tellowit/rubert-fake-news-classification

final

This model is a fine-tuned version of DeepPavlov/rubert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3717
• Accuracy: 0.8602
• Precision: 0.8165
• Recall: 0.8809
• F1-score: 0.8475

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1-score
0.6229	1.0	676	0.3717	0.8602	0.8165	0.8809	0.8475

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0