Albert Xlarge V2 Squad V2

🚀 ALBERT-XLARGE-V2 Fine-tuned on SQuAD V2

This project presents an ALBERT-XLARGE-V2 model fine-tuned on the SQuAD V2 dataset, enabling effective question - answering tasks.

🚀 Quick Start

The model is based on the pre - trained albert - xlarge - v2 and fine - tuned on the SQuAD V2 dataset using the run_squad.py script.

✨ Features

• Fine - tuned on the SQuAD V2 dataset, which allows the model to handle questions with or without answers.
• Capable of scoring whether a paragraph contains an answer to a given question.

📦 Installation

Training Environment

The model was trained on 4 NVIDIA GeForce RTX 2080 Ti 11Gb.

Training Command

BASE_MODEL=albert-xlarge-v2
python run_squad.py \
  --version_2_with_negative \
  --model_type albert \
  --model_name_or_path $BASE_MODEL \
  --output_dir $OUTPUT_MODEL \
  --do_eval \
  --do_lower_case \
  --train_file $SQUAD_DIR/train-v2.0.json \
  --predict_file $SQUAD_DIR/dev-v2.0.json \
  --per_gpu_train_batch_size 3 \
  --per_gpu_eval_batch_size 64 \
  --learning_rate 3e-5 \
  --num_train_epochs 3.0 \
  --max_seq_length 384 \
  --doc_stride 128 \
  --save_steps 2000 \
  --threads 24 \
  --warmup_steps 814 \
  --gradient_accumulation_steps 4 \
  --fp16 \
  --do_train

📚 Documentation

Evaluation

The model was evaluated on the dev set. The evaluation metrics are as follows:

💻 Usage Examples

Basic Usage

See huggingface documentation. Training on SQuAD V2 allows the model to score if a paragraph contains an answer:

start_scores, end_scores = model(input_ids) 
span_scores = start_scores.softmax(dim=1).log()[:,:,None] + end_scores.softmax(dim=1).log()[:,None,:]
ignore_score = span_scores[:,0,0] #no answer scores