ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan – AI Model by jaymanvirk | AlphaNeural AI

You can deploy this model and start earning money today!

jaymanvirk/
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

like

0

audio-spectrogram-transformer

audio-classification

generated_from_trainer

MIT/ast-finetuned-audioset-10-10-0.4593

endpoints_compatible

Views

No views yet

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: 0.5071
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
0.6259	1.0	112	0.7596	0.72
0.9466	2.0	225	0.6318	0.79
0.349	3.0	337	0.6183	0.84
0.1775	4.0	450	0.6978	0.83
0.0076	5.0	562	0.6868	0.85
0.0062	6.0	675	0.4879	0.88
0.0102	7.0	787	0.7735	0.85
0.0002	8.0	900	0.6003	0.9
0.0001	9.0	1012	0.4694	0.92
0.0001	10.0	1125	0.4915	0.91
0.0001	11.0	1237	0.4791	0.91
0.0001	12.0	1350	0.5129	0.91
0.0001	13.0	1462	0.5055	0.91
0.0001	14.0	1575	0.4978	0.91
0.0	14.93	1680	0.5071	0.91

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.1