---
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
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 an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1809
- Accuracy: 0.8231

## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0783        | 1.0   | 874  | 1.1569          | 0.6234   |
| 0.4485        | 2.0   | 1748 | 0.8199          | 0.7499   |
| 0.3201        | 3.0   | 2622 | 0.7982          | 0.7705   |
| 0.3439        | 4.0   | 3496 | 0.8584          | 0.8025   |
| 0.2061        | 5.0   | 4370 | 0.9085          | 0.8065   |
| 0.0801        | 6.0   | 5244 | 0.9950          | 0.8134   |
| 0.0178        | 7.0   | 6118 | 1.0729          | 0.8168   |
| 0.0002        | 8.0   | 6992 | 1.1714          | 0.8180   |
| 0.0001        | 9.0   | 7866 | 1.1886          | 0.8226   |
| 0.0001        | 10.0  | 8740 | 1.1809          | 0.8231   |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3