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: 0.5864
- Accuracy: 0.85
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 |
|---|---|---|---|---|
| 1.8272 | 1.0 | 113 | 1.8788 | 0.44 |
| 1.2356 | 2.0 | 226 | 1.4153 | 0.62 |
| 1.1365 | 3.0 | 339 | 1.1103 | 0.68 |
| 0.7226 | 4.0 | 452 | 0.9236 | 0.75 |
| 0.5402 | 5.0 | 565 | 0.8264 | 0.76 |
| 0.9363 | 6.0 | 678 | 0.7615 | 0.78 |
| 0.3935 | 7.0 | 791 | 0.7546 | 0.8 |
| 0.2594 | 8.0 | 904 | 0.5665 | 0.87 |
| 0.2275 | 9.0 | 1017 | 0.6310 | 0.84 |
| 0.0812 | 10.0 | 1130 | 0.5864 | 0.85 |
Framework versions
- Transformers 5.15.0.dev0
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2