---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan3
  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: 0.85
---

<!-- 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-gtzan3

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: 1.0442
- Accuracy: 0.85

## 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: 4
- eval_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9942        | 1.0   | 225  | 1.8990          | 0.51     |
| 1.2485        | 2.0   | 450  | 1.2682          | 0.62     |
| 0.9196        | 3.0   | 675  | 1.0459          | 0.69     |
| 0.9034        | 4.0   | 900  | 0.8488          | 0.75     |
| 0.3035        | 5.0   | 1125 | 0.7319          | 0.76     |
| 0.0715        | 6.0   | 1350 | 0.8713          | 0.77     |
| 0.1338        | 7.0   | 1575 | 0.8239          | 0.82     |
| 0.0254        | 8.0   | 1800 | 0.9324          | 0.83     |
| 0.0044        | 9.0   | 2025 | 0.7641          | 0.85     |
| 0.0024        | 10.0  | 2250 | 0.9133          | 0.83     |
| 0.19          | 11.0  | 2475 | 0.9976          | 0.84     |
| 0.0013        | 12.0  | 2700 | 0.9684          | 0.83     |
| 0.0011        | 13.0  | 2925 | 0.9241          | 0.85     |
| 0.001         | 14.0  | 3150 | 0.9540          | 0.86     |
| 0.0008        | 15.0  | 3375 | 1.0849          | 0.85     |
| 0.0007        | 16.0  | 3600 | 0.9005          | 0.85     |
| 0.0007        | 17.0  | 3825 | 0.9798          | 0.84     |
| 0.0007        | 18.0  | 4050 | 1.0058          | 0.84     |
| 0.0005        | 19.0  | 4275 | 1.0524          | 0.85     |
| 0.0006        | 20.0  | 4500 | 1.0442          | 0.85     |


### Framework versions

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