CTC-based-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: 0.7057
- Accuracy: 0.79
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: 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 |
|---|---|---|---|---|
| 2.0608 | 1.0 | 57 | 2.0361 | 0.43 |
| 1.663 | 2.0 | 114 | 1.5387 | 0.62 |
| 1.2399 | 3.0 | 171 | 1.2074 | 0.68 |
| 1.0662 | 4.0 | 228 | 1.0805 | 0.65 |
| 0.7986 | 5.0 | 285 | 0.8880 | 0.75 |
| 0.7328 | 6.0 | 342 | 0.8037 | 0.74 |
| 0.5891 | 7.0 | 399 | 0.7918 | 0.78 |
| 0.5227 | 8.0 | 456 | 0.7232 | 0.79 |
| 0.5123 | 9.0 | 513 | 0.7138 | 0.78 |
| 0.5578 | 10.0 | 570 | 0.7057 | 0.79 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 4