gender_mozilla_mel_spec_Vit_swin-tiny-patch4-window7-224_1
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: 0.1463
- Accuracy: 0.9533
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: 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 |
|---|---|---|---|---|
| 0.6887 | 1.0 | 11 | 0.5200 | 0.8367 |
| 0.3893 | 2.0 | 22 | 0.2368 | 0.92 |
| 0.2526 | 3.0 | 33 | 0.1906 | 0.94 |
| 0.1812 | 4.0 | 44 | 0.1990 | 0.93 |
| 0.158 | 5.0 | 55 | 0.2096 | 0.92 |
| 0.1333 | 6.0 | 66 | 0.1821 | 0.9333 |
| 0.1249 | 7.0 | 77 | 0.1546 | 0.95 |
| 0.0678 | 8.0 | 88 | 0.1535 | 0.9567 |
| 0.0524 | 9.0 | 99 | 0.1599 | 0.9433 |
| 0.0359 | 10.0 | 110 | 0.1463 | 0.9533 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0