learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use 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: 8
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
2.365	0.4444	20	nan
0.7782	0.8889	40	0.0002
0.0072	1.3333	60	0.0407
0.5034	1.7778	80	0.5761
0.815	2.2222	100	1.7751
0.3767	2.6667	120	0.0539
0.0	3.1111	140	1.4726
0.1596	3.5556	160	0.0963
0.1221	4.0	180	0.0002
0.0001	4.4444	200	0.8061
0.253	4.8889	220	0.0000
0.0859	5.3333	240	0.0000
0.0	5.7778	260	0.7759
0.0001	6.2222	280	0.0000
0.0622	6.6667	300	0.0000
0.1486	7.1111	320	0.1663
0.1506	7.5556	340	nan
0.0003	8.0	360	0.0001

MikeDoes/mmbert-multilingual-20250916-155528

mmbert-multilingual-20250916-155528