learning_rate: 2e-05
train_batch_size: 8
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
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
No log	1.0	53	0.8522
No log	2.0	106	0.6620
No log	3.0	159	0.6353
No log	4.0	212	0.6090
No log	5.0	265	0.6088
No log	6.0	318	0.6000
No log	7.0	371	0.6113
No log	8.0	424	0.6093
No log	9.0	477	0.6166
1.1074	10.0	530	0.6211
1.1074	11.0	583	0.6321
1.1074	12.0	636	0.6382
1.1074	13.0	689	0.6455
1.1074	14.0	742	0.6477
1.1074	15.0	795	0.6485

AnLeDinhMinh/vi-formal-converter-v1.2

vi-formal-converter-v1.2