vit-finetuned-chessman4
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1610
- Accuracy: 0.9636
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: 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
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5634 | 1.0 | 28 | 1.3402 | 0.6 |
| 0.9868 | 2.0 | 56 | 0.8429 | 0.7818 |
| 0.5282 | 3.0 | 84 | 0.4851 | 0.9455 |
| 0.2692 | 4.0 | 112 | 0.3099 | 0.9636 |
| 0.1534 | 5.0 | 140 | 0.2243 | 0.9636 |
| 0.1097 | 6.0 | 168 | 0.1897 | 0.9636 |
| 0.0894 | 7.0 | 196 | 0.1795 | 0.9818 |
| 0.0767 | 8.0 | 224 | 0.1681 | 0.9636 |
| 0.0673 | 9.0 | 252 | 0.1620 | 0.9636 |
| 0.06 | 10.0 | 280 | 0.1610 | 0.9636 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0
- Datasets 5.0.0
- Tokenizers 0.22.2