learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 4
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Cer	Validation Loss	Wer
0.0917	0.2531	4200	0.3473	0.0922	0.6812
0.078	0.5063	8400	0.3166	0.0766	0.5952
0.0689	0.7594	12600	0.2966	0.0691	0.5526
0.062	1.0126	16800	0.2926	0.0643	0.5457
0.0583	1.2657	21000	0.2725	0.0611	0.5045
0.0597	1.5189	25200	0.0592	0.5154	0.2810
0.0504	1.7720	29400	0.0577	0.5082	0.2784
0.0481	2.0252	33600	0.0565	0.4934	0.2707
0.049	2.2783	37800	0.0549	0.4839	0.2662
0.0483	2.5315	42000	0.0537	0.4911	0.2712
0.0495	2.7846	46200	0.0528	0.4930	0.2717

Arnold145/transcription_full

transcription_full