nominal-groups-recognition-bert-base-spanish-wwm-uncased

ALazcanoG/nominal-groups-recognition-bert-base-spanish-wwm-uncased

nominal-groups-recognition-bert-base-spanish-wwm-uncased is a token classification model from ALazcanoG. Use it when you need labels on individual words, such as names. It is set up for transformers.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

292

Public

Parameters

109M

874 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors437 MB · 100%

Parameter types

How the weights are stored.

F32109M · 100%

Try a prompt

Datasets

ALazcanoG/spanish_nominal_groups_conll2003

Model card

From the Hugging Face model README

nominal-groups-recognition-bert-base-spanish-wwm-uncased

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-uncased on the ALazcanoG/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set:

Loss: 0.2519
Body Part Precision: 0.6984
Body Part Recall: 0.7711
Body Part F1: 0.7329
Body Part Number: 1066
Disease Precision: 0.7230
Disease Recall: 0.7923
Disease F1: 0.7561
Disease Number: 2725
Family Member Precision: 0.9592
Family Member Recall: 0.8246
Family Member F1: 0.8868
Family Member Number: 57
Medication Precision: 0.7593
Medication Recall: 0.7625
Medication F1: 0.7609
Medication Number: 240
Procedure Precision: 0.5439
Procedure Recall: 0.6389
Procedure F1: 0.5876
Procedure Number: 853
Overall Precision: 0.6885
Overall Recall: 0.7602
Overall F1: 0.7226
Overall Accuracy: 0.9230

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: 13
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Body Part Precision	Body Part Recall	Body Part F1	Body Part Number	Disease Precision	Disease Recall	Disease F1	Disease Number	Family Member Precision	Family Member Recall	Family Member F1	Family Member Number	Medication Precision	Medication Recall	Medication F1	Medication Number	Procedure Precision	Procedure Recall	Procedure F1	Procedure Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.4144	1.0	703	0.2530	0.6907	0.6998	0.6952	1066	0.7309	0.7394	0.7351	2725	0.9565	0.7719	0.8544	57	0.7798	0.7083	0.7424	240	0.5502	0.5651	0.5575	853	0.6946	0.6997	0.6971	0.9199
0.2118	2.0	1406	0.2519	0.6984	0.7711	0.7329	1066	0.7230	0.7923	0.7561	2725	0.9592	0.8246	0.8868	57	0.7593	0.7625	0.7609	240	0.5439	0.6389	0.5876	853	0.6885	0.7602	0.7226	0.9230

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: bert
Languages: es
Created: Jul 11, 2023
Updated: Jul 11, 2023