salon_image_classifier_v1_convnext
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: 0.0299
- Accuracy: 0.9898
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1269 | 1.0 | 207 | 0.0501 | 0.9834 |
| 0.0572 | 2.0 | 415 | 0.0374 | 0.9871 |
| 0.0806 | 3.0 | 623 | 0.0336 | 0.9875 |
| 0.0589 | 4.0 | 831 | 0.0338 | 0.9885 |
| 0.0326 | 4.98 | 1035 | 0.0299 | 0.9898 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2