swin-tiny-patch4-window7-224-finetuned-car-models-classification-outer-layer-v001
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: 1.4877
- Accuracy: 0.5
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 3.2296 | 0.0 |
| No log | 2.0 | 4 | 2.7874 | 0.1667 |
| No log | 3.0 | 6 | 2.4640 | 0.3333 |
| No log | 4.0 | 8 | 2.2000 | 0.3333 |
| 1.5523 | 5.0 | 10 | 1.9602 | 0.5 |
| 1.5523 | 6.0 | 12 | 1.7736 | 0.5 |
| 1.5523 | 7.0 | 14 | 1.6539 | 0.5 |
| 1.5523 | 8.0 | 16 | 1.5736 | 0.5 |
| 1.5523 | 9.0 | 18 | 1.5169 | 0.5 |
| 0.6818 | 10.0 | 20 | 1.4877 | 0.5 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4