learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: 20

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.1816	1.0	29	0.41	2.1429
0.9004	2.0	58	0.61	1.7952
0.7342	3.0	87	0.62	1.6186
0.8389	4.0	116	0.67	1.4450
0.8045	5.0	145	0.72	1.2934
0.6668	6.0	174	0.81	1.1416
0.897	7.0	203	0.78	1.0876
0.5504	8.0	232	0.82	1.0412
0.4106	9.0	261	0.83	0.9954
0.4245	10.0	290	0.84	0.9752
0.2955	11.0	319	0.9407	0.8
0.2214	12.0	348	0.9383	0.8
0.5358	13.0	377	0.8892	0.81
0.3723	14.0	406	0.8386	0.82
0.3086	15.0	435	0.7704	0.86
0.2668	16.0	464	0.7496	0.81
0.2425	17.0	493	0.7069	0.85
0.2257	18.0	522	0.7138	0.85
0.1899	19.0	551	0.6733	0.86
0.1749	20.0	580	0.6618	0.86

dung8204/wav2vec2-base-finetuned-gtzan

wav2vec2-base-finetuned-gtzan-plus