stbl_clinical_bert_ft_rs3

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0833
  • F1: 0.9279

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: 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: 12

Training results

Training Loss Epoch Step Validation Loss F1
0.2731 1.0 101 0.1011 0.8363
0.0651 2.0 202 0.0683 0.8909
0.0314 3.0 303 0.0623 0.9063
0.0155 4.0 404 0.0705 0.9067
0.0098 5.0 505 0.0702 0.9176
0.006 6.0 606 0.0755 0.9213
0.0037 7.0 707 0.0797 0.9216
0.0031 8.0 808 0.0783 0.9252
0.0018 9.0 909 0.0818 0.9259
0.0014 10.0 1010 0.0809 0.9271
0.0011 11.0 1111 0.0833 0.9259
0.0009 12.0 1212 0.0833 0.9279

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.1
  • Tokenizers 0.12.1
Downloads last month
14
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.