metadata

license: mit
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: NHS-pubmedbert-binary
    results: []

NHS-pubmedbert-binary

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

Loss: 0.5861
Accuracy: 0.8246
Precision: 0.8180
Recall: 0.8240
F1: 0.8202

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: 3e-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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0592	1.0	397	0.3980	0.8246	0.8179	0.8220	0.8196
0.0542	2.0	794	0.4714	0.7943	0.7960	0.8064	0.7929
0.6307	3.0	1191	0.5861	0.8246	0.8180	0.8240	0.8202

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2