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
0.7144	1.0	13	0.7651	0.0359	0.0693	1.0	0.0359	0.5
0.7109	2.0	26	0.7570	0.0359	0.0693	1.0	0.0359	0.5
0.7222	3.0	39	0.7542	0.0359	0.0693	1.0	0.0359	0.5
0.6849	4.0	52	0.7506	0.0359	0.0693	1.0	0.0359	0.5
0.7012	5.0	65	0.7478	0.0359	0.0693	1.0	0.0359	0.5
0.7035	6.0	78	0.7465	0.0359	0.0693	1.0	0.0359	0.5
0.6665	7.0	91	0.7447	0.0359	0.0693	1.0	0.0359	0.5
0.7684	8.0	104	0.7451	0.0359	0.0693	1.0	0.0359	0.5
0.7179	9.0	117	0.7447	0.0359	0.0693	1.0	0.0359	0.5
0.6673	10.0	130	0.7428	0.0359	0.0693	1.0	0.0359	0.5
0.7015	11.0	143	0.7410	0.0359	0.0693	1.0	0.0359	0.5
0.6969	12.0	156	0.7392	0.0359	0.0693	1.0	0.0359	0.5
0.7305	13.0	169	0.7378	0.0359	0.0693	1.0	0.0359	0.5
0.699	14.0	182	0.7374	0.0359	0.0693	1.0	0.0359	0.5
0.7246	15.0	195	0.7374	0.0359	0.0693	1.0	0.0359	0.5

AnonymousCS/populism_classifier_bsample_187

populism_classifier_bsample_187