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	38	0.9078
No log	2.0	76	0.7170
No log	3.0	114	0.6119
No log	4.0	152	0.5992
No log	5.0	190	0.6054
No log	6.0	228	0.6054
No log	7.0	266	0.6149
No log	8.0	304	0.6246
No log	9.0	342	0.6371
No log	10.0	380	0.6388
No log	11.0	418	0.6509
No log	12.0	456	0.6504
No log	13.0	494	0.6649
1.0558	14.0	532	0.6664
1.0558	15.0	570	0.6669

AnLeDinhMinh/vi-formal-converter

vi-formal-converter