distilhubert-finetuned-music-genres-small
This model is a fine-tuned version of ntu-spml/distilhubert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6827
- Accuracy: 0.4
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.99 | 56 | 2.0784 | 0.36 |
| 2.098 | 1.99 | 112 | 1.8533 | 0.35 |
| 2.098 | 2.99 | 168 | 1.7524 | 0.39 |
| 1.7241 | 3.99 | 224 | 1.6827 | 0.4 |
| 1.7241 | 4.99 | 280 | 1.6565 | 0.39 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.11.0
- Datasets 2.6.1
- Tokenizers 0.11.6