distilhubert-finetuned-gtzan

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:

Model description

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: 132
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 18
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0102	1.0	113	0.7664	0.85
0.0078	2.0	226	0.7452	0.84
0.0175	3.0	339	0.8806	0.83
0.0020	4.0	452	0.8631	0.83
0.0018	5.0	565	0.6979	0.83
0.0015	6.0	678	0.7627	0.86
0.1259	7.0	791	0.7757	0.84
0.0010	8.0	904	0.7275	0.85
0.0009	9.0	1017	0.9678	0.84
0.0163	10.0	1130	0.7690	0.83
0.0008	11.0	1243	1.1376	0.82
0.0007	12.0	1356	0.7540	0.86
0.0007	13.0	1469	1.0279	0.83
0.0008	14.0	1582	0.7829	0.87
0.0006	15.0	1695	0.8600	0.86
0.0006	16.0	1808	0.8815	0.86
0.0006	17.0	1921	0.8768	0.85
0.0005	18.0	2034	0.8518	0.85