---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-bs-16-fp16-false
  results:
  - task:
      name: Audio Classification
      type: audio-classification
    dataset:
      name: GTZAN
      type: marsyas/gtzan
      config: default
      split: train
      args: default
    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. -->

# distilhubert-finetuned-gtzan-bs-16-fp16-false

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: 0.5225
- 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: 16
- eval_batch_size: 16
- 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: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1955        | 1.0   | 57   | 2.1121          | 0.44     |
| 1.6787        | 2.0   | 114  | 1.5681          | 0.62     |
| 1.1812        | 3.0   | 171  | 1.1904          | 0.74     |
| 1.0922        | 4.0   | 228  | 0.9769          | 0.7      |
| 0.7733        | 5.0   | 285  | 0.8104          | 0.78     |
| 0.6225        | 6.0   | 342  | 0.6892          | 0.83     |
| 0.609         | 7.0   | 399  | 0.6572          | 0.85     |
| 0.4223        | 8.0   | 456  | 0.5775          | 0.83     |
| 0.3115        | 9.0   | 513  | 0.5956          | 0.81     |
| 0.1942        | 10.0  | 570  | 0.5556          | 0.82     |
| 0.1602        | 11.0  | 627  | 0.6075          | 0.83     |
| 0.1206        | 12.0  | 684  | 0.5676          | 0.85     |
| 0.1265        | 13.0  | 741  | 0.5585          | 0.85     |
| 0.0776        | 14.0  | 798  | 0.5220          | 0.84     |
| 0.1085        | 15.0  | 855  | 0.5225          | 0.84     |


### Framework versions

- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3