 | 1680 | 1.1880 | 0.5563 |
68
+ | 1.0516 | 15.0 | 1800 | 1.1006 | 0.5992 |
69
+ | 1.0696 | 16.0 | 1920 | 1.0971 | 0.5751 |
70
+ | 0.9867 | 17.0 | 2040 | 1.1689 | 0.5827 |
71
+ | 1.0234 | 18.0 | 2160 | 1.1846 | 0.5751 |
72
+ | 1.0364 | 19.0 | 2280 | 1.1480 | 0.5739 |
73
+ | 1.0314 | 20.0 | 2400 | 1.0977 | 0.5880 |
74
+ | 1.0179 | 21.0 | 2520 | 1.1258 | 0.5851 |
75
+ | 1.0584 | 22.0 | 2640 | 1.1569 | 0.5822 |
76
+ | 1.0222 | 23.0 | 2760 | 1.1672 | 0.5839 |
77
+ | 0.996 | 24.0 | 2880 | 1.1737 | 0.5798 |
78
+ | 1.0343 | 25.0 | 3000 | 1.1588 | 0.5792 |
79
+ | 0.9854 | 26.0 | 3120 | 1.1758 | 0.5763 |
80
+ | 0.9753 | 27.0 | 3240 | 1.1715 | 0.5763 |
81
+ | 0.9881 | 28.0 | 3360 | 1.1403 | 0.5839 |
82
+ | 1.0057 | 29.0 | 3480 | 1.1765 | 0.5781 |
83
+ | 0.9824 | 30.0 | 3600 | 1.1659 | 0.5798 |
84
 
85
 
86
  ### Framework versions