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: 0.5513
- 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: 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 |
| 1.9949 |
1.0 |
113 |
1.8096 |
0.5 |
| 1.3453 |
2.0 |
226 |
1.2502 |
0.62 |
| 1.0267 |
3.0 |
339 |
0.9683 |
0.73 |
| 0.8382 |
4.0 |
452 |
0.8201 |
0.74 |
| 0.6864 |
5.0 |
565 |
0.6620 |
0.81 |
| 0.3746 |
6.0 |
678 |
0.8011 |
0.74 |
| 0.2883 |
7.0 |
791 |
0.5384 |
0.86 |
| 0.1192 |
8.0 |
904 |
0.4698 |
0.85 |
| 0.2028 |
9.0 |
1017 |
0.4610 |
0.85 |
| 0.1638 |
10.0 |
1130 |
0.5513 |
0.82 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
