---
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-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: 0.91
---

<!-- 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: 0.4517
- Accuracy: 0.91

## 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: Use OptimizerNames.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: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 1.3017        | 1.0     | 113  | 0.6180          | 0.78     |
| 0.5478        | 2.0     | 226  | 0.8031          | 0.77     |
| 0.3357        | 3.0     | 339  | 0.6511          | 0.87     |
| 0.1565        | 4.0     | 452  | 0.6858          | 0.87     |
| 0.0628        | 5.0     | 565  | 0.5638          | 0.86     |
| 0.0466        | 6.0     | 678  | 0.4399          | 0.91     |
| 0.0108        | 7.0     | 791  | 0.5120          | 0.88     |
| 0.0094        | 8.0     | 904  | 0.4854          | 0.89     |
| 0.0069        | 9.0     | 1017 | 0.4865          | 0.91     |
| 0.0061        | 10.0    | 1130 | 0.4674          | 0.91     |
| 0.0052        | 11.0    | 1243 | 0.4565          | 0.91     |
| 0.0027        | 12.0    | 1356 | 0.4557          | 0.91     |
| 0.0042        | 13.0    | 1469 | 0.4534          | 0.91     |
| 0.0028        | 14.0    | 1582 | 0.4523          | 0.91     |
| 0.0026        | 14.8711 | 1680 | 0.4517          | 0.91     |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.6.0+cu126
- Datasets 3.2.0
- Tokenizers 0.21.0