distilhubert-finetuned-finetuned-gtzan
This model is a fine-tuned version of weiren119/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.8658
- 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- 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 | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1441 | 1.0 | 57 | 0.5206 | 0.86 |
| 0.0992 | 2.0 | 114 | 0.6685 | 0.84 |
| 0.0881 | 3.0 | 171 | 0.8925 | 0.76 |
| 0.0792 | 4.0 | 228 | 1.0064 | 0.78 |
| 0.0045 | 5.0 | 285 | 0.8283 | 0.83 |
| 0.0695 | 6.0 | 342 | 0.7731 | 0.86 |
| 0.0303 | 7.0 | 399 | 1.0389 | 0.82 |
| 0.0026 | 8.0 | 456 | 0.9661 | 0.83 |
| 0.0014 | 9.0 | 513 | 0.8917 | 0.87 |
| 0.0012 | 10.0 | 570 | 0.8658 | 0.88 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.0
- Tokenizers 0.13.3