README.md

---
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 'hasAdditionalInformation: 8pg Self Cover Brochure Flat 17" x 8.5" Accordion
    Folded 4.25" x 8.5"  Ink - 4/4, 4CP + OA Satin AQ Stock - 100# Gloss Text  Finishing
    - Score, Trim, Accordion Fold, Shrink Wrap in 25''s, hasArtworkDoubleSidedStatus:
    Double Sided Different, hasCoatingOrSealer: Aqueous, hasColourDetails: Prints
    4/4, 4CP + OA Satin AQ, hasCreatedDate: 2024-04-12, hasCustomerHomeCountry: United
    States, hasCustomerID: 19754, hasCustomerName: Kenvue, Inc.(Kenvue - Skillman),
    hasCutting: Trim to size, hasElementID: 3229443, hasElementTitle: NTG General
    Sun Brochure 2024, hasFinishedSizeHeight: 8.5, hasFinishedSizeWidth: 4.25, hasFlatSizeHeight:
    8.5, hasFlatSizeWidth: 17, hasFscPaperBeenSpecified: No, hasInternalID: b7dd2ed8-0a5f-4e57-8d8a-4aa41afa9d84,
    hasMachineFinishing: Yes, hasMachineFinishingDetails: Score, Trim, Accordion Fold,
    Shrink Wrap in 25''s, hasMaterialCategory: Paper, hasMaterialDescription: 100#
    Gloss Text, hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 100,
    hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: GSM, hasNumberOfVersions:
    1, hasPackingRequirements: Delivers to Encompass Elements, hasPrice: 45 USD, hasPrintedSides:
    Double sided, hasProductCategory: Booklets & Brochures, hasProofType: PDF digital
    proof, hasQuantity: 200000, hasRecycledContentBeenOffered: N/A, hasSendToDetails:
    PDF PROOF to Rick Stoy ( [email protected] ), hasSupplierName: HH IC Preflight
    Fees(HH IC Preflight Fees), hasTotalColours: 4, hasTotalColoursFace: 4, hasUnitOfMeasure:
    Millimetres (mm), '
- text: 'hasArtworkDoubleSidedStatus: Double Sided Different, hasCreatedDate: 2024-01-05,
    hasCustomerHomeCountry: United States, hasCustomerID: 32045, hasCustomerName:
    Rent-A-Center, Inc.(Rent-A-Center), hasCutting: Trim to size, hasElementID: 3046855,
    hasElementTitle: Loyalty Postcards - 4 Versions , hasFinishedSizeHeight: 4.5,
    hasFinishedSizeWidth: 6, hasFlatSizeHeight: 4.5, hasFlatSizeWidth: 6, hasFscPaperBeenSpecified:
    No, hasInternalID: 7bad5a0e-1e7b-4a1a-94e6-97e6ccd30055, hasMaterialCategory:
    Paper, hasMaterialDescription: 80# Dull Cover, hasMaterialRecycledPercentage:
    0%, hasMaterialThicknessOrWeight: 80, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure:
    Pounds (lbs), hasNumberOfVersions: 4, hasPrice: 156.3 USD, hasPrintedSides: Double
    sided, hasProductCategory: Loose Print, hasProofType: PDF digital proof, hasQuantity:
    48, hasRecycledContentBeenOffered: N/A, hasSupplierName: American Printing & Mailing(American
    Printing & Mailing - HHGSP PI), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), '
- text: 'hasAdditionalInformation: QTY – 250 + Overs  Size Flat 2,625" x 2.375" Folded
    2.625" x 1.1875"  Prints 1/1 Stock -  80# Gloss Text   Finishing – Die cut to
    shape ( round corners ) Apply strip of fugitive glue on Blank Back Panel, Fold
    and Seal with dot of Fugitive Glue, hasArtworkDoubleSidedStatus: Double Sided
    Different, hasColourDetails: 1/1, Black, hasCreatedDate: 2024-02-08, hasCustomerHomeCountry:
    United States, hasCustomerID: 19754, hasCustomerName: Kenvue, Inc.(Kenvue - Skillman),
    hasCutting: Trim to size, hasElementID: 3111960, hasElementTitle: Project Pismo
    NTG Ultra Sheer Face Liquid Folded Panel FILLED , hasFinishedSizeHeight: 1.1875,
    hasFinishedSizeWidth: 2.625, hasFlatSizeHeight: 2.375, hasFlatSizeWidth: 2.625,
    hasFscPaperBeenSpecified: No, hasInternalID: 3948f154-5211-4628-b0cf-ac69cd6597d1,
    hasMachineFinishing: Yes, hasMachineFinishingDetails: Die cut folding panel and
    fold in half. seal closed with 1 removable low tack glue dot. Apply kleenstick
    strip with liner to back panel leaving liner in tact for application, hasMaterialCategory:
    Paper, hasMaterialDescription: 80# Gloss Text, hasMaterialRecycledPercentage:
    0%, hasMaterialThicknessOrWeight: 80, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure:
    GSM, hasNumberOfVersions: 1, hasPackingRequirements: Deliver to Skillman, hasPrice:
    1390 USD, hasPrintedSides: Double sided, hasProductCategory: Booklets & Brochures,
    hasProofType: PDF digital proof, hasQuantity: 250, hasQuantityPerVersion: 250,
    hasRecycledContentBeenOffered: No, hasSendToDetails: Send PDF PROOF to Shawn Beury
    ( [email protected] ), hasSupplierName: Hatteras Press(Hatteras Press -HHGSP
    - PI), hasTotalColours: 1, hasUnitOfMeasure: Inches (in), '
- text: 'hasAdditionalInformation: 2,400 packs of 25 of Trifold brochure, hasColourDetails:
    4/4 + Bleed, hasCreatedDate: 2024-09-20, hasCustomerHomeCountry: United States,
    hasCustomerID: 26760, hasCustomerName: Elanco Animal Health(Elanco Animal Health),
    hasCutting: Trim to size, hasElementID: 3522746, hasElementTitle: EM-US-20-0069,
    Dog Health Brochure Reprint, hasFinishedSizeHeight: 8.5, hasFinishedSizeWidth:
    3.67, hasFlatSizeHeight: 8.5, hasFlatSizeWidth: 11, hasFscPaperBeenSpecified:
    No, hasInternalID: bab8cdea-2c32-4de2-b783-3616742e6533, hasMachineFinishing:
    Yes, hasMachineFinishingDetails: Trim, Score, Fold & s/w in packs of 25, hasMaterialCategory:
    Paper, hasMaterialDescription: Dull Cover, hasMaterialRecycledPercentage: 0%,
    hasMaterialThicknessOrWeight: 80, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure:
    Pounds (lbs), hasNumberOfVersions: 1, hasPackingRequirements: Carton pack s/w
    packs of 25 - Label Cartons EM-US-20-0069, Dog Health Brochure  with item barcode
    and Qty per carton - & Ship to DFS, hasPrice: 2045 USD, hasPrintedSides: Double
    sided, hasProductCategory: Booklets & Brochures, hasProofType: PDF digital proof,
    hasQuantity: 5750, hasRecycledContentBeenOffered: N/A, hasSupplierName: Modern
    Litho – Kansas City(Modernlitho  -James Printing. Inc - HHGSP), hasTotalColours:
    4, hasTotalColoursFace: 4, hasUnitOfMeasure: Inches (in), '
- text: 'hasAdditionalInformation: 299mm x 200mm sheet size. Kiss cut magnets - Printed
    1 colour onto 1mm white magnetic sheets, CAD and kiss cut - see cutter guide.
    Layout - 13 deep and 20 wide @ 23mm x 10mm, hasColourDetails: Digitally printed
    1 colour black to face of 1mm white magnetic sheet, hasCreatedDate: 2024-05-17,
    hasCustomerHomeCountry: United Kingdom, hasCustomerID: 37488, hasCustomerName:
    Imperial Tobacco Ltd UK(Imperial Tobacco Ltd UK), hasCutting: Cut to shape, hasElementID:
    3293613, hasElementTitle: HHG0036F Generic Magnetic Price List Numerals, hasFinishedSizeHeight:
    299, hasFinishedSizeWidth: 200, hasFscPaperBeenSpecified: No, hasInternalID: 99124112-8ee2-44d4-9170-701acadadf62,
    hasMachineFinishing: Yes, hasMachineFinishingDetails: Cad and kiss cut, hasMaterialCategory:
    Plastic, hasMaterialDescription: 1mm white Isotropic ferrite powder with PVC binder,
    hasMaterialRecycledPercentage: 5%, hasMaterialThicknessOrWeight: 1, hasMaterialType:
    PVC, hasMaterialUnitOfMeasure: Millimetres (mm), hasNumberOfVersions: 1, hasPackingRequirements:
    Collate into sets with back boards and SKU magnets IF required, otherwise box
    in 50s, hasPressWetProofQuantity: 1, hasPrice: 2100 GBP, hasPrintedSides: Single
    sided, hasProductCategory: Indoor/Outdoor Signage, hasProofType: Press / wet proof,
    hasQuantity: 350, hasRecycledContentBeenOffered: No, hasSendToDetails: FAO Claire
    Jackway Imperial Brands Bristol., hasSupplierName: RDD Europe Ltd(RDD Europe Ltd),
    hasTotalColours: 1, hasUnitOfMeasure: Millimetres (mm), '
metrics:
- f1_micro
- f1_macro
- f1_weighted
- precision
- accuracy
- recall
pipeline_tag: text-classification
library_name: setfit
inference: false
model-index:
- name: SetFit
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: Northell/ros-classifiers-materials-flat
      type: unknown
      split: test
    metrics:
    - type: f1_micro
      value: 0.0
      name: F1_Micro
    - type: f1_macro
      value: 0.0
      name: F1_Macro
    - type: f1_weighted
      value: 0.0
      name: F1_Weighted
    - type: precision
      value: .nan
      name: Precision
    - type: accuracy
      value: 0.9772727489471436
      name: Accuracy
    - type: recall
      value: 0.0
      name: Recall
---

# SetFit

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A OneVsRestClassifier instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

## Model Details

### Model Description
- **Model Type:** SetFit
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
- **Classification head:** a OneVsRestClassifier instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 44 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### Model Sources

- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)

## Evaluation

### Metrics
| Label   | F1_Micro | F1_Macro | F1_Weighted | Precision | Accuracy | Recall |
|:--------|:---------|:---------|:------------|:----------|:---------|:-------|
| **all** | 0.0      | 0.0      | 0.0         | nan       | 0.9773   | 0.0    |

## Uses

### Direct Use for Inference

First install the SetFit library:

```bash
pip install setfit
```

Then you can load this model and run inference.

```python
from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("hasArtworkDoubleSidedStatus: Double Sided Different, hasCreatedDate: 2024-01-05, hasCustomerHomeCountry: United States, hasCustomerID: 32045, hasCustomerName: Rent-A-Center, Inc.(Rent-A-Center), hasCutting: Trim to size, hasElementID: 3046855, hasElementTitle: Loyalty Postcards - 4 Versions , hasFinishedSizeHeight: 4.5, hasFinishedSizeWidth: 6, hasFlatSizeHeight: 4.5, hasFlatSizeWidth: 6, hasFscPaperBeenSpecified: No, hasInternalID: 7bad5a0e-1e7b-4a1a-94e6-97e6ccd30055, hasMaterialCategory: Paper, hasMaterialDescription: 80# Dull Cover, hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 80, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: Pounds (lbs), hasNumberOfVersions: 4, hasPrice: 156.3 USD, hasPrintedSides: Double sided, hasProductCategory: Loose Print, hasProofType: PDF digital proof, hasQuantity: 48, hasRecycledContentBeenOffered: N/A, hasSupplierName: American Printing & Mailing(American Printing & Mailing - HHGSP PI), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), ")
```

<!--
### Downstream Use

*List how someone could finetune this model on their own dataset.*
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Set Metrics
| Training set | Min | Median   | Max |
|:-------------|:----|:---------|:----|
| Word count   | 77  | 113.9875 | 202 |

### Framework Versions
- Python: 3.10.16
- SetFit: 1.1.1
- Sentence Transformers: 3.4.1
- Transformers: 4.49.0
- PyTorch: 2.6.0+cu124
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## Citation

### BibTeX
```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}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->