snoweu_v3 / README.md
fjavigv's picture
Upload 12 files
778ae05 verified
|
Raw
History Blame Contribute Delete
68.4 kB
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:32897
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-m-v1.5
widget:
  - source_sentence: >-
      Entities such as governments and industry groups can seek official
      recognition for their sustainability certification programs concerning
      essential raw materials. To apply, they must provide evidence
      demonstrating compliance with established criteria. By a specified
      deadline, a standardized application template will be introduced to
      streamline submissions. The Commission will evaluate these applications
      and, if criteria are met, will formally recognize the schemes, detailing
      their scope in terms of the raw materials value chain and sustainability
      aspects. Regular assessments will ensure ongoing compliance, and any
      significant failures in adherence will prompt a review of the scheme's
      status.
    sentences:
      - >-
        "32018R0675: INSERTED") Carbetamide (ISO); (R)-1-(ethylcarbamoyl)ethyl
        carbanilate; (2R)-1-(ethylamino)-1-oxopropan-2-yl phenylcarbamate
        616-223-00-7 240-286-6 16118-49-3
        [▼M73](./../../../legal-content/EN/AUTO/?uri=celex:32023R1132
        "32023R1132: INSERTED") N-(2-nitrophenyl)phosphoric triamide
        616-238-00-9 477-690-9 874819-71-3 Reaction mass of
        3-(difluoromethyl)-1-methyl-N-[(1RS,4SR,9RS)-1,2,3,4-tetrahydro-9-isopropyl-1,4-methanonaphthalen-5-yl]pyrazole-4-carboxamide
        and
        3-(difluoromethyl)-1-methyl-N-[(1RS,4SR,9SR)-1,2,3,4-tetrahydro-9-isopropyl-1,4-methanonaphthalen-5-yl]pyrazole-4-carboxamide
        [> 78 % syn isomers < 15 % anti isomers relative content]; isopyrazam
        616-240-00-X - 881685-58-1
      - >-
        Article 27


        Foreign subsidies that cause or risk causing a distortion in a public
        procurement procedure shall be understood as foreign subsidies that
        enable an economic operator to submit a tender that is unduly
        advantageous in relation to the works, supplies or services concerned.
        The assessment pursuant to Article 4 of whether there is a distortion in
        the internal market and whether a tender is unduly advantageous in
        relation to the works, supplies or services concerned shall be limited
        to the public procurement procedure in question. Only foreign subsidies
        granted during the three years prior to the notification shall be taken
        into account in the assessment.
      - >-
        (c)


        vehicles produced in small series, as defined in Article 3, point (30),
        of Regulation (EU) 2018/858.


        SECTION 2


        Certification and environmental footprint


        Article 30


        Recognised schemes


        1.


        Governments, industry associations and groupings of interested
        organisations that have developed and oversee certification schemes
        related to the sustainability of critical raw materials (scheme owners)
        may apply to have their schemes recognised by the Commission.


        Applications referred in the first subparagraph of this paragraph shall
        contain any relevant evidence related to the fulfilment of the criteria
        laid down in Annex IV.


        By 24 May 2027, the Commission shall adopt implementing acts specifying
        a single template to be used by scheme owners to provide the minimum
        information that applications referred to in the first subparagraph of
        this paragraph are to contain. Those implementing acts shall be adopted
        in accordance with the examination procedure referred to in Article
        39(3).


        The extent of documentation required to complete the single template
        referred to in the third subparagraph shall be reasonable.


        2.


        Where, on the basis of the evidence provided pursuant to the paragraph 1
        of this Article, the Commission determines that a certification scheme
        meets the criteria laid down in Annex IV, or a subset thereof, it shall
        adopt implementing acts recognising that scheme and specifying the
        recognised coverage of the scheme. Those implementing acts shall be
        adopted in accordance with the examination procedure referred to in
        Article 39(3).


        3.


        The recognised coverage for each scheme shall be specified along the
        following dimensions:


        (a)


        the stages of the raw materials value chain covered by the scheme;


        (b)


        the stages of the life-cycle of a project, including before, during and
        after closure, that are covered by the scheme; and


        (c)


        the sustainability dimensions and environmental risk categories listed
        in Annex IV, point (2) that are addressed by the scheme.


        The requirements laid down in Annex IV, point 1(a) to (d) shall be a
        prerequisite for any recognition of the scheme.


        ▼C2


        4.


        The Commission shall verify, at least every three years from the date of
        application of any implementing act adopted pursuant to paragraph 2,
        that the scheme continues to fulfil the criteria laid down in Annex IV,
        or a recognised subset of those criteria.


        ▼B


        5.


        Owners of recognised schemes shall inform the Commission without delay
        of any changes or updates related to the fulfilment of the criteria laid
        down in Annex IV, or of a recognised subset of those criteria, made to
        those schemes. The Commission shall assess whether such changes or
        updates affect the basis for the recognition and take appropriate
        action.


        6.


        If there is evidence of repeated or significant cases where economic
        operators implementing a recognised scheme have failed to fulfil the
        requirements of that scheme, the Commission shall examine, in
        consultation with the owner of the recognised scheme, whether those
        cases indicate deficiencies in the scheme affecting the basis for the
        recognition and take appropriate action.


        7.


        Where the Commission identifies deficiencies in a recognised scheme
        affecting the basis for the recognition, it may grant the scheme owner
        an appropriate period, of not longer than 12 months, within which to
        take remedial action.


        8.


        Where the scheme owner fails or refuses to take the necessary remedial
        action and where the Commission has determined that the deficiencies
        referred to in paragraph 6 of this Article mean that the scheme no
        longer fulfils the criteria laid down in Annex IV, or of the recognised
        subset of those criteria, the Commission shall withdraw the recognition
        of the scheme by means of implementing acts. Those implementing acts
        shall be adopted in accordance with the examination procedure referred
        to in Article 39(3).


        9.


        The Commission shall establish and keep up-to-date a register of
        recognised schemes. That register shall be made publicly available on a
        free-access website. That website shall also allow for the collation of
        feedback from all relevant stakeholders concerning the implementation of
        recognised schemes. Such feedback shall be submitted to the relevant
        scheme owners for consideration.


        Article 31


        Environmental footprint declaration


        1.
  - source_sentence: >-
      What requirements must investment firms fulfill when providing information
      and marketing communications to clients to ensure clarity and fairness?
    sentences:
      - >-
        Section 2


        Provisions to ensure investor protection


        Article 24


        General principles and information to clients


        1.


        Member States shall require that, when providing investment services or,
        where appropriate, ancillary services to clients, an investment firm act
        honestly, fairly and professionally in accordance with the best
        interests of its clients and comply, in particular, with the principles
        set out in this Article and in Article 25.


        2.


        Investment firms which manufacture financial instruments for sale to
        clients shall ensure that those financial instruments are designed to
        meet the needs of an identified target market of end clients within the
        relevant category of clients, the strategy for distribution of the
        financial instruments is compatible with the identified target market,
        and the investment firm takes reasonable steps to ensure that the
        financial instrument is distributed to the identified target market.


        An investment firm shall understand the financial instruments they offer
        or recommend, assess the compatibility of the financial instruments with
        the needs of the clients to whom it provides investment services, also
        taking account of the identified target market of end clients as
        referred to in Article 16(3), and ensure that financial instruments are
        offered or recommended only when this is in the interest of the client.


        3.


        All information, including marketing communications, addressed by the
        investment firm to clients or potential clients shall be fair, clear and
        not misleading. Marketing communications shall be clearly identifiable
        as such.


        4.


        Appropriate information shall be provided in good time to clients or
        potential clients with regard to the investment firm and its services,
        the financial instruments and proposed investment strategies, execution
        venues and all costs and related charges. That information shall include
        the following:


        (a)


        when investment advice is provided, the investment firm must, in good
        time before it provides investment advice, inform the client:


        (i)


        whether or not the advice is provided on an independent basis;


        (ii)
      - >-
        3. Member States may derogate from the return and separate waste
        collection obligation in paragraph 1 of this Article for certain formats
        of waste, provided that collecting fractions of packaging waste
        together, or collecting packaging waste or fractions of such packaging
        waste together with other waste does not affect the capacity of such
        packaging or fractions of packaging waste to undergo preparing for
        re-use, recycling or other recovery operations in accordance with
        Articles 4 and 13 of Directive 2008/98/EC and generates output from
        those operations which is of comparable quality to that achieved through
        separate collection.
      - >-
        3. Prospective providers in the AI regulatory sandboxes, in particular
        SMEs and start-ups, shall be directed, where relevant, to pre-deployment
        services such as guidance on the implementation of this Regulation, to
        other value- adding services such as help with standardisation documents
        and certification, testing and experimentation facilities, European
        Digital Innovation Hubs and centres of excellence.


        4. Where national competent authorities consider authorising testing in
        real world conditions supervised within the framework of an AI
        regulatory sandbox to be established under this Article, they shall
        specifically agree the terms and conditions of such testing and, in
        particular, the appropriate safeguards with the participants, with a
        view to protecting fundamental rights, health and safety. Where
        appropriate, they shall cooperate with other national competent
        authorities with a view to ensuring consistent practices across the
        Union.


        Article 59


        Further processing of personal data for developing certain AI systems in
        the public interest in the AI regulatory sandbox


        1. In the AI regulatory sandbox, personal data lawfully collected for
        other purposes may be processed solely for the purpose of developing,
        training and testing certain AI systems in the sandbox when all of the
        following conditions are met:
  - source_sentence: >-
      Recent regulations have been introduced to enhance environmental
      protection and sustainability within the EU. These include measures for
      responsible supply chain management, the regulation of hazardous
      materials, and the promotion of transparency in financial disclosures
      related to sustainability, all aimed at fostering a more environmentally
      conscious economy.
    sentences:
      - >-
        (3) OJ L 282, 19.10.2016, p. 4.


        (4) Regulation (EU) 2021/1119 of the European Parliament and of the
        Council of 30 June 2021 establishing the framework for achieving climate
        neutrality and amending Regulations (EC) No 401/2009 and (EU) No
        2018/1999 (‘European Climate Law’) (OJ L 243, 9.7.2021, p. 1).


        (5) Decision (EU) 2022/591 of the European Parliament and of the Council
        of 6 April 2022 on a General Union Environment Action Programme to 2030
        (OJ L 114, 12.4.2022, p. 22).


        (6) Directive (EU) 2024/1619 of the European Parliament and of the
        Council of 31 May 2024 amending Directive 2013/36/EU as regards
        supervisory powers, sanctions, third-country branches, and
        environmental, social and governance risks (Capital Requirements
        Directive) (OJ L, 2024/1619, 19.6.2024, ELI:
        http://data.europa.eu/eli/dir/2024/1619/oj).


        (7) Regulation (EU) 2017/821 of the European Parliament and of the
        Council of 17 May 2017 laying down supply chain due diligence
        obligations for Union importers of tin, tantalum and tungsten, their
        ores, and gold originating from conflict-affected and high-risk areas
        (OJ L 130, 19.5.2017, p. 1).


        (8) Regulation (EU) 2023/1542 of the European Parliament and of the
        Council of 12 July 2023 concerning batteries and waste batteries,
        amending Directive 2008/98/EC and Regulation (EU) 2019/1020 and
        repealing Directive 2006/66/EC (OJ L 191, 28.7.2023, p. 1).


        (9) Regulation (EU) 2023/1115 of the European Parliament and of the
        Council of 31 May 2023 on the making available on the Union market and
        the export from the Union of certain commodities and products associated
        with deforestation and forest degradation and repealing Regulation (EU)
        No 995/2010 (OJ L 150, 9.6.2023, p. 206).


        (10) Directive (EU) 2016/2341 of the European Parliament and of the
        Council of 14 December 2016 on the activities and supervision of
        institutions for occupational retirement provision (IORPs) (OJ L 354,
        23.12.2016, p. 37).


        (11) Directive (EU) 2016/943 of the European Parliament and of the
        Council of 8 June 2016 on the protection of undisclosed know-how and
        business information (trade secrets) against their unlawful acquisition,
        use and disclosure (OJ L 157, 15.6.2016, p. 1).


        (12) Regulation (EU) 2021/821 of the European Parliament and of the
        Council of 20 May 2021 setting up a Union regime for the control of
        exports, brokering, technical assistance, transit and transfer of
        dual-use items (OJ L 206, 11.6.2021, p. 1).


        (13) Regulation (EU) 2019/125 of the European Parliament and of the
        Council of 16 January 2019 concerning trade in certain goods which could
        be used for capital punishment, torture or other cruel, inhuman or
        degrading treatment or punishment (OJ L 30, 31.1.2019, p. 1).


        (14) Directive 96/71/EC of the European Parliament and of the Council of
        16 December 1996 concerning the posting of workers in the framework of
        the provision of services (OJ L 18, 21.1.1997, p. 1).


        (15) Directive 2013/34/EU of the European Parliament and of the Council
        of 26 June 2013 on the annual financial statements, consolidated
        financial statements and related reports of certain types of
        undertakings, amending Directive 2006/43/EC of the European Parliament
        and of the Council and repealing Council Directives 78/660/EEC and
        83/349/EEC (OJ L 182, 29.6.2013, p. 19).


        (16) Directive (EU) 2019/1937 of the European Parliament and of the
        Council of 23 October 2019 on the protection of persons who report
        breaches of Union law (OJ L 305, 26.11.2019, p. 17).


        (17) Regulation (EU) 2019/2088 of the European Parliament and of the
        Council of 27 November 2019 on sustainability-related disclosures in the
        financial services sector (OJ L 317, 9.12.2019, p. 1).


        (18) Regulation (EU) 2023/2859 of the European Parliament and of the
        Council of 13 December 2023 establishing a European single access point
        providing centralised access to publicly available information of
        relevance to financial services, capital markets and sustainability (OJ
        L, 2023/2859, 20.12.2023, ELI:
        http://data.europa.eu/eli/reg/2023/2859/oj).


        (19) Regulation (EU) No 596/2014 of the European Parliament and of the
        Council of 16 April 2014 on market abuse (market abuse regulation) and
        repealing Directive 2003/6/EC of the European Parliament and of the
        Council and Commission Directives 2003/124/EC, 2003/125/EC and
        2004/72/EC (OJ L 173, 12.6.2014, p. 1).
      - >-
        In addition, 2,5 % of the total quantity of allowances between 2024 and
        2030 shall be auctioned for the Modernisation Fund. The beneficiary
        Member States for that amount of allowances shall be the Member States
        with a GDP per capita at market prices below 75 % of the Union average
        during the period from 2016 to 2018. The funds corresponding to that
        amount of allowances shall be distributed in accordance with Part B of
        Annex IIb.


        ▼M9


        The total remaining quantity of allowances to be auctioned by Member
        States shall be distributed in accordance with paragraph 2.


        ▼M7


        1a.
      - >-
        The objective of this Minimum Disclosure Requirement is to provide an
        understanding of the key actions taken and/or planned to prevent,
        mitigate and remediate actual and potential impacts , and to address
        risks and opportunities , and where applicable achieve the objectives
        and targets of related policies .


        Where the implementation of a policy requires actions , or a
        comprehensive action plan, to achieve its objectives, as well as when
        actions are implemented without a specific policy, the undertaking shall
        disclose the following information:


        (a)


        the list of key actions taken in the reporting year and planned for the
        future, their expected outcomes and, where relevant, how their
        implementation contributes to the achievement of policy objectives and
        targets ;


        (b)


        the scope of the key actions (i.e., coverage in terms of activities,
        upstream and/or downstream value chain, geographies and, where
        applicable, affected stakeholder groups);


        (c)


        the time horizons under which the undertaking intends to complete each
        key action;


        (d)


        if applicable, key actions taken (along with results) to provide for and
        cooperate in or support the provision of remedy for those harmed by
        actual material impacts;


        (e)


        if applicable, quantitative and qualitative information regarding the
        progress of actions or action plans disclosed in prior periods.


        Where the implementation of an action plan requires significant
        operational expenditures (Opex) and/or capital expenditures (Capex) the
        undertaking shall:


        (a)


        describe the type of current and future financial and other resources
        allocated to the action plan, including if applicable, the relevant
        terms of sustainable finance instruments, such as green bonds, social
        bonds and green loans, the environmental or social objectives, and
        whether the ability to implement the actions or action plan depends on
        specific preconditions, e.g., granting of financial support or public
        policy and market developments;


        (b)


        provide the amount of current financial resources and explain how they
        relate to the most relevant amounts presented in the financial
        statements; and


        (c)


        provide the amount of future financial resources.


        5. Metrics and targets


        This chapter sets out Minimum Disclosure Requirements that shall be
        included when the undertaking discloses information on its metrics and
        targets related to each material sustainability matter. They shall be
        applied together with the Disclosure Requirements, including Application
        Requirements, provided in the relevant topical ESRS. They shall also be
        applied when the undertaking prepares entity-specific disclosures.


        The corresponding disclosures shall be located alongside disclosures
        prescribed by the topical ESRS.


        If the undertaking cannot disclose the information on targets required
        under the relevant topical ESRS, because it has not set targets with
        reference to the specific sustainability matter concerned, it shall
        disclose this to be the case, and provide reasons for not having adopted
        targets. The undertaking may disclose a timeframe in which it aims to
        adopt them.


        Minimum disclosure requirement  Metrics MDR-M  Metrics in relation to
        material sustainability matters


        The undertaking shall apply the requirements for the content of
        disclosures in this provision when it discloses on the metrics it has in
        place with regard to each material sustainability matter .


        The objective of this Minimum Disclosure Requirement is to provide an
        understanding of the metrics the undertaking uses to track the
        effectiveness of its actions to manage material sustainability matters .


        The undertaking shall disclose any metrics that it uses to evaluate
        performance and effectiveness, in relation to a material impact, risk or
        opportunity.


        Metrics shall include those defined in ESRS, as well as metrics
        identified on an entity-specific basis, whether taken from other sources
        or developed by the undertaking itself.


        For each metric , the undertaking shall:


        (a)


        disclose the methodologies and significant assumptions behind the
        metric, including the limitations of the methodologies used;


        (b)


        disclose whether the measurement of the metric is validated by an
        external body other than the assurance provider and, if so, which body;


        (c)


        label and define the metric using meaningful, clear and precise names
        and descriptions;


        (d)


        when currency is specified as the unit of measure, use the presentation
        currency of its financial statements.
  - source_sentence: >-
      What specific categories must be used to report the quantity of electrical
      and electronic equipment (EEE) placed on the national market and the
      quantity of waste EEE that has been collected, recycled, recovered, and
      disposed of?
    sentences:
      - >-
        (50) Council Directive 2003/96/EC of 27 October 2003 restructuring the
        Community framework for the taxation of energy products and electricity
        (OJ L 283, 31.10.2003, p. 51).


        (51) Directive 2009/81/EC of the European Parliament and of the Council
        of 13 July 2009 on the coordination of procedures for the award of
        certain works contracts, supply contracts and service contracts by
        contracting authorities or entities in the fields of defence and
        security, and amending Directives 2004/17/EC and 2004/18/EC (OJ L 216,
        20.8.2009, p. 76).


        (52) Directive 2001/42/EC of the European Parliament and of the Council
        of 27 June 2001 on the assessment of the effects of certain plans and
        programmes on the environment (OJ L 197, 21.7.2001, p. 30).


        (53) Directive 2014/89/EU of the European Parliament and of the Council
        of 23 July 2014 establishing a framework for maritime spatial planning
        (OJ L 257, 28.8.2014, p. 135).


        (54) Directive (EU) 2023/2413 of the European Parliament and of the
        Council of 18 October 2023 amending Directive (EU) 2018/2001, Regulation
        (EU) 2018/1999 and Directive 98/70/EC as regards the promotion of energy
        from renewable sources, and repealing Council Directive (EU) 2015/652
        (OJ L, 2023/2413, 31.10.2023, ELI:
        http://data.europa.eu/eli/dir/2023/2413/oj).


        (55) Directive 94/22/EC of the European Parliament and of the Council of
        30 May 1994 on the conditions for granting and using authorizations for
        the prospection, exploration and production of hydrocarbons (OJ L 164,
        30.6.1994, p. 3).


        (56) Regulation (EU) No 952/2013 of the European Parliament and of the
        Council of 9 October 2013 laying down the Union Customs Code (OJ L 269,
        10.10.2013, p. 1).


        (57) Regulation (EU) 2023/955 of the European Parliament and of the
        Council of 10 May 2023 establishing a Social Climate Fund and amending
        Regulation (EU) 2021/1060 (OJ L 130, 16.5.2023, p. 1).


        (58) Regulation (EU) 2016/589 of the European Parliament and of the
        Council of 13 April 2016 on a European network of employment services
        (EURES), workers' access to mobility services and the further
        integration of labour markets, and amending Regulations (EU) No 492/2011
        and (EU) No 1296/2013 (OJ L 107, 22.4.2016, p. 1).
      - >-
        (d)


        the processes through which the undertaking supports the availability of
        such channels in the workplace of its own workforce; and


        (e)


        how it tracks and monitors issues raised and addressed, and, how it
        ensures the effectiveness of the channels, including through the
        involvement of stakeholders who are intended users .
      - >-
        4.


        Quantity of EEE placed on the national market, by weight.


        5.


        Quantity, by weight, of waste of EEE separately collected, recycled
        (including prepared for re-use), recovered and disposed of within the
        Member State or shipped within or outside the Union.


        Note: information set out in points 4 and 5 must be given by category.


        ANNEX XI


        PART A


        Repealed Directive with its successive amendments


        (referred to in Article 25)


        Directive 2002/96/EC on waste electrical and electronic equipment (WEEE)
        (OJ L 37, 13.2.2003, p. 24) Directive 2003/108/EC of the European
        Parliament and of the Council (OJ L 345, 31.12.2003, p. 106) Directive
        2008/34/EC of the European Parliament and of the Council (OJ L 81,
        20.3.2008, p. 65)


        PART B
  - source_sentence: >-
      How does the operational efficiency of energy systems impact the
      integration of renewable energy sources into the grid, and what role does
      this play in improving overall energy efficiency?
    sentences:
      - >-
        (58) Directive 2010/75/EU of the European Parliament and of the Council
        (21) lays down rules on installations that contribute to energy
        production or use energy for production purposes, and provides that
        information on the energy used in or generated by the installation is to
        be included in applications for integrated permits in accordance with
        Article 12(1), point (b) of that Directive. Moreover, Article 11 of that
        Directive provides that efficient use of energy is one of the general
        principles governing the basic obligations of the operator and one of
        the criteria for determining best available techniques pursuant to Annex
        III to that Directive. The operational efficiency of energy systems at
        any given moment is influenced by the ability to feed power generated
        from different sources with different degrees of inertia and start-up
        times into the grid smoothly and flexibly. Improving efficiency will
        enable better use to be made of renewable energy.


        (59) Improvement in energy efficiency can contribute to higher economic
        output. Member States and the Union should aim to decrease energy
        consumption regardless of levels of economic growth.


        (60) The energy savings obligation established by this Directive should
        be increased and should also apply after 2030. That ensures stability
        for investors and thus encourages long-term investments and long-term
        energy efficiency measures, such as the deep renovation of buildings
        with the long-term objective of facilitating the cost effective
        transformation of existing buildings into nearly zero-energy buildings.
        The energy savings obligation plays an important role in the creation of
        local growth, jobs, competitiveness and alleviating energy poverty. It
        should ensure that the Union can achieve its energy and climate
        objectives by creating further opportunities and by breaking the link
        between energy consumption and growth. Cooperation with the private
        sector is important to assess the conditions on which private investment
        for energy efficiency projects can be unlocked and to develop new
        revenue models for innovation in the field of energy efficiency.
      - >-
        where:


        ‘distance’ means the great circle distance between the aerodrome of
        departure and the aerodrome of arrival plus an additional fixed factor
        of 95 km; and


        ‘payload’ means the total mass of freight, mail and passengers carried.


        For the purposes of calculating the payload:


        the number of passengers shall be the number of persons on-board
        excluding crew members,


        an aircraft operator may choose to apply either the actual or standard
        mass for passengers and checked baggage contained in its mass and
        balance documentation for the relevant flights or a default value of 100
        kg for each passenger and his checked baggage.


        Reporting of tonne-kilometre data for the purpose of Articles 3e and 3f
      - >-
        Article 12


        1. Member States shall ensure that producers provide at least for the
        financing of the collection, treatment, recovery and environmentally
        sound disposal of WEEE from private households that has been deposited
        at collection facilities set up under Article 5(2) as follows:


        (a) for WEEE resulting from EEE referred to in Article 2(1), point (a),
        other than photovoltaic panels, where such EEE was placed on the market
        after 13 August 2005;


        (b) for WEEE resulting from photovoltaic panels where such photovoltaic
        panels were placed on the market from 13 August 2012; and


        (c) for WEEE resulting from EEE referred to in Article 2(1), point (b),
        and which does not fall within the scope of Article 2(1), point (a),
        where such EEE was placed on the market from 15 August 2018.


        3. Each producer shall be responsible for financing the operations
        referred to in paragraph 1 relating to the waste from his own products.
        The producer may choose to fulfil this obligation either individually or
        by joining a collective scheme.


        Member States shall ensure that each producer provides a guarantee when
        placing a product on the market showing that the management of all WEEE
        will be financed and shall ensure that producers clearly mark their
        products in accordance with Article 15(2). This guarantee shall ensure
        that the operations referred to in paragraph 1 relating to this product
        will be financed. The guarantee may take the form of participation by
        the producer in appropriate schemes for the financing of the management
        of WEEE, a recycling insurance or a blocked bank account.
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@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.8110473890733474
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9429520072441896
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.970419559311802
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9849079384243887
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8110473890733474
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.31431733574806314
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1940839118623604
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09849079384243888
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8110473890733474
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9429520072441896
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.970419559311802
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9849079384243887
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9068065758438455
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8807861287185174
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8816391915783972
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-m-v1.5

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-m-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: Snowflake/snowflake-arctic-embed-m-v1.5
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'How does the operational efficiency of energy systems impact the integration of renewable energy sources into the grid, and what role does this play in improving overall energy efficiency?',
    '(58) Directive 2010/75/EU of the European Parliament and of the Council (21) lays down rules on installations that contribute to energy production or use energy for production purposes, and provides that information on the energy used in or generated by the installation is to be included in applications for integrated permits in accordance with Article 12(1), point (b) of that Directive. Moreover, Article 11 of that Directive provides that efficient use of energy is one of the general principles governing the basic obligations of the operator and one of the criteria for determining best available techniques pursuant to Annex III to that Directive. The operational efficiency of energy systems at any given moment is influenced by the ability to feed power generated from different sources with different degrees of inertia and start-up times into the grid smoothly and flexibly. Improving efficiency will enable better use to be made of renewable energy.\n\n(59) Improvement in energy efficiency can contribute to higher economic output. Member States and the Union should aim to decrease energy consumption regardless of levels of economic growth.\n\n(60) The energy savings obligation established by this Directive should be increased and should also apply after 2030. That ensures stability for investors and thus encourages long-term investments and long-term energy efficiency measures, such as the deep renovation of buildings with the long-term objective of facilitating the cost effective transformation of existing buildings into nearly zero-energy buildings. The energy savings obligation plays an important role in the creation of local growth, jobs, competitiveness and alleviating energy poverty. It should ensure that the Union can achieve its energy and climate objectives by creating further opportunities and by breaking the link between energy consumption and growth. Cooperation with the private sector is important to assess the conditions on which private investment for energy efficiency projects can be unlocked and to develop new revenue models for innovation in the field of energy efficiency.',
    'where:\n\n‘distance’ means the great circle distance between the aerodrome of departure and the aerodrome of arrival plus an additional fixed factor of 95 km; and\n\n‘payload’ means the total mass of freight, mail and passengers carried.\n\nFor the purposes of calculating the payload:\n\nthe number of passengers shall be the number of persons on-board excluding crew members,\n\nan aircraft operator may choose to apply either the actual or standard mass for passengers and checked baggage contained in its mass and balance documentation for the relevant flights or a default value of 100 kg for each passenger and his checked baggage.\n\nReporting of tonne-kilometre data for the purpose of Articles 3e and 3f',
]
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

Metric Value
cosine_accuracy@1 0.811
cosine_accuracy@3 0.943
cosine_accuracy@5 0.9704
cosine_accuracy@10 0.9849
cosine_precision@1 0.811
cosine_precision@3 0.3143
cosine_precision@5 0.1941
cosine_precision@10 0.0985
cosine_recall@1 0.811
cosine_recall@3 0.943
cosine_recall@5 0.9704
cosine_recall@10 0.9849
cosine_ndcg@10 0.9068
cosine_mrr@10 0.8808
cosine_map@100 0.8816

Training Details

Training Dataset

Unnamed Dataset

  • Size: 32,897 training samples
  • Columns: sentence_0 and sentence_1
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1
    type string string
    details
    • min: 12 tokens
    • mean: 41.21 tokens
    • max: 184 tokens
    • min: 3 tokens
    • mean: 234.18 tokens
    • max: 512 tokens
  • Samples:
    sentence_0 sentence_1
    What is the maximum allowable concentration of Dimethylfumarate in articles or parts thereof, and what are the implications for market placement if this concentration is exceeded? "32011R0366: INSERTED") 60. Acrylamide CAS No 79-06-1 Shall not be placed on the market or used as a substance or constituent of mixtures in a concentration, equal to or greater than 0,1 % by weight for grouting applications after 5 November 2012. ▼M16 61. Dimethylfumarate (DMF) CAS No 624-49-7 EC 210-849-0 Shall not be used in articles or any parts thereof in concentrations greater than 0,1 mg/kg. Articles or any parts thereof containing DMF in concentrations greater than 0,1 mg/kg shall not be placed on the market. ▼M20 62. (a) Phenylmercury acetate EC No: 200-532-5 CAS No:
    The passage highlights the importance of ensuring that hygiene products made partly or wholly from plastics remain safe by avoiding harmful chemical substances. By calling for the assessment of additional restrictions under chemical regulations, it underscores a precautionary stance rooted in safeguarding consumer well-being, particularly for products intimately connected to human health. (19)
    What responsibilities do Member States have regarding penalties for infringements of national provisions adopted under the directive? Member States shall lay down the rules on penalties applicable to infringements of national provisions adopted pursuant to this Directive and shall take all measures necessary to ensure that they are implemented. The penalties provided for shall be effective, proportionate and dissuasive. Member States shall, by 3 July 2021, notify the Commission of those rules and those measures and shall notify it of any subsequent amendment affecting them.
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            768,
            512,
            256,
            128,
            64
        ],
        "matryoshka_weights": [
            1,
            1,
            1,
            1,
            1
        ],
        "n_dims_per_step": -1
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 4
  • per_device_eval_batch_size: 4
  • num_train_epochs: 4
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 4
  • per_device_eval_batch_size: 4
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • torch_empty_cache_steps: None
  • learning_rate: 5e-05
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1
  • num_train_epochs: 4
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.0
  • 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: False
  • 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}
  • 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
  • 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
  • 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
  • eval_on_start: False
  • use_liger_kernel: False
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand
Epoch Step Training Loss cosine_ndcg@10
0.0122 100 - 0.6297
0.0243 200 - 0.7126
0.0365 300 - 0.7753
0.0486 400 - 0.8207
0.0608 500 0.3802 0.8440
0.0729 600 - 0.8541
0.0851 700 - 0.8600
0.0973 800 - 0.8646
0.1094 900 - 0.8693
0.1216 1000 0.0994 0.8703
0.1337 1100 - 0.8769
0.1459 1200 - 0.8739
0.1581 1300 - 0.8716
0.1702 1400 - 0.8766
0.1824 1500 0.0749 0.8791
0.1945 1600 - 0.8791
0.2067 1700 - 0.8793
0.2188 1800 - 0.8810
0.2310 1900 - 0.8801
0.2432 2000 0.0834 0.8821
0.2553 2100 - 0.8851
0.2675 2200 - 0.8810
0.2796 2300 - 0.8790
0.2918 2400 - 0.8799
0.3040 2500 0.0686 0.8762
0.3161 2600 - 0.8785
0.3283 2700 - 0.8801
0.3404 2800 - 0.8754
0.3526 2900 - 0.8767
0.3647 3000 0.0402 0.8748
0.3769 3100 - 0.8742
0.3891 3200 - 0.8733
0.4012 3300 - 0.8801
0.4134 3400 - 0.8824
0.4255 3500 0.065 0.8796
0.4377 3600 - 0.8783
0.4498 3700 - 0.8707
0.4620 3800 - 0.8768
0.4742 3900 - 0.8761
0.4863 4000 0.0543 0.8797
0.4985 4100 - 0.8787
0.5106 4200 - 0.8796
0.5228 4300 - 0.8788
0.5350 4400 - 0.8808
0.5471 4500 0.0817 0.8813
0.5593 4600 - 0.8778
0.5714 4700 - 0.8794
0.5836 4800 - 0.8824
0.5957 4900 - 0.8820
0.6079 5000 0.0425 0.8809
0.6201 5100 - 0.8786
0.6322 5200 - 0.8794
0.6444 5300 - 0.8760
0.6565 5400 - 0.8765
0.6687 5500 0.0509 0.8743
0.6809 5600 - 0.8792
0.6930 5700 - 0.8835
0.7052 5800 - 0.8825
0.7173 5900 - 0.8826
0.7295 6000 0.0538 0.8817
0.7416 6100 - 0.8769
0.7538 6200 - 0.8793
0.7660 6300 - 0.8785
0.7781 6400 - 0.8775
0.7903 6500 0.0193 0.8790
0.8024 6600 - 0.8827
0.8146 6700 - 0.8782
0.8267 6800 - 0.8727
0.8389 6900 - 0.8807
0.8511 7000 0.0441 0.8819
0.8632 7100 - 0.8825
0.8754 7200 - 0.8822
0.8875 7300 - 0.8781
0.8997 7400 - 0.8794
0.9119 7500 0.0518 0.8799
0.9240 7600 - 0.8801
0.9362 7700 - 0.8792
0.9483 7800 - 0.8773
0.9605 7900 - 0.8759
0.9726 8000 0.03 0.8768
0.9848 8100 - 0.8748
0.9970 8200 - 0.8736
1.0 8225 - 0.8802
1.0091 8300 - 0.8779
1.0213 8400 - 0.8747
1.0334 8500 0.028 0.8798
1.0456 8600 - 0.8793
1.0578 8700 - 0.8773
1.0699 8800 - 0.8810
1.0821 8900 - 0.8823
1.0942 9000 0.0232 0.8782
1.1064 9100 - 0.8844
1.1185 9200 - 0.8772
1.1307 9300 - 0.8746
1.1429 9400 - 0.8739
1.1550 9500 0.0316 0.8806
1.1672 9600 - 0.8789
1.1793 9700 - 0.8818
1.1915 9800 - 0.8812
1.2036 9900 - 0.8871
1.2158 10000 0.0251 0.8876
1.2280 10100 - 0.8884
1.2401 10200 - 0.8859
1.2523 10300 - 0.8844
1.2644 10400 - 0.8840
1.2766 10500 0.0244 0.8844
1.2888 10600 - 0.8842
1.3009 10700 - 0.8874
1.3131 10800 - 0.8875
1.3252 10900 - 0.8827
1.3374 11000 0.0258 0.8831
1.3495 11100 - 0.8830
1.3617 11200 - 0.8831
1.3739 11300 - 0.8845
1.3860 11400 - 0.8868
1.3982 11500 0.0334 0.8871
1.4103 11600 - 0.8872
1.4225 11700 - 0.8886
1.4347 11800 - 0.8894
1.4468 11900 - 0.8876
1.4590 12000 0.0167 0.8906
1.4711 12100 - 0.8915
1.4833 12200 - 0.8910
1.4954 12300 - 0.8892
1.5076 12400 - 0.8894
1.5198 12500 0.0216 0.8877
1.5319 12600 - 0.8899
1.5441 12700 - 0.8881
1.5562 12800 - 0.8889
1.5684 12900 - 0.8869
1.5805 13000 0.0181 0.8879
1.5927 13100 - 0.8883
1.6049 13200 - 0.8876
1.6170 13300 - 0.8873
1.6292 13400 - 0.8895
1.6413 13500 0.0236 0.8913
1.6535 13600 - 0.8918
1.6657 13700 - 0.8933
1.6778 13800 - 0.8913
1.6900 13900 - 0.8937
1.7021 14000 0.0291 0.8941
1.7143 14100 - 0.8950
1.7264 14200 - 0.8957
1.7386 14300 - 0.8912
1.7508 14400 - 0.8937
1.7629 14500 0.0266 0.8922
1.7751 14600 - 0.8903
1.7872 14700 - 0.8930
1.7994 14800 - 0.8913
1.8116 14900 - 0.8913
1.8237 15000 0.018 0.8925
1.8359 15100 - 0.8928
1.8480 15200 - 0.8889
1.8602 15300 - 0.8884
1.8723 15400 - 0.8876
1.8845 15500 0.018 0.8891
1.8967 15600 - 0.8887
1.9088 15700 - 0.8891
1.9210 15800 - 0.8924
1.9331 15900 - 0.8891
1.9453 16000 0.0223 0.8902
1.9574 16100 - 0.8943
1.9696 16200 - 0.8925
1.9818 16300 - 0.8905
1.9939 16400 - 0.8892
2.0 16450 - 0.8897
2.0061 16500 0.0274 0.8889
2.0182 16600 - 0.8914
2.0304 16700 - 0.8871
2.0426 16800 - 0.8878
2.0547 16900 - 0.8882
2.0669 17000 0.0178 0.8879
2.0790 17100 - 0.8892
2.0912 17200 - 0.8896
2.1033 17300 - 0.8933
2.1155 17400 - 0.8936
2.1277 17500 0.0079 0.8942
2.1398 17600 - 0.8927
2.1520 17700 - 0.8914
2.1641 17800 - 0.8932
2.1763 17900 - 0.8917
2.1884 18000 0.0031 0.8921
2.2006 18100 - 0.8912
2.2128 18200 - 0.8879
2.2249 18300 - 0.8865
2.2371 18400 - 0.8847
2.2492 18500 0.0127 0.8869
2.2614 18600 - 0.8880
2.2736 18700 - 0.8885
2.2857 18800 - 0.8901
2.2979 18900 - 0.8880
2.3100 19000 0.019 0.8897
2.3222 19100 - 0.8918
2.3343 19200 - 0.8895
2.3465 19300 - 0.8918
2.3587 19400 - 0.8933
2.3708 19500 0.0177 0.8936
2.3830 19600 - 0.8919
2.3951 19700 - 0.8922
2.4073 19800 - 0.8923
2.4195 19900 - 0.8946
2.4316 20000 0.0085 0.8935
2.4438 20100 - 0.8944
2.4559 20200 - 0.8918
2.4681 20300 - 0.8948
2.4802 20400 - 0.8937
2.4924 20500 0.0073 0.8935
2.5046 20600 - 0.8942
2.5167 20700 - 0.8939
2.5289 20800 - 0.8950
2.5410 20900 - 0.8974
2.5532 21000 0.01 0.8961
2.5653 21100 - 0.8977
2.5775 21200 - 0.8985
2.5897 21300 - 0.8962
2.6018 21400 - 0.8981
2.6140 21500 0.0148 0.8978
2.6261 21600 - 0.8967
2.6383 21700 - 0.8978
2.6505 21800 - 0.8975
2.6626 21900 - 0.9010
2.6748 22000 0.0271 0.9000
2.6869 22100 - 0.8973
2.6991 22200 - 0.8987
2.7112 22300 - 0.9005
2.7234 22400 - 0.8990
2.7356 22500 0.0108 0.8993
2.7477 22600 - 0.9011
2.7599 22700 - 0.8998
2.7720 22800 - 0.8981
2.7842 22900 - 0.9006
2.7964 23000 0.0067 0.9010
2.8085 23100 - 0.9028
2.8207 23200 - 0.9024
2.8328 23300 - 0.9027
2.8450 23400 - 0.9024
2.8571 23500 0.01 0.9031
2.8693 23600 - 0.9029
2.8815 23700 - 0.9022
2.8936 23800 - 0.8992
2.9058 23900 - 0.9007
2.9179 24000 0.0081 0.9005
2.9301 24100 - 0.8990
2.9422 24200 - 0.8992
2.9544 24300 - 0.9021
2.9666 24400 - 0.9003
2.9787 24500 0.0142 0.9016
2.9909 24600 - 0.9018
3.0 24675 - 0.9014
3.0030 24700 - 0.9014
3.0152 24800 - 0.9012
3.0274 24900 - 0.9006
3.0395 25000 0.0033 0.9002
3.0517 25100 - 0.9013
3.0638 25200 - 0.9025
3.0760 25300 - 0.9022
3.0881 25400 - 0.9013
3.1003 25500 0.0072 0.9008
3.1125 25600 - 0.9007
3.1246 25700 - 0.8997
3.1368 25800 - 0.8982
3.1489 25900 - 0.8992
3.1611 26000 0.0147 0.8999
3.1733 26100 - 0.9010
3.1854 26200 - 0.9002
3.1976 26300 - 0.9024
3.2097 26400 - 0.9017
3.2219 26500 0.0154 0.9038
3.2340 26600 - 0.9039
3.2462 26700 - 0.9040
3.2584 26800 - 0.9031
3.2705 26900 - 0.9035
3.2827 27000 0.0078 0.9035
3.2948 27100 - 0.9038
3.3070 27200 - 0.9041
3.3191 27300 - 0.9039
3.3313 27400 - 0.9026
3.3435 27500 0.0041 0.9025
3.3556 27600 - 0.9027
3.3678 27700 - 0.9037
3.3799 27800 - 0.9029
3.3921 27900 - 0.9030
3.4043 28000 0.0043 0.9028
3.4164 28100 - 0.9027
3.4286 28200 - 0.9027
3.4407 28300 - 0.9037
3.4529 28400 - 0.9048
3.4650 28500 0.0102 0.9040
3.4772 28600 - 0.9042
3.4894 28700 - 0.9050
3.5015 28800 - 0.9046
3.5137 28900 - 0.9057
3.5258 29000 0.0075 0.9048
3.5380 29100 - 0.9045
3.5502 29200 - 0.9052
3.5623 29300 - 0.9053
3.5745 29400 - 0.9068

Framework Versions

  • Python: 3.10.11
  • Sentence Transformers: 3.4.1
  • Transformers: 4.48.1
  • PyTorch: 2.4.0+cu121
  • Accelerate: 1.4.0
  • Datasets: 3.3.2
  • Tokenizers: 0.21.0

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}
}