distilhubert_finetuned-finetuned-gtzan
This model is a fine-tuned version of JanLilan/distilhubert_finetuned-distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6325
- Accuracy: 0.9
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8777 | 0.99 | 33 | 0.4485 | 0.8333 |
| 0.6913 | 2.0 | 67 | 1.0592 | 0.7 |
| 0.5494 | 2.99 | 100 | 0.6168 | 0.7667 |
| 0.3589 | 4.0 | 134 | 0.7820 | 0.7833 |
| 0.2049 | 4.99 | 167 | 0.9303 | 0.7833 |
| 0.1663 | 6.0 | 201 | 0.3570 | 0.9 |
| 0.0446 | 6.99 | 234 | 0.5636 | 0.8667 |
| 0.0313 | 8.0 | 268 | 0.6592 | 0.85 |
| 0.0007 | 8.99 | 301 | 0.4721 | 0.8833 |
| 0.0004 | 9.85 | 330 | 0.6325 | 0.9 |
Check it out colab
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3