learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	15	2.6566	0.0504
No log	2.0	30	2.4304	0.2269
No log	3.0	45	2.0419	0.4622
No log	4.0	60	1.7104	0.6555
No log	5.0	75	1.4219	0.7983
No log	6.0	90	1.2776	0.7647
No log	7.0	105	1.0848	0.8487
No log	8.0	120	0.9949	0.8571
No log	9.0	135	0.9118	0.8824
No log	10.0	150	0.9037	0.8655

Frost0098/audio_classification

audio_classification