Hugging Face's logo

judithrosell
/
PubMedBERT_BC5CDR_NER_new

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
PubMedBERT_BC5CDR_NER_new / README.md
judithrosell's picture
judithrosell
End of training
5502b0c
preview code
|
raw
history blame contribute delete
1.85 kB
metadata
license: mit
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: PubMedBERT_BC5CDR_NER_new
    results: []

PubMedBERT_BC5CDR_NER_new

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0805
  • Precision: 0.9857
  • Recall: 0.9821
  • F1: 0.9839
  • Accuracy: 0.9769

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
  • 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 1.0 286 0.0837 0.9831 0.9782 0.9806 0.9725
0.126 2.0 572 0.0824 0.9847 0.9784 0.9815 0.9740
0.126 3.0 858 0.0805 0.9857 0.9821 0.9839 0.9769

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0