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: 0.5167
- Accuracy: 0.89
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2163 | 1.0 | 113 | 2.0720 | 0.34 |
| 1.7237 | 2.0 | 226 | 1.5361 | 0.59 |
| 1.3254 | 3.0 | 339 | 1.2044 | 0.65 |
| 1.0757 | 4.0 | 452 | 1.0578 | 0.66 |
| 1.0683 | 5.0 | 565 | 0.8947 | 0.78 |
| 0.9307 | 6.0 | 678 | 0.7716 | 0.82 |
| 1.0313 | 7.0 | 791 | 0.7210 | 0.82 |
| 0.6988 | 8.0 | 904 | 0.6506 | 0.8 |
| 0.8053 | 9.0 | 1017 | 0.5944 | 0.81 |
| 0.6243 | 10.0 | 1130 | 0.5637 | 0.87 |
| 0.6238 | 11.0 | 1243 | 0.5212 | 0.89 |
| 0.4493 | 12.0 | 1356 | 0.5167 | 0.89 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3