metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results: []
distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1809
- Accuracy: 0.8231
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 1.0783 | 1.0 | 874 | 1.1569 | 0.6234 |
| 0.4485 | 2.0 | 1748 | 0.8199 | 0.7499 |
| 0.3201 | 3.0 | 2622 | 0.7982 | 0.7705 |
| 0.3439 | 4.0 | 3496 | 0.8584 | 0.8025 |
| 0.2061 | 5.0 | 4370 | 0.9085 | 0.8065 |
| 0.0801 | 6.0 | 5244 | 0.9950 | 0.8134 |
| 0.0178 | 7.0 | 6118 | 1.0729 | 0.8168 |
| 0.0002 | 8.0 | 6992 | 1.1714 | 0.8180 |
| 0.0001 | 9.0 | 7866 | 1.1886 | 0.8226 |
| 0.0001 | 10.0 | 8740 | 1.1809 | 0.8231 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3