---
license: apache-2.0
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: 0.785
---

<!-- 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:
- Loss: 1.0228
- Accuracy: 0.785

## 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
- 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1613        | 1.0   | 100  | 2.1437          | 0.36     |
| 1.6412        | 2.0   | 200  | 1.4637          | 0.615    |
| 1.1977        | 3.0   | 300  | 1.1439          | 0.64     |
| 0.9222        | 4.0   | 400  | 0.9581          | 0.73     |
| 0.7547        | 5.0   | 500  | 0.8533          | 0.705    |
| 0.4407        | 6.0   | 600  | 0.7473          | 0.785    |
| 0.2775        | 7.0   | 700  | 0.8627          | 0.745    |
| 0.2278        | 8.0   | 800  | 0.7299          | 0.78     |
| 0.0881        | 9.0   | 900  | 0.7966          | 0.77     |
| 0.0358        | 10.0  | 1000 | 0.8457          | 0.79     |
| 0.0192        | 11.0  | 1100 | 0.9054          | 0.775    |
| 0.0197        | 12.0  | 1200 | 0.9318          | 0.775    |
| 0.0075        | 13.0  | 1300 | 0.9652          | 0.775    |
| 0.0058        | 14.0  | 1400 | 0.9544          | 0.785    |
| 0.0744        | 15.0  | 1500 | 0.9989          | 0.775    |
| 0.0043        | 16.0  | 1600 | 0.9860          | 0.785    |
| 0.0039        | 17.0  | 1700 | 1.0023          | 0.79     |
| 0.0037        | 18.0  | 1800 | 0.9807          | 0.79     |
| 0.0036        | 19.0  | 1900 | 1.0155          | 0.785    |
| 0.0034        | 20.0  | 2000 | 1.0228          | 0.785    |


### Framework versions

- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3