Hugging Face's logo

deepset
/
roberta-base-squad2-distilled

Question Answering
Transformers
PyTorch
Safetensors
English
roberta
exbert
Eval Results
Inference Endpoints
Model card Files Community
6
roberta-base-squad2-distilled / README.md
Sebastian
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#4)
765597d
preview code
|
raw
history blame
3.81 kB
metadata
language: en
license: mit
tags:
  - exbert
datasets:
  - squad_v2
thumbnail: >-
  https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg
model-index:
  - name: deepset/roberta-base-squad2-distilled
    results:
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad_v2
          type: squad_v2
          config: squad_v2
          split: validation
        metrics:
          - type: exact_match
            value: 80.8593
            name: Exact Match
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzVjNzkxNmNiNDkzNzdiYjJjZGM3ZTViMGJhOGM2ZjFmYjg1MjYxMDM2YzM5NWMwNDIyYzNlN2QwNGYyNDMzZSIsInZlcnNpb24iOjF9.Rgww8tf8D7nF2dh2U_DMrFzmp87k8s7RFibrDXSvQyA66PGWXwjlsd1552lzjHnNV5hvHUM1-h3PTuY_5p64BA
          - type: f1
            value: 84.0104
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTAyZDViNWYzNjA4OWQ5MzgyYmQ2ZDlhNWRhMTIzYTYxYzViMmI4NWE4ZGU5MzVhZTAwNTRlZmRlNWUwMjI0ZSIsInZlcnNpb24iOjF9.Er21BNgJ3jJXLuZtpubTYq9wCwO1i_VLQFwS5ET0e4eAYVVj0aOA40I5FvP5pZac3LjkCnVacxzsFWGCYVmnDA

Overview

Language model: deepset/roberta-base-squad2-distilled
Language: English
Training data: SQuAD 2.0 training set Eval data: SQuAD 2.0 dev set Infrastructure: 4x V100 GPU
Published: Dec 8th, 2021

Details

  • haystack's distillation feature was used for training. deepset/roberta-large-squad2 was used as the teacher model.

Hyperparameters 

batch_size = 80
n_epochs = 4
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 1.5
distillation_loss_weight = 0.75

Performance 

"exact": 79.8366040596311
"f1": 83.916407079888

Authors

Timo M枚ller: timo.moeller@deepset.ai
Julian Risch: julian.risch@deepset.ai
Malte Pietsch: malte.pietsch@deepset.ai
Michel Bartels: michel.bartels@deepset.ai

About us

deepset is the company behind the open-source NLP framework Haystack which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.

Some of our other work:

Get in touch and join the Haystack community

For more info on Haystack, visit our GitHub repo and Documentation.

We also have a Discord community open to everyone!

Twitter | LinkedIn | Discord | GitHub Discussions | Website

By the way: we're hiring!