bert-finetuned-ner

pnr-svc/bert-finetuned-ner

bert-finetuned-ner is a token classification model from pnr-svc. 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

6% of all-time downloads

All-time downloads

425

Public

Parameters

12.3M

3.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin440 MB · 89%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: albert
Access: Public
Created: Sep 17, 2022
Updated: Sep 26, 2024
SHA: de7d1711

Try a prompt

Base models

albert/albert-base-v1

Model card

From the Hugging Face model README

bert-finetuned-ner

This model is a fine-tuned version of albert/albert-base-v1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0994
Precision: 0.9628
Recall: 0.9740
F1: 0.9683
Accuracy: 0.9813

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
0.0688	1.0	5285	0.1227	0.9555	0.9670	0.9612	0.9769
0.0583	2.0	10570	0.1051	0.9581	0.9723	0.9652	0.9803
0.0798	3.0	15855	0.0994	0.9628	0.9740	0.9683	0.9813

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

Task: Token Classification
Library: transformers
Type: albert
License: apache-2.0
Created: Sep 17, 2022
Updated: Sep 26, 2024