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: 0.6028
- 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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|
2.1599 | 1.0 | 57 | 2.0321 | 0.64 |
1.5057 | 2.0 | 114 | 1.4337 | 0.58 |
1.2107 | 3.0 | 171 | 1.1677 | 0.69 |
0.9286 | 4.0 | 228 | 1.0566 | 0.71 |
0.8159 | 5.0 | 285 | 0.7997 | 0.81 |
0.7071 | 6.0 | 342 | 0.7576 | 0.8 |
0.6363 | 7.0 | 399 | 0.6601 | 0.85 |
0.4237 | 8.0 | 456 | 0.6692 | 0.78 |
0.4457 | 9.0 | 513 | 0.6314 | 0.81 |
0.4094 | 10.0 | 570 | 0.6028 | 0.83 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0a0+81ea7a4
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 30