<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilhubert-finetuned-gtzan-finetuned-gtzan
This model is a fine-tuned version of leksa-pramheda/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.3011
- Accuracy: 0.84
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0696 | 1.0 | 225 | 0.7689 | 0.83 |
| 0.0036 | 2.0 | 450 | 0.8851 | 0.85 |
| 0.0158 | 3.0 | 675 | 1.2591 | 0.78 |
| 0.0018 | 4.0 | 900 | 1.1447 | 0.84 |
| 0.0013 | 5.0 | 1125 | 0.9447 | 0.88 |
| 0.0007 | 6.0 | 1350 | 1.1113 | 0.83 |
| 0.0005 | 7.0 | 1575 | 1.2101 | 0.79 |
| 0.001 | 8.0 | 1800 | 1.1569 | 0.83 |
| 0.0003 | 9.0 | 2025 | 1.2569 | 0.82 |
| 0.0003 | 10.0 | 2250 | 1.3219 | 0.83 |
| 0.0005 | 11.0 | 2475 | 1.2195 | 0.83 |
| 0.0002 | 12.0 | 2700 | 1.3446 | 0.82 |
| 0.0003 | 13.0 | 2925 | 1.3032 | 0.84 |
| 0.0002 | 14.0 | 3150 | 1.3122 | 0.84 |
| 0.0002 | 15.0 | 3375 | 1.3011 | 0.84 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
