Edit model card

biobert-v1.1_pub_section

  • original model file name: textclassifer_biobert-v1.1_pubmed_20k
  • This is a fine-tuned checkpoint of dmis-lab/biobert-v1.1 for document section text classification
  • possible document section classes are:BACKGROUND, CONCLUSIONS, METHODS, OBJECTIVE, RESULTS,

metadata

training_metrics

  • val_accuracy: 0.8522772192955017

  • val_matthewscorrcoef: 0.8009328246116638

  • val_f1score: 0.8517481088638306

  • val_cross_entropy: 0.4344026446342468

  • epoch: 12.0

  • train_accuracy_step: 0.8203125

  • train_matthewscorrcoef_step: 0.7453048229217529

  • train_f1score_step: 0.8245896100997925

  • train_cross_entropy_step: 0.480397492647171

  • train_accuracy_epoch: 0.8297363519668579

  • train_matthewscorrcoef_epoch: 0.7703952193260193

  • train_f1score_epoch: 0.8274592757225037

  • train_cross_entropy_epoch: 0.5001224875450134

  • test_accuracy: 0.8441678881645203

  • test_matthewscorrcoef: 0.7905130982398987

  • test_f1score: 0.8435087203979492

  • test_cross_entropy: 0.4557005763053894

  • date_run: Apr-22-2022_t-14

  • huggingface_tag: dmis-lab/biobert-v1.1

Downloads last month
15
Safetensors
Model size
108M params
Tensor type
I64
·
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.

Dataset used to train ml4pubmed/biobert-v1.1_pub_section