vit-base-patch16-224-30-vit
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: 0.3414
- Accuracy: 0.95
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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.5714 | 1 | 1.5740 | 0.35 |
| No log | 1.7143 | 3 | 1.3520 | 0.3 |
| No log | 2.8571 | 5 | 0.6814 | 0.85 |
| No log | 4.0 | 7 | 0.4114 | 0.95 |
| No log | 4.5714 | 8 | 0.3727 | 0.95 |
| 0.8372 | 5.7143 | 10 | 0.3414 | 0.95 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1