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
0.6917	1.0	742	0.5995	6.7000
0.6008	2.0	1484	0.5330	8.7480
0.5208	3.0	2226	0.4989	9.7564
0.4962	4.0	2968	0.4808	10.3233
0.46	5.0	3710	0.4711	10.7276
0.4428	6.0	4452	0.4615	10.9196
0.4125	7.0	5194	0.4566	11.2077
0.3955	8.0	5936	0.4515	11.3811
0.3856	9.0	6678	0.4496	11.5736
0.3687	10.0	7420	0.4482	11.5727
0.3553	11.0	8162	0.4496	11.6036
0.3467	12.0	8904	0.4508	11.6907
0.3386	13.0	9646	0.4505	11.7970
0.3324	14.0	10388	0.4510	11.7524
0.3245	15.0	11130	0.4528	11.7921

IAmSkyDra/BARTBana_Translation_v51

BARTBana_Translation_v51