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
0.186	1.0	1321	0.2106	0.9427	0.9441	0.9448	0.9444	[[4283, 271], [267, 4573]]
0.2051	2.0	2642	0.2019	0.9452	0.9411	0.9533	0.9471	[[4265, 289], [226, 4614]]
0.1698	3.0	3963	0.2121	0.9467	0.9456	0.9512	0.9484	[[4289, 265], [236, 4604]]
0.2045	4.0	5284	0.2087	0.9453	0.9463	0.9475	0.9469	[[4294, 260], [254, 4586]]
0.1514	5.0	6605	0.2124	0.9459	0.9472	0.9479	0.9475	[[4298, 256], [252, 4588]]

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

bertweet-fake-news-detector-LLM-stacked