learning_rate: 2e-05
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
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.312	1.0	880	0.2660	0.8628	0.8288	0.8250	0.8326
0.2394	2.0	1760	0.2517	0.8733	0.8480	0.8131	0.8860
0.1871	3.0	2640	0.3012	0.8631	0.8397	0.7878	0.8989
0.1306	4.0	3520	0.4620	0.8781	0.8467	0.8495	0.8440
0.0825	5.0	4400	0.6897	0.8702	0.8400	0.8259	0.8547
0.0446	6.0	5280	0.7798	0.8696	0.8410	0.8186	0.8647
0.0267	7.0	6160	0.8386	0.8696	0.8314	0.8582	0.8063
0.0156	8.0	7040	0.9764	0.8696	0.8359	0.8392	0.8326
0.0134	9.0	7920	1.0167	0.8705	0.8369	0.8405	0.8333
0.0063	10.0	8800	1.0331	0.8722	0.8386	0.8447	0.8326

ilhamiuturkkan/fake-news-model-22000-samples

fake-news-model-22000-samples