PubMedBERT-LitCovid-v1.3.1

sofia-todeschini/PubMedBERT-LitCovid-v1.3.1

PubMedBERT-LitCovid-v1.3.1 is a text classification model from sofia-todeschini. Use it when you need a label for a piece of text. 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

17% of all-time downloads

All-time downloads

Public

Repo size

2.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin438 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Nov 1, 2023
Updated: Nov 2, 2023
SHA: 150b35ca

Try a prompt

Model card

From the Hugging Face model README

PubMedBERT-LitCovid-v1.3.1

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7014
Hamming loss: 0.0168
F1 micro: 0.8565
F1 macro: 0.3886
F1 weighted: 0.8851
F1 samples: 0.8840
Precision micro: 0.7895
Precision macro: 0.3132
Precision weighted: 0.8462
Precision samples: 0.8704
Recall micro: 0.9359
Recall macro: 0.7261
Recall weighted: 0.9359
Recall samples: 0.9449
Roc Auc: 0.9609
Accuracy: 0.7036

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Hamming loss	F1 micro	F1 macro	F1 weighted	F1 samples	Precision micro	Precision macro	Precision weighted	Precision samples	Recall micro	Recall macro	Recall weighted	Recall samples	Roc Auc	Accuracy
1.1393	1.0	2272	0.4732	0.0330	0.7499	0.2762	0.8361	0.8351	0.6321	0.2203	0.7818	0.8088	0.9217	0.7515	0.9217	0.9379	0.9456	0.5912
0.9007	2.0	4544	0.5250	0.0207	0.8267	0.3500	0.8670	0.8660	0.7488	0.2801	0.8287	0.8507	0.9226	0.7377	0.9226	0.9358	0.9525	0.6570
0.7636	3.0	6816	0.5985	0.0180	0.8488	0.3754	0.8781	0.8803	0.7720	0.2994	0.8302	0.8595	0.9426	0.7214	0.9426	0.9516	0.9634	0.6836
0.5932	4.0	9088	0.6243	0.0168	0.8571	0.3900	0.8844	0.8837	0.7892	0.3146	0.8434	0.8689	0.9377	0.7315	0.9377	0.9467	0.9617	0.6996
0.3396	5.0	11360	0.7014	0.0168	0.8565	0.3886	0.8851	0.8840	0.7895	0.3132	0.8462	0.8704	0.9359	0.7261	0.9359	0.9449	0.9609	0.7036

Framework versions

Transformers 4.28.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.13.3

Task: Text Classification
Library: transformers
Type: bert
License: mit
Created: Nov 1, 2023
Updated: Nov 2, 2023