metadata
license: bsd-3-clause
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
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: 0.3273
- 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: 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 |
---|---|---|---|---|
0.5056 | 1.0 | 112 | 0.5669 | 0.85 |
0.2324 | 2.0 | 225 | 0.5131 | 0.85 |
0.2623 | 3.0 | 337 | 0.6539 | 0.79 |
0.4419 | 4.0 | 450 | 0.7401 | 0.83 |
0.0177 | 5.0 | 562 | 0.5134 | 0.85 |
0.0026 | 6.0 | 675 | 0.3351 | 0.9 |
0.0046 | 7.0 | 787 | 0.5120 | 0.88 |
0.0005 | 8.0 | 900 | 0.5165 | 0.91 |
0.2003 | 9.0 | 1012 | 0.3453 | 0.91 |
0.0001 | 10.0 | 1125 | 0.3438 | 0.91 |
0.0003 | 11.0 | 1237 | 0.3324 | 0.92 |
0.0 | 12.0 | 1350 | 0.3999 | 0.89 |
0.0 | 13.0 | 1462 | 0.3152 | 0.91 |
0.0001 | 14.0 | 1575 | 0.3212 | 0.92 |
0.0 | 15.0 | 1687 | 0.3220 | 0.92 |
0.0 | 16.0 | 1800 | 0.3343 | 0.9 |
0.0 | 17.0 | 1912 | 0.3324 | 0.91 |
0.0 | 18.0 | 2025 | 0.3311 | 0.91 |
0.0 | 19.0 | 2137 | 0.3292 | 0.91 |
0.0 | 19.91 | 2240 | 0.3273 | 0.91 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3