learning_rate: 0.001
train_batch_size: 100
eval_batch_size: 100
seed: 43
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_steps: 1000
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
0.2913	0.0450	2000	0.4665
0.2560	0.0900	4000	0.4262
0.2500	0.1350	6000	0.4156
0.2387	0.1800	8000	0.4142
0.2258	0.2250	10000	0.3964
0.2220	0.2700	12000	0.3896
0.2183	0.3150	14000	0.3913
0.2112	0.3600	16000	0.3841
0.2086	0.4050	18000	0.3763
0.2042	0.4501	20000	0.3732
0.1944	0.4951	22000	0.3659
0.1893	0.5401	24000	0.3631
0.1942	0.5851	26000	0.3589
0.1861	0.6301	28000	0.3567
0.1894	0.6751	30000	0.3515
0.1807	0.7201	32000	0.3497
0.1794	0.7651	34000	0.3456
0.1745	0.8101	36000	0.3453
0.1704	0.8551	38000	0.3459
0.1754	0.9001	40000	0.3446
0.1735	0.9451	42000	0.3440
0.1737	0.9901	44000	0.3415
0.1755	1.0	44439	0.3428

mazesmazes/tiny-audio-next-thurs

tiny-audio-next-thurs