wavlm-base-plus-finetuned-gtzan
This model is a fine-tuned version of microsoft/wavlm-base-plus on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5247
- Accuracy: 0.8794
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8816 | 1.0 | 224 | 1.7730 | 0.5025 |
| 1.3422 | 2.0 | 448 | 1.4975 | 0.5930 |
| 1.0660 | 3.0 | 672 | 1.2443 | 0.6432 |
| 0.7029 | 4.0 | 896 | 0.8479 | 0.7487 |
| 0.5902 | 5.0 | 1120 | 0.6849 | 0.8291 |
| 0.4760 | 6.0 | 1344 | 0.5970 | 0.8492 |
| 0.3054 | 7.0 | 1568 | 0.5085 | 0.8744 |
| 0.2311 | 8.0 | 1792 | 0.5106 | 0.8744 |
| 0.3217 | 9.0 | 2016 | 0.5247 | 0.8794 |
| 0.3330 | 10.0 | 2240 | 0.5279 | 0.8643 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 2.21.0
- Tokenizers 0.22.2