learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
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: 25
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.27	1.1905	50	1.3918	0.9984	0.4481
0.8981	2.3810	100	1.6118	1.0	0.5281
0.7267	3.5714	150	1.3004	0.9825	0.3741
0.6363	4.7619	200	1.4469	0.9921	0.4690
0.5127	5.9524	250	1.5113	0.9921	0.4688
0.4366	7.1429	300	1.4040	0.9857	0.4185
0.4093	8.3333	350	1.3967	0.9778	0.4013
0.3749	9.5238	400	1.3272	0.9698	0.3684
0.341	10.7143	450	1.3528	0.9778	0.3724
0.2958	11.9048	500	1.3849	0.9762	0.3742
0.2908	13.0952	550	1.4275	0.9778	0.3823
0.2839	14.2857	600	1.3558	0.9762	0.3607
0.2429	15.4762	650	1.4134	0.9698	0.3693
0.2405	16.6667	700	1.5297	0.9810	0.3905
0.2337	17.8571	750	1.4542	0.9778	0.3735
0.2555	19.0476	800	1.5012	0.9746	0.3741
0.2141	20.2381	850	1.5030	0.9778	0.3786

tadgeis/xlsr-1b-ckt-staged-bible-radio-to-chuklang-source-eval-stage2

xlsr-1b-ckt-staged-bible-radio-to-chuklang-source-eval-stage2