You can deploy this model and start earning money today!

CarolusRenniusVitellius/
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-run4-ast

Name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-run4-ast
Availability: InStock

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:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3844	1.0	113	0.5709	0.77
0.9927	2.0	226	0.7106	0.74
0.0011	3.0	339	0.5417	0.85
0.0003	4.0	452	0.4402	0.9
0.0009	5.0	565	0.4112	0.89
0.0002	6.0	678	0.7092	0.83
0.0005	7.0	791	0.5334	0.89
0.0001	8.0	904	0.5155	0.89
0.0002	9.0	1017	0.5081	0.9
0.0	10.0	1130	0.5050	0.9