Roberta_covi19_rumor

This model is a fine-tuned version of adity12345/RoBerta_fnir on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3531
• Accuracy: 0.862
• Auc: 0.916
• Precision: 0.81
• Recall: 0.797
• F1: 0.803
• F1-macro: 0.848
• F1-micro: 0.862
• F1-weighted: 0.861

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision	Recall	F1	F1-macro	F1-micro	F1-weighted
0.6022	0.4329	50	0.4930	0.784	0.827	0.901	0.439	0.59	0.722	0.784	0.76
0.4141	0.8658	100	0.4461	0.792	0.889	0.667	0.824	0.737	0.782	0.792	0.795
0.3643	1.2944	150	0.3464	0.873	0.915	0.89	0.733	0.804	0.855	0.873	0.87
0.3101	1.7273	200	0.3531	0.862	0.916	0.81	0.797	0.803	0.848	0.862	0.861

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4