---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: music-genre-classifer-20-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: 0.82
---

<!-- 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. -->

# music-genre-classifer-20-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: 0.5510
- Accuracy: 0.82

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|:-------------:|:-----:|:----:|:--------:|:---------------:|
| 2.201         | 1.0   | 113  | 0.39     | 2.1256          |
| 1.6789        | 2.0   | 226  | 0.59     | 1.6543          |
| 1.5602        | 3.0   | 339  | 0.64     | 1.3917          |
| 1.1966        | 4.0   | 452  | 0.67     | 1.1946          |
| 1.1131        | 5.0   | 565  | 0.77     | 1.0492          |
| 1.0258        | 6.0   | 678  | 0.76     | 0.9712          |
| 0.988         | 7.0   | 791  | 0.76     | 0.9160          |
| 0.7303        | 8.0   | 904  | 0.8      | 0.8704          |
| 0.8036        | 9.0   | 1017 | 0.8      | 0.8425          |
| 0.742         | 10.0  | 1130 | 0.81     | 0.8224          |
| 0.7463        | 11.0  | 1243 | 0.81     | 0.8140          |
| 0.7428        | 12.0  | 1356 | 0.78     | 0.8112          |
| 0.6081        | 13.0  | 1469 | 0.82     | 0.6975          |
| 0.8154        | 14.0  | 1582 | 0.84     | 0.6636          |
| 0.3758        | 15.0  | 1695 | 0.84     | 0.6215          |
| 0.503         | 16.0  | 1808 | 0.81     | 0.6251          |
| 0.4542        | 17.0  | 1921 | 0.84     | 0.5869          |
| 0.3285        | 18.0  | 2034 | 0.85     | 0.5830          |
| 0.4309        | 19.0  | 2147 | 0.82     | 0.5844          |
| 0.342         | 20.0  | 2260 | 0.85     | 0.5840          |
| 0.3051        | 21.0  | 2373 | 0.83     | 0.5843          |
| 0.3558        | 22.0  | 2486 | 0.6144   | 0.79            |
| 0.3371        | 23.0  | 2599 | 0.5673   | 0.81            |
| 0.2882        | 24.0  | 2712 | 0.5365   | 0.84            |
| 0.2326        | 25.0  | 2825 | 0.5848   | 0.83            |
| 0.192         | 26.0  | 2938 | 0.5406   | 0.85            |
| 0.1528        | 27.0  | 3051 | 0.5482   | 0.82            |
| 0.1937        | 28.0  | 3164 | 0.5448   | 0.84            |
| 0.1264        | 29.0  | 3277 | 0.5487   | 0.84            |
| 0.1356        | 30.0  | 3390 | 0.5510   | 0.82            |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2