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: 0.5480
- 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: 4
- eval_batch_size: 8
- 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: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.8684 | 1.0 | 113 | 1.8820 | 0.51 |
| 2.4047 | 2.0 | 226 | 1.2371 | 0.69 |
| 2.1465 | 3.0 | 339 | 0.9845 | 0.73 |
| 1.4188 | 4.0 | 452 | 0.8159 | 0.8 |
| 0.8208 | 5.0 | 565 | 0.6649 | 0.82 |
| 0.7447 | 6.0 | 678 | 0.6084 | 0.83 |
| 0.6331 | 7.0 | 791 | 0.5582 | 0.83 |
| 0.2478 | 8.0 | 904 | 0.5733 | 0.84 |
| 0.3053 | 9.0 | 1017 | 0.5130 | 0.86 |
| 0.2160 | 10.0 | 1130 | 0.5480 | 0.85 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2