ast-finetuned-audioset-10-10-0.4593-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: 0.4138
- Accuracy: 0.91
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6863 | 1.0 | 113 | 0.4780 | 0.85 |
| 0.2975 | 2.0 | 226 | 0.7934 | 0.79 |
| 0.1764 | 3.0 | 339 | 0.7400 | 0.8 |
| 0.0218 | 4.0 | 452 | 0.4352 | 0.87 |
| 0.0011 | 5.0 | 565 | 0.5566 | 0.84 |
| 0.0439 | 6.0 | 678 | 0.5811 | 0.86 |
| 0.0294 | 7.0 | 791 | 0.4332 | 0.89 |
| 0.0002 | 8.0 | 904 | 0.4192 | 0.91 |
| 0.0002 | 9.0 | 1017 | 0.4150 | 0.91 |
| 0.0002 | 10.0 | 1130 | 0.4138 | 0.91 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.12.1+cu130
- Datasets 3.6.0
- Tokenizers 0.22.2