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: 0.9
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: 0.4700
- 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- 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 |
|---|---|---|---|---|
| 0.9627 | 1.0 | 112 | 0.7284 | 0.75 |
| 0.3776 | 1.99 | 224 | 0.4641 | 0.83 |
| 0.4536 | 3.0 | 337 | 0.5534 | 0.85 |
| 0.0602 | 4.0 | 449 | 0.4999 | 0.86 |
| 0.1927 | 4.99 | 561 | 0.5989 | 0.85 |
| 0.0122 | 6.0 | 674 | 0.7778 | 0.85 |
| 0.0006 | 6.99 | 786 | 0.4095 | 0.9 |
| 0.0005 | 8.0 | 899 | 0.5149 | 0.9 |
| 0.1723 | 9.0 | 1011 | 0.4558 | 0.9 |
| 0.0001 | 9.99 | 1123 | 0.4700 | 0.9 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3