swinv2-tiny-patch4-window8-256-finetuned-validshop-car-1
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2577
- Accuracy: 0.8915
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: 2
- total_train_batch_size: 32
- 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9275 | 1.0 | 37 | 0.2632 | 0.8605 |
| 0.7211 | 2.0 | 74 | 0.2196 | 0.9070 |
| 0.5262 | 3.0 | 111 | 0.2471 | 0.9070 |
| 0.4001 | 4.0 | 148 | 0.2224 | 0.9147 |
| 0.5917 | 5.0 | 185 | 0.1857 | 0.9225 |
| 0.3629 | 5.8493 | 216 | 0.2577 | 0.8915 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.6.0
- Tokenizers 0.21.0