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: 0.6949
- Accuracy: 0.88
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.1595 | 0.99 | 28 | 0.5827 | 0.86 |
| 0.122 | 1.98 | 56 | 0.5915 | 0.86 |
| 0.0598 | 2.97 | 84 | 0.6342 | 0.86 |
| 0.0233 | 4.0 | 113 | 0.6145 | 0.85 |
| 0.0163 | 4.99 | 141 | 0.6766 | 0.86 |
| 0.0125 | 5.98 | 169 | 0.6286 | 0.89 |
| 0.0091 | 6.97 | 197 | 0.7157 | 0.86 |
| 0.0088 | 8.0 | 226 | 0.6633 | 0.89 |
| 0.0074 | 8.99 | 254 | 0.7196 | 0.87 |
| 0.0074 | 9.91 | 280 | 0.6949 | 0.88 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3