jesusromerodev-vit-model-jesus-romero
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: 0.0621
- Accuracy: 0.9925
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.3846 | 50 | 0.5705 | 0.9474 |
| No log | 0.7692 | 100 | 0.2743 | 0.9850 |
| No log | 1.1538 | 150 | 0.1489 | 0.9925 |
| No log | 1.5385 | 200 | 0.1037 | 0.9925 |
| No log | 1.9231 | 250 | 0.0861 | 0.9925 |
| No log | 2.3077 | 300 | 0.0746 | 0.9925 |
| No log | 2.6923 | 350 | 0.0665 | 0.9925 |
| No log | 3.0769 | 400 | 0.0742 | 0.9925 |
| No log | 3.4615 | 450 | 0.0621 | 0.9925 |
| 0.2096 | 3.8462 | 500 | 0.0624 | 0.9925 |
| 0.2096 | 4.0 | 520 | 0.0621 | 0.9925 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1