metadata
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: 0.84
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: 0.7931
- Accuracy: 0.84
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: 4e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2107 | 1.0 | 56 | 0.4744 | 0.89 |
| 0.0867 | 1.99 | 112 | 0.7316 | 0.8 |
| 0.1117 | 2.99 | 168 | 0.6942 | 0.81 |
| 0.1024 | 4.0 | 225 | 0.6151 | 0.85 |
| 0.0141 | 5.0 | 281 | 0.7542 | 0.83 |
| 0.0089 | 5.99 | 337 | 0.7236 | 0.85 |
| 0.007 | 6.99 | 393 | 0.7115 | 0.84 |
| 0.0477 | 8.0 | 450 | 0.7334 | 0.85 |
| 0.0048 | 9.0 | 506 | 0.7772 | 0.85 |
| 0.0348 | 9.99 | 562 | 0.7465 | 0.85 |
| 0.0035 | 10.99 | 618 | 0.8011 | 0.84 |
| 0.004 | 11.95 | 672 | 0.7931 | 0.84 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1