Sebastian
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#8)
cf83ca2
|
raw
history blame
6.18 kB
metadata
language: en
license: cc-by-4.0
tags:
  - deberta
  - deberta-v3
  - deberta-v3-large
datasets:
  - squad_v2
model-index:
  - name: deepset/deberta-v3-large-squad2
    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: 88.0876
            name: Exact Match
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmE0MWEwNjBkNTA1MmU0ZDkyYTA1OGEwNzY3NGE4NWU4NGI0NTQzNjRlNjY1NGRmNDU2MjA0NjU1N2JlZmNhYiIsInZlcnNpb24iOjF9.PnBF_vD0HujNBSShGJzsJnjmiBP_qT8xb2E7ORmpKfNspKXEuN_pBk9iV0IHRzdqOSyllcxlCv93XMPblNjWDw
          - type: f1
            value: 91.1623
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDBkNDUzZmNkNDQwOGRkMmVlZjkxZWVlMzk3NzFmMGIxMTFmMjZlZDcyOWFiMjljNjM5MThlZDM4OWRmNzMwOCIsInZlcnNpb24iOjF9.bacyetziNI2DxO67GWpTyeRPXqF1POkyv00wEHXlyZu71pZngsNpZyrnuj2aJlCqQwHGnF_lT2ysaXKHprQRBg
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad
          type: squad
          config: plain_text
          split: validation
        metrics:
          - type: exact_match
            value: 89.2366
            name: Exact Match
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjQ1Yjk3YTdiYTY1NmYxMTI1ZGZlMjRkNTlhZTkyNjRkNjgxYWJiNDk2NzE3NjAyYmY3YmRjNjg4YmEyNDkyYyIsInZlcnNpb24iOjF9.SEWyqX_FPQJOJt2KjOCNgQ2giyVeLj5bmLI5LT_Pfo33tbWPWD09TySYdsthaVTjUGT5DvDzQLASSwBH05FyBw
          - type: f1
            value: 95.0569
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2QyODQ1NWVlYjQxMjA0YTgyNmQ2NmIxOWY3MDRmZjE3ZWI5Yjc4ZDE4NzA2YjE2YTE1YTBlNzNiYmNmNzI3NCIsInZlcnNpb24iOjF9.NcXEc9xoggV76w1bQKxuJDYbOTxFzdny2k-85_b6AIMtfpYV3rGR1Z5YF6tVY2jyp7mgm5Jd5YSgGI3NvNE-CQ

deberta-v3-large for QA

This is the deberta-v3-large model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.

Overview

Language model: deberta-v3-large
Language: English
Downstream-task: Extractive QA
Training data: SQuAD 2.0
Eval data: SQuAD 2.0
Code: See an example QA pipeline on Haystack
Infrastructure: 1x NVIDIA A10G

Hyperparameters

batch_size = 2
grad_acc_steps = 32
n_epochs = 6
base_LM_model = "microsoft/deberta-v3-large"
max_seq_len = 512
learning_rate = 7e-6
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

Usage

In Haystack

Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in Haystack:

reader = FARMReader(model_name_or_path="deepset/deberta-v3-large-squad2")
# or 
reader = TransformersReader(model_name_or_path="deepset/deberta-v3-large-squad2",tokenizer="deepset/deberta-v3-large-squad2")

In Transformers

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/deberta-v3-large-squad2"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Performance

Evaluated on the SQuAD 2.0 dev set with the official eval script.

"exact": 87.6105449338836,
"f1": 90.75307008866517,

"total": 11873,
"HasAns_exact": 84.37921727395411,
"HasAns_f1": 90.6732795483674,
"HasAns_total": 5928,
"NoAns_exact": 90.83263246425568,
"NoAns_f1": 90.83263246425568,
"NoAns_total": 5945

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!