learning_rate: 0.0001
train_batch_size: 64
eval_batch_size: 32
seed: 42
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: 2176
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Wer	Wer Ortho	Cer
0.5162	0.3444	500	0.5790	51.4221	54.3859	16.3021
0.3936	0.6887	1000	0.4636	40.6877	43.8625	13.3724
0.3192	1.0331	1500	0.4237	37.1166	40.2916	12.2298
0.3004	1.3774	2000	0.4044	35.4258	38.4338	11.7855
0.2904	1.7218	2500	0.3844	34.7824	37.6633	12.3830
0.2073	2.0661	3000	0.3724	32.2113	35.0304	10.6682
0.2124	2.4105	3500	0.3539	30.7883	33.7801	10.2432
0.2079	2.7548	4000	0.3436	30.6876	33.5884	10.0643
0.1405	3.0992	4500	0.3538	29.7492	32.7413	9.9562
0.1498	3.4435	5000	0.3421	29.6484	32.5631	9.7255
0.1566	3.7879	5500	0.3374	29.0830	32.0248	9.5126
0.0981	4.1322	6000	0.3621	29.0041	32.0248	9.7219
0.1059	4.4766	6500	0.3602	28.9169	31.8070	9.4974
0.1109	4.8209	7000	0.3538	28.6338	31.5190	9.4386
0.0685	5.1653	7500	0.3843	28.9487	31.9060	9.4235
0.0752	5.5096	8000	0.3902	28.7436	31.7404	9.4488
0.0777	5.8540	8500	0.3862	28.7363	31.6513	9.5293
0.0435	6.1983	9000	0.4288	29.4597	32.4632	9.8163
0.0473	6.5427	9500	0.4399	29.0994	32.0879	9.5760

ihanif/exp_008b_base_cv24_vanilla_no_aug

exp_008b_base_cv24_vanilla_no_aug