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
0.1827	1.0	1321	0.2130	0.9407	0.9371	0.9486	0.9428	[[4246, 308], [249, 4591]]
0.2063	2.0	2642	0.2016	0.9443	0.9415	0.9510	0.9462	[[4268, 286], [237, 4603]]
0.1656	3.0	3963	0.2102	0.9478	0.9473	0.9517	0.9495	[[4298, 256], [234, 4606]]
0.1817	4.0	5284	0.2195	0.9460	0.9483	0.9469	0.9476	[[4304, 250], [257, 4583]]
0.1245	5.0	6605	0.2417	0.9432	0.9459	0.9436	0.9448	[[4293, 261], [273, 4567]]

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

distilbert-fake-news-detector-LLM-stacked