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: 0.5498
- Accuracy: 0.82
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
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8993 | 1.0 | 113 | 1.8141 | 0.55 |
| 1.1604 | 2.0 | 226 | 1.2168 | 0.71 |
| 1.0317 | 3.0 | 339 | 1.0417 | 0.72 |
| 0.6570 | 4.0 | 452 | 0.7942 | 0.77 |
| 0.5415 | 5.0 | 565 | 0.6706 | 0.81 |
| 0.4332 | 6.0 | 678 | 0.5696 | 0.82 |
| 0.2953 | 7.0 | 791 | 0.5117 | 0.83 |
| 0.1570 | 8.0 | 904 | 0.5903 | 0.82 |
| 0.2064 | 9.0 | 1017 | 0.5343 | 0.82 |
| 0.1173 | 10.0 | 1130 | 0.5498 | 0.82 |
Framework versions
- Transformers 5.22.1
- Pytorch 2.14.1+cu130
- Datasets 4.8.5
- Tokenizers 0.23.3