ninaa510's picture
Update README.md
f887081 verified
|
raw
history blame
2.37 kB
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
  - medical
base_model: distilbert/distilbert-base-cased
model-index:
  - name: distilbert-finetuned-medical-diagnosis
    results:
      - task:
          type: text-classification
          name: Text classification
        dataset:
          type: ninaa510/diagnosis-text
          name: Symptoms and diseases for classification
          split: test
        metrics:
          - type: accuracy
            value: 58.68
            name: Accuracy
datasets:
  - ninaa510/diagnosis-text
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-classification
widget:
  - text: >-
      I have had a persistent cough for the last three days. The cough sometimes
      includes blood. I am also suffering from fatigue and  a loss of appetite.

distilbert-finetuned-medical-diagnosis

This model is a fine-tuned version of distilbert/distilbert-base-cased on the dataset here.

It achieves an accuracy of 58.68% on the test set of the dataset.

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:

  • optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': 1.0, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1663, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Framework versions

  • Transformers 4.41.0
  • TensorFlow 2.15.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1