nercomlower-bert-base-spanish-wwm-cased

simonestradasch/nercomlower-bert-base-spanish-wwm-cased

nercomlower-bert-base-spanish-wwm-cased is a token classification model from simonestradasch. 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

4% of all-time downloads

All-time downloads

280

Public

Parameters

109M

437 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

simonestradasch/NERcomp2lower

Model card

From the Hugging Face model README

nercomlower-bert-base-spanish-wwm-cased

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the simonestradasch/NERcomp2lower dataset. It achieves the following results on the evaluation set:

Loss: 0.2448
Body Part Precision: 0.7140
Body Part Recall: 0.7676
Body Part F1: 0.7398
Body Part Number: 413
Disease Precision: 0.7505
Disease Recall: 0.7805
Disease F1: 0.7652
Disease Number: 975
Family Member Precision: 0.875
Family Member Recall: 0.9333
Family Member F1: 0.9032
Family Member Number: 30
Medication Precision: 0.8764
Medication Recall: 0.8387
Medication F1: 0.8571
Medication Number: 93
Procedure Precision: 0.6571
Procedure Recall: 0.6656
Procedure F1: 0.6613
Procedure Number: 311
Overall Precision: 0.7344
Overall Recall: 0.7634
Overall F1: 0.7487
Overall Accuracy: 0.9277

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
0.355	1.0	1004	0.2520	0.7073	0.8015	0.7514	413	0.7485	0.7477	0.7481	975	0.8710	0.9	0.8852	30	0.7196	0.8280	0.77	93	0.5804	0.6270	0.6028	311	0.7093	0.7459	0.7271	0.9219
0.1869	2.0	2008	0.2448	0.7140	0.7676	0.7398	413	0.7505	0.7805	0.7652	975	0.875	0.9333	0.9032	30	0.8764	0.8387	0.8571	93	0.6571	0.6656	0.6613	311	0.7344	0.7634	0.7487	0.9277

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