metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - biocreative_gene_mention
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: gene_finetuned
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: biocreative_gene_mention
          type: biocreative_gene_mention
          config: default
          split: validation
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.8389085168758926
          - name: Recall
            type: recall
            value: 0.8737864077669902
          - name: F1
            type: f1
            value: 0.8559923298178332
          - name: Accuracy
            type: accuracy
            value: 0.9581707699896856

gene_finetuned

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the biocreative_gene_mention dataset. It achieves the following results on the evaluation set:

Loss: 0.1217
Precision: 0.8389
Recall: 0.8738
F1: 0.8560
Accuracy: 0.9582

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	157	0.1379	0.7838	0.8403	0.8111	0.9487
No log	2.0	314	0.1188	0.8394	0.8642	0.8516	0.9570
No log	3.0	471	0.1217	0.8389	0.8738	0.8560	0.9582

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.2