learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
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_steps: 500
training_steps: 3000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.6773	0.0850	100	1.2154	235.3315
1.0178	0.1700	200	0.6814	283.2863
0.4466	0.2550	300	0.2805	92.8068
0.2623	0.3400	400	0.2547	79.3018
0.2228	0.4250	500	0.2125	75.8463
0.1934	0.5100	600	0.1790	72.1086
0.1903	0.5950	700	0.1532	71.7913
0.1488	0.6800	800	0.1339	70.5571
0.137	0.7650	900	0.1205	69.2525
0.1275	0.8500	1000	0.1146	66.2200
0.1158	0.9350	1100	0.1049	66.3258
0.1088	1.0195	1200	0.1017	65.8674
0.0828	1.1045	1300	0.0989	62.3413
0.0716	1.1895	1400	0.0902	61.5656
0.0774	1.2745	1500	0.0867	70.3808
0.0769	1.3595	1600	0.0836	60.1904
0.0676	1.4445	1700	0.0792	58.4626
0.0669	1.5295	1800	0.0778	59.5910
0.0624	1.6145	1900	0.0708	57.8279
0.0585	1.6995	2000	0.0685	57.4753
0.057	1.7845	2100	0.0657	55.9238
0.0587	1.8695	2200	0.0609	57.0169
0.0487	1.9545	2300	0.0593	55.3244
0.0443	2.0391	2400	0.0564	52.7151
0.0287	2.1241	2500	0.0564	60.3315
0.0274	2.2091	2600	0.0554	52.1862
0.0303	2.2941	2700	0.0542	54.1961
0.0315	2.3791	2800	0.0508	52.1157
0.0275	2.4641	2900	0.0493	52.6798
0.0191	2.5491	3000	0.0494	51.4104

tranha1412/whisper-finetuned-v3_4kstep_augment

whisper-finetuned-v3_4kstep_augment