Roberta_feverous

This model is a fine-tuned version of adity12345/RoBerta_covi19_rumor on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6168
• Accuracy: 0.674
• Auc: 0.67
• Precision: 0.677
• Recall: 0.897
• F1: 0.771
• F1-macro: 0.6
• F1-micro: 0.674
• F1-weighted: 0.639

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
0.6385	0.2896	500	0.6240	0.666	0.646	0.656	0.96	0.779	0.546	0.666	0.599
0.6294	0.5793	1000	0.6270	0.665	0.652	0.673	0.885	0.764	0.593	0.665	0.632
0.627	0.8689	1500	0.6192	0.669	0.658	0.674	0.891	0.768	0.595	0.669	0.634
0.6126	1.1581	2000	0.6185	0.674	0.662	0.665	0.945	0.781	0.573	0.674	0.621
0.6044	1.4478	2500	0.6155	0.673	0.665	0.669	0.927	0.777	0.582	0.673	0.627
0.5942	1.7374	3000	0.6168	0.674	0.67	0.677	0.897	0.771	0.6	0.674	0.639

Framework versions

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