| --- |
| language: |
| - en |
| license: apache-2.0 |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - dense |
| - generated_from_trainer |
| - dataset_size:1200 |
| - loss:ContrastiveLoss |
| base_model: google/embeddinggemma-300m |
| widget: |
| - source_sentence: 'TaxYear: 2025 PRELIMINARY |
| |
| LandJustValue: $571,965 |
| |
| ImprovementsJustValue: $444,893 |
| |
| TotalJustValue: $1,016,858 |
| |
| SchoolAssessedValue: $657,902 |
| |
| CountyTaxableValue: $607,180 |
| |
| TotalTaxes: $5,881.02 |
| |
| |
| TaxYear: 2024 |
| |
| LandJustValue: $529,037 |
| |
| ImprovementsJustValue: $522,202 |
| |
| TotalJustValue: $1,051,239 |
| |
| SchoolAssessedValue: $639,361 |
| |
| CountyTaxableValue: $589,361 |
| |
| TotalTaxes: $6,003.53 |
| |
| |
| TaxYear: 2023 |
| |
| LandJustValue: $500,470 |
| |
| ImprovementsJustValue: $572,889 |
| |
| TotalJustValue: $1,073,359 |
| |
| SchoolAssessedValue: $620,739 |
| |
| CountyTaxableValue: $570,739 |
| |
| TotalTaxes: $5,956.52 |
| |
| |
| TaxYear: 2022 |
| |
| LandJustValue: $230,519 |
| |
| ImprovementsJustValue: $610,503 |
| |
| TotalJustValue: $841,022 |
| |
| SchoolAssessedValue: $602,659 |
| |
| CountyTaxableValue: $552,659 |
| |
| TotalTaxes: $6,124.86 |
| |
| |
| TaxYear: 2021 |
| |
| LandJustValue: $112,658 |
| |
| ImprovementsJustValue: $472,448 |
| |
| TotalJustValue: $585,106 |
| |
| SchoolAssessedValue: $585,106 |
| |
| CountyTaxableValue: $535,106 |
| |
| TotalTaxes: $6,190.98section: Tax, |
| |
| county: Collier, |
| |
| parcel_id: 82660002628' |
| sentences: |
| - 'area_under_air: 2111 |
| |
| livable_floor_area: 2111 |
| |
| parcel_identifier: 51978031927 |
| |
| property_structure_built_year: 2004 |
| |
| property_type: SingleFamily |
| |
| subdivision: INDIGO LAKES UNIT |
| |
| total_area: 2551' |
| - 'monthly_tax_amount: 490.09 |
| |
| period_end_date: 2025-12-31 |
| |
| period_start_date: 2025-01-01 |
| |
| property_assessed_value_amount: 657902 |
| |
| property_building_amount: 444893 |
| |
| property_land_amount: 571965 |
| |
| property_market_value_amount: 1016858 |
| |
| property_taxable_value_amount: 607180 |
| |
| tax_year: 2025 |
| |
| yearly_tax_amount: 5881.02 |
| |
| |
| monthly_tax_amount: 510.41 |
| |
| period_end_date: 2022-12-31 |
| |
| period_start_date: 2022-01-01 |
| |
| property_assessed_value_amount: 602659 |
| |
| property_building_amount: 610503 |
| |
| property_land_amount: 230519 |
| |
| property_market_value_amount: 841022 |
| |
| property_taxable_value_amount: 552659 |
| |
| tax_year: 2022 |
| |
| yearly_tax_amount: 6124.86' |
| - 'ownership_transfer_date: 2013-07-09 |
| |
| purchase_price_amount: 830000 |
| |
| |
| ownership_transfer_date: 2011-10-03 |
| |
| purchase_price_amount: 685000 |
| |
| |
| ownership_transfer_date: 2009-07-01 |
| |
| purchase_price_amount: 432500 |
| |
| |
| ownership_transfer_date: 1999-02-22 |
| |
| purchase_price_amount: 0 |
| |
| |
| ownership_transfer_date: 2001-01-25 |
| |
| purchase_price_amount: 360000' |
| - source_sentence: 'TaxYear: 2025 PRELIMINARY |
| |
| LandJustValue: $0 |
| |
| ImprovementsJustValue: $261,720 |
| |
| TotalJustValue: $261,720 |
| |
| SchoolAssessedValue: $261,720 |
| |
| CountyTaxableValue: $261,720 |
| |
| TotalTaxes: $3,142.17 |
| |
| |
| TaxYear: 2024 |
| |
| LandJustValue: $0 |
| |
| ImprovementsJustValue: $261,720 |
| |
| TotalJustValue: $261,720 |
| |
| SchoolAssessedValue: $261,720 |
| |
| CountyTaxableValue: $261,720 |
| |
| TotalTaxes: $3,551.55 |
| |
| |
| TaxYear: 2023 |
| |
| LandJustValue: $0 |
| |
| ImprovementsJustValue: $298,680 |
| |
| TotalJustValue: $298,680 |
| |
| SchoolAssessedValue: $298,680 |
| |
| CountyTaxableValue: $298,680 |
| |
| TotalTaxes: $4,125.27 |
| |
| |
| TaxYear: 2022 |
| |
| LandJustValue: $0 |
| |
| ImprovementsJustValue: $233,985 |
| |
| TotalJustValue: $233,985 |
| |
| SchoolAssessedValue: $233,985 |
| |
| CountyTaxableValue: $172,700 |
| |
| TotalTaxes: $2,771.07 |
| |
| |
| TaxYear: 2021 |
| |
| LandJustValue: $0 |
| |
| ImprovementsJustValue: $157,000 |
| |
| TotalJustValue: $157,000 |
| |
| SchoolAssessedValue: $157,000 |
| |
| CountyTaxableValue: $157,000 |
| |
| TotalTaxes: $2,342.18section: Tax, |
| |
| county: Collier, |
| |
| parcel_id: 31760000209' |
| sentences: |
| - 'first_name: George |
| |
| last_name: Lewis |
| |
| middle_name: P |
| |
| |
| first_name: Karen |
| |
| last_name: Lewis |
| |
| middle_name: L' |
| - 'area_under_air: 997 |
| |
| livable_floor_area: 997 |
| |
| parcel_identifier: 31731720000 |
| |
| property_legal_description_text: FAIRWAY FOREST GARDEN VILLAS A CONDOMINIUM UNIT |
| 179 |
| |
| property_structure_built_year: 1987 |
| |
| property_type: Condominium |
| |
| total_area: 997' |
| - 'monthly_tax_amount: 195.18 |
| |
| period_end_date: 2021-12-31 |
| |
| period_start_date: 2021-01-01 |
| |
| property_assessed_value_amount: 157000 |
| |
| property_building_amount: 157000 |
| |
| property_land_amount: 0 |
| |
| property_market_value_amount: 157000 |
| |
| property_taxable_value_amount: 157000 |
| |
| tax_year: 2021 |
| |
| yearly_tax_amount: 2342.18 |
| |
| |
| monthly_tax_amount: 261.85 |
| |
| period_end_date: 2025-12-31 |
| |
| period_start_date: 2025-01-01 |
| |
| property_assessed_value_amount: 261720 |
| |
| property_building_amount: 261720 |
| |
| property_land_amount: 0 |
| |
| property_market_value_amount: 261720 |
| |
| property_taxable_value_amount: 261720 |
| |
| tax_year: 2025 |
| |
| yearly_tax_amount: 3142.17 |
| |
| |
| monthly_tax_amount: 295.96 |
| |
| period_end_date: 2024-12-31 |
| |
| period_start_date: 2024-01-01 |
| |
| property_assessed_value_amount: 261720 |
| |
| property_building_amount: 261720 |
| |
| property_land_amount: 0 |
| |
| property_market_value_amount: 261720 |
| |
| property_taxable_value_amount: 261720 |
| |
| tax_year: 2024 |
| |
| yearly_tax_amount: 3551.55 |
| |
| |
| monthly_tax_amount: 230.92 |
| |
| period_end_date: 2022-12-31 |
| |
| period_start_date: 2022-01-01 |
| |
| property_assessed_value_amount: 233985 |
| |
| property_building_amount: 233985 |
| |
| property_land_amount: 0 |
| |
| property_market_value_amount: 233985 |
| |
| property_taxable_value_amount: 172700 |
| |
| tax_year: 2022 |
| |
| yearly_tax_amount: 2771.07 |
| |
| |
| monthly_tax_amount: 343.77 |
| |
| period_end_date: 2023-12-31 |
| |
| period_start_date: 2023-01-01 |
| |
| property_assessed_value_amount: 298680 |
| |
| property_building_amount: 298680 |
| |
| property_land_amount: 0 |
| |
| property_market_value_amount: 298680 |
| |
| property_taxable_value_amount: 298680 |
| |
| tax_year: 2023 |
| |
| yearly_tax_amount: 4125.27' |
| - source_sentence: 'ParcelID: 31347702043 |
| |
| FullAddress: 9424 MONTELANICO LOOP, NAPLES 34119 |
| |
| Legal: ESPLANADE GOLF AND COUNTRY CLUB OF NAPLES PHASE 3 BLOCKS K1 K2 AND H3 LOT |
| 1390 |
| |
| Subdivision: 281740 - ESPLANADE G&CC PH3 B-K1,K2,H3 CLUB OF NAPLES PHASE 3 BLOCKS |
| K1 K2 AND H3 |
| |
| UseCode: 1 - SINGLE FAMILY RESIDENTIAL |
| |
| Section: 15 |
| |
| Township: 48 |
| |
| Range: 26section: Property, |
| |
| county: Collier, |
| |
| parcel_id: 31347702043' |
| sentences: |
| - 'monthly_tax_amount: 1296.8 |
| |
| period_end_date: 2023-12-31 |
| |
| period_start_date: 2023-01-01 |
| |
| property_assessed_value_amount: 1452003 |
| |
| property_building_amount: 1459158 |
| |
| property_land_amount: 1594430 |
| |
| property_market_value_amount: 3053588 |
| |
| property_taxable_value_amount: 1402003 |
| |
| tax_year: 2023 |
| |
| yearly_tax_amount: 15561.55 |
| |
| |
| monthly_tax_amount: 1339.02 |
| |
| period_end_date: 2021-12-31 |
| |
| period_start_date: 2021-01-01 |
| |
| property_assessed_value_amount: 1368652 |
| |
| property_building_amount: 1188323 |
| |
| property_land_amount: 180329 |
| |
| property_market_value_amount: 1368652 |
| |
| property_taxable_value_amount: 1318652 |
| |
| tax_year: 2021 |
| |
| yearly_tax_amount: 16068.19 |
| |
| |
| monthly_tax_amount: 1315.87 |
| |
| period_end_date: 2024-12-31 |
| |
| period_start_date: 2024-01-01 |
| |
| property_assessed_value_amount: 1495563 |
| |
| property_building_amount: 1262216 |
| |
| property_land_amount: 1402668 |
| |
| property_market_value_amount: 2664884 |
| |
| property_taxable_value_amount: 1445563 |
| |
| tax_year: 2024 |
| |
| yearly_tax_amount: 15790.39 |
| |
| |
| monthly_tax_amount: 1187.99 |
| |
| period_end_date: 2025-12-31 |
| |
| period_start_date: 2025-01-01 |
| |
| property_assessed_value_amount: 1538934 |
| |
| property_building_amount: 1117620 |
| |
| property_land_amount: 1508245 |
| |
| property_market_value_amount: 2625865 |
| |
| property_taxable_value_amount: 1488212 |
| |
| tax_year: 2025 |
| |
| yearly_tax_amount: 14255.93 |
| |
| |
| monthly_tax_amount: 1334.85 |
| |
| period_end_date: 2022-12-31 |
| |
| period_start_date: 2022-01-01 |
| |
| property_assessed_value_amount: 1409712 |
| |
| property_building_amount: 1553410 |
| |
| property_land_amount: 470644 |
| |
| property_market_value_amount: 2024054 |
| |
| property_taxable_value_amount: 1359712 |
| |
| tax_year: 2022 |
| |
| yearly_tax_amount: 16018.16' |
| - 'area_under_air: 2313 |
| |
| livable_floor_area: 2313 |
| |
| parcel_identifier: 31347702043 |
| |
| property_legal_description_text: ESPLANADE GOLF AND COUNTRY CLUB OF NAPLES PHASE |
| 3 BLOCKS K1 K2 AND H3 LOT 1390 |
| |
| property_structure_built_year: 2018 |
| |
| property_type: SingleFamily |
| |
| subdivision: ESPLANADE G&CC PH3 B-K1,K2,H3 CLUB OF NAPLES PHASE 3 BLOCKS K1 K2 |
| AND H3 |
| |
| total_area: 2767' |
| - 'city_name: NAPLES |
| |
| county_name: Collier |
| |
| postal_code: 34105 |
| |
| range: 25 |
| |
| section: 14 |
| |
| state_code: FL |
| |
| street_name: WOODSHIRE |
| |
| street_number: 1018 |
| |
| street_suffix_type: Ln |
| |
| township: 49' |
| - source_sentence: 'OwnerLine 1: 21 VB PROPERTIES LLCsection: Owners, |
| |
| county: Collier, |
| |
| parcel_id: 23270120001' |
| sentences: |
| - 'first_name: Kenneth |
| |
| last_name: Holman |
| |
| middle_name: W' |
| - 'city_name: NAPLES |
| |
| county_name: Collier |
| |
| state_code: FL |
| |
| street_name: WILLOWBROOK |
| |
| street_number: 765 |
| |
| street_suffix_type: Dr |
| |
| township: 49' |
| - 'name: 21' |
| - source_sentence: 'FullAddress: 5852 NORTHRIDGE DR, NAPLES 34110 |
| |
| Legal: CARLTON LAKES UNIT NO 2 BLK A LOT 5 NKA VILLAS I AT CARLTON LAKES (HO) |
| UNIT A-5 |
| |
| Section: 19 |
| |
| Township: 48 |
| |
| Range: 26section: Address, |
| |
| county: Collier, |
| |
| parcel_id: 25540003380' |
| sentences: |
| - 'monthly_tax_amount: 317.4 |
| |
| period_end_date: 2022-12-31 |
| |
| period_start_date: 2022-01-01 |
| |
| property_assessed_value_amount: 381299 |
| |
| property_building_amount: 441115 |
| |
| property_land_amount: 134469 |
| |
| property_market_value_amount: 575584 |
| |
| property_taxable_value_amount: 331299 |
| |
| tax_year: 2022 |
| |
| yearly_tax_amount: 3808.76 |
| |
| |
| monthly_tax_amount: 517.39 |
| |
| period_end_date: 2025-12-31 |
| |
| period_start_date: 2025-01-01 |
| |
| property_assessed_value_amount: 692367 |
| |
| property_building_amount: 324162 |
| |
| property_land_amount: 368205 |
| |
| property_market_value_amount: 692367 |
| |
| property_taxable_value_amount: 641645 |
| |
| tax_year: 2025 |
| |
| yearly_tax_amount: 6208.64 |
| |
| |
| monthly_tax_amount: 320.37 |
| |
| period_end_date: 2021-12-31 |
| |
| period_start_date: 2021-01-01 |
| |
| property_assessed_value_amount: 370193 |
| |
| property_building_amount: 334803 |
| |
| property_land_amount: 35390 |
| |
| property_market_value_amount: 370193 |
| |
| property_taxable_value_amount: 320193 |
| |
| tax_year: 2021 |
| |
| yearly_tax_amount: 3844.46' |
| - 'first_name: Christina |
| |
| last_name: Zajac |
| |
| middle_name: R |
| |
| |
| first_name: Thomas |
| |
| last_name: Zajac |
| |
| middle_name: H' |
| - 'city_name: NAPLES |
| |
| county_name: Collier |
| |
| lot: 5 |
| |
| postal_code: 34110 |
| |
| range: 26 |
| |
| section: 19 |
| |
| state_code: FL |
| |
| street_name: NORTHRIDGE |
| |
| street_number: 5852 |
| |
| street_suffix_type: Dr |
| |
| township: 48' |
| pipeline_tag: sentence-similarity |
| library_name: sentence-transformers |
| metrics: |
| - cosine_accuracy |
| - cosine_accuracy_threshold |
| - cosine_f1 |
| - cosine_f1_threshold |
| - cosine_precision |
| - cosine_recall |
| - cosine_ap |
| - cosine_mcc |
| model-index: |
| - name: EmbeddingGemma-300m trained to measure coverage |
| results: |
| - task: |
| type: binary-classification |
| name: Binary Classification |
| dataset: |
| name: Unknown |
| type: unknown |
| metrics: |
| - type: cosine_accuracy |
| value: 0.96 |
| name: Cosine Accuracy |
| - type: cosine_accuracy_threshold |
| value: 0.9879488945007324 |
| name: Cosine Accuracy Threshold |
| - type: cosine_f1 |
| value: 0.9607843137254902 |
| name: Cosine F1 |
| - type: cosine_f1_threshold |
| value: 0.98133385181427 |
| name: Cosine F1 Threshold |
| - type: cosine_precision |
| value: 0.9423076923076923 |
| name: Cosine Precision |
| - type: cosine_recall |
| value: 0.98 |
| name: Cosine Recall |
| - type: cosine_ap |
| value: 0.9530095295398296 |
| name: Cosine Ap |
| - type: cosine_mcc |
| value: 0.920736884379251 |
| name: Cosine Mcc |
| --- |
| |
| # EmbeddingGemma-300m trained to measure coverage |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
|
|
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** Sentence Transformer |
| - **Base model:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 --> |
| - **Maximum Sequence Length:** 2048 tokens |
| - **Output Dimensionality:** 768 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - json |
| - **Language:** en |
| - **License:** apache-2.0 |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'}) |
| (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
| (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'}) |
| (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'}) |
| (4): Normalize() |
| ) |
| ``` |
|
|
| ## Usage |
|
|
| ### Direct Usage (Sentence Transformers) |
|
|
| First install the Sentence Transformers library: |
|
|
| ```bash |
| pip install -U sentence-transformers |
| ``` |
|
|
| Then you can load this model and run inference. |
| ```python |
| from sentence_transformers import SentenceTransformer |
| |
| # Download from the 🤗 Hub |
| model = SentenceTransformer("mancer146/embeddinggemma-300m-haystack-contrastive-thin-fixed") |
| # Run inference |
| queries = [ |
| "FullAddress: 5852 NORTHRIDGE DR, NAPLES 34110\nLegal: CARLTON LAKES UNIT NO 2 BLK A LOT 5 NKA VILLAS I AT CARLTON LAKES (HO) UNIT A-5\nSection: 19\nTownship: 48\nRange: 26section: Address,\ncounty: Collier,\nparcel_id: 25540003380", |
| ] |
| documents = [ |
| 'city_name: NAPLES\ncounty_name: Collier\nlot: 5\npostal_code: 34110\nrange: 26\nsection: 19\nstate_code: FL\nstreet_name: NORTHRIDGE\nstreet_number: 5852\nstreet_suffix_type: Dr\ntownship: 48', |
| 'monthly_tax_amount: 317.4\nperiod_end_date: 2022-12-31\nperiod_start_date: 2022-01-01\nproperty_assessed_value_amount: 381299\nproperty_building_amount: 441115\nproperty_land_amount: 134469\nproperty_market_value_amount: 575584\nproperty_taxable_value_amount: 331299\ntax_year: 2022\nyearly_tax_amount: 3808.76\n\nmonthly_tax_amount: 517.39\nperiod_end_date: 2025-12-31\nperiod_start_date: 2025-01-01\nproperty_assessed_value_amount: 692367\nproperty_building_amount: 324162\nproperty_land_amount: 368205\nproperty_market_value_amount: 692367\nproperty_taxable_value_amount: 641645\ntax_year: 2025\nyearly_tax_amount: 6208.64\n\nmonthly_tax_amount: 320.37\nperiod_end_date: 2021-12-31\nperiod_start_date: 2021-01-01\nproperty_assessed_value_amount: 370193\nproperty_building_amount: 334803\nproperty_land_amount: 35390\nproperty_market_value_amount: 370193\nproperty_taxable_value_amount: 320193\ntax_year: 2021\nyearly_tax_amount: 3844.46', |
| 'first_name: Christina\nlast_name: Zajac\nmiddle_name: R\n\nfirst_name: Thomas\nlast_name: Zajac\nmiddle_name: H', |
| ] |
| query_embeddings = model.encode_query(queries) |
| document_embeddings = model.encode_document(documents) |
| print(query_embeddings.shape, document_embeddings.shape) |
| # [1, 768] [3, 768] |
| |
| # Get the similarity scores for the embeddings |
| similarities = model.similarity(query_embeddings, document_embeddings) |
| print(similarities) |
| # tensor([[0.9881, 0.8106, 0.6785]]) |
| ``` |
|
|
| <!-- |
| ### Direct Usage (Transformers) |
|
|
| <details><summary>Click to see the direct usage in Transformers</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Downstream Usage (Sentence Transformers) |
|
|
| You can finetune this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Out-of-Scope Use |
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| --> |
|
|
| ## Evaluation |
|
|
| ### Metrics |
|
|
| #### Binary Classification |
|
|
| * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------------|:----------| |
| | cosine_accuracy | 0.96 | |
| | cosine_accuracy_threshold | 0.9879 | |
| | cosine_f1 | 0.9608 | |
| | cosine_f1_threshold | 0.9813 | |
| | cosine_precision | 0.9423 | |
| | cosine_recall | 0.98 | |
| | **cosine_ap** | **0.953** | |
| | cosine_mcc | 0.9207 | |
| |
| <!-- |
| ## 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 Dataset |
| |
| #### json |
| |
| * Dataset: json |
| * Size: 1,200 training samples |
| * Columns: <code>input_text</code>, <code>output_text</code>, and <code>label</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | input_text | output_text | label | |
| |:--------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------| |
| | type | string | string | int | |
| | details | <ul><li>min: 36 tokens</li><li>mean: 188.79 tokens</li><li>max: 536 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 165.35 tokens</li><li>max: 801 tokens</li></ul> | <ul><li>0: ~50.10%</li><li>1: ~49.90%</li></ul> | |
| * Samples: |
| | input_text | output_text | label | |
| |:-----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:---------------| |
| | <code>OwnerLine 1: JERI HURCKES LIVING TRUSTsection: Owners,<br>county: Collier,<br>parcel_id: 82660021104</code> | <code>name: JERI HURCKES LIVING TRUST</code> | <code>1</code> | |
| | <code>OwnerLine 1: GUALARIO, ANTHONY=& DIANAsection: Owners,<br>county: Collier,<br>parcel_id: 16054320005</code> | <code>first_name: Anthony<br>last_name: Gualario</code> | <code>0</code> | |
| | <code>Date: 02/11/14<br>Amount: $496,300<br>BookPage: 5009-963section: Sales,<br>county: Collier,<br>parcel_id: 69770005923</code> | <code>ownership_transfer_date: 2014-02-11<br>purchase_price_amount: 0</code> | <code>0</code> | |
| * Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: |
| ```json |
| { |
| "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", |
| "margin": 0.1, |
| "size_average": true |
| } |
| ``` |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `eval_strategy`: steps |
| - `per_device_train_batch_size`: 3 |
| - `per_device_eval_batch_size`: 3 |
| - `gradient_accumulation_steps`: 2 |
| - `learning_rate`: 2e-05 |
| - `num_train_epochs`: 5 |
| - `warmup_ratio`: 0.05 |
| - `fp16`: True |
| - `prompts`: {'input_text': 'STS', 'output_text': 'STS'} |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `overwrite_output_dir`: False |
| - `do_predict`: False |
| - `eval_strategy`: steps |
| - `prediction_loss_only`: True |
| - `per_device_train_batch_size`: 3 |
| - `per_device_eval_batch_size`: 3 |
| - `per_gpu_train_batch_size`: None |
| - `per_gpu_eval_batch_size`: None |
| - `gradient_accumulation_steps`: 2 |
| - `eval_accumulation_steps`: None |
| - `torch_empty_cache_steps`: None |
| - `learning_rate`: 2e-05 |
| - `weight_decay`: 0.0 |
| - `adam_beta1`: 0.9 |
| - `adam_beta2`: 0.999 |
| - `adam_epsilon`: 1e-08 |
| - `max_grad_norm`: 1.0 |
| - `num_train_epochs`: 5 |
| - `max_steps`: -1 |
| - `lr_scheduler_type`: linear |
| - `lr_scheduler_kwargs`: {} |
| - `warmup_ratio`: 0.05 |
| - `warmup_steps`: 0 |
| - `log_level`: passive |
| - `log_level_replica`: warning |
| - `log_on_each_node`: True |
| - `logging_nan_inf_filter`: True |
| - `save_safetensors`: True |
| - `save_on_each_node`: False |
| - `save_only_model`: False |
| - `restore_callback_states_from_checkpoint`: False |
| - `no_cuda`: False |
| - `use_cpu`: False |
| - `use_mps_device`: False |
| - `seed`: 42 |
| - `data_seed`: None |
| - `jit_mode_eval`: False |
| - `use_ipex`: False |
| - `bf16`: False |
| - `fp16`: True |
| - `fp16_opt_level`: O1 |
| - `half_precision_backend`: auto |
| - `bf16_full_eval`: False |
| - `fp16_full_eval`: False |
| - `tf32`: None |
| - `local_rank`: 0 |
| - `ddp_backend`: None |
| - `tpu_num_cores`: None |
| - `tpu_metrics_debug`: False |
| - `debug`: [] |
| - `dataloader_drop_last`: False |
| - `dataloader_num_workers`: 0 |
| - `dataloader_prefetch_factor`: None |
| - `past_index`: -1 |
| - `disable_tqdm`: False |
| - `remove_unused_columns`: True |
| - `label_names`: None |
| - `load_best_model_at_end`: False |
| - `ignore_data_skip`: False |
| - `fsdp`: [] |
| - `fsdp_min_num_params`: 0 |
| - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
| - `fsdp_transformer_layer_cls_to_wrap`: None |
| - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
| - `parallelism_config`: None |
| - `deepspeed`: None |
| - `label_smoothing_factor`: 0.0 |
| - `optim`: adamw_torch |
| - `optim_args`: None |
| - `adafactor`: False |
| - `group_by_length`: False |
| - `length_column_name`: length |
| - `ddp_find_unused_parameters`: None |
| - `ddp_bucket_cap_mb`: None |
| - `ddp_broadcast_buffers`: False |
| - `dataloader_pin_memory`: True |
| - `dataloader_persistent_workers`: False |
| - `skip_memory_metrics`: True |
| - `use_legacy_prediction_loop`: False |
| - `push_to_hub`: False |
| - `resume_from_checkpoint`: None |
| - `hub_model_id`: None |
| - `hub_strategy`: every_save |
| - `hub_private_repo`: None |
| - `hub_always_push`: False |
| - `hub_revision`: None |
| - `gradient_checkpointing`: False |
| - `gradient_checkpointing_kwargs`: None |
| - `include_inputs_for_metrics`: False |
| - `include_for_metrics`: [] |
| - `eval_do_concat_batches`: True |
| - `fp16_backend`: auto |
| - `push_to_hub_model_id`: None |
| - `push_to_hub_organization`: None |
| - `mp_parameters`: |
| - `auto_find_batch_size`: False |
| - `full_determinism`: False |
| - `torchdynamo`: None |
| - `ray_scope`: last |
| - `ddp_timeout`: 1800 |
| - `torch_compile`: False |
| - `torch_compile_backend`: None |
| - `torch_compile_mode`: None |
| - `include_tokens_per_second`: False |
| - `include_num_input_tokens_seen`: False |
| - `neftune_noise_alpha`: None |
| - `optim_target_modules`: None |
| - `batch_eval_metrics`: False |
| - `eval_on_start`: False |
| - `use_liger_kernel`: False |
| - `liger_kernel_config`: None |
| - `eval_use_gather_object`: False |
| - `average_tokens_across_devices`: False |
| - `prompts`: {'input_text': 'STS', 'output_text': 'STS'} |
| - `batch_sampler`: batch_sampler |
| - `multi_dataset_batch_sampler`: proportional |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
| |
| </details> |
| |
| ### Training Logs |
| | Epoch | Step | Training Loss | cosine_ap | |
| |:-----:|:----:|:-------------:|:---------:| |
| | 0.4 | 40 | - | 0.8426 | |
| | 0.8 | 80 | - | 0.8858 | |
| | 1.2 | 120 | - | 0.8194 | |
| | 1.6 | 160 | - | 0.8856 | |
| | 2.0 | 200 | - | 0.9643 | |
| | 2.4 | 240 | - | 0.9469 | |
| | 2.8 | 280 | - | 0.9426 | |
| | 3.2 | 320 | - | 0.9084 | |
| | 3.6 | 360 | - | 0.9337 | |
| | 4.0 | 400 | - | 0.9449 | |
| | 4.4 | 440 | - | 0.9555 | |
| | 4.8 | 480 | - | 0.9525 | |
| | 5.0 | 500 | 0.0006 | - | |
| | -1 | -1 | - | 0.9530 | |
| |
| |
| ### Framework Versions |
| - Python: 3.11.13 |
| - Sentence Transformers: 5.1.2 |
| - Transformers: 4.57.0.dev0 |
| - PyTorch: 2.6.0+cu124 |
| - Accelerate: 1.9.0 |
| - Datasets: 4.1.1 |
| - Tokenizers: 0.22.1 |
| |
| ## Citation |
| |
| ### BibTeX |
| |
| #### Sentence Transformers |
| ```bibtex |
| @inproceedings{reimers-2019-sentence-bert, |
| title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
| author = "Reimers, Nils and Gurevych, Iryna", |
| booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
| month = "11", |
| year = "2019", |
| publisher = "Association for Computational Linguistics", |
| url = "https://arxiv.org/abs/1908.10084", |
| } |
| ``` |
| |
| #### ContrastiveLoss |
| ```bibtex |
| @inproceedings{hadsell2006dimensionality, |
| author={Hadsell, R. and Chopra, S. and LeCun, Y.}, |
| booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, |
| title={Dimensionality Reduction by Learning an Invariant Mapping}, |
| year={2006}, |
| volume={2}, |
| number={}, |
| pages={1735-1742}, |
| doi={10.1109/CVPR.2006.100} |
| } |
| ``` |
| |
| <!-- |
| ## 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.* |
| --> |
