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
2.8256	1.0	196	2.0909	15.1069	26.5352
2.0816	2.0	392	1.8137	11.4787	23.8366
1.7841	3.0	588	1.6477	20.4124	48.0147
1.5486	4.0	784	1.5554	25.4066	46.6072
1.3411	5.0	980	1.5086	25.4066	43.2104
1.1955	6.0	1176	1.5009	35.3553	47.3758
1.0821	7.0	1372	1.4746	35.3553	50.4288
0.9838	8.0	1568	1.4638	35.3553	50.4288
0.8870	9.0	1764	1.4497	17.9652	57.7094
0.7993	10.0	1960	1.4479	17.9652	57.7094
0.7311	11.0	2156	1.4527	50.8133	68.3656
0.6652	12.0	2352	1.4618	50.8133	68.3656
0.6177	13.0	2548	1.4612	50.8133	75.7976
0.5655	14.0	2744	1.4740	50.8133	75.7976
0.5311	15.0	2940	1.4883	50.8133	68.3656
0.4830	16.0	3136	1.4928	50.8133	68.3656
0.4528	17.0	3332	1.5003	50.8133	68.3656
0.4296	18.0	3528	1.4984	50.8133	67.0024
0.4063	19.0	3724	1.5172	50.8133	67.0024
0.3840	20.0	3920	1.5165	50.8133	67.0024
0.3761	21.0	4116	1.5189	50.8133	67.0024
0.3571	22.0	4312	1.5259	50.8133	67.0024
0.3429	23.0	4508	1.5270	53.7285	73.2557
0.3399	24.0	4704	1.5288	53.7285	73.2557
0.3366	25.0	4900	1.5286	53.7285	73.2557

thunderboltc/marianmt_sanlish_to_bangla_1934_lr2

marianmt_sanlish_to_bangla_1934_lr2