<!-- 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
This model is a fine-tuned version of sanchit-gandhi/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.0598
- Accuracy: 0.82
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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| 1.4895 | 1.0 | 450 | 1.4867 | 0.58 |
| 0.6878 | 2.0 | 900 | 0.9345 | 0.7 |
| 0.9996 | 3.0 | 1350 | 0.7247 | 0.77 |
| 0.6172 | 4.0 | 1800 | 0.9400 | 0.78 |
| 0.0982 | 5.0 | 2250 | 0.6720 | 0.85 |
| 0.0072 | 6.0 | 2700 | 1.2256 | 0.79 |
| 0.0016 | 7.0 | 3150 | 0.8598 | 0.84 |
| 0.0018 | 8.0 | 3600 | 0.8537 | 0.85 |
| 0.0012 | 9.0 | 4050 | 0.9706 | 0.84 |
| 0.0019 | 10.0 | 4500 | 1.0598 | 0.82 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.3
- Tokenizers 0.13.3
