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: 1.4712
- Accuracy: 0.84
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 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: 9
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8396 | 1.0 | 113 | 1.6878 | 0.78 |
| 0.1548 | 2.0 | 226 | 2.0664 | 0.73 |
| 0.0015 | 3.0 | 339 | 1.6951 | 0.79 |
| 0.0006 | 4.0 | 452 | 1.4365 | 0.82 |
| 0.0007 | 5.0 | 565 | 1.5483 | 0.82 |
| 0.0001 | 6.0 | 678 | 1.3558 | 0.84 |
| 0.0002 | 7.0 | 791 | 1.4830 | 0.84 |
| 0.0002 | 8.0 | 904 | 1.4790 | 0.83 |
| 0.0002 | 9.0 | 1017 | 1.4712 | 0.84 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1