learning_rate: 1e-05
train_batch_size: 48
eval_batch_size: 32
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_steps: 87
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.0401	0.1730	50	1.1988	37.8200
0.9555	0.3460	100	1.0688	35.7265
0.7947	0.5190	150	0.8653	33.0325
0.6554	0.6920	200	0.6321	29.0670
0.5346	0.8651	250	0.4921	21.8841
0.4683	1.0381	300	0.4321	21.6291
0.4501	1.2111	350	0.4115	21.6392
0.4317	1.3841	400	0.3999	20.9716
0.4454	1.5571	450	0.3916	20.1765
0.4168	1.7301	500	0.3848	18.5091
0.4096	1.9031	550	0.3802	18.6701
0.3981	2.0761	600	0.3763	18.2474
0.4189	2.2491	650	0.3732	18.4487
0.4301	2.4221	700	0.3712	18.1870
0.4046	2.5952	750	0.3697	18.3380
0.4244	2.7682	800	0.3687	18.0897
0.4068	2.9412	850	0.3683	18.1098

greenw0lf/whisper-40hrs-random

whisper-40hrs-random