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: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0939	1.0	113	2.0040	0.51
1.2997	2.0	226	1.3618	0.62
1.0908	3.0	339	1.1472	0.66
0.6986	4.0	452	0.7296	0.81
0.5258	5.0	565	0.6688	0.81
0.3454	6.0	678	0.5717	0.82
0.2739	7.0	791	0.4986	0.86
0.0864	8.0	904	0.6373	0.83
0.0745	9.0	1017	0.5573	0.89
0.015	10.0	1130	0.6404	0.87
0.0052	11.0	1243	0.8518	0.84
0.002	12.0	1356	0.8975	0.85
0.0009	13.0	1469	0.9208	0.84
0.0006	14.0	1582	1.0636	0.86
0.0004	15.0	1695	1.0275	0.86

provetgrizzner/distilhubert-finetuned-gtzan

distilhubert-finetuned-gtzan