distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1988
- Accuracy: 0.9404
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 1.7008 | 1.0 | 76 | 1.6010 | 0.5497 |
| 0.8918 | 2.0 | 152 | 0.9346 | 0.6954 |
| 0.6802 | 3.0 | 228 | 0.6734 | 0.7815 |
| 0.3291 | 4.0 | 304 | 0.4803 | 0.8543 |
| 0.2609 | 5.0 | 380 | 0.3473 | 0.8808 |
| 0.1061 | 6.0 | 456 | 0.2439 | 0.9272 |
| 0.1252 | 7.0 | 532 | 0.2127 | 0.9536 |
| 0.084 | 8.0 | 608 | 0.1980 | 0.9404 |
| 0.0374 | 9.0 | 684 | 0.2005 | 0.9404 |
| 0.0431 | 10.0 | 760 | 0.1988 | 0.9404 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for politeles/distilhubert-finetuned-gtzan
Base model
ntu-spml/distilhubert