sebastiansarasti
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: 1.5460
- Accuracy: 0.3786
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 52 | 1.4555 | 0.3301 |
| No log | 2.0 | 104 | 1.4709 | 0.2621 |
| No log | 3.0 | 156 | 1.4634 | 0.3107 |
| No log | 4.0 | 208 | 1.6076 | 0.3301 |
| No log | 5.0 | 260 | 1.4538 | 0.3592 |
| No log | 6.0 | 312 | 1.5070 | 0.3981 |
| No log | 7.0 | 364 | 1.5530 | 0.3689 |
| No log | 8.0 | 416 | 1.4718 | 0.3398 |
| No log | 9.0 | 468 | 1.4676 | 0.3495 |
| 1.4219 | 10.0 | 520 | 1.5460 | 0.3786 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0