learning_rate: 1e-05
train_batch_size: 128
eval_batch_size: 128
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: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.601	1.0	5	0.6534	0.6692	0.0	0.0	0.0	0.5
0.6427	2.0	10	0.6305	0.6692	0.0	0.0	0.0	0.5
0.6068	3.0	15	0.6400	0.6692	0.0	0.0	0.0	0.5
0.7139	4.0	20	0.6143	0.6692	0.0	0.0	0.0	0.5
0.5395	5.0	25	0.5969	0.6692	0.0	0.0	0.0	0.5
0.5974	6.0	30	0.5701	0.7	0.1702	0.0930	1.0	0.5465
0.5214	7.0	35	0.5203	0.8077	0.5902	0.4186	1.0	0.7093
0.4061	8.0	40	0.4794	0.8615	0.7429	0.6047	0.9630	0.7966
0.4453	9.0	45	0.4435	0.8692	0.7671	0.6512	0.9333	0.8141
0.3981	10.0	50	0.4033	0.8692	0.7848	0.7209	0.8611	0.8317
0.4108	11.0	55	0.3717	0.8923	0.8205	0.7442	0.9143	0.8549
0.226	12.0	60	0.3681	0.8769	0.8049	0.7674	0.8462	0.8492
0.3163	13.0	65	0.3546	0.8846	0.8148	0.7674	0.8684	0.8550
0.2189	14.0	70	0.3438	0.8923	0.8205	0.7442	0.9143	0.8549
0.2799	15.0	75	0.3429	0.9	0.8354	0.7674	0.9167	0.8665

AnonymousCS/xlmr_all_immigration4

xlmr_all_immigration4