---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
  results: []
---

<!-- 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: 0.7713
- Accuracy: 0.87

## 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: 0.0001
- 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: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9891        | 0.99  | 56   | 1.9587          | 0.4      |
| 1.5271        | 2.0   | 113  | 1.4658          | 0.56     |
| 1.074         | 2.99  | 169  | 0.9198          | 0.79     |
| 0.8036        | 4.0   | 226  | 0.9191          | 0.7      |
| 0.5017        | 4.99  | 282  | 0.7299          | 0.8      |
| 0.3405        | 6.0   | 339  | 0.6682          | 0.8      |
| 0.2178        | 6.99  | 395  | 0.6877          | 0.82     |
| 0.116         | 8.0   | 452  | 0.6092          | 0.83     |
| 0.0616        | 8.99  | 508  | 0.6579          | 0.85     |
| 0.0229        | 10.0  | 565  | 0.8793          | 0.8      |
| 0.0128        | 10.99 | 621  | 0.6722          | 0.87     |
| 0.0094        | 12.0  | 678  | 0.7586          | 0.87     |
| 0.0073        | 12.99 | 734  | 0.7636          | 0.87     |
| 0.007         | 14.0  | 791  | 0.7728          | 0.87     |
| 0.0073        | 14.87 | 840  | 0.7713          | 0.87     |


### Framework versions

- Transformers 4.30.2
- Pytorch 1.11.0+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1