learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.5178	0.9999	4687	0.2928	0.3004
0.3795	1.9997	9374	0.2649	0.2722
0.2977	2.9995	14061	0.2630	0.2752
0.2195	3.9993	18748	0.2750	0.2650
0.1530	4.9990	23435	0.3107	0.2710
0.0920	5.9988	28122	0.3485	0.2668
0.0606	6.9986	32809	0.4061	0.2776
0.0290	7.9984	37496	0.4569	0.2710
0.0122	8.9982	42183	0.5061	0.2794
0.0072	9.9980	46870	0.5256	0.2764
0.0087	10.0	46880	0.5255	0.2770

karimnaimy/pashto-voice-v2

pashto-voice-v2