learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 48
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: cosine
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Sacrebleu
0.319	1.6476	5000	0.1981	0.0058	38.1039
0.1877	3.2949	10000	0.1761	0.0058	38.5248
0.1452	4.9425	15000	0.1700	0.0058	38.8388
0.1157	6.5899	20000	0.1703	0.0058	38.8842
0.0977	8.2373	25000	0.1752	0.0058	38.9902
0.0827	9.8848	30000	0.1765	0.0058	39.0245
0.0713	11.5322	35000	0.1865	0.0058	39.0606
0.0636	13.1796	40000	0.1902	0.0058	39.1080
0.0574	14.8272	45000	0.1944	0.0058	39.1167
0.0533	16.4745	50000	0.1978	0.0058	39.1640
0.0513	18.1219	55000	0.1980	0.0058	39.1460
0.0501	19.7695	60000	0.1986	0.0058	39.1743

hoanghaiduong/vit5-correction

vit5-correction