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: 0.8537
- Accuracy: 0.8333
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.05
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 1.9237 | 1.0 | 113 | 0.35 | 1.8671 |
| 1.3336 | 2.0 | 226 | 0.52 | 1.4288 |
| 1.1911 | 3.0 | 339 | 0.66 | 1.1495 |
| 0.9446 | 4.0 | 452 | 0.73 | 1.0394 |
| 0.5694 | 5.0 | 565 | 0.72 | 0.8961 |
| 0.4615 | 6.0 | 678 | 0.73 | 0.8940 |
| 0.3261 | 7.0 | 791 | 0.76 | 0.8762 |
| 0.1938 | 8.0 | 904 | 0.77 | 0.8958 |
| 0.243 | 9.0 | 1017 | 0.75 | 0.9046 |
| 0.1144 | 10.0 | 1130 | 0.77 | 0.8998 |
Framework versions
- Transformers 4.57.0.dev0
- Pytorch 2.9.0.dev20250716+cu129
- Datasets 4.0.0
- Tokenizers 0.22.0