<!-- 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 ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6340
- Accuracy: 0.83
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 1.9747 | 1.0 | 112 | 1.7879 | 0.56 |
| 1.322 | 1.99 | 224 | 1.2554 | 0.67 |
| 1.0047 | 3.0 | 337 | 0.9381 | 0.73 |
| 0.8037 | 4.0 | 449 | 0.8347 | 0.77 |
| 0.5617 | 4.99 | 561 | 0.7889 | 0.76 |
| 0.4773 | 6.0 | 674 | 0.6480 | 0.84 |
| 0.2749 | 6.99 | 786 | 0.6533 | 0.79 |
| 0.1649 | 8.0 | 899 | 0.6974 | 0.79 |
| 0.1132 | 9.0 | 1011 | 0.6771 | 0.81 |
| 0.1243 | 9.97 | 1120 | 0.6340 | 0.83 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 2.13.1
- Tokenizers 0.13.3
