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: 0.5555
- Accuracy: 0.84
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.0326 | 1.0 | 113 | 0.45 | 1.8397 |
| 1.3293 | 2.0 | 226 | 0.64 | 1.2497 |
| 0.9968 | 3.0 | 339 | 0.75 | 0.9469 |
| 0.8413 | 4.0 | 452 | 0.76 | 0.8033 |
| 0.6769 | 5.0 | 565 | 0.8 | 0.6373 |
| 0.3725 | 6.0 | 678 | 0.6338 | 0.8 |
| 0.4498 | 7.0 | 791 | 0.5539 | 0.85 |
| 0.2232 | 8.0 | 904 | 0.5405 | 0.83 |
| 0.2456 | 9.0 | 1017 | 0.5259 | 0.85 |
| 0.1777 | 10.0 | 1130 | 0.5555 | 0.84 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1