AVIARY
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8657
- Accuracy: 0.6875
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 45 | 1.9502 | 0.275 |
| 2.0454 | 2.0 | 90 | 1.5317 | 0.45 |
| 1.2292 | 3.0 | 135 | 1.1297 | 0.575 |
| 0.4581 | 4.0 | 180 | 0.9767 | 0.6625 |
| 0.1161 | 5.0 | 225 | 0.9035 | 0.6875 |
| 0.0268 | 6.0 | 270 | 0.9070 | 0.6875 |
| 0.0104 | 7.0 | 315 | 0.8726 | 0.6875 |
| 0.0074 | 8.0 | 360 | 0.8712 | 0.675 |
| 0.0063 | 9.0 | 405 | 0.8674 | 0.6875 |
| 0.0057 | 10.0 | 450 | 0.8657 | 0.6875 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2