NazzX1's picture
End of training
d2142e0 verified
metadata
library_name: transformers
base_model: medicalai/ClinicalBERT
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: section-classification-v2
    results: []

section-classification-v2

This model is a fine-tuned version of medicalai/ClinicalBERT on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9439
  • Accuracy: 0.7473
  • Precision: 0.6549
  • Recall: 0.7473
  • F1: 0.6918

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
No log 1.0 434 1.1859 0.6909 0.6054 0.6909 0.6422
1.2827 2.0 868 1.1446 0.7258 0.6268 0.7258 0.6721
1.1164 3.0 1302 1.0256 0.75 0.6546 0.75 0.6946
1.0728 4.0 1736 0.9982 0.7473 0.6517 0.7473 0.6921
1.0206 5.0 2170 0.9582 0.7446 0.6530 0.7446 0.6891
0.9745 6.0 2604 0.9439 0.7473 0.6549 0.7473 0.6918

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Tokenizers 0.21.1