learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
lr_scheduler_warmup_steps: 10
num_epochs: 6
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Chrf++	Bleu
3.453	0.4639	90	1.4171	31.5406	0.0619
0.7793	0.9278	180	1.2463	36.7296	0.0912
0.5573	1.3918	270	1.2096	38.6167	0.1059
0.506	1.8557	360	1.1481	39.9577	0.1186
0.3964	2.3196	450	1.1479	40.8569	0.1258
0.3543	2.7835	540	1.1372	41.3424	0.1261
0.2886	3.2474	630	1.1387	42.2531	0.1352
0.2554	3.7113	720	1.1344	42.0227	0.1348
0.2321	4.1753	810	1.1319	42.2876	0.1360
0.1921	4.6392	900	1.1365	42.7091	0.1374
0.1856	5.1031	990	1.1437	42.5069	0.1374
0.1533	5.5670	1080	1.1425	42.9292	0.1388

alinatl/m2m100-ky-en

m2m100-ky-en