learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Bleu	Cer	Wer	F1
0.3907	1.0	782	0.0338	83.8387	0.0343	0.0892	0.9626
0.0355	2.0	1564	0.0240	87.6565	0.0244	0.0669	0.9763
0.0278	3.0	2346	0.0225	88.6311	0.0216	0.0605	0.9804
0.021	4.0	3128	0.0220	88.8898	0.0200	0.0580	0.9821
0.0187	5.0	3910	0.0213	89.3574	0.0196	0.0563	0.9826

pqthinh232/HCMUS-vietnamese-correction-project

HCMUS-vietnamese-correction-project