metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results: []
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: 0.7339
- 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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|
| 1.9233 | 1.0 | 225 | 1.7014 | 0.49 |
| 0.8822 | 2.0 | 450 | 1.0546 | 0.68 |
| 0.676 | 3.0 | 675 | 0.7165 | 0.78 |
| 0.8326 | 4.0 | 900 | 0.5948 | 0.79 |
| 0.3184 | 5.0 | 1125 | 0.5484 | 0.81 |
| 0.6154 | 6.0 | 1350 | 0.5977 | 0.83 |
| 0.0305 | 7.0 | 1575 | 0.6213 | 0.81 |
| 0.0154 | 8.0 | 1800 | 0.7479 | 0.79 |
| 0.086 | 9.0 | 2025 | 0.6926 | 0.84 |
| 0.0103 | 10.0 | 2250 | 0.7339 | 0.82 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3