---
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-v2-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: 0.84
---

<!-- 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. -->

# hubert-base-ls960-v2-finetuned-gtzan

This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7772
- Accuracy: 0.84

## 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: 10
- eval_batch_size: 10
- 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.2028        | 1.0   | 90   | 2.1088          | 0.42     |
| 1.7214        | 2.0   | 180  | 1.6669          | 0.43     |
| 1.6141        | 3.0   | 270  | 1.5335          | 0.54     |
| 0.9971        | 4.0   | 360  | 1.1589          | 0.64     |
| 1.0174        | 5.0   | 450  | 0.9587          | 0.64     |
| 0.7295        | 6.0   | 540  | 0.8286          | 0.69     |
| 0.8034        | 7.0   | 630  | 0.8001          | 0.76     |
| 0.5709        | 8.0   | 720  | 0.9846          | 0.73     |
| 0.4724        | 9.0   | 810  | 0.6829          | 0.79     |
| 0.5161        | 10.0  | 900  | 0.9728          | 0.72     |
| 0.4247        | 11.0  | 990  | 0.7745          | 0.78     |
| 0.2696        | 12.0  | 1080 | 0.5330          | 0.87     |
| 0.1403        | 13.0  | 1170 | 0.7202          | 0.83     |
| 0.3434        | 14.0  | 1260 | 0.8506          | 0.82     |
| 0.2754        | 15.0  | 1350 | 0.6707          | 0.85     |
| 0.152         | 16.0  | 1440 | 0.8752          | 0.83     |
| 0.233         | 17.0  | 1530 | 0.5098          | 0.9      |
| 0.1169        | 18.0  | 1620 | 0.7069          | 0.86     |
| 0.1667        | 19.0  | 1710 | 0.7760          | 0.84     |
| 0.0691        | 20.0  | 1800 | 0.7772          | 0.84     |


### Framework versions

- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1