metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: "Tax Invoice\nOriginal for Buyer/ Duplicate for Transporter/ Triplicate for Assessee\n\nSupplier Legal_Name: Mahaneadi Coalfields 4rea Code +MOO1\nLimited Area Description Jagannath\nSupplier Addresa . Jagriti Vihar, Buria Inv3ice Number -9100065259\nSambalpur 768020 Invoice Date :Dec 3, 2022\nSupplier City - Sambalpur Con=zact Reference: 3030007756\nSupplier State - Odisha Conzzact type ;Spot Auction\nSupplier Pincode : 768020 Salas Order 11240002677\nP.O - Jagriti Vihar, Burla Supplier GSTIN 2134ABCM5188P1Z3 Sale Order Date :Nov 10, 2022\n\nDistrict : Sambalpur - Supplier Email 7 Vode of Dispatch ;ROAD\n768020 Odasha\n\n+91-663-2542461\n\n+91-663-2542770\nWWH .MAHANADICOAL. IN ae4a8clfeb29d373 2dedeaa25bd3 903 7eec4d£013a425b74bd5801750c2ab132\n\nReceiver (Billed To) Consignee (Shipped to) Details of Dispatch\nName »HINDALCO INDUSTRIES LIMITED Name :\nParty Code 2000000395 Party Code 12000000395 Grade ‘G12\nAddress _ HIRAKUD SAMBALPUR SAMBALPUR Addresa _Within Odisha acv + 3701-4000\n768016 Sire :-100 MM\n\nCity * SAMBALPUR City\nPincode - 768016 Pincode Dispatch date Dec 3, 2022\n\nState code Gdasha State code < Plant S046\nPhone number. 06632481365 Phone number\nGSTIN 21AAACH1201R122 GSTIN\n\nE-Mail ID aaurav panigrahi@adityabirla com E-Mail ID\n\nCompany Name\n\na\n\nPARTICULARS\n\nPricing Description i ih | Rate Per UOM (INR Amount (INR)\n\nSizing Charges Fi\nas\n\n \n\nDMF( 30% of Royalty} 18545.29\n\nCGST( 2 5% ) 122.29\n\n[es\n\nTotal Amount: $17597.31\n\nRemarks/Note/ Declaration\n\nReverse Charge Applicable; No\n\nTotal Bill Value In words SIX LAKH SEVENTEEN THOUSAND PIVE HUNDRED NINETY SEV&N RUPEES THIRTY ONE PAISE\n\nCertified that the particulars givan above are true and correct and the amount indicated reprasents the price actually charged and that\n\nthera is no flow of additional consideration directly or indirectly from the buyer.\n\nArea : Jagannath\n— Rete ” Telephone . 6760269528\nLe Amount ° Fax Number : 6760269527\n\nAdviaing Bank Name _NA E-Mail Address . so-sales-jaga.mcl@coalindia, in\n\nThis is digitally verified document hence manual/ physical signature 1s not required\n\nAuthorized Signatory\n\n \n\f"
- text: "Hirakud Administration\n\nFrom: Hirakud Administration\n\nSent: 18 December 2021 12:41 PM\n\nTo: sheela tower\n\nCe: Dusyant Dushkar; Sumit Kumar; Nagesh Pal; SANDEEP TIWARI; Raj Singh; Binay Dash\nSubject: RE: Room booking in hotel\n\nDear Sir,\n\nAs per trailing mail, kindly book 02 more rooms for our guest. Details as under:-\n\n1. Ms Alka Chaubey\n2. Mr Devguru Dash\n\nNote — Host will be Mr. Dusyant Dushkar. Check in date is 19.12.2021. Kindly correct the name of the guest\nin my previous mail, sl no 3 Mr.Subham Goel\n\nRegards\n~ Sandeep Kumar Ranbadia\n\nFrom: sheela tower [mailto:sheelatowers@gmail.com]\nSent: 18 December 2021 12:22 PM\n\nTo: Hirakud Administration <hind-hkd.admin@adityabirla.com>\n\nCe: Dusyant Dushkar <dusyant.dushkar@adityabirla.com>; Sumit Kumar <sumit.skumar@adityabirla.com>; Nagesh Pal\n<nagesh.pal@adityabirla.com>; SANDEEP TIWARI <sandeep.tiwari@adityabirla.com>; Raj Singh\n\n<raj.kumarsingh @adityabirla.com>; Binay Dash <binaya.dash@adityabirla.com>\n\nSubject: Re: Room booking in hotel\n\n \n \n\nCAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you recognize the\n‘sender and know the content is:safe.\n\nDear sir\nGreeting from sheelatowers!!!\n\nWe are confirm 04 business plus room for your guest.\n\nSra\n\nmcteCKotenat\n\na\n\na a\n\n \n\nRegards\nRanjt kumar sahoo\n9778403111\n\f"
- text: "Tax Invoice\nOriginal for Buyer/ Duplicate for Transporter/ Triplicate for Assessee\n\nan ¢\n6 , Mc Supplier Legal Nama, Mahanadi Coalfields Are2 Code .MOO1\n» ta . — i\n\nLimited area Description ;Jagannath 3% Lane a Metareriz ete!\nSupplier Address Jagriti Vihar, Bur-a |Invoice Number =. 9100067434 area isd Sooner at\nSambalpur 768020 Invoice Date :Dec 19, 2022 UA aarp LBL\n; Supplier City : Sambalpur Contract Reference:3030007756 :\n. L Supplier State : Odisha Contract type iSpot Auction\n+ Supplier Pincode : 7@8020 Sales Order 11240002677\nP.O. - Jagriti Vahar, Burla [Supplier GSTIN . 21 QAABCMS188P123 Sals Order Date «Nov 10, 2022\n\nDistrict : Sambalpur - Supplier Email Nod? of Dispatch .ROAD\n768020 Odasha\n\n+91-663-2542461\n\n*91-663+2542770\nWWW. MAHANADICOAL. IN IRN No: 21829066 2bd3486eef9a903185 74daciafc0«13744361e£93477eBd16aa0bast\n\nReceiver (Billed To} Conaignee (Shipred <a) Details of Dispatch\nName : HINDALCO INDUSTRIES LIMITED Name :\nParty Code ,2000000355 Party Code 7 20000003355 Grade » G12\nAddress . FTRAKUD = SAMBALFUR SAMBALPUR Address : Within Odis.a cv - 3701-4000\n768016 Size .-100 MM\n\nCity sSAMBALPUR city Dispatch date :Dec 19, 2022\nPincode . 768016 Pincode\n\nState code .Cdisha State code i Plant 15046\nPhone number: 06632481365 Phone number :\nGSTIN + 21AKRACH1201R122 GSTIN\n\nE-Mail ID : Saurav. panigrahi@adityabirla.com B-Mail ID\n\nCompany Name;\n\nPricing Desoription 7\n\nEvac Facility Charge 60.00 68384.40\nPoyalty Charges ( 14% of Basic Price) $84.12\n\nNMET Charges( 2% of Royalty)\n\neC\n\nGross Bill Value 5536.61 6309612.40\n\n6309612.40\nRemarks/Note/ Declaration Total Amount:\n\nReverse Charge Applicable No\n\nTotal Bill Value In words SIXTY THREE LAKH NINE THOUSAND SIX HUNDRED TWELVE RJPBES FORTY PAISE\n\nCertified that the particulars given above are true and correct and the amount indicated represents the price actually charged and that\n\nthere 18 no flow of additional consideration directly or indirectly Erom tke bayer.\n\nLC Ref.No NA\nLC Date\n\nLe Amount 90\nAdvising Bank Name - NA\n\nArea : Jagannath\nTelephone + 6760269528\nFax Number : ©760269527\nR-Mail Addresa : so-sales-jaga.mcl@coalindia. in\n\nThis is digitally verified document hence manual/ physical signature is not required\n\nAuthorized Signatory\n\n \n\n \n\f"
- text: "UNITED MEDICAL STORE Patient Name: KASTURI uENA\n‘EW MARKET, C/O PRAFULLA KUMAR JENA\nHIRAKUD. SAMBALPUR. Dr. Name :\n\nMedicine Advice Slip: MA/2223/0668 “\nPhone :0663-2431670 Prescription Indent:M/2223/06299\n\nDL No. :SAWZ 486 R/487 RC Invoice No. ; 0002785 Date : 21/11/2022\n\nSe|__Qiy. [Pack [Product “Batch [Exp] HSN [ MRP | Table | Dis [5051] CO3i] Amount |\n\n1. 30 TAB] 30'S TELMA H TAB 11/24 | 30049099; 484.00! 432.14 0.001 6.00\nNEOPRIDE TOTAL CAP 7/24 30049099) 445.00) 0,00; 6.00\n\n \n\n \n\n \n\nSUB TOTAL :\n\nSGST\ner rH 2 ROFF :\n— ha GRAND TOTAL\n\nTe & Con itions For UNITED MEDICAL STORE R a ah\nBILL GRAND TOTAL IS CALCULATED ACCORDING TO 1D- 3306 Im- 1220\nMRP PRICE ( INCLUDING ALL GST TAXES ) Q _ 06 (ped)\n\n \n\f"
- text: "Original for Buyer/\n\nSupplier\n\nSupplier\n\nSupplier\nSupplier\nSupplier\nSupplier\nSupplier\n\nP.O. - Jagriti Vihar, Burla\n\nDistrict : Sambalpur -\n\nLegal _Name:\n\nAddress\n\nCity\nState\nPincode\nGSTIN\nEmail\n\nTax Invoice\nDuplicate for Transporter/ Triplicate for Assessea\n\nMahanadi Coalfields\nLimited\n\nJagriti Vihar, Burla\nSambalpur 768020\n\n: Sambalpur\n\n: Odisha\n\n: 768020\n\n: 21AABCM5186P123\n\nArea Code\n\nArea Description\nInvaice Number\nInvoice Date\n\n:MOO1\nJagannath K Ss pasts\n9100067646 Le\n\nEee yy\n-Dec 21, 2022 4 PSIG Nae\nca ee\n\npar\n\nContract Raference 3030007756\n\nContract typa\nSales Order\n\nSale Order Date\nYods of Dispatch\n\n:Spot Auction\n11240002677\n:Nov 10, 2022\n:ROAD\n\n768020 Odisha\n+91-663-2542461\n+91-663-2542770\nWWW. MAHANADICOAL.IN\nReceiver (Billed To)\n-HINDALCO INDUSTRIES LIMITED\n: 2000000395\nHIRAKUD\n768016\n: SAMBALPUR\nPincoda : 768016\nState code Odisha\nPhone number. 06632481365\nGSTIN . 21AAACH1201R12Z\n\nE-Mail Ip\n\nIRN No. b£1b63c27ecdbbbeOedf{d3b343825 £06861 d200cd310b3e3344c6c0de297£635\n\nConsignee (Shipred -o)\n\nDetails of Dispatch\n\nName\nParty Code\n\nAddress\n\nName\nParty Code\n\nAddress\n\n'Gl2\n: 3701-4000\n-100 MM\n\n'Dec 21,\n\nGrade\n@cv\nSize\n\nDispatch date\n\n: 2000000395\n\nSAMBALPUR SAMBALPUR Within Odisha\n\nCity city\n\nPincede\n\nState code\nPhone number :\nGSTIN\n\n2022\n\nPlant : 5046\n\n- Saurav.panigrahi@adityabirla.com E-Mail ID\n\nCompany Name.\n\n8001237358 42e00c0000 Bituminous Coal 27011200 1128.42\n\nPricing Description TW ate Pee WONT a ay\n\nSizing Charges 87.00 $8172.54\n\nSTC Charges\n\n60.00 67705,20\n\nEvac Facility Charge\n\n$54.12 625280.909\n\nRoyalty Charges ( 14% of Basic Price)\n\n \n\n11.08 12505.$0\n\nNMET Charges{ 2% of Royalty)\n\n166.24 187584 .03\n\nDLMF({ 30% of Royalty)\n137989.92\n\n \n\nCGST( 2.56}\n\n122.28 137989.92\n\nSGST( 2.5% }\n\n400.00 451368.00\n\nGST Comp Cess\n\nGross Bill Value\n\nNet Value\n\nRemarks/Note/ Declaration\n\nTotal Bill Value In words\n\nLC Ref No NA\nLc Date\n\nLe Amount 6\n\nAdvising Bank Name_: NA\n\n \n\nReverse Charge Applicable: No\n\nSIMTY TWO LAKH FORTY SIX THOUSAND NINE HUNDRED FOPTY FOUR RUPEES SEVENTY SIX PAISE\n\nCertified that the particulars givan above are true and correct and tha amount indicated represents the price\nthere is no flow of additional consideration directly or indirectly from the buyer.\n\nArea . Jagannath\nTelephone - 6760269528\nFax Number : 6760269527\n\nE-Mail Address\n\nThie is digitally verified document hence manual/ physical signature 16 not requ.red\n\n5536.01\n\n$536.01 6246944.76\n\nTotal Amount: 6246944.76\n\nactually charged and that\n\n: g0-sales-jaga.mel@coalindia.in\n\nAuthorized Signatory\n\n \n\f"
pipeline_tag: text-classification
inference: true
base_model: BAAI/bge-small-en-v1.5
model-index:
- name: SetFit with BAAI/bge-small-en-v1.5
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 1
name: Accuracy
SetFit with BAAI/bge-small-en-v1.5
This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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: BAAI/bge-small-en-v1.5
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 2 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 |
|---|---|
| 0 |
|
| 1 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 1.0 |
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("Gopal2002/COAL_INVOICE_ZEON")
# Run inference
preds = model("UNITED MEDICAL STORE Patient Name: KASTURI uENA
‘EW MARKET, C/O PRAFULLA KUMAR JENA
HIRAKUD. SAMBALPUR. Dr. Name :
Medicine Advice Slip: MA/2223/0668 “
Phone :0663-2431670 Prescription Indent:M/2223/06299
DL No. :SAWZ 486 R/487 RC Invoice No. ; 0002785 Date : 21/11/2022
Se|__Qiy. [Pack [Product “Batch [Exp] HSN [ MRP | Table | Dis [5051] CO3i] Amount |
1. 30 TAB] 30'S TELMA H TAB 11/24 | 30049099; 484.00! 432.14 0.001 6.00
NEOPRIDE TOTAL CAP 7/24 30049099) 445.00) 0,00; 6.00
SUB TOTAL :
SGST
er rH 2 ROFF :
— ha GRAND TOTAL
Te & Con itions For UNITED MEDICAL STORE R a ah
BILL GRAND TOTAL IS CALCULATED ACCORDING TO 1D- 3306 Im- 1220
MRP PRICE ( INCLUDING ALL GST TAXES ) Q _ 06 (ped)
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 1 | 270.5442 | 4241 |
| Label | Training Sample Count |
|---|---|
| 0 | 130 |
| 1 | 85 |
Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- 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
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0013 | 1 | 0.2394 | - |
| 0.0657 | 50 | 0.1203 | - |
| 0.1314 | 100 | 0.0095 | - |
| 0.1971 | 150 | 0.0029 | - |
| 0.2628 | 200 | 0.0014 | - |
| 0.3285 | 250 | 0.0014 | - |
| 0.3942 | 300 | 0.0011 | - |
| 0.4599 | 350 | 0.0009 | - |
| 0.5256 | 400 | 0.0008 | - |
| 0.5913 | 450 | 0.0007 | - |
| 0.6570 | 500 | 0.0008 | - |
| 0.7227 | 550 | 0.0008 | - |
| 0.7884 | 600 | 0.0006 | - |
| 0.8541 | 650 | 0.0005 | - |
| 0.9198 | 700 | 0.0004 | - |
| 0.9855 | 750 | 0.0005 | - |
| 1.0512 | 800 | 0.0004 | - |
| 1.1170 | 850 | 0.0005 | - |
| 1.1827 | 900 | 0.0004 | - |
| 1.2484 | 950 | 0.0004 | - |
| 1.3141 | 1000 | 0.0003 | - |
| 1.3798 | 1050 | 0.0004 | - |
| 1.4455 | 1100 | 0.0004 | - |
| 1.5112 | 1150 | 0.0004 | - |
| 1.5769 | 1200 | 0.0005 | - |
| 1.6426 | 1250 | 0.0004 | - |
| 1.7083 | 1300 | 0.0003 | - |
| 1.7740 | 1350 | 0.0004 | - |
| 1.8397 | 1400 | 0.0005 | - |
| 1.9054 | 1450 | 0.0004 | - |
| 1.9711 | 1500 | 0.0003 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
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}
}