vit-base-patch16-224-R1-10
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2451
- Accuracy: 0.7049
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1675 | 0.99 | 38 | 0.9972 | 0.6393 |
| 0.5606 | 1.99 | 76 | 0.7603 | 0.6885 |
| 0.3159 | 2.98 | 114 | 0.8954 | 0.6885 |
| 0.2253 | 4.0 | 153 | 1.0227 | 0.6885 |
| 0.17 | 4.99 | 191 | 1.1025 | 0.7213 |
| 0.1174 | 5.99 | 229 | 1.1453 | 0.7377 |
| 0.1032 | 6.98 | 267 | 1.0995 | 0.6885 |
| 0.1051 | 8.0 | 306 | 1.2167 | 0.7049 |
| 0.0853 | 8.99 | 344 | 1.2042 | 0.7377 |
| 0.0802 | 9.93 | 380 | 1.2451 | 0.7049 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0