vpingale07/distilhubert-v2-finetuned-gtzan
This model is a fine-tuned version of vpingale07/distilhubert-v2-v4 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.9254
- 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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0001 | 1.0 | 75 | 0.8660 | 0.88 |
| 0.0001 | 2.0 | 150 | 0.9036 | 0.8825 |
| 0.0 | 3.0 | 225 | 0.9178 | 0.88 |
| 0.0 | 4.0 | 300 | 0.9254 | 0.88 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2