metadata
license: apache-2.0
base_model: bookbot/distil-ast-audioset
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distil-ast-audioset-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: 0.89
distil-ast-audioset-finetuned-gtzan
This model is a fine-tuned version of bookbot/distil-ast-audioset on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4548
- Accuracy: 0.89
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: 20
- eval_batch_size: 20
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- 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 |
|---|---|---|---|---|
| 1.9887 | 0.9778 | 11 | 0.9550 | 0.79 |
| 0.8046 | 1.9556 | 22 | 0.6496 | 0.79 |
| 0.517 | 2.9333 | 33 | 0.5969 | 0.8 |
| 0.3425 | 4.0 | 45 | 0.4936 | 0.87 |
| 0.1616 | 4.9778 | 56 | 0.5090 | 0.88 |
| 0.1274 | 5.9556 | 67 | 0.4367 | 0.88 |
| 0.071 | 6.9333 | 78 | 0.4128 | 0.88 |
| 0.026 | 8.0 | 90 | 0.4548 | 0.89 |
| 0.0185 | 8.9778 | 101 | 0.3586 | 0.88 |
| 0.0089 | 9.7778 | 110 | 0.3642 | 0.88 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1