Hugging Face's logo

aai520-group6
/
distilbert-finetuned-uncased-squad_v2

Question Answering
Transformers
PyTorch
English
distilbert
Eval Results
Inference Endpoints
Model card Files Community
distilbert-finetuned-uncased-squad_v2 / README.md
jonathanagustin's picture
jonathanagustin
Upload README.md with huggingface_hub
425c5f8
preview code
|
raw
history blame
9.43 kB
metadata
language: en
license: mit
model_details: |2-

          ## Abstract
          This model, 'distilbert-finetuned-uncased', is a question-answering chatbot trained on the SQuAD dataset, demonstrating competency in building conversational AI using recent advances in natural language processing. It utilizes a BERT model fine-tuned for extractive question answering.

          ## Data Collection and Preprocessing
          The model was trained on the Stanford Question Answering Dataset (SQuAD), which contains over 100,000 question-answer pairs based on Wikipedia articles. The data preprocessing involved tokenizing context paragraphs and questions, truncating sequences to fit BERT's max length, and adding special tokens to mark question and paragraph segments.

          ## Model Architecture and Training
          The architecture is based on the BERT transformer model, which was pretrained on large unlabeled text corpora. For this project, the BERT base model was fine-tuned on SQuAD for extractive question answering, with additional output layers for predicting the start and end indices of the answer span.

          ## SQuAD 2.0 Dataset
          SQuAD 2.0 combines the existing SQuAD data with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. This version of the dataset challenges models to not only produce answers when possible but also determine when no answer is supported by the paragraph and abstain from answering.
          
intended_use: |2-

          - Answering questions from the squad_v2 dataset.
          - Developing question-answering systems within the scope of the aai520-project.
          - Research and experimentation in the NLP question-answering domain.
          
limitations_and_bias: |2-

          The model inherits limitations and biases from the 'distilbert-base-uncased' model, as it was trained on the same foundational data.
          It may underperform on questions that are ambiguous or too far outside the scope of the topics covered in the squad_v2 dataset.
          Additionally, the model may reflect societal biases present in its training data.
          
ethical_considerations: |2-

          This model should not be used for making critical decisions without human oversight,
          as it can generate incorrect or biased answers, especially for topics not covered in the training data.
          Users should also consider the ethical implications of using AI in decision-making processes and the potential for perpetuating biases.
          
evaluation: |2-

          The model was evaluated on the squad_v2 dataset using various metrics. These metrics, along with their corresponding scores,
          are detailed in the 'eval_results' section. The evaluation process ensured a comprehensive assessment of the model's performance
          in question-answering scenarios.
          
training: |2-

          The model was trained over 10 epochs with a learning rate of 2e-05, using a batch size of 128.
          The training utilized a cross-entropy loss function and the AdamW optimizer, with gradient accumulation over 4 steps.
          
tips_and_tricks: |2-

          For optimal performance, questions should be clear, concise, and grammatically correct.
          The model performs best on questions related to topics covered in the squad_v2 dataset.
          It is advisable to pre-process text for consistency in encoding and punctuation, and to manage expectations for questions on topics outside the training data.
          
model-index:
  - name: distilbert-finetuned-uncased
    results:
      - task:
          type: question-answering
        dataset:
          name: SQuAD v2
          type: squad_v2
        metrics:
          - type: Exact
            value: 100
          - type: F1
            value: 100
          - type: Total
            value: 2
          - type: Hasans Exact
            value: 100
          - type: Hasans F1
            value: 100
          - type: Hasans Total
            value: 2
          - type: Best Exact
            value: 100
          - type: Best Exact Thresh
            value: 0.967875599861145
          - type: Best F1
            value: 100
          - type: Best F1 Thresh
            value: 0.967875599861145
          - type: Total Time In Seconds
            value: 0.03484977200002959
          - type: Samples Per Second
            value: 57.389184640814925
          - type: Latency In Seconds
            value: 0.017424886000014794

Model Card for Model ID

Model Details

Model Description

  • Developed by: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): en
  • License: mit
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

  • Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]