learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer
0.698	1.0	1114	0.4865	14.7030
0.5294	2.0	2228	0.3672	13.2286
0.3749	3.0	3342	0.3083	12.6513
0.3479	4.0	4456	0.2905	12.6933
0.2457	5.0	5570	0.2796	11.9239
0.2168	6.0	6684	0.2719	11.9318
0.2455	7.0	7798	0.2724	11.4557
0.2279	8.0	8912	0.2631	11.1006
0.2242	9.0	10026	0.2637	10.9585
0.1664	10.0	11140	0.2613	10.9862