metadata
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
(a) The terms below are defined for the purposes of this section: (1)
Smoke or Smoking means the inhaling, exhaling, burning, or carrying of any
lit cigarette, cigar, pipe, or smoking paraphernalia used for consuming
the smoke of tobacco or any other burning product. (2) Use means the use
of any tobacco product. (3) Residential Space means the private living
areas of staff. Residential Space does not include the living areas of
incarcerated persons or family visiting areas. Residential space includes,
but is not limited to, residential areas at institutions, correctional
training academies, and conservation camps. (4) Facility means any
building, areas of any building, or group of buildings owned, leased, or
utilized by the Department. This shall include, but not be limited to,
institutions, conservation camps, community correctional facility, and
reentry furlough, and restitution centers. (b) No person shall smoke
within 20 feet of any operative window of, entrance/exit to, or within the
interior of any state owned or state occupied building, with the following
exceptions: (1) Residential spaces of staff excluding correctional
training academies, Staff Quarters at conservation camps, and designated
non-smoking housing on institutional grounds. For these excluded areas,
smoking will be permitted for staff in designated areas at designated
times. (2) In areas designated by each institution head for the purpose of
approved incarcerated person religious ceremonies as specified. (c) In
addition to (b), no person shall smoke in any area that may pose a safety
or security risk, e.g., within any fire hazardous areas. (d) Signs shall
be posted at entrances of all areas designated no smoking and, as
necessary, any other outside areas of a facility not designated for
smoking, along with a citation of the authority requiring such
prohibition. (e) No person shall smoke in any vehicle that is state-owned
or -leased by the state.
- text: >-
The purpose of this chapter is to set forth the rules and requirements
which the Commissioner deems necessary to apply to producers marketing
credit insurance coverage, as described in the Alabama Consumer Credit
Act, Title 5, Chapter 19, Code of Ala. 1975, (commonly referred to as the
"Mini-Code"); the Alabama Small Loan Act, Title 5, Chapter 18, Code of
Ala. 1975; the Alabama Insurance Code, Title 27, Code of Ala. 1975; as
well as rules and regulations promulgated pursuant to these statutes. This
chapter is to clarify future licensing procedures concerning credit
insurance and in no way reflects on previous practices. The information
required by this chapter is hereby declared to be necessary and
appropriate and in the public interest and for the protection of
policyholders in this state. Additionally this chapter is to promote the
public welfare by regulating credit insurance in this state. Author: Reyn
Norman, Associate Counsel
- text: >-
Creation of this program was directed by Act 94-680, Regular Session 1994,
Alabama State Legislature. Concurrently, there was established the State
Employee Injury Compensation Trust Fund, with all receipts deposited in
the Trust Fund used only to carry out the provisions of Act 94-680. The
purpose of the Employee Injury Compensation Program is to provide
compensation for employees of the state and its agencies, departments,
boards, or commissions, except as excluded by law, who suffer personal
injury as a result of accidents arising out of and in the course of their
state employment. Terms and conditions of the Program are to be determined
by the Director of Finance, State of Alabama. The Program is effective
October 1, 1994. The cost of the program and its administration will be
paid from the funds appropriated for the operation of state departments,
agencies, boards and commissions, to which the Director of Finance may
apportion the cost. Author:
- text: >-
The purpose of this Part is to establish the new source review (NSR)
preconstruction, construction and operation requirements for new and
modified facilities in a manner which furthers the policy and objectives
of article 19 of the Environmental Conservation Law, and meets the plan
requirements for nonattainment areas (part D) and prevention of
significant deterioration (PSD) of air quality (part C) of subchapter I of
the act.
- text: >-
(a) Chapter 864 of the Laws of 1985 amended section 4240 of the Insurance
Law (relating to separate accounts) to add to the circumstances in which
an insurance company may guarantee the value of assets allocated to a
separate account, or any interest therein, or the investment results
thereof. The amendment allows such a guarantee to be made if the insurance
company submits annually to the superintendent an opinion and memorandum
of a qualified actuary, in form and substance satisfactory to the
superintendent, that, after taking into account any risk charge payable
from the assets of the separate account with respect to such guarantee,
the assets in the separate account make good and sufficient provision for
the liabilities of the insurance company with respect thereto. (b) Section
4240 of the Insurance Law was also amended to permit the insurance company
to value the assets allocated to such a separate account at their market
value, and section 4217 was amended to authorize the valuation of the
benefits funded by the separate account on a consistent basis. (c) The
purpose of this Part is to prescribe: (1) the terms and conditions under
which life insurance companies may issue contracts (of the kind described
in section 97.2[a] of this Part) that: (i) are funded by separate accounts
in which assets are valued at market; and (ii) provide for fixed or
guaranteed minimum benefits; (2) the procedures for establishing and
maintaining such separate accounts; and (3) the reserve requirements for
such contracts and agreements.
inference: true
SetFit
This is a SetFit model that can be used for Text Classification. 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
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 200 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
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("rkoh/setfit-bert-a6")
# Run inference
preds = model("The purpose of this Part is to establish the new source review (NSR) preconstruction, construction and operation requirements for new and modified facilities in a manner which furthers the policy and objectives of article 19 of the Environmental Conservation Law, and meets the plan requirements for nonattainment areas (part D) and prevention of significant deterioration (PSD) of air quality (part C) of subchapter I of the act.")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | tensor(15) | tensor(242.2050) | tensor(4265) |
| Label | Training Sample Count |
|---|---|
| Purpose - Regulatory Objective | 0 |
| Scope and Applicability | 0 |
| Authority and Legal Basis | 0 |
| Administrative Details | 0 |
| Non-Purpose | 0 |
Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- 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
- eval_max_steps: -1
- load_best_model_at_end: True
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.004 | 1 | 0.3869 | - |
| 0.04 | 10 | 0.4354 | - |
| 0.08 | 20 | 0.3435 | - |
| 0.12 | 30 | 0.2742 | - |
| 0.16 | 40 | 0.2615 | - |
| 0.2 | 50 | 0.2462 | - |
| 0.24 | 60 | 0.2092 | - |
| 0.28 | 70 | 0.2323 | - |
| 0.32 | 80 | 0.1956 | - |
| 0.36 | 90 | 0.2324 | - |
| 0.4 | 100 | 0.2026 | - |
| 0.44 | 110 | 0.1941 | - |
| 0.48 | 120 | 0.1728 | - |
| 0.52 | 130 | 0.1674 | - |
| 0.56 | 140 | 0.1754 | - |
| 0.6 | 150 | 0.1746 | - |
| 0.64 | 160 | 0.1502 | - |
| 0.68 | 170 | 0.1704 | - |
| 0.72 | 180 | 0.1373 | - |
| 0.76 | 190 | 0.152 | - |
| 0.8 | 200 | 0.15 | - |
| 0.84 | 210 | 0.1397 | - |
| 0.88 | 220 | 0.135 | - |
| 0.92 | 230 | 0.137 | - |
| 0.96 | 240 | 0.106 | - |
| 1.0 | 250 | 0.1309 | 0.2323 |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.2.1
- Transformers: 4.44.2
- PyTorch: 2.4.1+cu121
- Datasets: 3.0.2
- Tokenizers: 0.19.1
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}
}