results1

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

• Loss: 0.0207
• Accuracy: 0.9960
• Precision: 0.9960
• Recall: 0.9960
• F1: 0.9960
• Roc Auc: 0.9998

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.0672	0.2202	500	0.0532	0.9832	0.9833	0.9832	0.9832	0.9985
0.0369	0.4403	1000	0.0380	0.9886	0.9886	0.9886	0.9886	0.9992
0.0347	0.6605	1500	0.0298	0.9910	0.9910	0.9910	0.9910	0.9995
0.0382	0.8807	2000	0.0265	0.9922	0.9922	0.9922	0.9922	0.9995
0.0209	1.1008	2500	0.0228	0.9942	0.9942	0.9942	0.9942	0.9997
0.0558	1.3210	3000	0.0245	0.9947	0.9947	0.9947	0.9947	0.9997
0.0184	1.5412	3500	0.0299	0.9931	0.9932	0.9931	0.9931	0.9997
0.0021	1.7613	4000	0.0215	0.9949	0.9949	0.9949	0.9949	0.9998
0.0296	1.9815	4500	0.0250	0.9936	0.9936	0.9936	0.9936	0.9998
0.0012	2.2017	5000	0.0211	0.9955	0.9955	0.9955	0.9955	0.9998
0.0078	2.4218	5500	0.0212	0.9961	0.9961	0.9961	0.9961	0.9998
0.0009	2.6420	6000	0.0239	0.9952	0.9952	0.9952	0.9952	0.9998
0.0105	2.8622	6500	0.0209	0.9956	0.9956	0.9956	0.9956	0.9998

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.21.2