---
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: 0.86
---

<!-- 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](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.88

## 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: 8e-05
- train_batch_size: 12
- eval_batch_size: 12
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1317        | 1.0   | 75   | 2.0386          | 0.33     |
| 1.36          | 2.0   | 150  | 1.4142          | 0.58     |
| 1.1456        | 3.0   | 225  | 1.1110          | 0.66     |
| 0.6417        | 4.0   | 300  | 1.0142          | 0.69     |
| 0.3324        | 5.0   | 375  | 0.5881          | 0.82     |
| 0.2208        | 6.0   | 450  | 0.5516          | 0.84     |
| 0.3346        | 7.0   | 525  | 0.5267          | 0.87     |
| 0.2309        | 8.0   | 600  | 0.7404          | 0.8      |
| 0.0267        | 9.0   | 675  | 0.6636          | 0.8      |
| 0.0309        | 10.0  | 750  | 0.6390          | 0.84     |
| 0.0076        | 11.0  | 825  | 0.6949          | 0.85     |
| 0.0053        | 12.0  | 900  | 0.6405          | 0.87     |
| 0.005         | 13.0  | 975  | 0.7065          | 0.84     |
| 0.004         | 14.0  | 1050 | 0.8570          | 0.84     |
| 0.0031        | 15.0  | 1125 | 0.6735          | 0.88     |
| 0.0028        | 16.0  | 1200 | 0.7023          | 0.85     |
| 0.0027        | 17.0  | 1275 | 0.6823          | 0.86     |
| 0.0369        | 18.0  | 1350 | 0.7320          | 0.85     |
| 0.0024        | 19.0  | 1425 | 0.6656          | 0.86     |
| 0.0023        | 20.0  | 1500 | 0.6628          | 0.86     |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3