roberta-fake-news-detector-TEST2

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2059
• Accuracy: 0.9455
• Precision: 0.9488
• Recall: 0.9457
• F1: 0.9472
• Confusion Matrix: [[18379, 1063], [1130, 19688]]

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Confusion Matrix
0.2058	1.0	661	0.2244	0.9373	0.9356	0.9432	0.9394	[[4240, 314], [275, 4565]]
0.2149	2.0	1322	0.2037	0.9435	0.9429	0.9477	0.9453	[[4276, 278], [253, 4587]]
0.1552	3.0	1983	0.2065	0.9452	0.9487	0.9446	0.9467	[[4307, 247], [268, 4572]]
0.1791	3.9947	2640	0.2030	0.9462	0.9489	0.9467	0.9478	[[4307, 247], [258, 4582]]

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1
• Datasets 3.5.0
• Tokenizers 0.21.1