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
0.7017	1.0	8	0.7740	0.0295	0.0573	1.0	0.0295	0.5
0.6096	2.0	16	0.7458	0.0295	0.0573	1.0	0.0295	0.5
0.6461	3.0	24	0.7163	0.0295	0.0573	1.0	0.0295	0.5
0.7868	4.0	32	0.6938	0.0295	0.0573	1.0	0.0295	0.5
0.634	5.0	40	0.6722	0.9705	0.0	0.0	0.0	0.5
0.7419	6.0	48	0.6617	0.9705	0.0	0.0	0.0	0.5
0.8392	7.0	56	0.6498	0.9705	0.0	0.0	0.0	0.5
0.6242	8.0	64	0.6411	0.9705	0.0	0.0	0.0	0.5
0.7454	9.0	72	0.6365	0.9705	0.0	0.0	0.0	0.5
0.6543	10.0	80	0.6324	0.9705	0.0	0.0	0.0	0.5
0.6166	11.0	88	0.6287	0.9705	0.0	0.0	0.0	0.5
0.6474	12.0	96	0.6255	0.9705	0.0	0.0	0.0	0.5
0.742	13.0	104	0.6232	0.9705	0.0	0.0	0.0	0.5
0.5817	14.0	112	0.6223	0.9705	0.0	0.0	0.0	0.5
0.8097	15.0	120	0.6223	0.9705	0.0	0.0	0.0	0.5

AnonymousCS/populism_classifier_bsample_210

populism_classifier_bsample_210