---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-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: 0.81
---

<!-- 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. -->

# wav2vec2-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:
- Loss: 0.5746
- 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0253        | 0.99  | 28   | 1.8206          | 0.38     |
| 1.3127        | 1.98  | 56   | 1.1930          | 0.64     |
| 0.9726        | 2.97  | 84   | 0.9269          | 0.69     |
| 1.2272        | 4.0   | 113  | 1.1682          | 0.66     |
| 0.6441        | 4.99  | 141  | 0.9781          | 0.71     |
| 0.5447        | 5.98  | 169  | 0.8603          | 0.74     |
| 0.3067        | 6.97  | 197  | 0.6313          | 0.86     |
| 0.1481        | 8.0   | 226  | 0.5746          | 0.89     |
| 0.0599        | 8.99  | 254  | 0.7602          | 0.84     |
| 0.0306        | 9.91  | 280  | 0.8119          | 0.81     |


### Framework versions

- Transformers 4.32.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3