learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	4	3.3199	100.0
6.3947	2.0	8	3.2238	100.0
6.3570	3.0	12	1.7064	100.0
3.6043	4.0	16	0.8654	75.0
1.3034	5.0	20	0.1943	0.0
1.3034	6.0	24	0.0241	0.0
0.1757	7.0	28	0.0071	0.0
0.0055	8.0	32	0.0000	0.0
0.0002	9.0	36	0.0000	0.0
0.0000	10.0	40	0.0000	0.0
0.0000	11.0	44	0.0000	0.0
0.0000	12.0	48	0.0000	0.0
0.0000	13.0	52	0.0000	0.0
0.0000	14.0	56	0.0000	0.0
0.0000	15.0	60	0.0000	0.0
0.0000	16.0	64	0.0000	0.0
0.0000	17.0	68	0.0000	0.0
0.0000	18.0	72	0.0000	0.0
0.0000	19.0	76	0.0000	0.0
0.0000	20.0	80	0.0000	0.0

masumcsepust/whisper-small-alif

whisper-small-alif