learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
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
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Sacrebleu
0.695	1.0	742	0.6021	6.3321
0.5976	2.0	1484	0.5291	8.6429
0.5171	3.0	2226	0.4958	9.7101
0.4919	4.0	2968	0.4781	10.3323
0.4556	5.0	3710	0.4680	10.7812
0.4387	6.0	4452	0.4577	10.8965
0.4095	7.0	5194	0.4538	11.1963
0.3924	8.0	5936	0.4499	11.2119
0.3815	9.0	6678	0.4486	11.4155
0.3647	10.0	7420	0.4468	11.4443
0.3525	11.0	8162	0.4479	11.5941
0.3435	12.0	8904	0.4489	11.5933
0.3349	13.0	9646	0.4500	11.7211
0.3289	14.0	10388	0.4508	11.7113
0.3202	15.0	11130	0.4520	11.7352

IAmSkyDra/BARTBana_Translation_v2

BARTBana_Translation_v2