learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 32
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: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Acc
1.2242	1.0	449	0.6769	0.9833	0.5
2.4482	2.0	898	0.7154	0.9833	0.5
0.0054	3.0	1347	0.6086	0.9833	0.5
0.0083	4.0	1796	0.5472	0.9833	0.5
0.0095	5.0	2245	0.5068	0.9833	0.5
0.9129	6.0	2694	0.4756	0.9833	0.5
0.8618	7.0	3143	0.5492	0.9833	0.5
1.624	8.0	3592	0.5120	0.9833	0.5
0.0052	9.0	4041	0.6046	0.9833	0.5
0.0201	10.0	4490	0.4285	0.9833	0.5
0.0109	11.0	4939	0.5213	0.9833	0.5
0.0068	12.0	5388	0.5858	0.9833	0.5
0.8892	13.0	5837	0.5636	0.9833	0.5
0.8009	14.0	6286	0.5437	0.9833	0.5
0.8449	15.0	6735	0.5525	0.9833	0.5

AnonymousCS/populism_classifier_394

populism_classifier_394