distilhubert-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: 0.5201
- Accuracy: 0.87
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: 6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.08 | 0.99 | 56 | 1.9899 | 0.34 |
| 1.5207 | 2.0 | 113 | 1.4384 | 0.63 |
| 1.141 | 2.99 | 169 | 1.0620 | 0.76 |
| 0.9619 | 4.0 | 226 | 0.9648 | 0.74 |
| 0.6937 | 4.99 | 282 | 0.8175 | 0.76 |
| 0.4903 | 6.0 | 339 | 0.7837 | 0.76 |
| 0.5162 | 6.99 | 395 | 0.6165 | 0.82 |
| 0.4026 | 8.0 | 452 | 0.5812 | 0.86 |
| 0.2924 | 8.99 | 508 | 0.5499 | 0.85 |
| 0.2344 | 10.0 | 565 | 0.5076 | 0.86 |
| 0.147 | 10.99 | 621 | 0.5171 | 0.86 |
| 0.1643 | 11.89 | 672 | 0.5201 | 0.87 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3