learning_rate: 1e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use 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_ratio: 0.06
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.5448	1.0	8	1.0716	0.0295	0.0573	1.0	0.0295	0.5
0.8134	2.0	16	1.0558	0.0295	0.0573	1.0	0.0295	0.5
0.8261	3.0	24	1.0399	0.0295	0.0573	1.0	0.0295	0.5
0.9282	4.0	32	1.0228	0.0295	0.0573	1.0	0.0295	0.5
0.5454	5.0	40	1.0064	0.0295	0.0573	1.0	0.0295	0.5
0.9706	6.0	48	0.9933	0.0295	0.0573	1.0	0.0295	0.5
0.6615	7.0	56	0.9817	0.0295	0.0573	1.0	0.0295	0.5
0.5593	8.0	64	0.9710	0.0295	0.0573	1.0	0.0295	0.5
0.8249	9.0	72	0.9636	0.0295	0.0573	1.0	0.0295	0.5
0.9571	10.0	80	0.9570	0.0295	0.0573	1.0	0.0295	0.5
1.001	11.0	88	0.9510	0.0295	0.0573	1.0	0.0295	0.5
0.9016	12.0	96	0.9473	0.0295	0.0573	1.0	0.0295	0.5
0.8054	13.0	104	0.9450	0.0295	0.0573	1.0	0.0295	0.5
0.6523	14.0	112	0.9436	0.0295	0.0573	1.0	0.0295	0.5
0.6263	15.0	120	0.9426	0.0295	0.0573	1.0	0.0295	0.5

AnonymousCS/populism_classifier_bsample_184

populism_classifier_bsample_184