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: 0.8
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: 0.8209
- Accuracy: 0.8
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8561 | 1.0 | 225 | 1.6555 | 0.56 |
| 1.109 | 2.0 | 450 | 1.2396 | 0.58 |
| 0.6901 | 3.0 | 675 | 0.8904 | 0.71 |
| 0.2618 | 4.0 | 900 | 0.6728 | 0.8 |
| 0.296 | 5.0 | 1125 | 0.6022 | 0.8 |
| 0.1734 | 6.0 | 1350 | 0.6310 | 0.83 |
| 0.1562 | 7.0 | 1575 | 0.6711 | 0.8 |
| 0.1927 | 8.0 | 1800 | 0.7798 | 0.8 |
| 0.0102 | 9.0 | 2025 | 0.8040 | 0.78 |
| 0.0102 | 10.0 | 2250 | 0.8209 | 0.8 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1