learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Confusion Matrix
0.1755	1.0	1321	0.2020	0.9442	0.9411	0.9512	0.9462	[[4266, 288], [236, 4604]]
0.19	2.0	2642	0.2028	0.9466	0.9430	0.9539	0.9484	[[4275, 279], [223, 4617]]
0.1548	3.0	3963	0.2152	0.9465	0.9491	0.9469	0.9480	[[4308, 246], [257, 4583]]
0.1679	4.0	5284	0.2194	0.9452	0.9467	0.9469	0.9468	[[4296, 258], [257, 4583]]
0.1216	5.0	6605	0.2489	0.9438	0.9466	0.9442	0.9454	[[4296, 258], [270, 4570]]

wildgeese25/bert-fake-news-detector-LLM-stacked

bert-fake-news-detector-LLM-stacked