Back to all models
Model card Files and versions Use in transformers
question-answering mask_token: [MASK]
Query this model
馃敟 This model is currently loaded and running on the Inference API. 鈿狅笍 This model could not be loaded by the inference API. 鈿狅笍 This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

鈿★笍 Upgrade your account to access the Inference API

Share Copied link to clipboard

Contributed by

twmkn9 Travis McGuire
4 models

This model is Distilbert base uncased trained on SQuAD v2 as:

export SQUAD_DIR=../../squad2
    --model_type distilbert 
    --model_name_or_path distilbert-base-uncased
    --save_steps 100000 
    --train_file $SQUAD_DIR/train-v2.0.json 
    --predict_file $SQUAD_DIR/dev-v2.0.json 
    --per_gpu_train_batch_size 8 
    --num_train_epochs 3 
    --learning_rate 3e-5 
    --max_seq_length 384 
    --doc_stride 128 
    --output_dir ./tmp/distilbert_fine_tuned/

Performance on a dev subset is close to the original paper:

    'exact': 64.88976637051661, 
    'f1': 68.1776176526635, 
    'total': 6078, 
    'HasAns_exact': 69.7594501718213, 
    'HasAns_f1': 76.62665295288285, 
    'HasAns_total': 2910, 
    'NoAns_exact': 60.416666666666664, 
    'NoAns_f1': 60.416666666666664, 
    'NoAns_total': 3168, 
    'best_exact': 64.88976637051661, 
    'best_exact_thresh': 0.0, 
    'best_f1': 68.17761765266337, 
    'best_f1_thresh': 0.0

We are hopeful this might save you time, energy, and compute. Cheers!