<!-- 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: 0.6319
- 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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9649 | 1.0 | 113 | 1.7979 | 0.47 |
| 1.3283 | 2.0 | 226 | 1.1892 | 0.64 |
| 0.9491 | 3.0 | 339 | 0.9385 | 0.76 |
| 0.8013 | 4.0 | 452 | 0.8300 | 0.72 |
| 0.6314 | 5.0 | 565 | 0.6822 | 0.8 |
| 0.322 | 6.0 | 678 | 0.7438 | 0.8 |
| 0.4727 | 7.0 | 791 | 0.5545 | 0.83 |
| 0.1464 | 8.0 | 904 | 0.5576 | 0.86 |
| 0.2615 | 9.0 | 1017 | 0.5783 | 0.83 |
| 0.1233 | 10.0 | 1130 | 0.6319 | 0.84 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
