metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
Exclusive Invitation: Job Fair at XYZ Corporation
Hi [Name],\n\nWe are thrilled to invite you to the upcoming career fair
for XYZ Corporation! This is a unique opportunity to meet our hiring
managers, learn more about open positions, and experience our company
culture firsthand. We look forward to seeing you there!\n\nDate/Time:
[Details]\nLocation: [Details]\n\nRSVP today at: [Link]\n\nWarm
regards,\nThe XYZ Corporation Team
- text: >-
Action Required: Update Your Resume
Hello Avocado, We noticed your resume was last updated in 2023. Consider
refreshing it to highlight recent experience. Update here:
https://profile.jobsite.com/resume. Recent resumes get 40% more employer
views. Job Board Team
- text: >-
Background Check Authorization Needed
Dear Candidate, Congratulations! You're advancing to our final stages.
Next step: background check authorization. Please complete the attached
form and return by Oct 15. We use Checkr for verification of: Employment
history, Education credentials, Criminal background. This does NOT mean an
offer has been made yet. It helps expedite the process. Questions? Contact
hr@company.com. HR Compliance
- text: >-
Your application to Front End Dev Intern at Metis
Your update from Metis Front End Dev Intern Metis · San Francisco,
California, United States Applied on Jul 11 Thank you for your interest in
the Front End Dev Intern position at Metis in San Francisco, California,
United States. Unfortunately, we will not be moving forward with your
application, but we appreciate your time and interest in Metis. Regards,
Metis Top jobs looking for your skills Frontend Developer, New Grad &
Entry Level Jobright.ai · Ohio, United States Software Engineer,
Routing - New Grad Nuro · Mountain View, California, United States
College Graduates - Full-Time - Junior Software Engineer (2026) Old
Mission · Chicago, Illinois, United States Entry Level Software
Developer Lensa · Vienna, Virginia, United States Junior Front End
Developer Predictive Sales AI a Spectrum Communications & Consulting LLC
Brand · Chicago, Illinois, United States See more jobs Get the new
LinkedIn desktop app Also available on mobile This email was intended for
Oluwatomiwa Jinadu (Aspiring Software Developer | Actively Seeking
Entry-Level Role | Java ¥ React ¥ C# ¥ SQL | B.S. in Computing) Learn why
we included this. You are receiving LinkedIn notification emails.
Unsubscribe á Help © 2025 LinkedIn Corporation, 1‌000 West Maude
Avenue, Sunnyvale, CA 94085. LinkedIn and the LinkedIn logo are registered
trademarks of LinkedIn.
- text: >-
Intro to Web Development course - Admissions update
Hi [Applicant Name],
Thank you for your interest in CodePath�s Intro to Web Development Fall
2024 course. Unfortunately, we are not able to offer you a spot. Usually,
this is due to one of the following factors:
We did not receive your complete application and/or prework/HackerRank
assessment prior to the deadline.
We had an overwhelming number of applicants to the program, and have run
out of spots in the course.
We initially sent you an acceptance for this course, but have not heard
back from you. Because the deadline we set for you to respond has passed,
your spot has been given to another applicant.
Moreover, we have filled all the spots in the program.
We will ensure that you receive opt-in observer access to the curriculum
before the class starts, so you are still able to follow along. We believe
that you will benefit from diving into the curriculum as an observer.
Additionally, we will run this course again in the future, and we hope
you�ll re-apply for future cohorts. You can join our waitlist for
upcoming courses here.
WHAT IS AN OBSERVER?
Here's an overview of what an observer means:
You will get access to the full course material, along with the list of
practice problems.
You are not required and will not be able to attend any instructor-led
sessions.
You are not required to submit any assignments and do not have to meet any
deadlines.
You will have access to the session recordings of the most recent cohort
through our course learning portal
If you think we've made a mistake and you do indeed meet the requirements
for this course, please email us at admissions@codepath.org.
Sincerely,
Team at CodePath
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2
SetFit with sentence-transformers/all-MiniLM-L6-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: sentence-transformers/all-MiniLM-L6-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 256 tokens
- Number of Classes: 7 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
| Label | Examples |
|---|---|
| next-phase |
|
| interview |
|
| applied |
|
| rejected |
|
| not-job-related |
|
| not-job-status-update |
|
| offer |
|
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("Action Required: Update Your Resume
Hello Avocado, We noticed your resume was last updated in 2023. Consider refreshing it to highlight recent experience. Update here: https://profile.jobsite.com/resume. Recent resumes get 40% more employer views. Job Board Team")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 13 | 110.3913 | 385 |
| Label | Training Sample Count |
|---|---|
| applied | 72 |
| interview | 50 |
| next-phase | 54 |
| not-job-related | 78 |
| not-job-status-update | 72 |
| offer | 34 |
| rejected | 54 |
Training Hyperparameters
- batch_size: (64, 64)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 8
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 0.001
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- evaluation_strategy: no
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0096 | 1 | 0.2741 | - |
| 0.2404 | 25 | 0.2423 | - |
| 0.4808 | 50 | 0.1811 | - |
| 0.7212 | 75 | 0.1315 | - |
| 0.9615 | 100 | 0.0947 | - |
| 1.2019 | 125 | 0.08 | - |
| 1.4423 | 150 | 0.0697 | - |
| 1.6827 | 175 | 0.0669 | - |
| 1.9231 | 200 | 0.0606 | - |
Framework Versions
- Python: 3.11.13
- SetFit: 1.1.3
- Sentence Transformers: 5.1.0
- Transformers: 4.56.1
- PyTorch: 2.2.2
- Datasets: 4.0.0
- Tokenizers: 0.22.0
Citation
BibTeX
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}