chintagunta85's picture
update model card README.md
a4ee051
metadata
tags:
  - generated_from_trainer
datasets:
  - bc2gm_corpus
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: electramed-small-BC2GM-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: bc2gm_corpus
          type: bc2gm_corpus
          config: bc2gm_corpus
          split: train
          args: bc2gm_corpus
        metrics:
          - name: Precision
            type: precision
            value: 0.7652071701439906
          - name: Recall
            type: recall
            value: 0.823399209486166
          - name: F1
            type: f1
            value: 0.7932373771989948
          - name: Accuracy
            type: accuracy
            value: 0.9756735092182762

electramed-small-BC2GM-ner

This model is a fine-tuned version of giacomomiolo/electramed_small_scivocab on the bc2gm_corpus dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0720
  • Precision: 0.7652
  • Recall: 0.8234
  • F1: 0.7932
  • Accuracy: 0.9757

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: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.085 1.0 782 0.1112 0.6147 0.7777 0.6867 0.9634
0.0901 2.0 1564 0.0825 0.7141 0.8028 0.7559 0.9720
0.0303 3.0 2346 0.0759 0.7310 0.8049 0.7662 0.9724
0.0037 4.0 3128 0.0735 0.7430 0.8168 0.7781 0.9735
0.0325 5.0 3910 0.0723 0.7571 0.8142 0.7846 0.9748
0.0582 6.0 4692 0.0701 0.7664 0.8144 0.7897 0.9759
0.0073 7.0 5474 0.0701 0.7711 0.8212 0.7953 0.9761
0.1031 8.0 6256 0.0712 0.7602 0.8258 0.7916 0.9756
0.0248 9.0 7038 0.0722 0.7691 0.8231 0.7952 0.9759
0.0136 10.0 7820 0.0720 0.7652 0.8234 0.7932 0.9757

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1