---
base_model: google/flan-t5-xl
datasets:
- 2024-mcm-everitt-ryan/job-bias-synthetic-human-benchmark
language: en
license: apache-2.0
model_id: flan-t5-xl-job-bias-seq2seq-cls
model_description: The model is a multi-label classifier designed to detect various
  types of bias within job descriptions.
developers: Tristan Everitt and Paul Ryan
model_card_authors: See developers
model_card_contact: See developers
repo: https://gitlab.computing.dcu.ie/everitt2/2024-mcm-everitt-ryan
compute_infrastructure: Linux 6.5.0-35-generic x86_64
software: Python 3.10.12
hardware_type: x86_64
hours_used: N/A
cloud_provider: N/A
cloud_region: N/A
co2_emitted: N/A
direct_use: "\n    ```python\n    from transformers import pipeline\n\n    pipe =\
  \ pipeline(\"text-classification\", model=\"2024-mcm-everitt-ryan/flan-t5-xl-job-bias-seq2seq-cls\"\
  , return_all_scores=True)\n\n    results = pipe(\"Join our dynamic and fast-paced\
  \ team as a Junior Marketing Specialist. We seek a tech-savvy and energetic individual\
  \ who thrives in a vibrant environment. Ideal candidates are digital natives with\
  \ a fresh perspective, ready to adapt quickly to new trends. You should have recent\
  \ experience in social media strategies and a strong understanding of current digital\
  \ marketing tools. We're looking for someone with a youthful mindset, eager to bring\
  \ innovative ideas to our young and ambitious team. If you're a recent graduate\
  \ or early in your career, this opportunity is perfect for you!\")\n    print(results)\n\
  \    ```\n    >> [[\n    {'label': 'age', 'score': 0.9883460402488708}, \n    {'label':\
  \ 'disability', 'score': 0.00787709467113018}, \n    {'label': 'feminine', 'score':\
  \ 0.007224376779049635}, \n    {'label': 'general', 'score': 0.09967829287052155},\
  \ \n    {'label': 'masculine', 'score': 0.0035264550242573023}, \n    {'label':\
  \ 'racial', 'score': 0.014618005603551865}, \n    {'label': 'sexuality', 'score':\
  \ 0.005568435415625572}\n    ]]\n\n\n    Classification Report:\n    \n        \
  \              precision    recall  f1-score   support\n    \n             age \
  \      0.72      0.57      0.63        81\n       sexuality       0.84      0.79\
  \      0.82        81\n      disability       0.70      0.60      0.65        81\n\
  \       masculine       0.64      0.62      0.63        81\n        feminine   \
  \    0.84      0.89      0.86        81\n         general       0.28      0.44 \
  \     0.34        82\n          racial       0.62      0.86      0.72        78\n\
  \    \n       micro avg       0.63      0.68      0.65       565\n       macro avg\
  \       0.66      0.68      0.66       565\n    weighted avg       0.66      0.68\
  \      0.66       565\n     samples avg       0.31      0.35      0.32       565\n\
  \    \n    "
model-index:
- name: flan-t5-xl-job-bias-seq2seq-cls
  results:
  - task:
      type: multi_label_classification
    dataset:
      name: 2024-mcm-everitt-ryan/job-bias-synthetic-human-benchmark
      type: mix_human-eval_synthetic
    metrics:
    - type: loss
      value: 0.6297690868377686
    - type: accuracy
      value: 0.724596391263058
    - type: f1_micro
      value: 0.6541737649063032
    - type: f1_macro
      value: 0.6649871410336159
    - type: f1_samples
      value: 0.7891104779993668
    - type: f1_weighted
      value: 0.6641255154887347
    - type: precision_micro
      value: 0.6305418719211823
    - type: precision_macro
      value: 0.6632750205440888
    - type: precision_samples
      value: 0.8839822728711617
    - type: precision_weighted
      value: 0.6628306019545424
    - type: recall_micro
      value: 0.679646017699115
    - type: recall_macro
      value: 0.6810192216696281
    - type: recall_samples
      value: 0.8638809749920862
    - type: recall_weighted
      value: 0.679646017699115
    - type: roc_auc_micro
      value: 0.8232934760843503
    - type: roc_auc_macro
      value: 0.8239776029004718
    - type: runtime
      value: 228.4627
    - type: samples_per_second
      value: 4.609
    - type: steps_per_second
      value: 0.578
    - type: epoch
      value: 1.0
---

# Model Card for flan-t5-xl-job-bias-seq2seq-cls

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

The model is a multi-label classifier designed to detect various types of bias within job descriptions.

- **Developed by:** Tristan Everitt and Paul Ryan
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** en
- **License:** apache-2.0
- **Finetuned from model [optional]:** google/flan-t5-xl

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://gitlab.computing.dcu.ie/everitt2/2024-mcm-everitt-ryan
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->


    ```python
    from transformers import pipeline

    pipe = pipeline("text-classification", model="2024-mcm-everitt-ryan/flan-t5-xl-job-bias-seq2seq-cls", return_all_scores=True)

    results = pipe("Join our dynamic and fast-paced team as a Junior Marketing Specialist. We seek a tech-savvy and energetic individual who thrives in a vibrant environment. Ideal candidates are digital natives with a fresh perspective, ready to adapt quickly to new trends. You should have recent experience in social media strategies and a strong understanding of current digital marketing tools. We're looking for someone with a youthful mindset, eager to bring innovative ideas to our young and ambitious team. If you're a recent graduate or early in your career, this opportunity is perfect for you!")
    print(results)
    ```
    >> [[
    {'label': 'age', 'score': 0.9883460402488708}, 
    {'label': 'disability', 'score': 0.00787709467113018}, 
    {'label': 'feminine', 'score': 0.007224376779049635}, 
    {'label': 'general', 'score': 0.09967829287052155}, 
    {'label': 'masculine', 'score': 0.0035264550242573023}, 
    {'label': 'racial', 'score': 0.014618005603551865}, 
    {'label': 'sexuality', 'score': 0.005568435415625572}
    ]]


    Classification Report:
    
                      precision    recall  f1-score   support
    
             age       0.72      0.57      0.63        81
       sexuality       0.84      0.79      0.82        81
      disability       0.70      0.60      0.65        81
       masculine       0.64      0.62      0.63        81
        feminine       0.84      0.89      0.86        81
         general       0.28      0.44      0.34        82
          racial       0.62      0.86      0.72        78
    
       micro avg       0.63      0.68      0.65       565
       macro avg       0.66      0.68      0.66       565
    weighted avg       0.66      0.68      0.66       565
     samples avg       0.31      0.35      0.32       565
    
    

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

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

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** x86_64
- **Hours used:** N/A
- **Cloud Provider:** N/A
- **Compute Region:** N/A
- **Carbon Emitted:** N/A

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

Linux 6.5.0-35-generic x86_64

#### Hardware

[More Information Needed]

#### Software

Python 3.10.12

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

See developers

## Model Card Contact

See developers