Francesco-A
/

bert-finetuned-ner

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

bert-finetuned-ner

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: 0.0592
Precision: 0.9324
Recall: 0.9488
F1: 0.9405
Accuracy: 0.9861

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0774	1.0	1756	0.0764	0.9146	0.9337	0.9241	0.9802
0.0394	2.0	3512	0.0554	0.9265	0.9483	0.9373	0.9860
0.0261	3.0	5268	0.0592	0.9324	0.9488	0.9405	0.9861

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3

Downloads last month: 18

Inference Examples

Token Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Francesco-A/bert-finetuned-ner

Base model

google-bert/bert-base-cased

Finetuned

(2004)

this model

Dataset used to train Francesco-A/bert-finetuned-ner

Evaluation results

Precision on conll2003
validation set self-reported

0.932
Recall on conll2003
validation set self-reported

0.949
F1 on conll2003
validation set self-reported

0.941
Accuracy on conll2003
validation set self-reported

0.986

View on Papers With Code