learning_rate: 4e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
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	Precision	Recall	F1	Confusion Matrix
0.2053	1.0	661	0.2131	0.9401	0.9346	0.9502	0.9423	[[4232, 322], [241, 4599]]
0.2106	2.0	1322	0.2036	0.9442	0.9400	0.9525	0.9462	[[4260, 294], [230, 4610]]
0.1403	3.0	1983	0.2086	0.9440	0.9486	0.9424	0.9455	[[4307, 247], [279, 4561]]
0.1672	4.0	2644	0.2071	0.9458	0.9475	0.9473	0.9474	[[4300, 254], [255, 4585]]
0.1152	5.0	3305	0.2228	0.9449	0.9493	0.9434	0.9463	[[4310, 244], [274, 4566]]
0.0964	6.0	3966	0.2541	0.9409	0.9426	0.9428	0.9427	[[4276, 278], [277, 4563]]
0.089	7.0	4627	0.2853	0.9402	0.9416	0.9424	0.9420	[[4271, 283], [279, 4561]]

wildgeese25/distilbert-fake-news-detector-2

distilbert-fake-news-detector-2