learning_rate: 0.0001
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: 24
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.8772	0.2963	24	0.9649	34.4248
0.4905	0.5926	48	0.4846	20.3040
0.4376	0.8889	72	0.4124	18.7372
0.3835	1.1852	96	0.3908	18.4520
0.3649	1.4815	120	0.3779	17.2443
0.365	1.7778	144	0.3717	16.9994
0.3455	2.0741	168	0.3660	16.6840
0.3926	2.3704	192	0.3647	16.8585
0.2964	2.6667	216	0.3619	15.8889
0.2999	2.9630	240	0.3612	15.7715

greenw0lf/whisper-10hrs-meta-seed333

whisper-10hrs-meta-seed333