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
1.2433	1.0	742	0.8630	0.8963
1.0005	2.0	1484	0.8077	1.7612
0.9144	3.0	2226	0.7620	2.8192
0.8945	4.0	2968	0.7246	3.6968
0.8435	5.0	3710	0.6943	4.8346
0.8251	6.0	4452	0.6687	5.5850
0.7872	7.0	5194	0.6513	6.1145
0.7674	8.0	5936	0.6385	6.5998
0.76	9.0	6678	0.6263	7.0741
0.7407	10.0	7420	0.6198	7.3214
0.7301	11.0	8162	0.6100	7.5060
0.7294	12.0	8904	0.6077	7.6978
0.7174	13.0	9646	0.6032	7.8715
0.7131	14.0	10388	0.6020	7.9509
0.7028	15.0	11130	0.6015	7.9382

IAmSkyDra/BARTBana_Translation_v00

BARTBana_Translation_v00