Edit model card

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
Downloads last month
10
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for intermezzo672/NHS-pubmedbert-binary

Finetuned
(16)
this model

Collection including intermezzo672/NHS-pubmedbert-binary