---
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: 0.5528
- 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: 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1578        | 0.99  | 56   | 2.1203          | 0.55     |
| 1.6815        | 2.0   | 113  | 1.6607          | 0.57     |
| 1.2921        | 2.99  | 169  | 1.2421          | 0.64     |
| 1.0324        | 4.0   | 226  | 1.0260          | 0.7      |
| 0.8661        | 4.99  | 282  | 0.8973          | 0.7      |
| 0.6192        | 6.0   | 339  | 0.7420          | 0.79     |
| 0.5437        | 6.99  | 395  | 0.6951          | 0.8      |
| 0.4917        | 8.0   | 452  | 0.6996          | 0.78     |
| 0.3868        | 8.99  | 508  | 0.6648          | 0.81     |
| 0.3816        | 10.0  | 565  | 0.6584          | 0.79     |
| 0.1935        | 10.99 | 621  | 0.6101          | 0.84     |
| 0.128         | 12.0  | 678  | 0.5445          | 0.85     |
| 0.1144        | 12.99 | 734  | 0.5703          | 0.84     |
| 0.0828        | 14.0  | 791  | 0.5632          | 0.83     |
| 0.0928        | 14.87 | 840  | 0.5528          | 0.84     |


### Framework versions

- Transformers 4.30.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3