---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
- precision
- recall
- f1
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: 0.87
    - name: Precision
      type: precision
      value: 0.8753213453213452
    - name: Recall
      type: recall
      value: 0.87
    - name: F1
      type: f1
      value: 0.8641214483158217
pipeline_tag: audio-classification
---

<!-- 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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/raspuntinov_ai/huggingface/runs/cefsu57q)
# 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: 0.5488
- Accuracy: 0.87
- Precision: 0.8753
- Recall: 0.87
- F1: 0.8641

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 2.1729        | 1.0   | 113  | 2.0581          | 0.63     | 0.6670    | 0.63   | 0.5957 |
| 1.6552        | 2.0   | 226  | 1.3957          | 0.7      | 0.6894    | 0.7    | 0.6857 |
| 1.0753        | 3.0   | 339  | 0.9783          | 0.75     | 0.8154    | 0.75   | 0.7277 |
| 0.8519        | 4.0   | 452  | 0.8087          | 0.75     | 0.8120    | 0.75   | 0.7380 |
| 0.8623        | 5.0   | 565  | 0.7393          | 0.75     | 0.7622    | 0.75   | 0.7373 |
| 0.506         | 6.0   | 678  | 0.6861          | 0.81     | 0.8449    | 0.81   | 0.7997 |
| 0.2052        | 7.0   | 791  | 0.6505          | 0.81     | 0.8254    | 0.81   | 0.8024 |
| 0.1583        | 8.0   | 904  | 0.5365          | 0.86     | 0.8770    | 0.86   | 0.8545 |
| 0.0699        | 9.0   | 1017 | 0.5488          | 0.87     | 0.8753    | 0.87   | 0.8641 |
| 0.0177        | 10.0  | 1130 | 0.6330          | 0.83     | 0.8312    | 0.83   | 0.8245 |
| 0.0071        | 11.0  | 1243 | 0.6268          | 0.84     | 0.8410    | 0.84   | 0.8348 |
| 0.0746        | 12.0  | 1356 | 0.6051          | 0.87     | 0.8732    | 0.87   | 0.8675 |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1