learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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_ratio: 0.3
num_epochs: 12
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Lr
1.2755	1.0	251	1.0659	71.4900	45.8103	0.0001
0.8309	2.0	502	0.7274	63.6103	44.2868	0.0002
0.5827	3.0	753	0.5902	56.1605	38.9283	0.0002
0.3714	4.0	1004	0.5072	53.2951	38.7444	0.0003
0.1876	5.0	1255	0.4535	46.2751	32.8080	0.0003
0.1278	6.0	1506	0.3975	44.8424	33.0444	0.0002
0.0562	7.0	1757	0.3698	36.1032	26.3987	0.0002
0.0209	8.0	2008	0.4188	56.3037	46.4145	0.0001
0.0123	9.0	2259	0.3916	40.8309	29.8398	0.0001
0.005	10.0	2510	0.3819	41.5473	30.4965	0.0001
0.0031	11.0	2761	0.3779	41.8338	30.7591	0.0000
0.0018	12.0	3012	0.3776	41.2607	30.2338	0.0000

miosipof/asr2_medium_v0.7

Whisper Medium