--- tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: '"MSME AUTO RENEWAL renewal criteria for defaults?"' - text: '"HARIT current account NRI eligibility for overseas projects?"' - text: '"Current account disaster relief funding?"' - text: '"How to track Foreign Exchange transactions online?"' - text: '"RERA Current account insurance for project risks?"' metrics: - accuracy pipeline_tag: text-classification library_name: setfit inference: true base_model: sentence-transformers/paraphrase-mpnet-base-v2 model-index: - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.9351851851851852 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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 body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 135 classes ### 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) ### Model Labels | Label | Examples | |:-----------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Remittance To India | | | Executive Director’s Profile | | | INDIAN BANK MUTUAL FUND | | | IND MSME VEHICLE | | | Awards & Accolades | | | Supply Chain Finance | | | Merchant UPI QR Code | | | Loan/OD against Deposit | | | Re-KYC: Periodic Update of KYC Details | | | IND SUPER 400 DAYS | | |  Centralized Pension Processing Centre | | | CA FOR STATE /CENTRAL GOVT & CONSULAR & IND PFMS | | | Indian Bank, IFSC Banking Unit, GIFT City | | | F.A.Qs | | |  IND GST ADVANTAGE | | | Digitizing the Indian Banking Experience | | | Terms and Conditions Indian Bank Digital Rupee | | | National Common Mobility Card (NCMC) | | | IMAGE | | | IndSMART: Indian Bank’s Omni channel Mobile App | | | Disclaimer | | | Term Deposits | | | Interest Rates for Small Savings Schemes | | | NRI and Forex | | | Azadi Ka Amrit Mahotsav #TogetherforBiggerThings | | | IB MSME Jewel Loan | | | IB Golden Ager Term Deposit Product for Super Senior Citizens | | | What is a Credit Score and How it Shapes Financial Health | | | IMPORTANT TERMS AND CONDITIONS CA | | | Credit Cards | | | Managing Director & CEO’s Profile | | | Jewel Loan | | | Corporate Social Responsibility | | | Scheme on financing Manufacturers / Suppliers / Vendors of Solar panels and other ancillary products | | | Board of Directors | | | Quick Contact | | | Vision and Mission | | | Corporate | | | Service Charges / Forex Rates | | | Welfare of Minorities | | | Bancassurance | | |  IND PM Vishwakarma | | | IB Tax Saver Scheme | | | Weaver MUDRA | | | Chief Vigilance Officer | | | Careers | | | Press Releases | | | Online Collection Products | | | IND-SURYA SHAKTI | | | IND-SME EASE | | | e-Allahabad Bank Journey | | | IndSMART | | | Fixed Deposit | | | Scheme for financing MSMEs for setting up Biomass Pellets manufacturing units | | | TERMS AND CONDITIONS-TERM DEPOSIT ACCOUNT | | | IND SME Secure | | | Investor Relations | | | Ind Advantage (Reward Program) | | | Welcome aboard! | | | Deposit Rates | | |  Loyalty Program Delights: Unlocking Special Rewards for Your Loyalty | | | NETC FASTag | | | IB Tradewell | | | PM Surya Ghar: Muft Bijli Yojna | | | IND SUPREME 300 DAYS | | | Sukanya Samriddhi Account | | | IND NAVYA | | | Short Term Deposits | | | Block Lost ATM Card | | | MSME DIGI Jewel Loan and Jewel Loan (Re-Pledge) | | | Nodal Officers- Customer service | | | MSME AUTO RENEWAL | | | IB COMFORT- DOMESTIC AND NRE | | | LOAN AGAINST LEASE RENTALS | | | IB HARIT | | | SMS Banking/ Missed Call Service | | | MSME LAP | | | Head Office Departments | | | Current Account | | | IND COURT | | | Amalgamation | | | IND Professional Special | | | Foreign Branches | | | Regulatory Disclosures Section | | | N R I / Foreign Exchange | | | NRI A/cs | | | Reverse Mortgage | | | Block Lost Credit Card | | | Death Claim Settlement | | | Online Loans | | | Service Charges | | | Notifications | | | Corporate Blog | | | Premium Current Account | | | Pre Approved Business Loan | | | Doorstep Banking | | | Point of Sale (PoS) | | | ATM / Debit Cards | | | BHIM Aadhaar Pay | | | Capital Gains | | | Indian Bank Financial Results | | | Customer Centric Services | | | Positive Pay System (PPS) | | | Motor Accident Claim Tribunal Deposit(MACAD) Scheme | | | IND HEALTH CARE | | | Loan / OD against NSC / KVP / Relief bonds of RBI / LIC policies | | | Lab Grown Diamond Scheme | | |  IB RERA Current Account | | | IND EQUIPMENT & WHEELS (CE/CV) scheme | | | IMAGE Email Id’s | | | General Managers | | | Money multiplier Deposits | | | IB Loan against Sovereign Gold Bond | | | Branch ATM | | | Financial Inclusion in India: Filling the Void | | | Jaffna Branch | | | Financial Inclusion | | | Featured Products / Services / Schemes | | | Another Option for Pension | | | Bank’s Profile | | | SHISHU MUDRA | | | e Payment of Indirect Taxes | | | IND Non-Callable Deposit | | | Services rendered free of charge | | | Debit Cards | | | Chief General Managers | | | Colombo Branch | | | Ind Mortgage | | | Recurring Deposit | | | e Payment of Direct Taxes | | | Lending rates | | | Entity: Internet banking | | | Customer Complaints / Awareness | | | IND-SME E-VAAHAN | | | Variable Recurring Deposit | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.9352 | ## 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("kneau007/my-classifier-2") # Run inference preds = model("\"Current account disaster relief funding?\"") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:-------|:----| | Word count | 3 | 5.5968 | 11 | | Label | Training Sample Count | |:-----------------------------------------------------------------------------------------------------|:----------------------| | Corporate Blog | 11 | | Doorstep Banking | 17 | | ATM / Debit Cards | 15 | | Amalgamation | 17 | | Another Option for Pension | 17 | | Awards & Accolades | 18 | | Azadi Ka Amrit Mahotsav #TogetherforBiggerThings | 16 | | BHIM Aadhaar Pay | 12 | | Bancassurance | 17 | | Bank’s Profile | 16 | | Block Lost ATM Card | 16 | | Block Lost Credit Card | 17 | | Board of Directors | 15 | | Branch ATM | 14 | | CA FOR STATE /CENTRAL GOVT & CONSULAR & IND PFMS | 18 | | Capital Gains | 18 | | Careers | 15 | | Chief General Managers | 16 | | Chief Vigilance Officer | 19 | | Colombo Branch | 16 | | Corporate | 15 | | Corporate Social Responsibility | 17 | | Credit Cards | 19 | | Current Account | 16 | | Customer Centric Services | 15 | | Customer Complaints / Awareness | 13 | | Death Claim Settlement | 17 | | Debit Cards | 17 | | Deposit Rates | 12 | | Digitizing the Indian Banking Experience | 17 | | Disclaimer | 16 | | Entity: Internet banking | 15 | | Executive Director’s Profile | 17 | | F.A.Qs | 15 | | Featured Products / Services / Schemes | 16 | | Financial Inclusion | 15 | | Financial Inclusion in India: Filling the Void | 16 | | Fixed Deposit | 16 | | Foreign Branches | 15 | | General Managers | 16 | | Head Office Departments | 16 | | IB COMFORT- DOMESTIC AND NRE | 14 | | IB Golden Ager Term Deposit Product for Super Senior Citizens | 18 | | IB HARIT | 15 | | IB Loan against Sovereign Gold Bond | 16 | | IB MSME Jewel Loan | 13 | | IB Tax Saver Scheme | 18 | | IB Tradewell | 17 | | IMAGE | 18 | | IMAGE Email Id’s | 17 | | IMPORTANT TERMS AND CONDITIONS CA | 16 | | IND COURT | 17 | | IND EQUIPMENT & WHEELS (CE/CV) scheme | 12 | | IND HEALTH CARE | 17 | | IND MSME VEHICLE | 17 | | IND NAVYA | 17 | | IND Non-Callable Deposit | 14 | | IND Professional Special | 17 | | IND SME Secure | 18 | | IND SUPER 400 DAYS | 13 | | IND SUPREME 300 DAYS | 18 | | IND-SME E-VAAHAN | 15 | | IND-SME EASE | 12 | | IND-SURYA SHAKTI | 14 | | INDIAN BANK MUTUAL FUND | 18 | | Ind Advantage (Reward Program) | 17 | | Ind Mortgage | 14 | | IndSMART | 15 | | IndSMART: Indian Bank’s Omni channel Mobile App | 14 | | Indian Bank Financial Results | 18 | | Indian Bank, IFSC Banking Unit, GIFT City | 17 | | Interest Rates for Small Savings Schemes | 18 | | Investor Relations | 17 | | Jaffna Branch | 18 | | Jewel Loan | 17 | | LOAN AGAINST LEASE RENTALS | 14 | | Lab Grown Diamond Scheme | 14 | | Lending rates | 17 | | Loan / OD against NSC / KVP / Relief bonds of RBI / LIC policies | 20 | | Loan/OD against Deposit | 15 | | MSME AUTO RENEWAL | 19 | | MSME DIGI Jewel Loan and Jewel Loan (Re-Pledge) | 16 | | MSME LAP | 18 | | Managing Director & CEO’s Profile | 17 | | Merchant UPI QR Code | 14 | | Money multiplier Deposits | 14 | | Motor Accident Claim Tribunal Deposit(MACAD) Scheme | 14 | | N R I / Foreign Exchange | 14 | | NETC FASTag | 17 | | NRI A/cs | 17 | | NRI and Forex | 15 | | National Common Mobility Card (NCMC) | 16 | | Nodal Officers- Customer service | 16 | | Notifications | 16 | | Online Collection Products | 12 | | Online Loans | 15 | | PM Surya Ghar: Muft Bijli Yojna | 19 | | Point of Sale (PoS) | 17 | | Positive Pay System (PPS) | 15 | | Pre Approved Business Loan | 16 | | Premium Current Account | 18 | | Press Releases | 16 | | Quick Contact | 14 | | Re-KYC: Periodic Update of KYC Details | 17 | | Recurring Deposit | 17 | | Regulatory Disclosures Section | 15 | | Remittance To India | 14 | | Reverse Mortgage | 16 | | SHISHU MUDRA | 19 | | SMS Banking/ Missed Call Service | 15 | | Scheme for financing MSMEs for setting up Biomass Pellets manufacturing units | 15 | | Scheme on financing Manufacturers / Suppliers / Vendors of Solar panels and other ancillary products | 15 | | Service Charges | 19 | | Service Charges / Forex Rates | 16 | | Services rendered free of charge | 17 | | Short Term Deposits | 16 | | Sukanya Samriddhi Account | 13 | | Supply Chain Finance | 15 | | TERMS AND CONDITIONS-TERM DEPOSIT ACCOUNT | 18 | | Term Deposits | 16 | | Terms and Conditions Indian Bank Digital Rupee | 17 | | Variable Recurring Deposit | 16 | | Vision and Mission | 16 | | Weaver MUDRA | 18 | | Welcome aboard! | 16 | | Welfare of Minorities | 15 | | What is a Credit Score and How it Shapes Financial Health | 18 | | e Payment of Direct Taxes | 14 | | e Payment of Indirect Taxes | 17 | | e-Allahabad Bank Journey | 13 | |  Centralized Pension Processing Centre | 15 | |  IB RERA Current Account | 19 | |  IND GST ADVANTAGE | 16 | |  IND PM Vishwakarma | 15 | |  Loyalty Program Delights: Unlocking Special Rewards for Your Loyalty | 18 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (1, 1) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 20 - body_learning_rate: (2e-05, 2e-05) - head_learning_rate: 2e-05 - 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: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:----:|:-------------:|:---------------:| | 0.0002 | 1 | 0.1566 | - | | 0.0093 | 50 | 0.146 | - | | 0.0185 | 100 | 0.1398 | - | | 0.0278 | 150 | 0.1027 | - | | 0.0371 | 200 | 0.0887 | - | | 0.0463 | 250 | 0.071 | - | | 0.0556 | 300 | 0.0644 | - | | 0.0649 | 350 | 0.0492 | - | | 0.0741 | 400 | 0.05 | - | | 0.0834 | 450 | 0.0464 | - | | 0.0927 | 500 | 0.0325 | - | | 0.1019 | 550 | 0.0312 | - | | 0.1112 | 600 | 0.033 | - | | 0.1205 | 650 | 0.0266 | - | | 0.1297 | 700 | 0.0225 | - | | 0.1390 | 750 | 0.0206 | - | | 0.1483 | 800 | 0.0188 | - | | 0.1576 | 850 | 0.0229 | - | | 0.1668 | 900 | 0.0164 | - | | 0.1761 | 950 | 0.0168 | - | | 0.1854 | 1000 | 0.0159 | - | | 0.1946 | 1050 | 0.0131 | - | | 0.2039 | 1100 | 0.0122 | - | | 0.2132 | 1150 | 0.0098 | - | | 0.2224 | 1200 | 0.0093 | - | | 0.2317 | 1250 | 0.0159 | - | | 0.2410 | 1300 | 0.0104 | - | | 0.2502 | 1350 | 0.014 | - | | 0.2595 | 1400 | 0.0074 | - | | 0.2688 | 1450 | 0.0089 | - | | 0.2780 | 1500 | 0.0176 | - | | 0.2873 | 1550 | 0.0118 | - | | 0.2966 | 1600 | 0.0068 | - | | 0.3058 | 1650 | 0.0105 | - | | 0.3151 | 1700 | 0.0076 | - | | 0.3244 | 1750 | 0.0122 | - | | 0.3336 | 1800 | 0.0134 | - | | 0.3429 | 1850 | 0.0088 | - | | 0.3522 | 1900 | 0.0134 | - | | 0.3614 | 1950 | 0.0052 | - | | 0.3707 | 2000 | 0.0074 | - | | 0.3800 | 2050 | 0.0069 | - | | 0.3892 | 2100 | 0.0056 | - | | 0.3985 | 2150 | 0.0059 | - | | 0.4078 | 2200 | 0.0064 | - | | 0.4171 | 2250 | 0.0075 | - | | 0.4263 | 2300 | 0.0064 | - | | 0.4356 | 2350 | 0.0042 | - | | 0.4449 | 2400 | 0.0053 | - | | 0.4541 | 2450 | 0.0061 | - | | 0.4634 | 2500 | 0.0062 | - | | 0.4727 | 2550 | 0.0076 | - | | 0.4819 | 2600 | 0.004 | - | | 0.4912 | 2650 | 0.009 | - | | 0.5005 | 2700 | 0.0096 | - | | 0.5097 | 2750 | 0.0066 | - | | 0.5190 | 2800 | 0.0084 | - | | 0.5283 | 2850 | 0.0052 | - | | 0.5375 | 2900 | 0.0079 | - | | 0.5468 | 2950 | 0.005 | - | | 0.5561 | 3000 | 0.0053 | - | | 0.5653 | 3050 | 0.0055 | - | | 0.5746 | 3100 | 0.0049 | - | | 0.5839 | 3150 | 0.0066 | - | | 0.5931 | 3200 | 0.0074 | - | | 0.6024 | 3250 | 0.0063 | - | | 0.6117 | 3300 | 0.0039 | - | | 0.6209 | 3350 | 0.0042 | - | | 0.6302 | 3400 | 0.0072 | - | | 0.6395 | 3450 | 0.0047 | - | | 0.6487 | 3500 | 0.0037 | - | | 0.6580 | 3550 | 0.0048 | - | | 0.6673 | 3600 | 0.0034 | - | | 0.6766 | 3650 | 0.0067 | - | | 0.6858 | 3700 | 0.0049 | - | | 0.6951 | 3750 | 0.0048 | - | | 0.7044 | 3800 | 0.0041 | - | | 0.7136 | 3850 | 0.0088 | - | | 0.7229 | 3900 | 0.0035 | - | | 0.7322 | 3950 | 0.0047 | - | | 0.7414 | 4000 | 0.005 | - | | 0.7507 | 4050 | 0.0047 | - | | 0.7600 | 4100 | 0.0051 | - | | 0.7692 | 4150 | 0.0035 | - | | 0.7785 | 4200 | 0.0043 | - | | 0.7878 | 4250 | 0.0062 | - | | 0.7970 | 4300 | 0.0029 | - | | 0.8063 | 4350 | 0.0076 | - | | 0.8156 | 4400 | 0.0027 | - | | 0.8248 | 4450 | 0.0026 | - | | 0.8341 | 4500 | 0.0037 | - | | 0.8434 | 4550 | 0.0069 | - | | 0.8526 | 4600 | 0.0037 | - | | 0.8619 | 4650 | 0.0027 | - | | 0.8712 | 4700 | 0.0025 | - | | 0.8804 | 4750 | 0.0024 | - | | 0.8897 | 4800 | 0.0076 | - | | 0.8990 | 4850 | 0.0036 | - | | 0.9082 | 4900 | 0.0028 | - | | 0.9175 | 4950 | 0.0027 | - | | 0.9268 | 5000 | 0.0028 | - | | 0.9361 | 5050 | 0.005 | - | | 0.9453 | 5100 | 0.0041 | - | | 0.9546 | 5150 | 0.0042 | - | | 0.9639 | 5200 | 0.004 | - | | 0.9731 | 5250 | 0.0027 | - | | 0.9824 | 5300 | 0.0049 | - | | 0.9917 | 5350 | 0.0044 | - | ### Framework Versions - Python: 3.11.11 - SetFit: 1.1.1 - Sentence Transformers: 3.4.1 - Transformers: 4.48.3 - PyTorch: 2.6.0+cu124 - Datasets: 3.4.0 - 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} } ```