---
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-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: 0.86
---

<!-- 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. -->

# ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5051
- Accuracy: 0.86

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.8767        | 1.0   | 112  | 0.6930          | 0.78     |
| 0.5251        | 2.0   | 225  | 0.5514          | 0.82     |
| 0.5388        | 3.0   | 337  | 0.5380          | 0.81     |
| 0.1679        | 4.0   | 450  | 0.3927          | 0.9      |
| 0.0227        | 5.0   | 562  | 0.5077          | 0.87     |
| 0.0012        | 6.0   | 675  | 0.5441          | 0.88     |
| 0.0472        | 7.0   | 787  | 0.7029          | 0.86     |
| 0.0015        | 8.0   | 900  | 0.5576          | 0.84     |
| 0.0095        | 9.0   | 1012 | 0.6228          | 0.85     |
| 0.0002        | 10.0  | 1125 | 0.4116          | 0.88     |
| 0.0001        | 11.0  | 1237 | 0.7136          | 0.82     |
| 0.0001        | 12.0  | 1350 | 0.4885          | 0.88     |
| 0.0001        | 13.0  | 1462 | 0.4831          | 0.87     |
| 0.0001        | 14.0  | 1575 | 0.4606          | 0.87     |
| 0.0           | 15.0  | 1687 | 0.4930          | 0.87     |
| 0.0           | 16.0  | 1800 | 0.4937          | 0.87     |
| 0.0           | 17.0  | 1912 | 0.4974          | 0.86     |
| 0.0           | 18.0  | 2025 | 0.4989          | 0.86     |
| 0.0           | 19.0  | 2137 | 0.5060          | 0.86     |
| 0.0           | 19.91 | 2240 | 0.5051          | 0.86     |


### Framework versions

- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3