Bert Large Finetuned Squad2

🚀 bert-large-finetuned-squad2

This model is based on BERT and fine-tuned on the SQuAD2.0 dataset, designed for question-answering tasks.

🚀 Quick Start

This model is based on bert-large-uncased and was finetuned on SQuAD2.0. The corresponding papers you can found here (model) and here (data).

✨ Features

• Tags: pytorch, question-answering
• Datasets: squad2
• Metrics: exact, f1

💻 Usage Examples

Basic Usage

from transformers.pipelines import pipeline

model_name = "phiyodr/bert-large-finetuned-squad2"
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
inputs = {
    'question': 'What discipline did Winkelmann create?',
    'context': 'Johann Joachim Winckelmann was a German art historian and archaeologist. He was a pioneering Hellenist who first articulated the difference between Greek, Greco-Roman and Roman art. "The prophet and founding hero of modern archaeology", Winckelmann was one of the founders of scientific archaeology and first applied the categories of style on a large, systematic basis to the history of art. '
}
nlp(inputs)

🔧 Technical Details

Training procedure

{
    "base_model": "bert-large-uncased",
    "do_lower_case": True,
    "learning_rate": 3e-5,
    "num_train_epochs": 4,
    "max_seq_length": 384,
    "doc_stride": 128,
    "max_query_length": 64,
    "batch_size": 96 
}

Eval results

• Data: dev-v2.0.json
• Script: evaluate-v2.0.py (original script from here)

{
  "exact": 76.22336393497852,
  "f1": 79.72527570261339,
  "total": 11873,
  "HasAns_exact": 76.19770580296895,
  "HasAns_f1": 83.21157193271408,
  "HasAns_total": 5928,
  "NoAns_exact": 76.24894869638352,
  "NoAns_f1": 76.24894869638352,
  "NoAns_total": 5945
}

📄 License

No license information provided in the original document.