distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5561
- 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: 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9198 | 1.0 | 113 | 1.8298 | 0.49 |
| 1.2106 | 2.0 | 226 | 1.1905 | 0.68 |
| 0.9757 | 3.0 | 339 | 0.9692 | 0.75 |
| 0.7117 | 4.0 | 452 | 0.8159 | 0.73 |
| 0.5184 | 5.0 | 565 | 0.6510 | 0.79 |
| 0.3797 | 6.0 | 678 | 0.5643 | 0.85 |
| 0.3364 | 7.0 | 791 | 0.5896 | 0.84 |
| 0.1232 | 8.0 | 904 | 0.5961 | 0.85 |
| 0.2065 | 9.0 | 1017 | 0.5676 | 0.85 |
| 0.0881 | 10.0 | 1130 | 0.5561 | 0.84 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0