learning_rate: 0.001
train_batch_size: 2
eval_batch_size: 8
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: 100
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
9.4884	0.2070	100	2.9621	0.9885
1.9509	0.4141	200	1.6554	0.6431
1.548	0.6211	300	1.6815	0.6276
1.4225	0.8282	400	1.5680	0.6218
1.5012	1.0352	500	1.3856	0.6255
1.5559	1.2422	600	1.5377	0.6050
1.2943	1.4493	700	1.4902	0.5942
1.2103	1.6563	800	1.5580	0.6001
1.3807	1.8634	900	1.4564	0.5954
1.4473	2.0704	1000	1.3519	0.5918
1.2579	2.2774	1100	1.4598	0.5799
1.2094	2.4845	1200	1.4669	0.5760
1.1881	2.6915	1300	1.4301	0.5673
1.3112	2.8986	1400	1.2790	0.5641
1.1826	3.1056	1500	1.3800	0.5652
1.2704	3.3126	1600	1.3190	0.5761
1.063	3.5197	1700	1.2034	0.5587
1.0273	3.7267	1800	1.2164	0.5601
1.1572	3.9337	1900	1.2023	0.5539
1.0812	4.1408	2000	1.2923	0.5538
1.1074	4.3478	2100	1.3394	0.5460
1.0665	4.5549	2200	1.3474	0.5456
1.0396	4.7619	2300	1.3025	0.5480
1.0812	4.9689	2400	1.3110	0.5480

robertp408/wav2vec2-large-mms-1b-aft-aln

wav2vec2-large-mms-1b-aft-aln