bert-base-cased-NER-favsbot

jacquesle/bert-base-cased-NER-favsbot

bert-base-cased-NER-favsbot is a token classification model from jacquesle. 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

2% of all-time downloads

All-time downloads

414

Public

Repo size

1.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin431 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Oct 20, 2022
Updated: Nov 7, 2022
SHA: a29944b3

Try a prompt

Datasets

favsbot

Model card

From the Hugging Face model README

bert-base-cased-NER-favsbot

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

Loss: 0.0992
Precision: 0.8571
Recall: 0.96
F1: 0.9057
Accuracy: 0.9583

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: 1.5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	10	1.7643	0.0	0.0	0.0	0.5694
No log	2.0	20	1.1420	0.0	0.0	0.0	0.5833
No log	3.0	30	0.7946	0.9375	0.6	0.7317	0.8056
No log	4.0	40	0.5625	0.8182	0.72	0.7660	0.8611
No log	5.0	50	0.4217	0.8148	0.88	0.8462	0.9306
No log	6.0	60	0.3082	0.8519	0.92	0.8846	0.9444
No log	7.0	70	0.2386	0.8148	0.88	0.8462	0.9444
No log	8.0	80	0.1965	0.8148	0.88	0.8462	0.9444
No log	9.0	90	0.1626	0.8148	0.88	0.8462	0.9444
No log	10.0	100	0.1465	0.8571	0.96	0.9057	0.9583
No log	11.0	110	0.1314	0.8571	0.96	0.9057	0.9583
No log	12.0	120	0.1215	0.8571	0.96	0.9057	0.9583
No log	13.0	130	0.1160	0.8571	0.96	0.9057	0.9583
No log	14.0	140	0.1104	0.8571	0.96	0.9057	0.9583
No log	15.0	150	0.1050	0.8571	0.96	0.9057	0.9583
No log	16.0	160	0.1012	0.8571	0.96	0.9057	0.9583
No log	17.0	170	0.0997	0.8571	0.96	0.9057	0.9583
No log	18.0	180	0.0997	0.8571	0.96	0.9057	0.9583
No log	19.0	190	0.0995	0.8571	0.96	0.9057	0.9583
No log	20.0	200	0.0992	0.8571	0.96	0.9057	0.9583

Framework versions

Transformers 4.21.1
Pytorch 1.12.1
Datasets 2.6.1
Tokenizers 0.12.1

Task: Token Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Oct 20, 2022
Updated: Nov 7, 2022