swin-tiny-patch4-window7-224-finetuned-cloudy
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: 0.0694
- 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 0.2993 | 0.8182 |
| No log | 2.0 | 3 | 0.1963 | 0.9091 |
| No log | 3.0 | 5 | 0.1130 | 0.9091 |
| No log | 4.0 | 6 | 0.0694 | 1.0 |
| No log | 5.0 | 7 | 0.0569 | 1.0 |
| No log | 6.0 | 9 | 0.0902 | 0.9091 |
| 0.08 | 7.0 | 11 | 0.0973 | 0.9091 |
| 0.08 | 8.0 | 12 | 0.0746 | 1.0 |
| 0.08 | 9.0 | 13 | 0.0527 | 1.0 |
| 0.08 | 10.0 | 15 | 0.0392 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0