PubMedBERT_JNLPBA_NER

judithrosell/PubMedBERT_JNLPBA_NER

PubMedBERT_JNLPBA_NER is a token classification model from judithrosell. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

109M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors436 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Dec 23, 2023
Updated: Dec 24, 2023
SHA: 5035cf11

Try a prompt

Base models

Model card

From the Hugging Face model README

PubMedBERT_JNLPBA_NER

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1449
Precision: 0.9556
Recall: 0.9503
F1: 0.9529
Accuracy: 0.9508

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
0.2769	1.0	582	0.1556	0.9519	0.9473	0.9496	0.9472
0.1456	2.0	1164	0.1493	0.9551	0.9488	0.9519	0.9495
0.1291	3.0	1746	0.1449	0.9556	0.9503	0.9529	0.9508

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.0
Tokenizers 0.15.0

Task: Token Classification
Library: transformers
Type: bert
License: mit
Created: Dec 23, 2023
Updated: Dec 24, 2023