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: 0.5249
- Accuracy: 0.88
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.3372 | 1.0 | 57 | 2.1037 | 0.37 |
| 3.5091 | 2.0 | 114 | 1.7248 | 0.55 |
| 2.9802 | 3.0 | 171 | 1.4436 | 0.57 |
| 2.3109 | 4.0 | 228 | 1.3017 | 0.66 |
| 1.8822 | 5.0 | 285 | 1.1528 | 0.68 |
| 1.9275 | 6.0 | 342 | 0.9594 | 0.72 |
| 1.6896 | 7.0 | 399 | 0.7778 | 0.85 |
| 1.2257 | 8.0 | 456 | 0.7596 | 0.83 |
| 0.9672 | 9.0 | 513 | 0.8690 | 0.79 |
| 0.8144 | 10.0 | 570 | 0.5945 | 0.88 |
| 0.7628 | 11.0 | 627 | 0.7198 | 0.81 |
| 0.5727 | 12.0 | 684 | 0.5887 | 0.87 |
| 0.4335 | 13.0 | 741 | 0.5249 | 0.88 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 2.18.0
- Tokenizers 0.22.1