metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.83
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: 0.5708
- 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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Use OptimizerNames.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 |
|---|---|---|---|---|
| 2.0536 | 1.0 | 75 | 1.9482 | 0.35 |
| 1.4103 | 2.0 | 150 | 1.4342 | 0.63 |
| 1.1862 | 3.0 | 225 | 1.1184 | 0.7 |
| 0.8092 | 4.0 | 300 | 0.9554 | 0.73 |
| 0.5852 | 5.0 | 375 | 0.7298 | 0.84 |
| 0.5186 | 6.0 | 450 | 0.6516 | 0.83 |
| 0.4123 | 7.0 | 525 | 0.6696 | 0.79 |
| 0.3285 | 8.0 | 600 | 0.5844 | 0.86 |
| 0.328 | 9.0 | 675 | 0.6136 | 0.83 |
| 0.2715 | 10.0 | 750 | 0.5708 | 0.83 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0