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: 22
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.9534	0.3014	22	1.0118	34.9113
0.5657	0.6027	44	0.5371	22.1760
0.4539	0.9041	66	0.4350	21.7063
0.4046	1.2055	88	0.4113	19.6162
0.3979	1.5068	110	0.3997	19.0090
0.4126	1.8082	132	0.3915	18.1937
0.3756	2.1096	154	0.3871	18.2206
0.3822	2.4110	176	0.3838	17.8414
0.3753	2.7123	198	0.3821	17.2409

greenw0lf/whisper-10hrs-random-seed2025

whisper-10hrs-random-seed2025