results

• Loss: 0.2443
• Classification Report: precision recall f1-score support
  ALLERGY 0.84 0.94 0.89 17
  ASSESSMENT 0.00 0.00 0.00 10 CC 0.47 0.36 0.41 22 DIAGNOSIS 0.00 0.00 0.00 6 DISPOSITION 0.00 0.00 0.00 4 EDCOURSE 0.00 0.00 0.00 2 EXAM 0.00 0.00 0.00 8 FAM/SOCHX 0.87 0.97 0.92 98 GENHX 0.76 0.92 0.83 75 IMAGING 0.00 0.00 0.00 3 IMMUNIZATIONS 0.00 0.00 0.00 3 LABS 0.00 0.00 0.00 1 MEDICATIONS 0.73 0.94 0.82 17 OTHER_HISTORY 0.00 0.00 0.00 3 PASTMEDICALHX 0.59 0.78 0.67 37 PASTSURGICAL 0.73 0.79 0.76 14 PLAN 0.00 0.00 0.00 5 PROCEDURES 0.00 0.00 0.00 2 ROS 0.35 0.43 0.39 14
  accuracy 0.73 341 macro avg 0.28 0.32 0.30 341 weighted avg 0.63 0.73 0.68 341

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

 accuracy                           0.70       341
macro avg       0.27      0.30      0.28       341

 accuracy                           0.73       341
macro avg       0.28      0.32      0.30       341

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0