tsec_vit_model
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: 0.2717
- Accuracy: 0.8866
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
- 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 |
|---|---|---|---|---|
| 0.4387 | 1.0 | 280 | 0.4179 | 0.8151 |
| 0.4239 | 2.0 | 560 | 0.3611 | 0.8399 |
| 0.3148 | 3.0 | 840 | 0.3156 | 0.8600 |
| 0.2988 | 4.0 | 1120 | 0.3002 | 0.8729 |
| 0.2498 | 5.0 | 1400 | 0.3087 | 0.8694 |
| 0.3028 | 6.0 | 1680 | 0.2966 | 0.8716 |
| 0.2179 | 7.0 | 1960 | 0.2742 | 0.8808 |
| 0.2274 | 8.0 | 2240 | 0.2861 | 0.8814 |
| 0.2195 | 9.0 | 2520 | 0.2626 | 0.8895 |
| 0.1886 | 10.0 | 2800 | 0.2717 | 0.8866 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1