vit-base-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0292
- Accuracy: 0.9926
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
precision recall f1-score support
0 1.00 1.00 1.00 11315
1 0.92 0.94 0.93 204
2 0.95 0.97 0.96 714
3 0.87 0.98 0.92 171
macro avg 0.93 0.97 0.95 12404 weighted avg 0.99 0.99 0.99 12404 accuracy 0.99 12404
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0206 | 1.72 | 1000 | 0.0422 | 0.9854 |
| 0.0008 | 3.44 | 2000 | 0.0316 | 0.9918 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 0