metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:17198
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
widget:
  - source_sentence: >-
      How should we proceed if the installed valve or its appurtenances do not
      conform to the City's criteria, and what steps are involved in remedying
      the situation?
    sentences:
      - >-
        1.1 SUMMARY:

        2. The valve shall perform as intended with no deformation, leaking or
        damage of any kind for the pressure ranges indicated.

        3. Before acceptance of the installed valve, provide the City the
        opportunity to inspect and operate the valve.

        a. The City will assess the ease of operating the ball valves and
        corporation stops, where applicable.

        4. The Combination Air Valve assembly shall be free from any leaks.

        B. Non-Conforming Work

        1. Ifaccess and operation of the valve or its appurtenances does not
        meet the City's criteria, the Contractor will remedy the situation until
        it meets the City's criteria, at the Contractor's expense.

        3.8. SYSTEM STARTUP [NOT USED]

        3.9 ADJUSTING [NOT USED]

        3.10 CLEANING [NOT USED]

        3.11 CLOSEOUT ACTIVITIES [NOT USED]

        3.12, PROTECTION [NOT USED]

        3.13 MAINTENANCE [NOT USED]

        3.14 ATTACHMENTS [NOT USED]
      - >-
        b. Miscellaneous Areas:

        layer.. , 1 = . , 2 = 3). , 3 = Take corrective action if an adequate
        bond does not exist between the. , 1 = . , 2 = . , 3 = current and
        underlying layer to ensure an adequate bond will be achieved. , 1 = . ,
        2 = . , 3 = during subsequent placement operations.. , 1 = . , 2 = 4). ,
        3 = The untrimmed core height must be in accordance with the
        requirements in. , 1 = . , 2 = . , 3 = Table 17.. , 1 = . , 2 = 5). , 3
        = If the cores are an acceptable height, trim the cores immediately
        after. , 1 = . , 2 = . , 3 = obtaining the cores in accordance with
        Tex-207-F.. , 1 = . , 2 = . , 3 = Any core that does not meet the
        requirements in Table 17 will be rejected.. , 1 = . , 2 = 6). , 3 =
        more. , 1 = . , 2 = . , 3 = The City may request additional cores to be
        taken within the area. If. , 1 = . , 2 = 7). , 3 = than 2 cores are
      - >-
        4. Other Activities:

        a. Rental of storage units, rental of storage space for recreational
        vehicles (RV) and boats, and the sale of moving related items are
        allowed uses.

        b. No other land use or business activity within storage units is
        allowed.

        c. The rental of moving trucks and moving related equipment shall
        constitute an Equipment Sales and Rental use.

        d. The sale and leasing of recreational vehicles (RVs) and boats shall
        constitute an Automotive Sales and Leasing use.
  - source_sentence: >-
      How do the setback regulations in the R1 District affect the design and
      placement of structures on the lot?
    sentences:
      - >-
        B. R11 District Dimensional Standards:

        Table 3.2-B: R1 District Dimensional Standards, 1 = Table 3.2-B: R1
        District Dimensional Standards. Table 3.2-B: R1 District Dimensional
        Standards, 2 = Table 3.2-B: R1 District Dimensional Standards. Table
        3.2-B: R1 District Dimensional Standards, 3 = Table 3.2-B: R1 District
        Dimensional Standards. Dimensional Standards, 1 = Dimensional Standards.
        Dimensional Standards, 2 = Dimensional Standards. Dimensional Standards,
        3 = Additional Standards. LOT DIMENSIONS (MINIMUM), 1 = LOT DIMENSIONS
        (MINIMUM). LOT DIMENSIONS (MINIMUM), 2 = LOT DIMENSIONS (MINIMUM). LOT
        DIMENSIONS (MINIMUM), 3 = LOT DIMENSIONS (MINIMUM). oN, 1 = Lot area.
        oN, 2 = 32,000 sq ft. oN, 3 = 3.7.2: Lot and Site Requirements. iam, 1 =
        Lot width. iam, 2 = 80 feet. iam, 3 = 3.7.2: Lot and Site Requirements.
        fem, 1 = Lot depth 100. fem, 2 = feet. fem, 3 = 3.7.2: Lot and Site
        Requirements. SETBACKS
      - >-
        1. R7 Zoning District:

        Self-service laundry facilities shall only be permitted as an accessory
        use to multifamily dwellings, and such use shall be located within a
        multifamily structure.
      - >-
        1.3 > REFERENCES:

        NY, 1 = A.. NY, 2 = Abbreviations and Acronyms 1. AWG: American wire
        gauge 2.. Fw, 1 = . Fw, 2 = PVC: polyvinyl chloride. UN, 1 = Reference
        Standards. UN, 2 = Reference Standards. COAINID, 1 = 1.. COAINID, 2 =
        Reference standards cited in this Section refer to the current reference
        standard published at the time of the latest revision date logged at the
        end of this Section unless a date is cited.. , 1 = 2.. , 2 =
        specifically Texas Department of Transportation, Standard Specifications
        for Construction and Maintenance of Highways, Streets and Bridges
        (TxDOT):. , 1 = a.. , 2 = Item 684, Traffic Signal Cables. 3. TxDOT
        Departmental Materials Specification:. , 1 = 4.. , 2 = Underwriters
        Laboratories, Inc.. , 1 = . , 2 = (UL).. , 1 = 5.. , 2 = International
        Municipal Signal Association (IMSA).. , 1 = ADMINISTRATIVE REQUIREMENTS
        [NOT USED]. , 2 = ADMINISTRATIVE REQUIREMENTS [NOT USED]. , 1 =
        SUBMITTALS. , 2 = SUBMITTALS.
  - source_sentence: >-
      How do the Dimensional Standards apply to our development project in the
      specified zoning districts?
    sentences:
      - >-
        v = Entire Site = Development Impact Area Only:

        . . Dimensional Standards, DDC Reference = Subchapter 3: Zoning
        Districts. . . Dimensional Standards, New A Construction = Vv. . .
        Dimensional Standards, Minor: Tier 1 = 0). . . Dimensional Standards,
        Major: Tier 2 = v. Land-Disturbing Activities, DDC Reference = 7.2.
        Land-Disturbing Activities, New A Construction = All development, see
        Section 7.2. Land-Disturbing Activities, Minor: Tier 1 = All
        development, see Section 7.2. Land-Disturbing Activities, Major: Tier 2
        = All development, see Section 7.2. Environmentally Sensitive Areas, DDC
        Reference = 74. Environmentally Sensitive Areas, New A Construction =
        All development, see Section 7.4. Environmentally Sensitive Areas,
        Minor: Tier 1 = . Environmentally Sensitive Areas, Major: Tier 2 = .
        Drainage, DDC Reference = 74. Drainage, New A Construction = All
        development, see Section 7.4. Drainage, Minor: Tier 1 = . Drainage,
        Major: Tier 2 = . Water and Wastewater, DDC Reference = 7.6. Water and
        Wastewater, New A Construction = All development,
      - >-
        3. Step 3: Determination of Procedure:

        Upon receipt of a complete application for a Certificate of Design
        Consistency, the Director must determine the appropriate review
        procedure prescribed by sections 2.10.1.D.3.a-d below.

        Denton, Texas — Denton Development Code

        Print Date: August 30, 2024

        136
      - >-
        4B A. Tests and Inspections:

        CITY OF DENTON STANDARD CONSTRUCTION SPECIFICATION DOCUMENTS Revised
        October 22, 2020

        Effective

        July 1, 2024

        [Insert Bid Number] [Insert Engineering Project Number]

        3.5

        REPAIR

        33 31 23

        COMBINATION AIR VALVE ASSEMBLIES FOR SEWER FORCE MAINS

        Page 6 of 7

        1. Testing and inspection of Combination Air Valves shall be in
        accordance with AWWA C512.
  - source_sentence: >-
      How do the regulations for Light Industrial (LI) and Heavy Industrial (HI)
      districts differ in terms of permitted uses and development standards?
    sentences:
      - >-
        This print version includes the following Code amendments::

        Other Nonresidential Districts. , 3 = . , 1 = 3.5.1 GO - General
        Office... , 2 = 3.5.1 GO - General Office... , 3 = . , 1 = - LI - Light
        Industrial. , 2 = - LI - Light Industrial. , 3 = . , 1 = 3.5.2. , 2 = .
        , 3 = . , 1 = 3.5.3.. , 2 = HI - Heavy Industrial. , 3 = . , 1 = 3.5.4.
        , 2 = PF - Public Facilities.. , 3 = oa. , 1 = Summary -. , 2 = Summary
        -. , 3 = . 3.6, 1 = PD Planned Development District. 3.6, 2 = PD Planned
        Development District. 3.6, 3 = . , 1 = 3.6.1 Purpose...
        seeesesnsnseeeenens Review Procedure ... esse. , 2 = 3.6.1 Purpose...
        seeesesnsnseeeenens Review Procedure ... esse. , 3 = . , 1 = 3.6.2. , 2
        = .
      - >-
        1.1 SUMMARY:

        AADUNAPWNK, 1 = . AADUNAPWNK, 2 = . AADUNAPWNK, 3 = ensure the conduit
        is clean and free from obstructions.. , 1 = . , 2 = . , 3 = 17) Conduits
        shall be placed in an open trench at a minimum 24 inches (612. , 1 = . ,
        2 = . , 3 = mm) depth below the curb grade in the sidewalk areas, or 18
        inches (450 mm) below the finished street grade in the street area.. PW
        CUO, 1 = . PW CUO, 2 = 18). PW CUO, 3 = Conduit placed for concrete
        encasement shall be secured and supported in. HP, 1 = . HP, 2 = . HP, 3
        = such a manner the alignment will not be disturbed during placement of
        the. , 1 = . , 2 = . , 3 = concrete.. CPAIANDNAHBPWNYRK, 1 = .
        CPAIANDNAHBPWNYRK, 2 = . CPAIANDNAHBPWNYRK, 3 = Noconcrete shall be
        until all conduit ends have been and. , 1 = . ,
      - >-
        E. Water Control:

        1. Surface Water

        a. Furnish all materials and equipment and perform all incidental work
        required to direct surface water away from the excavation.
  - source_sentence: >-
      How can I ensure that the curing compound we receive at the job site meets
      the required specifications with the manufacturer's original containers
      and labels intact?
    sentences:
      - >-
        B. Exemptions:

        Unless otherwise provided in this DDC, the following shall be exempt
        from the provisions of this Section 7.3: Land-Disturbing Activities:

        1. Grading and clearing in emergency situations involving immediate
        danger to life and property or substantial fire hazards;

        2. Any activity where the total volume of material disturbed, stored,
        disposed of or used as fill does not exceed 25 cubic yards and the area
        disturbed does not exceed 2,000 square feet, provided it does not
        obstruct a watercourse and is not located in a floodplain or other
        environmentally sensitive area;

        3. Soil-disturbing activities, excluding tree removal, that are
        associated with normal agricultural crop operations; or

        4. Stockpiling and handling of earth material associated with commercial
        quarry and landfill operations licensed under the state.

        Denton, Texas — Denton Development Code

        Print Date: August 30, 2024

        353
      - >-
        8. Curing:

        03 00 00

        CONCRETE AND CONCRETE REINFORCING

        Page 10 of 18

        6) Curing compound to be delivered to the job site in the manufacturer's
        original containers only, with original label containing the following:

        a) Manufacturer's name

        b) Trade name of the material

        c) Batch number or symbol with which test samples may be correlated
      - >-
        2. For Large Wind Energy Systems:

        a. The minimum acreage for a large wind system shall be established
        based on the setbacks of the turbine(s) and the height of the
        turbine(s);

        b. All turbines located within the same large wind system property shall
        be of a similar tower design, including the type, number of blades, and
        direction of blade rotation;

        c. Large wind systems shall be setback at least one and one-half times
        the height of the turbine and rotor diameter from the property line.
        Large wind systems shall also be setback at least one and one-half times
        the height of the turbine from above ground telephone, electrical lines,
        and other uninhabitable structures;

        d. Towers shall not be climbable up to 15 feet above ground level.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@1
  - cosine_ndcg@3
  - cosine_ndcg@5
  - cosine_ndcg@10
  - cosine_mrr@1
  - cosine_mrr@3
  - cosine_mrr@5
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: worksphere
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 1024
          type: dim_1024
        metrics:
          - type: cosine_accuracy@1
            value: 0.030697674418604652
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3986046511627907
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5774418604651163
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7881395348837209
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.030697674418604652
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13286821705426355
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11548837209302326
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07881395348837208
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.030697674418604652
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3986046511627907
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5774418604651163
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7881395348837209
            name: Cosine Recall@10
          - type: cosine_ndcg@1
            value: 0.030697674418604652
            name: Cosine Ndcg@1
          - type: cosine_ndcg@3
            value: 0.23179382587458858
            name: Cosine Ndcg@3
          - type: cosine_ndcg@5
            value: 0.3040553564598666
            name: Cosine Ndcg@5
          - type: cosine_ndcg@10
            value: 0.37531956376470604
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.030697674418604652
            name: Cosine Mrr@1
          - type: cosine_mrr@3
            value: 0.17515503875969318
            name: Cosine Mrr@3
          - type: cosine_mrr@5
            value: 0.21443410852713862
            name: Cosine Mrr@5
          - type: cosine_mrr@10
            value: 0.24572388335179296
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2550755013176846
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.030697674418604652
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3986046511627907
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5774418604651163
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7881395348837209
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.030697674418604652
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13286821705426355
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11548837209302326
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07881395348837208
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.030697674418604652
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3986046511627907
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5774418604651163
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7881395348837209
            name: Cosine Recall@10
          - type: cosine_ndcg@1
            value: 0.030697674418604652
            name: Cosine Ndcg@1
          - type: cosine_ndcg@3
            value: 0.23179382587458858
            name: Cosine Ndcg@3
          - type: cosine_ndcg@5
            value: 0.3040553564598666
            name: Cosine Ndcg@5
          - type: cosine_ndcg@10
            value: 0.37531956376470604
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.030697674418604652
            name: Cosine Mrr@1
          - type: cosine_mrr@3
            value: 0.17515503875969318
            name: Cosine Mrr@3
          - type: cosine_mrr@5
            value: 0.21443410852713862
            name: Cosine Mrr@5
          - type: cosine_mrr@10
            value: 0.24572388335179296
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2550755013176846
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.03
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.39069767441860465
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5644186046511628
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.781860465116279
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.03
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13023255813953488
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11288372093023255
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0781860465116279
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.03
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.39069767441860465
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5644186046511628
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.781860465116279
            name: Cosine Recall@10
          - type: cosine_ndcg@1
            value: 0.03
            name: Cosine Ndcg@1
          - type: cosine_ndcg@3
            value: 0.22663893445598368
            name: Cosine Ndcg@3
          - type: cosine_ndcg@5
            value: 0.2968091108509391
            name: Cosine Ndcg@5
          - type: cosine_ndcg@10
            value: 0.37060640353852903
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.03
            name: Cosine Mrr@1
          - type: cosine_mrr@3
            value: 0.17096899224806486
            name: Cosine Mrr@3
          - type: cosine_mrr@5
            value: 0.20909689922481253
            name: Cosine Mrr@5
          - type: cosine_mrr@10
            value: 0.2416426725729079
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2512032580492767
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.029534883720930234
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3774418604651163
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5502325581395349
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7644186046511627
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.029534883720930234
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1258139534883721
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11004651162790699
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07644186046511628
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.029534883720930234
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3774418604651163
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5502325581395349
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7644186046511627
            name: Cosine Recall@10
          - type: cosine_ndcg@1
            value: 0.029534883720930234
            name: Cosine Ndcg@1
          - type: cosine_ndcg@3
            value: 0.21910859618189715
            name: Cosine Ndcg@3
          - type: cosine_ndcg@5
            value: 0.2887354612410299
            name: Cosine Ndcg@5
          - type: cosine_ndcg@10
            value: 0.3613007541197287
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.029534883720930234
            name: Cosine Mrr@1
          - type: cosine_mrr@3
            value: 0.16538759689922747
            name: Cosine Mrr@3
          - type: cosine_mrr@5
            value: 0.20312015503876593
            name: Cosine Mrr@5
          - type: cosine_mrr@10
            value: 0.23504817275747772
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2452995067602724
            name: Cosine Map@100

worksphere

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sabber/worksphere-regulations-embedding_bge")
# Run inference
sentences = [
    "How can I ensure that the curing compound we receive at the job site meets the required specifications with the manufacturer's original containers and labels intact?",
    "8. Curing:\n03 00 00\nCONCRETE AND CONCRETE REINFORCING\nPage 10 of 18\n6) Curing compound to be delivered to the job site in the manufacturer's original containers only, with original label containing the following:\na) Manufacturer's name\nb) Trade name of the material\nc) Batch number or symbol with which test samples may be correlated",
    '2. For Large Wind Energy Systems:\na. The minimum acreage for a large wind system shall be established based on the setbacks of the turbine(s) and the height of the turbine(s);\nb. All turbines located within the same large wind system property shall be of a similar tower design, including the type, number of blades, and direction of blade rotation;\nc. Large wind systems shall be setback at least one and one-half times the height of the turbine and rotor diameter from the property line. Large wind systems shall also be setback at least one and one-half times the height of the turbine from above ground telephone, electrical lines, and other uninhabitable structures;\nd. Towers shall not be climbable up to 15 feet above ground level.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Datasets: dim_1024, dim_768, dim_512 and dim_256
Evaluated with InformationRetrievalEvaluator

Metric	dim_1024	dim_768	dim_512	dim_256
cosine_accuracy@1	0.0307	0.0307	0.03	0.0295
cosine_accuracy@3	0.3986	0.3986	0.3907	0.3774
cosine_accuracy@5	0.5774	0.5774	0.5644	0.5502
cosine_accuracy@10	0.7881	0.7881	0.7819	0.7644
cosine_precision@1	0.0307	0.0307	0.03	0.0295
cosine_precision@3	0.1329	0.1329	0.1302	0.1258
cosine_precision@5	0.1155	0.1155	0.1129	0.11
cosine_precision@10	0.0788	0.0788	0.0782	0.0764
cosine_recall@1	0.0307	0.0307	0.03	0.0295
cosine_recall@3	0.3986	0.3986	0.3907	0.3774
cosine_recall@5	0.5774	0.5774	0.5644	0.5502
cosine_recall@10	0.7881	0.7881	0.7819	0.7644
cosine_ndcg@1	0.0307	0.0307	0.03	0.0295
cosine_ndcg@3	0.2318	0.2318	0.2266	0.2191
cosine_ndcg@5	0.3041	0.3041	0.2968	0.2887
cosine_ndcg@10	0.3753	0.3753	0.3706	0.3613
cosine_mrr@1	0.0307	0.0307	0.03	0.0295
cosine_mrr@3	0.1752	0.1752	0.171	0.1654
cosine_mrr@5	0.2144	0.2144	0.2091	0.2031
cosine_mrr@10	0.2457	0.2457	0.2416	0.235
cosine_map@100	0.2551	0.2551	0.2512	0.2453

Training Details

Training Dataset

Unnamed Dataset

Size: 17,198 training samples
Columns: question and context
Approximate statistics based on the first 1000 samples:
question context
type string string
details
min: 14 tokens
mean: 26.6 tokens
max: 57 tokens

min: 23 tokens
mean: 140.8 tokens
max: 259 tokens

	question	context
type	string	string
details	min: 14 tokens mean: 26.6 tokens max: 57 tokens	min: 23 tokens mean: 140.8 tokens max: 259 tokens

Samples:

question	context
`Are there any specific guidelines or requirements for the installation of tree supports as outlined in the regulations?`	SECTION 32 93 00: Cast-in-Place 31 25 14 - Erosion and 32 13 13 - Concrete Paving. 32 13 16 - Decorative Concrete. a. Measurement 1) Measured per each Tree planted. b. Payment 1) The work performed and materials and measured as provided under price bid per each for Tree 2) Various caliper inches. The price bid shall include: 1) Furnishing and installing Tree as 2) Preparing excavation pit 3) Topsoil, fertilizer, mulch, and planting mix, 1 = . , 1 = Tree. , 1 = furnished in accordance with this item "Measurement" will be paid for at the unit for:. planted, 1 = . specified, 1 = . by the Drawings, 1 = . supports, 1 = . [Insert Bid Number], 1 = . [Insert, 1 = . 4), 1 = Plant. Number], 1 = Number]. Engineering Project, 1 = Engineering Project Effective July 1, 2024 32 93 00 PLANTINGS Page 2 of 24 eee BER BPRERR
`What specific information do I need to include in my application to meet the standards for grouted installations?`	1.1 SUMMARY: = . 36, 2 = . 36, 3 = (1) requirements a qualified testing laboratory.. 37, 1 = . 37, 2 = . 37, 3 = Submit a minimum of 3 other similar projects where the proposed grout mix. 38, 1 = . 38, 2 = . 38, 3 = design was used.. 39 40, 1 = . 39 40, 2 = . 39 40, 3 = anticipated volumes of grout to be pumped for each. , 1 = . , 2 = . , 3 = Submit application and reach grouted.. 41, 1 = 4.. 41, 2 = . 41, 3 = Additional requirements for installations of carrier pipe 24-inch and larger:. 42, 1 = . 42, 2 = a.. 42, 3 = Submit work plan describing the carrier pipe installation equipment, materials. 43 44, 1 = . 43 44, 2 = b.. 43 44, 3 = employed. For installations without holding jacks or a restrained spacer, provide buoyant CITY OF DENTON STANDARD CONSTRUCTION SPECIFICATION DOCUMENTS Revised October 22, 2020 Effective July 1, 2024 [Insert Engineering Project Number] [Insert Bid Number] eK BWN nA 20 21 22 23 24
`In the event of a quasi judicial hearing, who else besides the site owner(s) should we inform about the decision notification process, and how do we manage their requests for a copy of the decision?`	Notice of Decision: 1. Within 10 days after a final decision on an application, the Director shall provide written notification of the decision, unless the applicant was present at the meeting where the decision was made or required by law. 2. If the review involves a quasi-judicial hearing, the Director shall, within 10 days after a final decision on the application, provide a written notification of the decision to the owner(s) of the subject site (unless the applicant was present at the meeting where the decision was made or required by law), and any other person that submitted a written request for a copy of the decision before its effective date.

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256
    ],
    "matryoshka_weights": [
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 8
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_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: 8
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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: True
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}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_1024_cosine_ndcg@10	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10
0.2974	10	2.3168	-	-	-	-
0.5948	20	1.2839	-	-	-	-
0.8922	30	0.6758	-	-	-	-
0.9814	33	-	0.3592	0.3592	0.3556	0.3496
1.1896	40	0.4651	-	-	-	-
1.4870	50	0.3707	-	-	-	-
1.7844	60	0.2941	-	-	-	-
1.9926	67	-	0.3732	0.3732	0.3699	0.3601
2.0818	70	0.2651	-	-	-	-
2.3792	80	0.2341	-	-	-	-
2.6766	90	0.2093	-	-	-	-
2.9740	100	0.1812	0.3747	0.3747	0.3718	0.3626
3.2714	110	0.1717	-	-	-	-
3.5688	120	0.1496	-	-	-	-
3.8662	130	0.1472	-	-	-	-
3.9851	134	-	0.3742	0.3742	0.3727	0.3628
4.1636	140	0.1304	-	-	-	-
4.4610	150	0.1229	-	-	-	-
4.7584	160	0.1085	-	-	-	-
4.9963	168	-	0.3745	0.3745	0.3717	0.361
5.0558	170	0.1144	-	-	-	-
5.3532	180	0.1088	-	-	-	-
5.6506	190	0.0937	-	-	-	-
5.9480	200	0.1023	-	-	-	-
5.9777	201	-	0.3749	0.3749	0.3704	0.3603
6.2454	210	0.0942	-	-	-	-
6.5428	220	0.0919	-	-	-	-
6.8401	230	0.0939	-	-	-	-
6.9888	235	-	0.3755	0.3755	0.3705	0.3603
7.1375	240	0.0925	-	-	-	-
7.4349	250	0.0928	-	-	-	-
7.7323	260	0.0869	-	-	-	-
7.8513	264	-	0.3753	0.3753	0.3706	0.3613

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.10
Sentence Transformers: 3.3.1
Transformers: 4.41.2
PyTorch: 2.4.1+cu124
Accelerate: 1.3.0
Datasets: 2.19.1
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}