Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
5
ongkn commited on
Commit
d7bdffb
•
1 Parent(s): 3db2a3e

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -12
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5072
36
  - Accuracy: 0.8188
37
 
38
  ## Model description
@@ -58,23 +58,25 @@ The following hyperparameters were used during training:
58
  - seed: 69
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - lr_scheduler_warmup_ratio: 0.1
62
  - num_epochs: 15
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.4952 | 1.16 | 150 | 0.5743 | 0.7009 |
69
- | 0.4475 | 2.33 | 300 | 0.4772 | 0.7729 |
70
- | 0.4287 | 3.49 | 450 | 0.4688 | 0.7642 |
71
- | 0.2978 | 4.65 | 600 | 0.5202 | 0.7707 |
72
- | 0.3176 | 5.81 | 750 | 0.4475 | 0.7926 |
73
- | 0.2602 | 6.98 | 900 | 0.4760 | 0.7882 |
74
- | 0.2526 | 8.14 | 1050 | 0.4766 | 0.8188 |
75
- | 0.1601 | 9.3 | 1200 | 0.4925 | 0.8122 |
76
- | 0.1925 | 10.47 | 1350 | 0.5308 | 0.8079 |
77
- | 0.1343 | 11.63 | 1500 | 0.5072 | 0.8188 |
 
 
78
 
79
 
80
  ### Framework versions
 
32
 
33
  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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5289
36
  - Accuracy: 0.8188
37
 
38
  ## Model description
 
58
  - seed: 69
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.05
62
  - num_epochs: 15
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.5055 | 1.16 | 150 | 0.5578 | 0.6943 |
69
+ | 0.4352 | 2.33 | 300 | 0.4578 | 0.7817 |
70
+ | 0.4009 | 3.49 | 450 | 0.4632 | 0.7795 |
71
+ | 0.295 | 4.65 | 600 | 0.5191 | 0.7729 |
72
+ | 0.297 | 5.81 | 750 | 0.4560 | 0.7926 |
73
+ | 0.2507 | 6.98 | 900 | 0.4803 | 0.7969 |
74
+ | 0.2317 | 8.14 | 1050 | 0.4836 | 0.7969 |
75
+ | 0.1745 | 9.3 | 1200 | 0.5272 | 0.7860 |
76
+ | 0.1714 | 10.47 | 1350 | 0.5344 | 0.8035 |
77
+ | 0.1437 | 11.63 | 1500 | 0.5477 | 0.7969 |
78
+ | 0.1356 | 12.79 | 1650 | 0.5300 | 0.7904 |
79
+ | 0.1148 | 13.95 | 1800 | 0.5289 | 0.8188 |
80
 
81
 
82
  ### Framework versions