ViT_Flower102
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0587
- Accuracy: 0.9853
- Precision: 0.9853
- Recall: 0.9853
- F1: 0.9853
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
1.3962 | 0.22 | 100 | 1.7861 | 0.7373 | 0.7373 | 0.7373 | 0.7373 |
0.5196 | 0.45 | 200 | 0.7527 | 0.8951 | 0.8951 | 0.8951 | 0.8951 |
0.355 | 0.67 | 300 | 0.3937 | 0.9451 | 0.9451 | 0.9451 | 0.9451 |
0.1966 | 0.89 | 400 | 0.3312 | 0.9422 | 0.9422 | 0.9422 | 0.9422 |
0.1262 | 1.11 | 500 | 0.2145 | 0.9608 | 0.9608 | 0.9608 | 0.9608 |
0.1512 | 1.34 | 600 | 0.1652 | 0.9706 | 0.9706 | 0.9706 | 0.9706 |
0.1414 | 1.56 | 700 | 0.2562 | 0.9471 | 0.9471 | 0.9471 | 0.9471 |
0.1235 | 1.78 | 800 | 0.1742 | 0.9657 | 0.9657 | 0.9657 | 0.9657 |
0.0428 | 2.0 | 900 | 0.1809 | 0.9578 | 0.9578 | 0.9578 | 0.9578 |
0.0202 | 2.23 | 1000 | 0.1518 | 0.9637 | 0.9637 | 0.9637 | 0.9637 |
0.0451 | 2.45 | 1100 | 0.1214 | 0.9725 | 0.9725 | 0.9725 | 0.9725 |
0.0208 | 2.67 | 1200 | 0.1274 | 0.9725 | 0.9725 | 0.9725 | 0.9725 |
0.0673 | 2.9 | 1300 | 0.1904 | 0.9627 | 0.9627 | 0.9627 | 0.9627 |
0.0347 | 3.12 | 1400 | 0.1101 | 0.9765 | 0.9765 | 0.9765 | 0.9765 |
0.0035 | 3.34 | 1500 | 0.1274 | 0.9765 | 0.9765 | 0.9765 | 0.9765 |
0.0629 | 3.56 | 1600 | 0.0743 | 0.9833 | 0.9833 | 0.9833 | 0.9833 |
0.0368 | 3.79 | 1700 | 0.0801 | 0.9804 | 0.9804 | 0.9804 | 0.9804 |
0.0021 | 4.01 | 1800 | 0.0947 | 0.9794 | 0.9794 | 0.9794 | 0.9794 |
0.0037 | 4.23 | 1900 | 0.0990 | 0.9775 | 0.9775 | 0.9775 | 0.9775 |
0.0015 | 4.45 | 2000 | 0.0782 | 0.9824 | 0.9824 | 0.9824 | 0.9824 |
0.002 | 4.68 | 2100 | 0.0924 | 0.9775 | 0.9775 | 0.9775 | 0.9775 |
0.0013 | 4.9 | 2200 | 0.0648 | 0.9892 | 0.9892 | 0.9892 | 0.9892 |
0.0013 | 5.12 | 2300 | 0.0705 | 0.9843 | 0.9843 | 0.9843 | 0.9843 |
0.0012 | 5.35 | 2400 | 0.0667 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
0.0011 | 5.57 | 2500 | 0.0654 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.001 | 5.79 | 2600 | 0.0809 | 0.9804 | 0.9804 | 0.9804 | 0.9804 |
0.001 | 6.01 | 2700 | 0.0603 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
0.0009 | 6.24 | 2800 | 0.0587 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
0.0009 | 6.46 | 2900 | 0.0613 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0354 | 6.68 | 3000 | 0.0625 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0009 | 6.9 | 3100 | 0.0640 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0009 | 7.13 | 3200 | 0.0637 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0008 | 7.35 | 3300 | 0.0640 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0007 | 7.57 | 3400 | 0.0638 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0008 | 7.8 | 3500 | 0.0632 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 8.02 | 3600 | 0.0628 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 8.24 | 3700 | 0.0628 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0007 | 8.46 | 3800 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 8.69 | 3900 | 0.0628 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0007 | 8.91 | 4000 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 9.13 | 4100 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0005 | 9.35 | 4200 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 9.58 | 4300 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
0.0006 | 9.8 | 4400 | 0.0629 | 0.9863 | 0.9863 | 0.9863 | 0.9863 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Inference API (serverless) is not available, repository is disabled.
Model tree for KietZer0/ViT_flower102
Base model
google/vit-base-patch16-224-in21k
Finetuned
this model