---
license: apache-2.0
base_model: ntu-spml/distilhubert
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: 0.85
---

<!-- 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-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: 0.6094
- 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 16

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1935        | 0.99  | 56   | 2.1282          | 0.42     |
| 1.6089        | 2.0   | 113  | 1.5367          | 0.57     |
| 1.2446        | 2.99  | 169  | 1.1485          | 0.74     |
| 0.98          | 4.0   | 226  | 0.9621          | 0.76     |
| 0.7296        | 4.99  | 282  | 0.7948          | 0.82     |
| 0.5111        | 6.0   | 339  | 0.7578          | 0.79     |
| 0.583         | 6.99  | 395  | 0.6152          | 0.86     |
| 0.4002        | 8.0   | 452  | 0.5863          | 0.85     |
| 0.2924        | 8.99  | 508  | 0.5834          | 0.84     |
| 0.1789        | 10.0  | 565  | 0.6087          | 0.85     |
| 0.1181        | 10.99 | 621  | 0.5911          | 0.84     |
| 0.0673        | 12.0  | 678  | 0.5887          | 0.85     |
| 0.0633        | 12.99 | 734  | 0.6294          | 0.84     |
| 0.0393        | 14.0  | 791  | 0.6205          | 0.84     |
| 0.0362        | 14.99 | 847  | 0.6382          | 0.85     |
| 0.0328        | 15.86 | 896  | 0.6094          | 0.85     |


### Framework versions

- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3