bert-finetuned-ner-model

This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0645
• Precision: 0.9352
• Recall: 0.9492
• F1: 0.9421
• Accuracy: 0.9862

Intended uses & limitations

Educational purposes on the safety of LLMs

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0764	1.0	1756	0.0713	0.9011	0.9310	0.9158	0.9810
0.0357	2.0	3512	0.0743	0.9291	0.9414	0.9352	0.9841
0.0213	3.0	5268	0.0645	0.9352	0.9492	0.9421	0.9862

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cpu
• Datasets 3.2.0
• Tokenizers 0.21.0