premsa's picture
Update README.md
a3d9828 verified
metadata
license: apache-2.0

model base: https://huggingface.co/google-bert/bert-base-uncased

dataset: https://github.com/ramybaly/Article-Bias-Prediction

training parameters:

  • batch_size: 100
  • epochs: 5
  • dropout: 0.05
  • max_length: 512
  • learning_rate: 3e-5
  • warmup_steps: 100
  • random_state: 239

training methodology:

  • sanitize dataset following specific rule-set, utilize random split as provided in the dataset
  • train on train split and evaluate on validation split in each epoch
  • evaluate test split only on the model that performed best on validation loss

result summary:

  • throughout the five training epochs, model of second epoch achieved the lowest validation loss of 0.3314
  • on test split second epoch model achieved f1 score of 0.9041

usage:

from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer


def main(repository: str):

    model = AutoModelForSequenceClassification.from_pretrained(repository)

    tokenizer = AutoTokenizer.from_pretrained(repository)

    nlp = pipeline("text-classification", model=model, tokenizer=tokenizer)

    print(nlp("the masses are controlled by media."))

if __name__ == "__main__":
    main(repository="premsa/political-bias-prediction-allsides-BERT")