---
library_name: transformers
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-gtzan
  results:
  - task:
      name: Audio Classification
      type: audio-classification
    dataset:
      name: GTZAN
      type: marsyas/gtzan
      config: all
      split: None
      args: all
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9
---

<!-- 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-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: 0.3410
- Accuracy: 0.9

## 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 25
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.627         | 1.0   | 50   | 0.8714          | 0.795    |
| 0.4145        | 2.0   | 100  | 0.5660          | 0.825    |
| 0.2344        | 3.0   | 150  | 0.4988          | 0.85     |
| 0.1334        | 4.0   | 200  | 0.3726          | 0.87     |
| 0.0341        | 5.0   | 250  | 0.3637          | 0.895    |
| 0.0172        | 6.0   | 300  | 0.4197          | 0.87     |
| 0.0338        | 7.0   | 350  | 0.5035          | 0.87     |
| 0.002         | 8.0   | 400  | 0.5825          | 0.86     |
| 0.001         | 9.0   | 450  | 0.4126          | 0.895    |
| 0.0093        | 10.0  | 500  | 0.4564          | 0.89     |
| 0.0056        | 11.0  | 550  | 0.4783          | 0.84     |
| 0.0162        | 12.0  | 600  | 0.3161          | 0.89     |
| 0.0019        | 13.0  | 650  | 0.4062          | 0.875    |
| 0.0005        | 14.0  | 700  | 0.3630          | 0.895    |
| 0.0098        | 15.0  | 750  | 0.3410          | 0.9      |
| 0.008         | 16.0  | 800  | 0.3385          | 0.89     |
| 0.0001        | 17.0  | 850  | 0.3434          | 0.895    |
| 0.0067        | 18.0  | 900  | 0.3414          | 0.885    |
| 0.0064        | 19.0  | 950  | 0.3453          | 0.895    |
| 0.0001        | 20.0  | 1000 | 0.3422          | 0.885    |
| 0.0001        | 21.0  | 1050 | 0.3520          | 0.89     |
| 0.0036        | 22.0  | 1100 | 0.3403          | 0.89     |
| 0.0001        | 23.0  | 1150 | 0.3394          | 0.89     |
| 0.0001        | 24.0  | 1200 | 0.3407          | 0.89     |
| 0.0026        | 25.0  | 1250 | 0.3417          | 0.89     |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 2.18.0
- Tokenizers 0.22.1