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: 25
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf
2.8387	1.0	196	2.2046	0.6422	15.3476
2.1040	2.0	392	1.9528	1.3720	19.8281
1.8124	3.0	588	1.7823	2.9177	24.4750
1.5736	4.0	784	1.6974	6.5991	28.8474
1.3648	5.0	980	1.6412	5.6960	30.1347
1.2160	6.0	1176	1.6423	9.0882	32.2068
1.0999	7.0	1372	1.6123	9.3129	33.2494
1.0003	8.0	1568	1.6063	10.9129	33.4587
0.9010	9.0	1764	1.5883	10.5600	35.6147
0.8126	10.0	1960	1.5826	13.8346	36.8960
0.7450	11.0	2156	1.5904	10.9749	37.7168
0.6777	12.0	2352	1.6041	14.4225	38.6026
0.6260	13.0	2548	1.5994	14.0511	37.9777
0.5762	14.0	2744	1.6140	15.6413	40.1306
0.5417	15.0	2940	1.6293	14.7248	39.4384
0.4926	16.0	3136	1.6299	15.6485	39.7425
0.4622	17.0	3332	1.6423	15.1540	38.6979
0.4387	18.0	3528	1.6342	15.1172	38.8870
0.4134	19.0	3724	1.6588	14.4538	39.5993
0.3898	20.0	3920	1.6585	14.5759	39.0584
0.3818	21.0	4116	1.6620	14.5808	39.0646
0.3653	22.0	4312	1.6677	14.0915	39.0470
0.3502	23.0	4508	1.6737	14.2037	38.8062
0.3457	24.0	4704	1.6736	14.4161	39.4732
0.3424	25.0	4900	1.6735	14.5937	39.3821

thunderboltc/marianmt_sanlish_to_bangla_1934_lr2_duijonChara

marianmt_sanlish_to_bangla_1934_lr2_duijonChara