metadata
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: 0.94
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 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 2.0656
- Accuracy: 0.94
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: 1e-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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0155 | 1.0 | 113 | 2.5288 | 0.86 |
| 0.7164 | 2.0 | 226 | 2.2767 | 0.88 |
| 0.8683 | 3.0 | 339 | 2.2711 | 0.87 |
| 0.0006 | 4.0 | 452 | 2.7214 | 0.89 |
| 0.4962 | 5.0 | 565 | 1.9165 | 0.92 |
| 0.0 | 6.0 | 678 | 3.1595 | 0.88 |
| 0.0 | 7.0 | 791 | 1.9683 | 0.91 |
| 0.0 | 8.0 | 904 | 1.9617 | 0.91 |
| 0.0 | 9.0 | 1017 | 2.0516 | 0.94 |
| 0.0 | 10.0 | 1130 | 2.0656 | 0.94 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1