bert-finetuned-ner-conll2003

jeferal/bert-finetuned-ner-conll2003

bert-finetuned-ner-conll2003 is a token classification model from jeferal. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

23% of all-time downloads

All-time downloads

Public

Parameters

108M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors862 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Dec 28, 2025
Updated: Jan 2, 2026
SHA: 760041dc

Try a prompt

Base models

Datasets

conll2003

Model card

From the Hugging Face model README

bert-finetuned-ner-conll2003

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: 0.1660
Model Preparation Time: 0.0018
Precision: 0.9072
Recall: 0.9210
F1: 0.9141
Accuracy: 0.9830

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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Precision	Recall	F1	Accuracy
0.0622	1.0	878	0.0559	0.0018	0.9014	0.9159	0.9086	0.9852
0.0373	2.0	1756	0.0444	0.0018	0.9434	0.9423	0.9428	0.9898
0.0162	3.0	2634	0.0386	0.0018	0.9462	0.9498	0.9480	0.9910
0.0107	4.0	3512	0.0397	0.0018	0.9437	0.9537	0.9487	0.9915
0.0065	5.0	4390	0.0423	0.0018	0.9509	0.9573	0.9540	0.9918
0.0044	6.0	5268	0.0481	0.0018	0.9505	0.9541	0.9523	0.9917
0.0022	7.0	6146	0.0489	0.0018	0.9493	0.9552	0.9523	0.9918
0.0015	8.0	7024	0.0509	0.0018	0.9490	0.9576	0.9533	0.9919
0.0008	9.0	7902	0.0527	0.0018	0.9512	0.9583	0.9547	0.9921
0.0004	10.0	8780	0.0535	0.0018	0.9515	0.9573	0.9544	0.9920

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.22.1

Task: Token Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Dec 28, 2025
Updated: Jan 2, 2026