metadata

license: mit
datasets:
  - squad_v2
  - squad
language:
  - en
library_name: transformers
tags:
  - question-answering
  - squad
  - squad_v2
  - t5
  - lora
  - peft
model-index:
  - name: sjrhuschlee/flan-t5-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: 86.785
            name: Exact Match
          - type: f1
            value: 89.537
            name: F1
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad
          type: squad
          config: plain_text
          split: validation
        metrics:
          - type: exact_match
            value: 85.998
            name: Exact Match
          - type: f1
            value: 91.296
            name: F1
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: adversarial_qa
          type: adversarial_qa
          config: adversarialQA
          split: validation
        metrics:
          - type: exact_match
            value: 35.767
            name: Exact Match
          - type: f1
            value: 45.565
            name: F1
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad_adversarial
          type: squad_adversarial
          config: AddOneSent
          split: validation
        metrics:
          - type: exact_match
            value: 75.322
            name: Exact Match
          - type: f1
            value: 79.327
            name: F1
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squadshifts
          type: squadshifts
          config: nyt
          split: test
        metrics:
          - type: exact_match
            value: 83.815
            name: Exact Match
          - type: f1
            value: 90.416
            name: F1

flan-t5-large for Extractive QA

This is the flan-t5-large model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering.

This model was trained using LoRA available through the PEFT library.

NOTE: The token must be manually added to the beginning of the question for this model to work properly. It uses the token to be able to make "no answer" predictions. The t5 tokenizer does not automatically add this special token which is why it is added manually.

Overview

Language model: flan-t5-large
Language: English
Downstream-task: Extractive QA
Training data: SQuAD 2.0
Eval data: SQuAD 2.0
Infrastructure: 1x NVIDIA 3070

Model Usage

Using Transformers

This uses the merged weights (base model weights + LoRA weights) to allow for simple use in Transformers pipelines. It has the same performance as using the weights separately when using the PEFT library.

import torch
from transformers import(
  AutoModelForQuestionAnswering,
  AutoTokenizer,
  pipeline
)
model_name = "sjrhuschlee/flan-t5-large-squad2"

# a) Using pipelines
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
qa_input = {
'question': f'{nlp.tokenizer.cls_token}Where do I live?',  # '<cls>Where do I live?'
'context': 'My name is Sarah and I live in London'
}
res = nlp(qa_input)
# {'score': 0.984, 'start': 30, 'end': 37, 'answer': ' London'}

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

question = f'{tokenizer.cls_token}Where do I live?'  # '<cls>Where do I live?'
context = 'My name is Sarah and I live in London'
encoding = tokenizer(question, context, return_tensors="pt")
start_scores, end_scores = model(
  encoding["input_ids"],
  attention_mask=encoding["attention_mask"],
  return_dict=False
)

all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0].tolist())
answer_tokens = all_tokens[torch.argmax(start_scores):torch.argmax(end_scores) + 1]
answer = tokenizer.decode(tokenizer.convert_tokens_to_ids(answer_tokens))
# 'London'

Metrics

# Squad v2
{
    "eval_HasAns_exact": 85.08771929824562,
    "eval_HasAns_f1": 90.598422845031,
    "eval_HasAns_total": 5928,
    "eval_NoAns_exact": 88.47771236333053,
    "eval_NoAns_f1": 88.47771236333053,
    "eval_NoAns_total": 5945,
    "eval_best_exact": 86.78514276088605,
    "eval_best_exact_thresh": 0.0,
    "eval_best_f1": 89.53654936623764,
    "eval_best_f1_thresh": 0.0,
    "eval_exact": 86.78514276088605,
    "eval_f1": 89.53654936623776,
    "eval_runtime": 1908.3189,
    "eval_samples": 12001,
    "eval_samples_per_second": 6.289,
    "eval_steps_per_second": 0.787,
    "eval_total": 11873
}

# Squad
{
    "eval_HasAns_exact": 85.99810785241249,
    "eval_HasAns_f1": 91.296119057944,
    "eval_HasAns_total": 10570,
    "eval_best_exact": 85.99810785241249,
    "eval_best_exact_thresh": 0.0,
    "eval_best_f1": 91.296119057944,
    "eval_best_f1_thresh": 0.0,
    "eval_exact": 85.99810785241249,
    "eval_f1": 91.296119057944,
    "eval_runtime": 1508.9596,
    "eval_samples": 10657,
    "eval_samples_per_second": 7.062,
    "eval_steps_per_second": 0.883,
    "eval_total": 10570
}

Using with Peft

NOTE: This requires code in the PR https://github.com/huggingface/peft/pull/473 for the PEFT library.

#!pip install peft

from peft import LoraConfig, PeftModelForQuestionAnswering
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model_name = "sjrhuschlee/flan-t5-large-squad2"