README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - source_data
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: SourceData_GP-CHEM-ROLES_v_1-0-0_BioLinkBERT_large
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: source_data
          type: source_data
          args: ROLES_MULTI
        metrics:
          - name: Precision
            type: precision
            value: 0.9572859572859573
          - name: Recall
            type: recall
            value: 0.9649457039436083
          - name: F1
            type: f1
            value: 0.9611005692599621

SourceData_GP-CHEM-ROLES_v_1-0-0_BioLinkBERT_large

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

• Loss: 0.0100
• Accuracy Score: 0.9975
• Precision: 0.9573
• Recall: 0.9649
• F1: 0.9611

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: 1.5e-05
• train_batch_size: 32
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adafactor
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Score	Precision	Recall	F1
0.0068	1.0	863	0.0100	0.9975	0.9573	0.9649	0.9611

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0a0+bfe5ad2
• Datasets 2.10.1
• Tokenizers 0.12.1