Edit model card

bluebert-pubmed-uncased-L-12-H-768-A-12_pub_section

  • original model file name: textclassifer_bluebert_pubmed_uncased_L-12_H-768_A-12_pubmed_20k
  • This is a fine-tuned checkpoint of bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12 for document section text classification
  • possible document section classes are:BACKGROUND, CONCLUSIONS, METHODS, OBJECTIVE, RESULTS,

metadata

training_metrics

  • val_accuracy: 0.8367536067962646

  • val_matthewscorrcoef: 0.779039740562439

  • val_f1score: 0.834040641784668

  • val_cross_entropy: 0.5102494359016418

  • epoch: 18.0

  • train_accuracy_step: 0.7890625

  • train_matthewscorrcoef_step: 0.7113237380981445

  • train_f1score_step: 0.7884777784347534

  • train_cross_entropy_step: 0.5615811944007874

  • train_accuracy_epoch: 0.7955580949783325

  • train_matthewscorrcoef_epoch: 0.7233519554138184

  • train_f1score_epoch: 0.7916122078895569

  • train_cross_entropy_epoch: 0.6050205230712891

  • test_accuracy: 0.8310602307319641

  • test_matthewscorrcoef: 0.7718994617462158

  • test_f1score: 0.8283351063728333

  • test_cross_entropy: 0.5230290293693542

  • date_run: Apr-22-2022_t-05

  • huggingface_tag: bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12

Downloads last month
4
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/bluebert-pubmed-uncased-L-12-H-768-A-12_pub_section