drAbreu's picture
End of training
c27c75d verified
metadata
library_name: transformers
license: apache-2.0
base_model: michiyasunaga/BioLinkBERT-large
tags:
  - generated_from_trainer
datasets:
  - source_data
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: SourceData_NER_v1_0_0_BioLinkBERT_large
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: source_data
          type: source_data
          config: NER
          split: validation
          args: NER
        metrics:
          - name: Precision
            type: precision
            value: 0.822425590865203
          - name: Recall
            type: recall
            value: 0.8583257878902941
          - name: F1
            type: f1
            value: 0.8399922822412943

SourceData_NER_v1_0_0_BioLinkBERT_large

This model is a fine-tuned version of michiyasunaga/BioLinkBERT-large on the source_data dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1324
  • Accuracy Score: 0.9585
  • Precision: 0.8224
  • Recall: 0.8583
  • F1: 0.8400

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Use adafactor and the args are: No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 2.0

Training results

Training Loss Epoch Step Validation Loss Accuracy Score Precision Recall F1
0.1047 0.9994 863 0.1295 0.9563 0.8179 0.8437 0.8306
0.0747 1.9988 1726 0.1324 0.9585 0.8224 0.8583 0.8400

Framework versions

  • Transformers 4.46.3
  • Pytorch 1.13.1+cu117
  • Datasets 3.1.0
  • Tokenizers 0.20.3