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: 0.83
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: 0.9736
- 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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| 1.7415 | 1.0 | 450 | 1.4915 | 0.61 |
| 1.2771 | 2.0 | 900 | 1.2322 | 0.64 |
| 0.3833 | 3.0 | 1350 | 0.7804 | 0.78 |
| 0.4718 | 4.0 | 1800 | 0.5409 | 0.82 |
| 0.0278 | 5.0 | 2250 | 0.7579 | 0.85 |
| 0.0044 | 6.0 | 2700 | 0.7676 | 0.82 |
| 0.002 | 7.0 | 3150 | 1.0458 | 0.81 |
| 0.0018 | 8.0 | 3600 | 0.5839 | 0.88 |
| 0.0013 | 9.0 | 4050 | 0.9576 | 0.83 |
| 0.0015 | 10.0 | 4500 | 0.9736 | 0.83 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.14.7
- Tokenizers 0.15.0