wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of facebook/wav2vec2-base on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4857
- Accuracy: 0.9
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: 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: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8804 | 1.0 | 113 | 1.6910 | 0.51 |
| 1.3130 | 2.0 | 226 | 1.3362 | 0.58 |
| 1.0612 | 3.0 | 339 | 0.9780 | 0.72 |
| 0.7034 | 4.0 | 452 | 0.8776 | 0.8 |
| 0.5422 | 5.0 | 565 | 0.8788 | 0.69 |
| 0.6099 | 6.0 | 678 | 0.7172 | 0.81 |
| 0.2883 | 7.0 | 791 | 0.6293 | 0.84 |
| 0.2441 | 8.0 | 904 | 0.5204 | 0.87 |
| 0.3616 | 9.0 | 1017 | 0.5045 | 0.88 |
| 0.0690 | 10.0 | 1130 | 0.4857 | 0.9 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.11.0+cu130
- Datasets 3.6.0
- Tokenizers 0.23.2