learning_rate: 0.0001
train_batch_size: 32
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: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bleu Msl	Ter Msl	Ter Asl
No log	1.0	67	1.0924	16.5734	78.3784	100
No log	2.0	134	0.5283	66.9864	17.2037	100
No log	3.0	201	0.4500	32.7340	24.8960	100
No log	4.0	268	0.4546	64.2241	17.0998	100
No log	5.0	335	0.4371	79.5661	12.3181	100
No log	6.0	402	0.4183	62.3356	12.4740	100
No log	7.0	469	0.4174	78.8409	12.2141	100
0.5741	8.0	536	0.4236	73.4058	13.0977	100
0.5741	9.0	603	0.4365	80.4263	11.6424	100
0.5741	10.0	670	0.4230	78.2192	11.5904	100
0.5741	11.0	737	0.4461	81.5222	11.0187	100
0.5741	12.0	804	0.4361	81.0763	10.8108	100
0.5741	13.0	871	0.4462	80.2271	11.4345	100
0.5741	14.0	938	0.4487	81.2932	10.0832	100
0.0399	15.0	1005	0.4535	82.0574	10.1351	100
0.0399	16.0	1072	0.4561	81.1900	10.7069	100
0.0399	17.0	1139	0.4498	80.5848	10.3430	100
0.0399	18.0	1206	0.4704	81.2086	10.4470	100
0.0399	19.0	1273	0.4780	83.3481	9.7713	100
0.0399	20.0	1340	0.4697	82.5737	9.8753	100
0.0399	21.0	1407	0.4675	82.5187	9.8753	100
0.0399	22.0	1474	0.4678	82.9501	10.0312	100
0.0155	23.0	1541	0.4708	82.3160	9.9792	100
0.0155	24.0	1608	0.4732	82.1759	10.0832	100
0.0155	25.0	1675	0.4777	82.5015	9.8233	100
0.0155	26.0	1742	0.4723	81.7682	10.1351	100
0.0155	27.0	1809	0.4755	82.1104	9.9792	100
0.0155	28.0	1876	0.4763	82.2547	10.1351	100
0.0155	29.0	1943	0.4756	82.2633	10.0832	100
0.01	30.0	2010	0.4761	82.2721	10.0312	100

vania2911/2120mslsamples

2120mslsamples