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: 0.5438
- Accuracy: 0.87
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0028 | 1.0 | 113 | 1.7975 | 0.52 |
| 1.3164 | 2.0 | 226 | 1.2010 | 0.68 |
| 1.0627 | 3.0 | 339 | 0.9305 | 0.76 |
| 0.8829 | 4.0 | 452 | 0.8470 | 0.74 |
| 0.6671 | 5.0 | 565 | 0.7021 | 0.78 |
| 0.4053 | 6.0 | 678 | 0.6707 | 0.79 |
| 0.4309 | 7.0 | 791 | 0.5799 | 0.84 |
| 0.1564 | 8.0 | 904 | 0.5560 | 0.8 |
| 0.2747 | 9.0 | 1017 | 0.5645 | 0.84 |
| 0.1592 | 10.0 | 1130 | 0.5438 | 0.87 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hewliyang/distilhubert-fintuned-gtzan
Base model
ntu-spml/distilhubert