learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 3
total_train_batch_size: 6
optimizer: Use 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	Accuracy	Validation Loss
1.6725	1.0	150	0.61	1.5409
1.0698	2.0	300	0.67	1.1464
0.8261	3.0	450	0.77	0.9681
0.6195	4.0	600	0.77	0.8018
0.5423	5.0	750	0.82	0.7095
0.4058	6.0	900	0.6112	0.79
0.3604	7.0	1050	0.5092	0.88
0.2333	8.0	1200	0.6296	0.82
0.1044	9.0	1350	0.5599	0.85
0.0986	10.0	1500	0.5498	0.87

bytewhisperer11/distilhubert-finetuned-gtzan

distilhubert-finetuned-gtzan