NER-BERT

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

• Loss: 0.0001
• Token Accuracy: 1.0000
• Token Precision: 1.0000
• Token Recall: 1.0000
• Token F1: 1.0000
• Entity Precision: 0.9998
• Entity Recall: 0.9998
• Entity F1: 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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Token Accuracy	Token Precision	Token Recall	Token F1	Entity Precision	Entity Recall	Entity F1
0.0004	1.0	2250	0.0002	1.0000	1.0000	1.0000	1.0000	0.9994	0.9995	0.9995
0.0001	2.0	4500	0.0001	1.0000	1.0000	1.0000	1.0000	0.9998	0.9998	0.9998
0.0001	3.0	6750	0.0001	1.0000	1.0000	1.0000	1.0000	0.9998	0.9998	0.9998

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1