SpanBERT base fine-tuned on SQuAD v1

SpanBERT created by Facebook Research and fine-tuned on SQuAD 1.1 for Q&A downstream task (by them).

Details of SpanBERT

SpanBERT: Improving Pre-training by Representing and Predicting Spans

Details of the downstream task (Q&A) - Dataset 📚 🧐 ❓

Model fine-tuning 🏋️‍

You can get the fine-tuning script here

python code/run_squad.py \
  --do_train \
  --do_eval \
  --model spanbert-base-cased \
  --train_file train-v1.1.json \
  --dev_file dev-v1.1.json \
  --train_batch_size 32 \
  --eval_batch_size 32  \
  --learning_rate 2e-5 \
  --num_train_epochs 4 \
  --max_seq_length 512 \
  --doc_stride 128 \
  --eval_metric f1 \
  --output_dir squad_output \
  --fp16

Results Comparison 📝

	SQuAD 1.1	SQuAD 2.0	Coref	TACRED
	F1	F1	avg. F1	F1
BERT (base)	88.5	76.5	73.1	67.7
SpanBERT (base)	92.4 (this one)	83.6	77.4	68.2
BERT (large)	91.3	83.3	77.1	66.4
SpanBERT (large)	94.6	88.7	79.6	70.8

Note: The numbers marked as * are evaluated on the development sets because those models were not submitted to the official SQuAD leaderboard. All the other numbers are test numbers.

Model in action

Fast usage with pipelines:

from transformers import pipeline

qa_pipeline = pipeline(
    "question-answering",
    model="mrm8488/spanbert-base-finetuned-squadv1",
    tokenizer="SpanBERT/spanbert-base-cased"
)

qa_pipeline({
    'context': "Manuel Romero has been working very hard in the repository hugginface/transformers lately",
    'question': "How has been working Manuel Romero lately?"

})

# Output: {'answer': 'very hard in the repository hugginface/transformers',
 'end': 82,
 'score': 0.327230326857725,
 'start': 31}

Created by Manuel Romero/@mrm8488

Made with ♥ in Spain