ast-finetuned-gtzan
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4088
- Accuracy: 0.885
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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6612 | 1.0 | 100 | 0.6092 | 0.805 |
| 0.3836 | 2.0 | 200 | 0.6416 | 0.8 |
| 0.1854 | 3.0 | 300 | 0.4391 | 0.865 |
| 0.0247 | 4.0 | 400 | 0.7096 | 0.82 |
| 0.0255 | 5.0 | 500 | 0.4970 | 0.875 |
| 0.0006 | 6.0 | 600 | 0.4860 | 0.855 |
| 0.0006 | 7.0 | 700 | 0.4456 | 0.885 |
| 0.0002 | 8.0 | 800 | 0.4370 | 0.89 |
| 0.0314 | 9.0 | 900 | 0.4168 | 0.885 |
| 0.0046 | 10.0 | 1000 | 0.4097 | 0.885 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.23.1