swin-tiny-patch4-window7-224-finetuned-arty
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: 0.0002
- Accuracy: 1.0
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 |
|---|---|---|---|---|
| 0.2386 | 0.43 | 50 | 0.0643 | 0.9967 |
| 0.0359 | 0.87 | 100 | 0.0035 | 0.9996 |
| 0.058 | 1.3 | 150 | 0.0015 | 0.9996 |
| 0.0297 | 1.74 | 200 | 0.0003 | 1.0 |
| 0.0175 | 2.17 | 250 | 0.0002 | 1.0 |
| 0.0166 | 2.6 | 300 | 0.0002 | 1.0 |
| 0.0318 | 3.04 | 350 | 0.0001 | 1.0 |
| 0.0062 | 3.47 | 400 | 0.0002 | 1.0 |
| 0.0101 | 3.9 | 450 | 0.0002 | 1.0 |
| 0.0066 | 4.34 | 500 | 0.0002 | 1.0 |
| 0.005 | 4.77 | 550 | 0.0002 | 1.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3