learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 300
num_epochs: 100
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
3.6561	6.25	100	3.1439	1.0	0.9246
5.5678	12.5	200	4.0590	1.1777	0.7807
5.583	18.75	300	4.0602	1.1533	0.7807
5.2971	25.0	400	4.0607	1.1498	0.7845
5.6771	31.25	500	4.0620	1.1568	0.7791
0.0	37.5	600	nan	1.0	1.0
0.0	43.75	700	nan	1.0	1.0
0.0	50.0	800	nan	1.0	1.0
0.0	56.25	900	nan	1.0	1.0
0.0	62.5	1000	nan	1.0	1.0
0.0	68.75	1100	nan	1.0	1.0
0.0	75.0	1200	nan	1.0	1.0
0.0	81.25	1300	nan	1.0	1.0
0.0	87.5	1400	nan	1.0	1.0
0.0	93.75	1500	nan	1.0	1.0
0.0	100.0	1600	nan	1.0	1.0

aconeil/w2v-bert-2.0-lmk_man_align_updated

w2v-bert-2.0-lmk_man_align_updated