learning_rate: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
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: 400
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
1.034	1.0	59	0.4106	0.0113	0.1457
0.3451	2.0	118	0.3813	0.0113	0.1515
0.2836	3.0	177	0.4086	0.0113	0.1441
0.2443	4.0	236	0.4156	0.0113	0.1723
0.204	5.0	295	0.3826	0.0113	0.1654
0.1922	6.0	354	0.4312	0.0113	0.1779
0.186	7.0	413	0.4824	0.0113	0.2273
0.1789	8.0	472	0.4474	0.0113	0.1921
0.143	9.0	531	0.4736	0.0113	0.1903
0.1246	10.0	590	0.4682	0.0113	0.1457
0.1015	11.0	649	0.5285	0.0113	0.1854
0.1041	12.0	708	0.4769	0.0113	0.1795
0.0844	13.0	767	0.5024	0.0113	0.1567
0.0748	14.0	826	0.5189	0.0113	0.1468
0.0696	15.0	885	0.5037	0.0113	0.1678
0.0508	16.0	944	0.5499	0.0113	0.1402
0.0427	17.0	1003	0.5307	0.0113	0.1538
0.0268	18.0	1062	0.5700	0.0113	0.1430
0.0178	19.0	1121	0.5722	0.0113	0.1515
0.011	19.6638	1160	0.5782	0.0113	0.1452

dhaval0108/whisper-large-ce-only

ap-GFar2A5U2x3BasPO59aj8H