vit-base-patch16-224-in21k-finetuned-SMD-shuffled-transformed
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: 0.0602
- Accuracy: 1.0
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.524 | 1.0 | 40 | 1.5157 | 0.5915 |
| 0.8485 | 2.0 | 80 | 0.7746 | 0.8592 |
| 0.3255 | 3.0 | 120 | 0.3268 | 0.9577 |
| 0.1379 | 4.0 | 160 | 0.1649 | 0.9859 |
| 0.0948 | 5.0 | 200 | 0.1110 | 1.0 |
| 0.0749 | 6.0 | 240 | 0.0897 | 1.0 |
| 0.0654 | 7.0 | 280 | 0.0761 | 1.0 |
| 0.0536 | 8.0 | 320 | 0.0602 | 1.0 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0