---
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert-finetuned-gtzan
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: 0.89
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# distilhubert-finetuned-gtzan

This model is a fine-tuned version of [ntu-spml/distilhubert-finetuned-gtzan](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2277
- Accuracy: 0.89

## 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: 16
- eval_batch_size: 16
- 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.279         | 1.0   | 50   | 0.4636          | 0.88     |
| 0.1597        | 2.0   | 100  | 0.3688          | 0.895    |
| 0.0882        | 3.0   | 150  | 0.4473          | 0.88     |
| 0.0486        | 4.0   | 200  | 0.5118          | 0.87     |
| 0.0341        | 5.0   | 250  | 0.4274          | 0.895    |
| 0.0058        | 6.0   | 300  | 0.5832          | 0.86     |
| 0.0017        | 7.0   | 350  | 0.5238          | 0.9      |
| 0.0004        | 8.0   | 400  | 0.6152          | 0.895    |
| 0.0001        | 9.0   | 450  | 0.6718          | 0.915    |
| 0.0           | 10.0  | 500  | 0.9763          | 0.875    |
| 0.0           | 11.0  | 550  | 1.0753          | 0.885    |
| 0.0           | 12.0  | 600  | 0.9361          | 0.905    |
| 0.1016        | 13.0  | 650  | 1.1638          | 0.89     |
| 0.0           | 14.0  | 700  | 1.1003          | 0.895    |
| 0.0           | 15.0  | 750  | 1.0716          | 0.89     |
| 0.0           | 16.0  | 800  | 1.1925          | 0.89     |
| 0.0609        | 17.0  | 850  | 1.1557          | 0.89     |
| 0.0           | 18.0  | 900  | 1.1128          | 0.89     |
| 0.0           | 19.0  | 950  | 1.2144          | 0.89     |
| 0.0           | 20.0  | 1000 | 1.2277          | 0.89     |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0