CRAFT_bioBERT_NER

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

CRAFT_bioBERT_NER

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1106

• Seqeval classification report: precision recall f1-score support

   CHEBI       0.83      0.76      0.80      1109
      CL       0.91      0.90      0.90      3871
     GGP       0.76      0.66      0.71       600
      GO       0.87      0.84      0.85      1061
      SO       0.99      0.99      0.99     87954
   Taxon       0.83      0.87      0.85      3104
  

  micro avg 0.98 0.97 0.97 97699 macro avg 0.87 0.84 0.85 97699 weighted avg 0.98 0.97 0.97 97699

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

   CHEBI       0.82      0.65      0.72      1109
      CL       0.90      0.87      0.89      3871
     GGP       0.75      0.62      0.68       600
      GO       0.88      0.77      0.82      1061
      SO       0.99      0.99      0.99     87954
   Taxon       0.79      0.88      0.83      3104

micro avg 0.97 0.97 0.97 97699 macro avg 0.86 0.80 0.82 97699 weighted avg 0.97 0.97 0.97 97699 | | 0.1705 | 2.0 | 695 | 0.1121 | precision recall f1-score support

   CHEBI       0.86      0.73      0.79      1109
      CL       0.90      0.90      0.90      3871
     GGP       0.73      0.65      0.69       600
      GO       0.87      0.82      0.85      1061
      SO       0.99      0.99      0.99     87954
   Taxon       0.79      0.89      0.84      3104

micro avg 0.97 0.97 0.97 97699 macro avg 0.86 0.83 0.84 97699 weighted avg 0.97 0.97 0.97 97699 | | 0.04 | 3.0 | 1041 | 0.1106 | precision recall f1-score support

   CHEBI       0.83      0.76      0.80      1109
      CL       0.91      0.90      0.90      3871
     GGP       0.76      0.66      0.71       600
      GO       0.87      0.84      0.85      1061
      SO       0.99      0.99      0.99     87954
   Taxon       0.83      0.87      0.85      3104

micro avg 0.98 0.97 0.97 97699 macro avg 0.87 0.84 0.85 97699 weighted avg 0.98 0.97 0.97 97699 |

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0