music_genres_classification-finetuned-gtzan
This model is a fine-tuned version of dima806/music_genres_classification on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.3618
- 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4157 | 1.0 | 113 | 2.2560 | 0.73 |
| 1.7996 | 2.0 | 226 | 1.8615 | 0.74 |
| 1.4872 | 3.0 | 339 | 1.9090 | 0.74 |
| 0.8284 | 4.0 | 452 | 2.1178 | 0.75 |
| 0.6863 | 5.0 | 565 | 1.6002 | 0.85 |
| 1.1591 | 6.0 | 678 | 2.2502 | 0.79 |
| 1.2149 | 7.0 | 791 | 1.1801 | 0.87 |
| 0.4908 | 8.0 | 904 | 1.4180 | 0.87 |
| 0.2958 | 9.0 | 1017 | 1.3262 | 0.87 |
| 0.0493 | 10.0 | 1130 | 1.3618 | 0.89 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2