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: 0.3612
- Accuracy: 0.9179
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7792 | 1.0 | 125 | 1.7555 | 0.5125 |
| 1.694 | 2.0 | 250 | 1.4309 | 0.5275 |
| 1.2489 | 3.0 | 375 | 1.4102 | 0.4915 |
| 1.143 | 4.0 | 500 | 0.8560 | 0.7508 |
| 1.0382 | 5.0 | 625 | 0.7584 | 0.7768 |
| 0.4631 | 6.0 | 750 | 0.6003 | 0.7988 |
| 0.8061 | 7.0 | 875 | 0.4438 | 0.8709 |
| 0.6985 | 8.0 | 1000 | 0.4876 | 0.8679 |
| 0.4943 | 9.0 | 1125 | 0.5800 | 0.8268 |
| 0.4353 | 10.0 | 1250 | 0.3612 | 0.9179 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1