Edit model card

Yepes_5e-05_31_03

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: 0.1043
  • Precision: 0.7017
  • Recall: 0.5476
  • F1: 0.6152
  • Accuracy: 0.9834

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.4466 1.92 25 0.1761 0.0 0.0 0.0 0.9704
0.1328 3.85 50 0.1094 0.2957 0.1799 0.2237 0.9747
0.0932 5.77 75 0.0997 0.5656 0.3307 0.4174 0.9793
0.0627 7.69 100 0.0822 0.6353 0.4471 0.5248 0.9822
0.0455 9.62 125 0.0815 0.7116 0.5026 0.5891 0.9838
0.0332 11.54 150 0.0929 0.7302 0.4868 0.5841 0.9829
0.0246 13.46 175 0.0912 0.6894 0.5344 0.6021 0.9826
0.0195 15.38 200 0.1108 0.708 0.4683 0.5637 0.9828
0.0179 17.31 225 0.0881 0.7021 0.5423 0.6119 0.9837
0.0132 19.23 250 0.1011 0.7053 0.5635 0.6265 0.9837
0.0104 21.15 275 0.1043 0.7017 0.5476 0.6152 0.9834

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.1+cu116
  • Datasets 2.11.0
  • Tokenizers 0.13.2
Downloads last month
10