swin-tiny-patch4-window7-224-finetuned-mobile-eye-tracking-dataset-v2
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0536
- Accuracy: 0.9880
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2775 | 1.0 | 37 | 0.3024 | 0.8876 |
| 0.471 | 2.0 | 74 | 0.1297 | 0.9598 |
| 0.3266 | 3.0 | 111 | 0.0955 | 0.9679 |
| 0.2738 | 4.0 | 148 | 0.0536 | 0.9880 |
| 0.2532 | 5.0 | 185 | 0.0857 | 0.9578 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2