IoannisKat1's picture
Add new SentenceTransformer model
84577ad verified
metadata
language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1580
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-m3
widget:
  - source_sentence: How can the duties of a member end?
    sentences:
      - >-
        **Court (Civil/Criminal):**

        Provisions: Articles 8 of Law 2251/1994, Articles 2, 4, 48 et seq. of
        Law 4537/2018, Article 11 paragraph 1 of Law 4261/2014, Articles 830,
        806, 827, 914, 932 of the Civil Code and 176 of the Code of Civil
        Procedure.

        Time of commission of the act:

        Outcome (not guilty, guilty):

        Rationale: Electronic fraud through the method of phishing. A third
        party fraudulently obtained money from the plaintiff's bank account and
        transferred it to another bank account. Both the defendant is liable for
        the inadequate protection of its systems, which should have been
        excellent, and the plaintiff who failed to fulfill his obligation to
        protect his information and disregarded the defendant's security
        instructions. Law 4537/2018 introduces mandatory law in favor of users,
        as according to Article 103, payment service providers are prohibited
        from deviating from the provisions to the detriment of payment service
        users. It is determined that a resumption of the discussion should be
        ordered in order to provide all possible evidence, with diligence from
        both parties, especially from the defendant, who has access to the
        transaction data through its systems, but also bears the relevant burden
        of proof concerning the exact timing of the execution of the money
        transfer order at each stage (withdrawal from the plaintiff's account,
        transfer to another bank, transfer to the third party's account).

        Facts: The plaintiff maintains a joint bank account with his wife at the
        defendant bank and has also agreed to online banking transactions
        (e-banking). On July 31, 2020, at 13:45, the plaintiff was informed of a
        transfer of €3,000 from his account, which he had not initiated, nor had
        his wife. At 14:05, he immediately contacted the bank’s customer service
        line and reported the incident, stating that it was not his action and
        requesting its cancellation. The bank employee found that the plaintiff
        had provided his details to a fake website 10 days earlier, and
        subsequently, the mobile number used for transaction confirmations had
        been changed. The employee informed him that the money was at the other
        bank and that they would logically be able to retrieve it, provided it
        had not already been transferred to a third party's account. Since then,
        the plaintiff has not seen any return of the amount to his account, and
        he has made numerous attempts to resolve the issue with the bank, with
        effort, costs, and distress; however, nothing was achieved, as the money
        had already entered a third party's account and the defendant denied
        responsibility for the transfer of the funds.

        Facts: The plaintiff maintained a joint account with his wife at a bank
        and used internet banking services. On July 21, 2020, a third party
        deceived the plaintiff through phishing (a misleading SMS with a link),
        obtaining his banking credentials. The third party, using the stolen
        information, requested a phone number change for receiving OTP (one-time
        password) and completing electronic transactions. The bank completed the
        change process based on the correct credentials. On July 31, 2020, a
        transfer of €3,000 was made from the plaintiff's account to a third
        party. The plaintiff was immediately informed, called the bank, and
        reported the fraud; however, the recovery of the funds was not
        successful. The plaintiff claims that the bank is responsible for
        inadequate protection of its systems, while the bank asserts that it
        followed the procedure based on the agreed identification methods. 

        The court recognizes that there is responsibility on both sides: the
        bank for inadequate security and prevention of phishing, and the
        plaintiff for negligence in safeguarding his personal information,
        despite the bank's relevant warnings. A critical issue is the exact
        timing of the completion of the transfer: if the bank was timely
        notified of the fraud but did not intervene, it may be fully liable. The
        court requests a resumption of the discussion and further evidence,
        mainly from the bank, which has access to the relevant technical
        details.
      - >-
        Email phishing is a type of identity theft scam conducted via email or
        SMS. The attacker uses social engineering tactics such as impersonating
        trusted entities and inducing urgency. Victims are tricked into
        disclosing personal information or downloading malware.


        Scenarios:

        - Scenario 1: Emails impersonating high-ranking executives accuse
        victims of crimes to coerce them into revealing information or opening
        malware-laden attachments.

        - Scenario 2: Emails/SMS from fake banks or authorities alert victims of
        data breaches, directing them to spoofed websites to input credentials.

        - Scenario 3: SMS messages deliver disguised malware apps that harvest
        sensitive data.

        - Scenario 4: SMS links lead to pharming sites that mimic trusted brands
        and steal login data through fake pop-ups.
      - >-
        1.Member States shall provide for each member of their supervisory
        authorities to be appointed by means of a transparent procedure by: — 
        their parliament; —  their government; —  their head of State; or —  an
        independent body entrusted with the appointment under Member State law.

        2.Each member shall have the qualifications, experience and skills, in
        particular in the area of the protection of personal data, required to
        perform its duties and exercise its powers.

        3.The duties of a member shall end in the event of the expiry of the
        term of office, resignation or compulsory retirement, in accordance with
        the law of the Member State concerned.

        4.A member shall be dismissed only in cases of serious misconduct or if
        the member no longer fulfils the conditions required for the performance
        of the duties.
  - source_sentence: What is covered under point (i)?
    sentences:
      - >-
        1.The Member States, the supervisory authorities, the Board and the
        Commission shall encourage the drawing up of codes of conduct intended
        to contribute to the proper application of this Regulation, taking
        account of the specific features of the various processing sectors and
        the specific needs of micro, small and medium-sized enterprises.

        2.Associations and other bodies representing categories of controllers
        or processors may prepare codes of conduct, or amend or extend such
        codes, for the purpose of specifying the application of this Regulation,
        such as with regard to: (a)  fair and transparent processing; 4.5.2016 L
        119/56   (b)  the legitimate interests pursued by controllers in
        specific contexts; (c)  the collection of personal data; (d)  the
        pseudonymisation of personal data; (e)  the information provided to the
        public and to data subjects; (f)  the exercise of the rights of data
        subjects; (g)  the information provided to, and the protection of,
        children, and the manner in which the consent of the holders of parental
        responsibility over children is to be obtained; (h)  the measures and
        procedures referred to in Articles 24 and 25 and the measures to ensure
        security of processing referred to in Article 32; (i)  the notification
        of personal data breaches to supervisory authorities and the
        communication of such personal data breaches to data subjects; (j)  the
        transfer of personal data to third countries or international
        organisations; or (k)  out-of-court proceedings and other dispute
        resolution procedures for resolving disputes between controllers and
        data subjects with regard to processing, without prejudice to the rights
        of data subjects pursuant to Articles 77 and 79

        3.In addition to adherence by controllers or processors subject to this
        Regulation, codes of conduct approved pursuant to paragraph 5 of this
        Article and having general validity pursuant to paragraph 9 of this
        Article may also be adhered to by controllers or processors that are not
        subject to this Regulation pursuant to Article 3 in order to provide
        appropriate safeguards within the framework of personal data transfers
        to third countries or international organisations under the terms
        referred to in point (e) of Article 46(2). Such controllers or
        processors shall make binding and enforceable commitments, via
        contractual or other legally binding instruments, to apply those
        appropriate safeguards including with regard to the rights of data
        subjects.

        4.A code of conduct referred to in paragraph 2 of this Article shall
        contain mechanisms which enable the body referred to in Article 41(1) to
        carry out the mandatory monitoring of compliance with its provisions by
        the controllers or processors which undertake to apply it, without
        prejudice to the tasks and powers of supervisory authorities competent
        pursuant to Article 55 or 56

        5.Associations and other bodies referred to in paragraph 2 of this
        Article which intend to prepare a code of conduct or to amend or extend
        an existing code shall submit the draft code, amendment or extension to
        the supervisory authority which is competent pursuant to Article 55. The
        supervisory authority shall provide an opinion on whether the draft
        code, amendment or extension complies with this Regulation and shall
        approve that draft code, amendment or extension if it finds that it
        provides sufficient appropriate safeguards.

        6.Where the draft code, or amendment or extension is approved in
        accordance with paragraph 5, and where the code of conduct concerned
        does not relate to processing activities in several Member States, the
        supervisory authority shall register and publish the code.

        7.Where a draft code of conduct relates to processing activities in
        several Member States, the supervisory authority which is competent
        pursuant to Article 55 shall, before approving the draft code, amendment
        or extension, submit it in the procedure referred to in Article 63 to
        the Board which shall provide an opinion on whether the draft code,
        amendment or extension complies with this Regulation or, in the
        situation referred to in paragraph 3 of this Article, provides
        appropriate safeguards.

        8.Where the opinion referred to in paragraph 7 confirms that the draft
        code, amendment or extension complies with this Regulation, or, in the
        situation referred to in paragraph 3, provides appropriate safeguards,
        the Board shall submit its opinion to the Commission.

        9.The Commission may, by way of implementing acts, decide that the
        approved code of conduct, amendment or extension submitted to it
        pursuant to paragraph 8 of this Article have general validity within the
        Union. Those implementing acts shall be adopted in accordance with the
        examination procedure set out in Article 93(2)

        10.The Commission shall ensure appropriate publicity for the approved
        codes which have been decided as having general validity in accordance
        with paragraph

        11.The Board shall collate all approved codes of conduct, amendments and
        extensions in a register and shall make them publicly available by way
        of appropriate means.
      - >-
        **Court (Civil/Criminal): Civil**  

        **Provisions:**  

        **Time of commission of the act:**  

        **Outcome (not guilty, guilty):**  

        **Reasoning:** Claim for compensation and monetary satisfaction due to
        moral damage against a mobile phone company and a credit institution
        within the framework of inadequate fulfillment of a payment services
        contract for "web banking." Appropriate actions for mobile phone
        companies in case of a request for a "sim" card replacement due to wear
        or loss. They must verify the customer's identity based on the personal
        details and identification information registered in their system but
        are not liable for any changes in the latter that were not timely
        communicated to them. Further security measures such as phone
        communication or sending an SMS to the mobile number holder are not
        required. Payment services under Law 4357/2018. Obligation of the
        payment service provider, such as banks, to inform the payer after
        receiving a relevant order for making a payment. The content of this
        varies per case, such as sending a personalized code to the user's
        mobile phone for transaction approval, as well as sending an email
        immediately after its completion. However, the bank is not liable for
        customer damage resulting from illicit electronic transactions due to
        third-party interception of either the access codes for electronic
        banking transactions or the sim card and the phone number to which the
        personalized codes for approving the aforementioned transactions are
        sent, within the framework of increased security protocols. Appropriate
        actions by banks upon diagnosing illicit banking transactions that may
        be fraudulent. Relevant criteria for consideration. The evidence did not
        indicate negligent and thus tortious behavior from all defendants. The
        claim is dismissed.  


        **Facts:** In the present claim, upon due assessment of its content, the
        plaintiff states that he has a mobile phone subscription with the first
        defendant, a mobile phone company. On October 26, 2020, in the morning,
        he realized that his mobile phone was offline, and by noon, he received
        email notifications from Bank .......... and ............ (whose third
        and fourth defendants are de facto universal successors, respectively),
        with which he holds an account, regarding transactions he had made. From
        phone calls from his home phone to Bank .............. and ............
        Bank, he was informed that on the same day, in a very short period, four
        money transfers had been made from the account he maintains at Bank
        .............., specifically, an amount of €15,000 was transferred to
        the account mentioned in the claim document under the name ...........,
        at ........ an amount of €15,000 was transferred to the account
        mentioned in the claim document under the name ......... at ...........
        Bank, an amount of €15,000 was transferred to the plaintiff's account
        with his daughter as a co-holder at ......... Bank, and an amount of
        €6,700 was transferred from another of his accounts to the account from
        which the transfer to the aforementioned accounts of €45,000 was made.
        Additionally, from the plaintiff's account with his daughter as a
        co-holder at .......... Bank, an amount of €9,999 was transferred to an
        account under the name of .... . He attempted to log into the online
        banking service of Bank ......... from his home computer, but found that
        the service was locked, while regarding the corresponding service of
        ........... Bank, he requested alongside his daughter to 'lock' it. In a
        phone call with the call center of Bank ............, he was informed
        about the locking of his electronic account in the online banking
        service and was told to dispute the transactions, which he did
        immediately through ... banking, while his daughter communicated about
        this with ....... Bank. The transfer to the account with the beneficiary
        was canceled, and the amount of €15,000 was returned to the plaintiff.
        After his investigation, he discovered that an unknown individual
        appeared at the branch of the first defendant, served by the second
        defendant, who posed as the plaintiff and presented a forged military ID
        card of the plaintiff, requesting and receiving a new sim card,
        resulting in the deactivation of the plaintiff's sim card and gaining
        access to the codes sent to him by the banks for completing the
        transfers. Due to the negligence of the second defendant, he did not
        realize that the identity used was forged, as since 2010, when the
        plaintiff retired, he has had a police identification card. The first
        defendant does not have security protocols to prevent such incidents,
        which constitute the sim .... method, despite the issuance of a press
        release from the Attica Security and numerous publications regarding the
        aforementioned method, unlike other mobile phone companies, which
        implement a specific procedure for changing sim cards. The second
        defendant did not take the obvious step to check the functioning of the
        sim card before replacing it, where he would have realized that the
        plaintiff's mobile phone was functioning normally. Bank .......... and
        ........... Bank: a) accepted requests for transferring large amounts of
        money from accounts that had no similar activity in the past, while the
        plaintiff's online banking account with the above banks was locked quite
        some time later, b) sent email notifications regarding successful
        transactions in succession, under a single email, c) did not check the
        address ... of the perpetrators, which was different from that used by
        the plaintiff, and d) did not take necessary security measures to
        prevent fraud via sim ... against the plaintiff, as the security code
        (pin) sent by the banks via message to the mobile phone proved to be
        compromised. As a result of the above illegal and culpable behavior of
        the defendants, the plaintiff suffered property damage amounting to a
        total of €24,999, which constitutes the total amount of the transfers
        made by third unknown persons to accounts of unknown individuals, as
        stated above, and has not been refunded despite his repeated inquiries,
        while he also suffered distress and mental anguish, and his trust in the
        banks was shaken, thus entitling him to monetary compensation for his
        moral damage, amounting to €5,000.
      - >-
        Any processing of personal data in the context of the activities of an
        establishment of a controller or a processor in the Union should be
        carried out in accordance with this Regulation, regardless of whether
        the processing itself takes place within the Union. Establishment
        implies the effective and real exercise of activity through stable
        arrangements. The legal form of such arrangements, whether through a
        branch or a subsidiary with a legal personality, is not the determining
        factor in that respect. 4.5.2016 L 119/4 Official Journal of the
        European Union EN
  - source_sentence: On what date did the defendant file the motion?
    sentences:
      - >-
        In order to enhance compliance with this Regulation where processing
        operations are likely to result in a high risk to the rights and
        freedoms of natural persons, the controller should be responsible for
        the carrying-out of a data protection impact assessment to evaluate, in
        particular, the origin, nature, particularity and severity of that risk.
        The outcome of the assessment should be taken into account when
        determining the appropriate measures to be taken in order to demonstrate
        that the processing of personal data complies with this Regulation.
        Where a data-protection impact assessment indicates that processing
        operations involve a high risk which the controller cannot mitigate by
        appropriate measures in terms of available technology and costs of
        implementation, a consultation of the supervisory authority should take
        place prior to the processing.
      - >-
        Court (Civil/Criminal): Criminal  

        Provisions: Article 42 paragraphs 1, 2, 3, and 7 of Law 4557/2018  

        Time of commission of the act:  

        Outcome (not guilty, guilty):  

        Reasoning: Obligation of the payment service provider, such as banks, to
        inform their contracting customer after receiving a relevant order for a
        payment to be made on their behalf. Content of the above notification at
        the stage of receiving the payment order and during its execution. Terms
        of liability for the provider regarding compensation for non-execution,
        erroneous, or delayed execution of payment transactions. In particular,
        in the case of an unauthorized or erroneous payment, the user is
        required to notify the provider within a specified timeframe as soon as
        they become aware of the corresponding transaction. The provisions of
        Law 4357/2018 establish mandatory legal regulations in favor of users of
        payment services and cannot be contractually modified to their
        detriment, but only to their benefit. Defenses available to payment
        service providers to relieve them of liability. Burden of proof
        distribution between the parties. This responsibility of banks may also
        stem from Law 2251/1994, as they provide services to the public and are
        considered suppliers. Conditions for supplier liability under the
        aforementioned legislation. Distribution of the burden of proof between
        the litigants to demonstrate liability for compensation under Law
        2251/1994. Terms of concurrency between contractual and tort liability
        for compensation. The court partially accepts the lawsuit.  

        Facts: On 01/09/2021, an unknown perpetrator sent an email to her from
        the electronic address “...............”, in which they stated that for
        security reasons she needed to confirm her account with the bank .......
        Not realizing that it was a scam, she followed the attached hyperlink,
        entered her personal information, resulting in an unknown perpetrator
        intercepting her online banking credentials and making a transfer
        totaling 7,000.00 euros to account number ................ of the bank
        .........  

        C) The beneficiary of the aforementioned account is ......... born on
        16/05/1995 in the Municipality of ........., residing at ..............,
        with ID number .................... issued on 02/10/2009 by T.A
        .............. and tax number ............. from the tax office
        ...................  

        D) The criminal proceeds reportedly arising from the above criminal
        activity amount to a total of seven thousand euros (7,000.00€).
        Following the above, serious suspicions arise that the aforementioned
        criminal proceeds transferred to the aforementioned bank account were
        unlawfully appropriated by her and subsequently mixed with other legally
        held assets, which she used in her overall economic activities, aiming
        to launder them, thus concealing their true origin and making it
        impossible for them to be seized. Therefore, there are reasonable
        suspicions that the aforementioned individual committed not only the
        primary offense but also the criminal act of “Money Laundering” (Article
        2 §1 a, d of Law 4557/2018, in conjunction with Article 4 subparagraph z
        of the same law as it stands, as well as Article 39 paragraph 1
        subparagraphs a & c of the same Law 4557/2018). Because there are
        serious suspicions that the bank account numbered .......... maintained
        at the bank ....................., whose beneficiary is ..... (Tax ID
        ....................), contains part of the monetary amount from the
        aforementioned criminal activity that was placed behind banking secrecy
        to conceal its true origin and ultimately to launder it. Because, in
        this case, part of the criminal proceeds has been found while the
        remainder has not been found in its entirety, there is a lawful reason
        and an urgent case for prohibiting the sale or any other transfer of the
        following assets, given that they are subject to seizure and forfeiture
        according to Articles 40 and 42 of Law 4557/2018 as they currently
        stand.
      - >-
        1.The data protection officer shall have at least the following tasks:
        (a)  to inform and advise the controller or the processor and the
        employees who carry out processing of their obligations pursuant to this
        Regulation and to other Union or Member State data protection
        provisions; (b)  to monitor compliance with this Regulation, with other
        Union or Member State data protection provisions and with the policies
        of the controller or processor in relation to the protection of personal
        data, including the assignment of responsibilities, awareness-raising
        and training of staff involved in processing operations, and the related
        audits; (c)  to provide advice where requested as regards the data
        protection impact assessment and monitor its performance pursuant to
        Article 35; (d)  to cooperate with the supervisory authority; (e)  to
        act as the contact point for the supervisory authority on issues
        relating to processing, including the prior consultation referred to in
        Article 36, and to consult, where appropriate, with regard to any other
        matter.

        2.The data protection officer shall in the performance of his or her
        tasks have due regard to the risk associated with processing operations,
        taking into account the nature, scope, context and purposes of
        processing. Section 5 Codes of conduct and certification
  - source_sentence: >-
      What should the processing of personal data by public authorities comply
      with?
    sentences:
      - >-
        **Court (Civil/Criminal): Civil**


        **Provisions:**


        **Time of commission of the act:**


        **Outcome (not guilty, guilty):**


        **Rationale:**


        **Facts:**

        The plaintiff holds credit card number ............ with the defendant
        banking corporation. Based on the application for alternative networks
        dated 19/7/2015 with number ......... submitted at a branch of the
        defendant, he was granted access to the electronic banking service
        (e-banking) to conduct banking transactions (debit, credit, updates,
        payments) remotely. On 30/11/2020, the plaintiff fell victim to
        electronic fraud through the "phishing" method, whereby an unknown
        perpetrator managed to withdraw a total amount of €3,121.75 from the
        aforementioned credit card. Specifically, the plaintiff received an
        email at 1:35 PM on 29/11/2020 from sender ...... with address ........,
        informing him that due to an impending system change, he needed to
        verify the mobile phone number linked to the credit card, urging him to
        complete the verification process within the next 24 hours by following
        a link titled ........; otherwise, his account would be locked for
        security reasons. The plaintiff read this email on the afternoon of 30
        November 2020 and, believing it was from the defendant, followed the
        instructions and proceeded via the provided link to a website that was
        identical (a clone) to that of the defendant. On this page, he was asked
        to enter the six-digit security code (.........) that had just been sent
        to his mobile phone by the defendant at 3:41 PM, with the note that it
        was an activation code for his ........ card at ........., which he
        entered.


        Subsequently, the plaintiff received, according to his statements, a new
        email (not submitted), which requested him to enter the details of the
        aforementioned credit card, specifically the name of the cardholder and
        the card number, not the PIN, which he also entered, convinced that he
        was within the online environment of the defendant. Then, at 3:47 PM, he
        received a message on his mobile phone from the defendant containing the
        exact same content as the one he received at 3:41 PM, while at 3:50 PM
        he received a message stating that the activation of his ......... card
        at ....... had been completed. Once the plaintiff read this, he became
        concerned that something was not right, and immediately called (at 4:41
        PM) the defendant's call center to inform them. There, the employees,
        with whom he finally connected at 5:04 PM due to high call center
        volume, advised him to delete the relevant emails, cancel his credit
        card, change his access passwords for the service, and submit a dispute
        request regarding the conducted transactions. The plaintiff
        electronically sent this request to the defendant, disputing the
        detailed transactions amounting to €3,121.75, which were conducted on
        30/11/2020 during the time frame of 16:37:45-16:43:34 PM, arguing that
        he had neither performed them himself nor authorized anyone else to do
        so. The plaintiff specifically disputed the following transactions, as
        evidenced by the account activity of the disputed credit card during the
        aforementioned timeframe: a) transaction number ......... amounting to
        €150.62 conducted on 30/11/2020 at 4:43:34 PM, b) transaction number
        ........ amounting to €293.20 conducted on 30/11/2020 at 4:42:40 PM, c)
        transaction number ............ amounting to €295.21 conducted on
        30/11/2020 at 4:42:10 PM, d) transaction number .......... amounting to
        €299.22 conducted on 30/11/2020 at 4:41:31 PM, e) transaction number
        ........ amounting to €297.21 conducted on 30/11/2020 at 4:41:01 PM, f)
        transaction number ........ amounting to €299.22 conducted on 30/11/2020
        at 4:40:27 PM, g) transaction number ....... amounting to €299.22
        conducted on 30/11/2020 at 4:39:55 PM, h) transaction number ......
        amounting to €299.22 conducted on 30/11/2020 at 4:39:22 PM, i)
        transaction number ......... amounting to €297.22 conducted on
        30/11/2020 at 4:38:52 PM, j) transaction number ......... amounting to
        €295.21 conducted on 30/11/2020 at 4:38:17 PM, and k) transaction number
        ......... amounting to €296.21 conducted on 30/11/2020 at 4:37:45 PM. In
        its response letter dated 21/12/2020, the defendant denied
        responsibility for the costs of the aforementioned transactions, placing
        the entire blame on the plaintiff for the leak of his card details and
        security code to the fraudulent page. The plaintiff, completely denying
        any fault for the conducted transactions, repeatedly contacted the
        defendant, both by phone and via email (see emails dated 15/1/2021 and
        11/2/2021), while on 2/3/2021, he electronically sent a report dated
        1/03/2021 to the Consumer Advocate’s email address, recounting the
        events and requesting that the aforementioned Independent Authority
        intervene to have the disputed debt canceled. In its letter with
        reference number ...../27.04.2021, the aforementioned Independent
        Authority informed the plaintiff that the case was outside its mediating
        role and was therefore archived. Subsequently, the plaintiff sent the
        defendant on 5/3/2021 his extrajudicial statement dated 4/3/2021,
        calling upon it to fully cancel the debt of €3,121.75 that had been
        unjustly incurred against him within two days and to immediately
        instruct the representatives of the collection agency working with it to
        cease contacting him regarding the disputed case. The defendant sent the
        plaintiff a message on his mobile phone on 20/04/2021 informing him that
        his case was still being processed due to lengthy operational
        requirements, while on 23/04/2021, via email, it informed him that
        considering their good cooperation and his efforts to keep them updated,
        it had reviewed his case and decided to refund him the amounts of the
        transactions that were conducted after his contact with their
        representatives on 30/11/2020 at 4:41 PM, totaling €1,038.25,
        specifically the following: a) transaction of €150.62 conducted on
        30/11/2020 at 4:43 PM, b) transaction of €295.21 conducted on 30/11/2020
        at 4:42 PM, c) transaction of €293.20 conducted on 30/11/2020 at 4:42
        PM, and d) transaction of €299.22 conducted on 30/11/2020 at 4:41 PM.
        Beyond this, the defendant refused to refund the plaintiff the amount of
        the remaining transactions conducted on 30/11/2020, totaling €2,376.08
        (and not €2,376.48 as incorrectly stated by the plaintiff in his
        lawsuit), which the plaintiff ultimately fully paid, transferring
        €2,342.77 to the defendant on 7/06/2021 and €33.31 on 15/06/2021 (see
        related deposit receipts).
      - >-
        1.Where a type of processing in particular using new technologies, and
        taking into account the nature, scope, context and purposes of the
        processing, is likely to result in a high risk to the rights and
        freedoms of natural persons, the controller shall, prior to the
        processing, carry out an assessment of the impact of the envisaged
        processing operations on the protection of personal data. A single
        assessment may address a set of similar processing operations that
        present similar high risks.

        2.The controller shall seek the advice of the data protection officer,
        where designated, when carrying out a data protection impact assessment.

        3.A data protection impact assessment referred to in paragraph 1 shall
        in particular be required in the case of: (a)  a systematic and
        extensive evaluation of personal aspects relating to natural persons
        which is based on automated processing, including profiling, and on
        which decisions are based that produce legal effects concerning the
        natural person or similarly significantly affect the natural person;
        (b)  processing on a large scale of special categories of data referred
        to in Article 9(1), or of personal data relating to criminal convictions
        and offences referred to in Article 10; or (c)  a systematic monitoring
        of a publicly accessible area on a large scale.

        4.The supervisory authority shall establish and make public a list of
        the kind of processing operations which are subject to the requirement
        for a data protection impact assessment pursuant to paragraph 1. The
        supervisory authority shall communicate those lists to the Board
        referred to in Article 68

        5.The supervisory authority may also establish and make public a list of
        the kind of processing operations for which no data protection impact
        assessment is required. The supervisory authority shall communicate
        those lists to the Board.

        6.Prior to the adoption of the lists referred to in paragraphs 4 and 5,
        the competent supervisory authority shall apply the consistency
        mechanism referred to in Article 63 where such lists involve processing
        activities which are related to the offering of goods or services to
        data subjects or to the monitoring of their behaviour in several Member
        States, or may substantially affect the free movement of personal data
        within the Union. 4.5.2016 L 119/53  

        7.The assessment shall contain at least: (a)  a systematic description
        of the envisaged processing operations and the purposes of the
        processing, including, where applicable, the legitimate interest pursued
        by the controller; (b)  an assessment of the necessity and
        proportionality of the processing operations in relation to the
        purposes; (c)  an assessment of the risks to the rights and freedoms of
        data subjects referred to in paragraph 1; and (d)  the measures
        envisaged to address the risks, including safeguards, security measures
        and mechanisms to ensure the protection of personal data and to
        demonstrate compliance with this Regulation taking into account the
        rights and legitimate interests of data subjects and other persons
        concerned.

        8.Compliance with approved codes of conduct referred to in Article 40 by
        the relevant controllers or processors shall be taken into due account
        in assessing the impact of the processing operations performed by such
        controllers or processors, in particular for the purposes of a data
        protection impact assessment.

        9.Where appropriate, the controller shall seek the views of data
        subjects or their representatives on the intended processing, without
        prejudice to the protection of commercial or public interests or the
        security of processing operations.

        10.Where processing pursuant to point (c) or (e) of Article 6(1) has a
        legal basis in Union law or in the law of the Member State to which the
        controller is subject, that law regulates the specific processing
        operation or set of operations in question, and a data protection impact
        assessment has already been carried out as part of a general impact
        assessment in the context of the adoption of that legal basis,
        paragraphs 1 to 7 shall not apply unless Member States deem it to be
        necessary to carry out such an assessment prior to processing
        activities.

        11. Where necessary, the controller shall carry out a review to assess
        if processing is performed in accordance with the data protection impact
        assessment at least when there is a change of the risk represented by
        processing operations.
      - >-
        Public authorities to which personal data are disclosed in accordance
        with a legal obligation for the exercise of their official mission, such
        as tax and customs authorities, financial investigation units,
        independent administrative authorities, or financial market authorities
        responsible for the regulation and supervision of securities markets
        should not be regarded as recipients if they receive personal data which
        are necessary to carry out a particular inquiry in the general interest,
        in accordance with Union or Member State law. The requests for
        disclosure sent by the public authorities should always be in writing,
        reasoned and occasional and should not concern the entirety of a filing
        system or lead to the interconnection of filing systems. The processing
        of personal data by those public authorities should comply with the
        applicable data-protection rules according to the purposes of the
        processing.
  - source_sentence: What are the consequences for unlawful interference with sensitive data?
    sentences:
      - >
        Any person who, in contravention of the provisions of this law or of the
        provisions of lawfully ratified multilateral international conventions
        on the protection of copyright, unlawfully makes a fixation of a work or
        of copies, reproduces them directly or indirectly, temporarily or
        permanently in any form, in whole or in part, translates, adapts, alters
        or transforms them, or distributes them to the public by sale or other
        means, or possesses with the intent of distributing them, rents,
        performs in public, broadcasts by radio or television or any other
        means, communicates to the public works or copies by any means, imports
        copies of a work illegally produced abroad without the consent of the
        author and, in general, exploits works, reproductions or copies being
        the object of copyright or acts against the moral right of the author to
        decide freely on the publication and the presentation of his work to the
        public without additions or deletions, shall be liable to imprisonment
        of no less than a year and to a fine from 2.900-15.000 Euro.

        Without the permission of the performers: fixes their performance;
        directly or indirectly, temporarily or permanently reproduces by any
        means and form, in whole or in part, the fixation of their performance;
        distributes to the public the fixation of their performance or possesses
        them with the purpose of distribution; rents the fixation of their
        performance; broadcasts by radio and television by any means, the live
        performance, unless such broadcasting is rebroadcasting of a legitimate
        broadcasting; communicates to the public the live performance made by
        any means, except radio and television broadcasting; makes available to
        the public, by wire or wireless means, in such a way that members of the
        public may access them from a place and at a time individually chosen by
        them, the fixation of their performance.

        Without the permission of phonogram producers (producers of sound
        recordings): directly or indirectly, temporarily or permanently
        reproduces by any means and form, in whole or in part, their phonograms;
        distributes to the public the above recordings, or possesses them with
        the purpose of distribution; rents the said recordings; makes available
        to the public, by wire or wireless means, in such a way that members of
        the public may access them from a place and at a time individually
        chosen by them, their phonograms; imports the said recordings produced
        abroad without their consent.

        Without the permission of producers of audiovisual works (producers of
        visual or sound and visual recordings): directly or indirectly,
        temporarily or permanently reproduces by any means and form, in whole or
        in part, the original and the copies of their films; distributes to the
        public the above recordings, including the copies thereof, or possesses
        them with the purpose of distribution; rents the said recordings; makes
        available to the public, by wire or wireless means, in such a way that
        members of the public may access them from a place and at a time
        individually chosen by them, the original and the copies of their films;
        imports the said recordings produced abroad without their consent;
        broadcasts by radio or television by any means including satellite
        transmission and cable retransmission, as well as the communication to
        the public.

        Without the permission of radio and television organizations:
        rebroadcasts their broadcasts by any means; presents their broadcasts to
        the public in places accessible to the public against payment of an
        entrance fee; fixes their broadcasts on sound or sound and visual
        recordings, regardless of whether the broadcasts are transmitted by wire
        or by the air, including by cable or satellite; directly or indirectly,
        temporarily or permanently reproduces by any means and form, in whole or
        in part, the fixation of their broadcasts; distributes to the public the
        recordings containing the fixation or their broadcasts; rents the
        recordings containing the fixation of their broadcasts; makes available
        to the public, by wire or wireless means, in such a way that members of
        the public may access them from a place and at a time individually
        chosen by them, the fixation of their broadcasts.

        If the financial gain sought or the damage caused by the perpetration of
        an act listed in paragraphs (1) and (2), above, is particularly great,
        the sanction shall be not less than two years imprisonment and a fine of
        from 2 to 10 million drachmas. If the guilty party has perpetrated any
        of the aforementioned acts by profession or at a commercial scale or if
        the circumstances in connection with the perpetration of the act
        indicate that the guilty party poses a serious threat to the protection
        of copyright or related rights, the sanction shall be imprisonment of up
        to ten (10) years and a fine of from 5 to 10 million drachmas, together
        with the withdrawal of the trading license of the undertaking which has
        served as the vehicle for the act. The act shall be likewise deemed to
        have been perpetrated by way of standard practice if the guilty party
        has on a previous occasion been convicted of a contravention pursuant to
        the provisions of the Article or for a violation of the preceding
        copyright legislation and sentenced to a non-redeemable period of
        imprisonment. Any infringement of copyright and related rights in the
        form of felony is tried by the competent Three-member Court of Appeal
        for Felonies.

        Any person who did not pay the remuneration provided for by Article 18,
        paragraph (3) hereof to a collecting society is punished with the
        sanction of paragraph (1), (2) and (3). The same sentence is imposed on
        the debtor who, after the issuance of the decision of the one-member
        first instance court, does not submit the declaration under the
        provisions of article 18, par. 6, of this law.

        The sanctions specified in paragraph (1), above, shall be applicable
        likewise to any person who: uses or distributes, or possesses with the
        intent to distribute, any system or means whose sole purpose is to
        facilitate the unpermitted removal or neutralization of a technical
        system used to protect a computer program; manufactures or imports or
        distributes, or possesses with intent to distribute, equipment and other
        materials utilizable for the reproduction of a work which do not conform
        to the specifications determined pursuant to Article 59 of this Law;
        manufactures or imports or distributes, or possesses with intent to
        distribute, objects which can thwart the efficacy of the above-mentioned
        specifications, or engages in an act which can have that result;
        reproduces or uses a work without utilizing the equipment or without
        applying the systems specified pursuant to Article 60 of this Law;
        distributes, or possesses with intent to distribute, a phonogram or film
        without the special mark or control label specified pursuant to Article
        61 of this Law.

        Where a sentence of imprisonment is imposed with the option of
        redeemability, the sum payable for the redemption shall be 10 times the
        sum specified as per the case in the Penal Code.

        Where mitigating circumstances exist, the fine imposed shall not be less
        than half of the minimum fine imposable as per the case under this Law.

        Any person who proceeds to authorized temporary or permanent
        reproduction of the database, translation, adaptation, arrangement and
        any other alteration of the database, distribution to the public of the
        database or of copies thereof, communication, display or performance of
        the database to the public, is punished by imprisonment of at least one
        (1) year and a fine of one (1) to five (5) million drachmas.

        Any person who proceeds to extraction and/or re-utilization of the whole
        or of a substantial part of the contents of the database without the
        authorization of the author thereof, is punished by imprisonment of at
        least one (1) year and a fine of one (1) to five (5) million drachmas
        (article 12 of Directive 96/9).

        When the object of the infringement refers to computer software, the
        culpable character of the action, as described in paragraph 1 of article
        65A and under the prerequisites provided there, is raised under the
        condition that the infringer proceeds in the unreserved payment of the
        administrative fee and the infringement concerns a quantity of up to 50
        programs.

        When the object of infringement concerns recordings of sound in which a
        work protected by copyright law has been recorded, the unreserved
        payment of an administrative fee according to the stipulation of par.2
        of article 65A and under the prerequisites provided there, the culpable
        character of the action is raised under the condition that the
        infringement concerns a quantity of up to five hundred (500) illegal
        sound recording carriers.

        The payment of the administrative fee and the raising of the culpable
        character of the action, do not relieve the infringers from the duty of
        buying off the copyright and related rights or from the duty of
        compensating and paying the rest expenses to the holders of these
        rights, according to the provisions of the relevant laws.

        In case of recidivism during the same financial year the administrative
        fee provided for by article 65A doubles.
      - >
        Failure to notify the Authority of file establishment or permit changes
        is punished by up to three years’ imprisonment and a fine of one to five
        million Drachmas.

        Maintaining a file without a permit or violating permit terms is
        punished by at least one year’s imprisonment and a fine of one to five
        million Drachmas.

        Unauthorized file interconnection or without permit is punished by up to
        three years’ imprisonment and a fine of one to five million Drachmas.

        Unlawful interference with personal data is punished by imprisonment and
        a fine; for sensitive data, at least one year’s imprisonment and a fine
        of one to ten million Drachmas.

        Controllers who fail to comply with Authority decisions or violate data
        transfer rules face at least two years’ imprisonment and a fine of one
        to five million Drachmas.

        If acts were committed for unlawful benefit or to cause harm, punishment
        is up to ten years’ imprisonment and a fine of two to ten million
        Drachmas.

        If acts jeopardize democratic governance or national security,
        punishment is confinement in a penitentiary and a fine of five to ten
        million Drachmas.

        Acts committed due to negligence result in at least three months’
        imprisonment and a fine.

        If the Controller is not a natural person, the responsible party is the
        representative or head of the organization with administrative or
        managerial duties.

        Authorized members of the Authority may carry out preliminary
        investigations even without Prosecutor’s order for certain offenses.

        The Authority's President must notify the Public Prosecutor of any
        offenses under investigation, forwarding all relevant evidence.

        Preliminary investigations must conclude within two months of charges,
        and trial must begin within three months of completion.

        Continuation of proceedings is allowed only once and for extremely
        important reasons, with adjournment not exceeding two months.

        Felonies under this law fall under the jurisdiction of the Court of
        Appeal.
      - >-
        1.The competent supervisory authority shall approve binding corporate
        rules in accordance with the consistency mechanism set out in Article
        63, provided that they: (a)  are legally binding and apply to and are
        enforced by every member concerned of the group of undertakings, or
        group of enterprises engaged in a joint economic activity, including
        their employees; 4.5.2016 L 119/62   (b)  expressly confer enforceable
        rights on data subjects with regard to the processing of their personal
        data; and (c)  fulfil the requirements laid down in paragraph 2

        2.The binding corporate rules referred to in paragraph 1 shall specify
        at least: (a)  the structure and contact details of the group of
        undertakings, or group of enterprises engaged in a joint economic
        activity and of each of its members; (b)  the data transfers or set of
        transfers, including the categories of personal data, the type of
        processing and its purposes, the type of data subjects affected and the
        identification of the third country or countries in question; (c)  their
        legally binding nature, both internally and externally; (d)  the
        application of the general data protection principles, in particular
        purpose limitation, data minimisation, limited storage periods, data
        quality, data protection by design and by default, legal basis for
        processing, processing of special categories of personal data, measures
        to ensure data security, and the requirements in respect of onward
        transfers to bodies not bound by the binding corporate rules; (e)  the
        rights of data subjects in regard to processing and the means to
        exercise those rights, including the right not to be subject to
        decisions based solely on automated processing, including profiling in
        accordance with Article 22, the right to lodge a complaint with the
        competent supervisory authority and before the competent courts of the
        Member States in accordance with Article 79, and to obtain redress and,
        where appropriate, compensation for a breach of the binding corporate
        rules; (f)  the acceptance by the controller or processor established on
        the territory of a Member State of liability for any breaches of the
        binding corporate rules by any member concerned not established in the
        Union; the controller or the processor shall be exempt from that
        liability, in whole or in part, only if it proves that that member is
        not responsible for the event giving rise to the damage; (g)  how the
        information on the binding corporate rules, in particular on the
        provisions referred to in points (d), (e) and (f) of this paragraph is
        provided to the data subjects in addition to Articles 13 and 14; (h) 
        the tasks of any data protection officer designated in accordance with
        Article 37 or any other person or entity in charge of the monitoring
        compliance with the binding corporate rules within the group of
        undertakings, or group of enterprises engaged in a joint economic
        activity, as well as monitoring training and complaint-handling; (i) 
        the complaint procedures; (j)  the mechanisms within the group of
        undertakings, or group of enterprises engaged in a joint economic
        activity for ensuring the verification of compliance with the binding
        corporate rules. Such mechanisms shall include data protection audits
        and methods for ensuring corrective actions to protect the rights of the
        data subject. Results of such verification should be communicated to the
        person or entity referred to in point (h) and to the board of the
        controlling undertaking of a group of undertakings, or of the group of
        enterprises engaged in a joint economic activity, and should be
        available upon request to the competent supervisory authority; (k)  the
        mechanisms for reporting and recording changes to the rules and
        reporting those changes to the supervisory authority; (l)  the
        cooperation mechanism with the supervisory authority to ensure
        compliance by any member of the group of undertakings, or group of
        enterprises engaged in a joint economic activity, in particular by
        making available to the supervisory authority the results of
        verifications of the measures referred to in point (j); (m)  the
        mechanisms for reporting to the competent supervisory authority any
        legal requirements to which a member of the group of undertakings, or
        group of enterprises engaged in a joint economic activity is subject in
        a third country which are likely to have a substantial adverse effect on
        the guarantees provided by the binding corporate rules; and (n)  the
        appropriate data protection training to personnel having permanent or
        regular access to personal data. 4.5.2016 L 119/63  

        3.The Commission may specify the format and procedures for the exchange
        of information between controllers, processors and supervisory
        authorities for binding corporate rules within the meaning of this
        Article. Those implementing acts shall be adopted in accordance with the
        examination procedure set out in Article 93(2).
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: ModernBERT Embed base Legal Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.4595959595959596
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5025252525252525
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5202020202020202
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5656565656565656
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4595959595959596
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.44528619528619523
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.4166666666666667
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.36287878787878786
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.09165916350710272
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2306549962850208
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3069127804735972
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4211855701941311
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5076744210018042
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.484268278018278
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5664503864728206
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.4595959595959596
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.49747474747474746
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5151515151515151
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5732323232323232
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4595959595959596
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.44360269360269355
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.4146464646464647
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.3661616161616162
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.0911697609343668
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2289623216756795
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3039527967844468
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.42391112595488795
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5097410896532786
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.48467813051146386
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5636729515882724
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.43434343434343436
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4595959595959596
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4772727272727273
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5303030303030303
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.43434343434343436
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.41329966329966333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.3858585858585859
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.3416666666666667
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08666211766664289
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2099599446222272
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.2767937661015934
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.39114273606113564
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47542048434929435
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4539331810165143
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5311664794885055
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.41414141414141414
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.44696969696969696
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4671717171717172
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5050505050505051
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.41414141414141414
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.398989898989899
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.37727272727272726
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.3340909090909091
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07958141271625109
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.19645395412649433
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.2640705077398205
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.3706613130677149
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.45730976306219634
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.43498777457110793
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.507884562461354
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.3661616161616162
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3888888888888889
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.41414141414141414
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.44191919191919193
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3661616161616162
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.351010101010101
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.32929292929292925
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.2906565656565657
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07054343654955235
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.17865690678889054
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.23753083290232105
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.3325729030102926
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.40277157483949066
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3831329164662498
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.45598855399752575
            name: Cosine Map@100

ModernBERT Embed base Legal Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-m3 on the json dataset. It maps sentences & paragraphs to a 1024-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-m3
  • Maximum Sequence Length: 8192 tokens
  • Output Dimensionality: 1024 dimensions
  • Similarity Function: Cosine Similarity
  • Training Dataset:
    • json
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("IoannisKat1/bge-m3-legal-matryoshka")
# Run inference
sentences = [
    'What are the consequences for unlawful interference with sensitive data?',
    "Failure to notify the Authority of file establishment or permit changes is punished by up to three years’ imprisonment and a fine of one to five million Drachmas.\nMaintaining a file without a permit or violating permit terms is punished by at least one year’s imprisonment and a fine of one to five million Drachmas.\nUnauthorized file interconnection or without permit is punished by up to three years’ imprisonment and a fine of one to five million Drachmas.\nUnlawful interference with personal data is punished by imprisonment and a fine; for sensitive data, at least one year’s imprisonment and a fine of one to ten million Drachmas.\nControllers who fail to comply with Authority decisions or violate data transfer rules face at least two years’ imprisonment and a fine of one to five million Drachmas.\nIf acts were committed for unlawful benefit or to cause harm, punishment is up to ten years’ imprisonment and a fine of two to ten million Drachmas.\nIf acts jeopardize democratic governance or national security, punishment is confinement in a penitentiary and a fine of five to ten million Drachmas.\nActs committed due to negligence result in at least three months’ imprisonment and a fine.\nIf the Controller is not a natural person, the responsible party is the representative or head of the organization with administrative or managerial duties.\nAuthorized members of the Authority may carry out preliminary investigations even without Prosecutor’s order for certain offenses.\nThe Authority's President must notify the Public Prosecutor of any offenses under investigation, forwarding all relevant evidence.\nPreliminary investigations must conclude within two months of charges, and trial must begin within three months of completion.\nContinuation of proceedings is allowed only once and for extremely important reasons, with adjournment not exceeding two months.\nFelonies under this law fall under the jurisdiction of the Court of Appeal.\n",
    'Any person who, in contravention of the provisions of this law or of the provisions of lawfully ratified multilateral international conventions on the protection of copyright, unlawfully makes a fixation of a work or of copies, reproduces them directly or indirectly, temporarily or permanently in any form, in whole or in part, translates, adapts, alters or transforms them, or distributes them to the public by sale or other means, or possesses with the intent of distributing them, rents, performs in public, broadcasts by radio or television or any other means, communicates to the public works or copies by any means, imports copies of a work illegally produced abroad without the consent of the author and, in general, exploits works, reproductions or copies being the object of copyright or acts against the moral right of the author to decide freely on the publication and the presentation of his work to the public without additions or deletions, shall be liable to imprisonment of no less than a year and to a fine from 2.900-15.000 Euro.\nWithout the permission of the performers: fixes their performance; directly or indirectly, temporarily or permanently reproduces by any means and form, in whole or in part, the fixation of their performance; distributes to the public the fixation of their performance or possesses them with the purpose of distribution; rents the fixation of their performance; broadcasts by radio and television by any means, the live performance, unless such broadcasting is rebroadcasting of a legitimate broadcasting; communicates to the public the live performance made by any means, except radio and television broadcasting; makes available to the public, by wire or wireless means, in such a way that members of the public may access them from a place and at a time individually chosen by them, the fixation of their performance.\nWithout the permission of phonogram producers (producers of sound recordings): directly or indirectly, temporarily or permanently reproduces by any means and form, in whole or in part, their phonograms; distributes to the public the above recordings, or possesses them with the purpose of distribution; rents the said recordings; makes available to the public, by wire or wireless means, in such a way that members of the public may access them from a place and at a time individually chosen by them, their phonograms; imports the said recordings produced abroad without their consent.\nWithout the permission of producers of audiovisual works (producers of visual or sound and visual recordings): directly or indirectly, temporarily or permanently reproduces by any means and form, in whole or in part, the original and the copies of their films; distributes to the public the above recordings, including the copies thereof, or possesses them with the purpose of distribution; rents the said recordings; makes available to the public, by wire or wireless means, in such a way that members of the public may access them from a place and at a time individually chosen by them, the original and the copies of their films; imports the said recordings produced abroad without their consent; broadcasts by radio or television by any means including satellite transmission and cable retransmission, as well as the communication to the public.\nWithout the permission of radio and television organizations: rebroadcasts their broadcasts by any means; presents their broadcasts to the public in places accessible to the public against payment of an entrance fee; fixes their broadcasts on sound or sound and visual recordings, regardless of whether the broadcasts are transmitted by wire or by the air, including by cable or satellite; directly or indirectly, temporarily or permanently reproduces by any means and form, in whole or in part, the fixation of their broadcasts; distributes to the public the recordings containing the fixation or their broadcasts; rents the recordings containing the fixation of their broadcasts; makes available to the public, by wire or wireless means, in such a way that members of the public may access them from a place and at a time individually chosen by them, the fixation of their broadcasts.\nIf the financial gain sought or the damage caused by the perpetration of an act listed in paragraphs (1) and (2), above, is particularly great, the sanction shall be not less than two years imprisonment and a fine of from 2 to 10 million drachmas. If the guilty party has perpetrated any of the aforementioned acts by profession or at a commercial scale or if the circumstances in connection with the perpetration of the act indicate that the guilty party poses a serious threat to the protection of copyright or related rights, the sanction shall be imprisonment of up to ten (10) years and a fine of from 5 to 10 million drachmas, together with the withdrawal of the trading license of the undertaking which has served as the vehicle for the act. The act shall be likewise deemed to have been perpetrated by way of standard practice if the guilty party has on a previous occasion been convicted of a contravention pursuant to the provisions of the Article or for a violation of the preceding copyright legislation and sentenced to a non-redeemable period of imprisonment. Any infringement of copyright and related rights in the form of felony is tried by the competent Three-member Court of Appeal for Felonies.\nAny person who did not pay the remuneration provided for by Article 18, paragraph (3) hereof to a collecting society is punished with the sanction of paragraph (1), (2) and (3). The same sentence is imposed on the debtor who, after the issuance of the decision of the one-member first instance court, does not submit the declaration under the provisions of article 18, par. 6, of this law.\nThe sanctions specified in paragraph (1), above, shall be applicable likewise to any person who: uses or distributes, or possesses with the intent to distribute, any system or means whose sole purpose is to facilitate the unpermitted removal or neutralization of a technical system used to protect a computer program; manufactures or imports or distributes, or possesses with intent to distribute, equipment and other materials utilizable for the reproduction of a work which do not conform to the specifications determined pursuant to Article 59 of this Law; manufactures or imports or distributes, or possesses with intent to distribute, objects which can thwart the efficacy of the above-mentioned specifications, or engages in an act which can have that result; reproduces or uses a work without utilizing the equipment or without applying the systems specified pursuant to Article 60 of this Law; distributes, or possesses with intent to distribute, a phonogram or film without the special mark or control label specified pursuant to Article 61 of this Law.\nWhere a sentence of imprisonment is imposed with the option of redeemability, the sum payable for the redemption shall be 10 times the sum specified as per the case in the Penal Code.\nWhere mitigating circumstances exist, the fine imposed shall not be less than half of the minimum fine imposable as per the case under this Law.\nAny person who proceeds to authorized temporary or permanent reproduction of the database, translation, adaptation, arrangement and any other alteration of the database, distribution to the public of the database or of copies thereof, communication, display or performance of the database to the public, is punished by imprisonment of at least one (1) year and a fine of one (1) to five (5) million drachmas.\nAny person who proceeds to extraction and/or re-utilization of the whole or of a substantial part of the contents of the database without the authorization of the author thereof, is punished by imprisonment of at least one (1) year and a fine of one (1) to five (5) million drachmas (article 12 of Directive 96/9).\nWhen the object of the infringement refers to computer software, the culpable character of the action, as described in paragraph 1 of article 65A and under the prerequisites provided there, is raised under the condition that the infringer proceeds in the unreserved payment of the administrative fee and the infringement concerns a quantity of up to 50 programs.\nWhen the object of infringement concerns recordings of sound in which a work protected by copyright law has been recorded, the unreserved payment of an administrative fee according to the stipulation of par.2 of article 65A and under the prerequisites provided there, the culpable character of the action is raised under the condition that the infringement concerns a quantity of up to five hundred (500) illegal sound recording carriers.\nThe payment of the administrative fee and the raising of the culpable character of the action, do not relieve the infringers from the duty of buying off the copyright and related rights or from the duty of compensating and paying the rest expenses to the holders of these rights, according to the provisions of the relevant laws.\nIn case of recidivism during the same financial year the administrative fee provided for by article 65A doubles.\n',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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 0.4596
cosine_accuracy@3 0.5025
cosine_accuracy@5 0.5202
cosine_accuracy@10 0.5657
cosine_precision@1 0.4596
cosine_precision@3 0.4453
cosine_precision@5 0.4167
cosine_precision@10 0.3629
cosine_recall@1 0.0917
cosine_recall@3 0.2307
cosine_recall@5 0.3069
cosine_recall@10 0.4212
cosine_ndcg@10 0.5077
cosine_mrr@10 0.4843
cosine_map@100 0.5665

Information Retrieval

Metric Value
cosine_accuracy@1 0.4596
cosine_accuracy@3 0.4975
cosine_accuracy@5 0.5152
cosine_accuracy@10 0.5732
cosine_precision@1 0.4596
cosine_precision@3 0.4436
cosine_precision@5 0.4146
cosine_precision@10 0.3662
cosine_recall@1 0.0912
cosine_recall@3 0.229
cosine_recall@5 0.304
cosine_recall@10 0.4239
cosine_ndcg@10 0.5097
cosine_mrr@10 0.4847
cosine_map@100 0.5637

Information Retrieval

Metric Value
cosine_accuracy@1 0.4343
cosine_accuracy@3 0.4596
cosine_accuracy@5 0.4773
cosine_accuracy@10 0.5303
cosine_precision@1 0.4343
cosine_precision@3 0.4133
cosine_precision@5 0.3859
cosine_precision@10 0.3417
cosine_recall@1 0.0867
cosine_recall@3 0.21
cosine_recall@5 0.2768
cosine_recall@10 0.3911
cosine_ndcg@10 0.4754
cosine_mrr@10 0.4539
cosine_map@100 0.5312

Information Retrieval

Metric Value
cosine_accuracy@1 0.4141
cosine_accuracy@3 0.447
cosine_accuracy@5 0.4672
cosine_accuracy@10 0.5051
cosine_precision@1 0.4141
cosine_precision@3 0.399
cosine_precision@5 0.3773
cosine_precision@10 0.3341
cosine_recall@1 0.0796
cosine_recall@3 0.1965
cosine_recall@5 0.2641
cosine_recall@10 0.3707
cosine_ndcg@10 0.4573
cosine_mrr@10 0.435
cosine_map@100 0.5079

Information Retrieval

Metric Value
cosine_accuracy@1 0.3662
cosine_accuracy@3 0.3889
cosine_accuracy@5 0.4141
cosine_accuracy@10 0.4419
cosine_precision@1 0.3662
cosine_precision@3 0.351
cosine_precision@5 0.3293
cosine_precision@10 0.2907
cosine_recall@1 0.0705
cosine_recall@3 0.1787
cosine_recall@5 0.2375
cosine_recall@10 0.3326
cosine_ndcg@10 0.4028
cosine_mrr@10 0.3831
cosine_map@100 0.456

Training Details

Training Dataset

json

  • Dataset: json
  • Size: 1,580 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 1000 samples:
    anchor positive
    type string string
    details
    • min: 7 tokens
    • mean: 17.16 tokens
    • max: 39 tokens
    • min: 27 tokens
    • mean: 714.22 tokens
    • max: 2824 tokens
  • Samples:
    anchor positive
    At what time must the controller provide the data subject with the required information? 1.Where personal data relating to a data subject are collected from the data subject, the controller shall, at the time when personal data are obtained, provide the data subject with all of the following information: (a) the identity and the contact details of the controller and, where applicable, of the controller's representative; (b) the contact details of the data protection officer, where applicable; (c) the purposes of the processing for which the personal data are intended as well as the legal basis for the processing; 4.5.2016 L 119/40 (d) where the processing is based on point (f) of Article 6(1), the legitimate interests pursued by the controller or by a third party; (e) the recipients or categories of recipients of the personal data, if any; (f) where applicable, the fact that the controller intends to transfer personal data to a third country or international organisation and the existence or absence of an adequacy decision by the Commission, or in the case of trans...
    What information does the duty of professional secrecy cover during the term of office? 1.Each Member State shall provide by law for all of the following: (a) the establishment of each supervisory authority; 4.5.2016 L 119/66 (b) the qualifications and eligibility conditions required to be appointed as member of each supervisory authority; (c) the rules and procedures for the appointment of the member or members of each supervisory authority; (d) the duration of the term of the member or members of each supervisory authority of no less than four years, except for the first appointment after 24 May 2016, part of which may take place for a shorter period where that is necessary to protect the independence of the supervisory authority by means of a staggered appointment procedure; (e) whether and, if so, for how many terms the member or members of each supervisory authority is eligible for reappointment; (f) the conditions governing the obligations of the member or members and staff of each supervisory authority, prohibitions on actions, occupations and benefits inco...
    Under what circumstances should the controller be allowed to further process personal data? The processing of personal data for purposes other than those for which the personal data were initially collected should be allowed only where the processing is compatible with the purposes for which the personal data were initially collected. In such a case, no legal basis separate from that which allowed the collection of the personal data is required. If the processing is necessary for the performance of a task carried out in the public interest or in the exercise of official authority vested in the controller, Union or Member State law may determine and specify the tasks and purposes for which the further processing should be regarded as compatible and lawful. Further processing for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes should be considered to be compatible lawful processing operations. The legal basis provided by Union or Member State law for the processing of personal data may also provide a legal basis for ...
  • 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: epoch
  • per_device_train_batch_size: 4
  • per_device_eval_batch_size: 4
  • gradient_accumulation_steps: 2
  • learning_rate: 2e-05
  • num_train_epochs: 15
  • 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: 4
  • per_device_eval_batch_size: 4
  • 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: 15
  • 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}
  • tp_size: 0
  • 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: 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
  • 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: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss dim_768_cosine_ndcg@10 dim_512_cosine_ndcg@10 dim_256_cosine_ndcg@10 dim_128_cosine_ndcg@10 dim_64_cosine_ndcg@10
0.0506 10 4.3827 - - - - -
0.1013 20 5.2903 - - - - -
0.1519 30 5.2656 - - - - -
0.2025 40 4.4887 - - - - -
0.2532 50 4.7901 - - - - -
0.3038 60 4.6387 - - - - -
0.3544 70 5.4387 - - - - -
0.4051 80 6.2548 - - - - -
0.4557 90 4.9473 - - - - -
0.5063 100 4.9107 - - - - -
0.5570 110 5.0153 - - - - -
0.6076 120 4.1909 - - - - -
0.6582 130 4.0142 - - - - -
0.7089 140 4.5879 - - - - -
0.7595 150 2.8352 - - - - -
0.8101 160 3.7297 - - - - -
0.8608 170 3.1522 - - - - -
0.9114 180 3.4329 - - - - -
0.9620 190 2.7274 - - - - -
1.0 198 - 0.4858 0.4823 0.4370 0.4147 0.3524
1.0101 200 2.9423 - - - - -
1.0608 210 3.0553 - - - - -
1.1114 220 1.98 - - - - -
1.1620 230 2.2939 - - - - -
1.2127 240 1.4246 - - - - -
1.2633 250 3.4192 - - - - -
1.3139 260 2.1508 - - - - -
1.3646 270 3.2516 - - - - -
1.4152 280 3.213 - - - - -
1.4658 290 2.6625 - - - - -
1.5165 300 1.8449 - - - - -
1.5671 310 3.1901 - - - - -
1.6177 320 1.6783 - - - - -
1.6684 330 3.9872 - - - - -
1.7190 340 3.4367 - - - - -
1.7696 350 3.2959 - - - - -
1.8203 360 2.8447 - - - - -
1.8709 370 3.0028 - - - - -
1.9215 380 2.7218 - - - - -
1.9722 390 2.4789 - - - - -
2.0 396 - 0.5077 0.5097 0.4754 0.4573 0.4028
2.0203 400 2.7682 - - - - -
2.0709 410 2.1641 - - - - -
2.1215 420 1.9279 - - - - -
2.1722 430 0.8415 - - - - -
2.2228 440 2.4362 - - - - -
2.2734 450 1.3782 - - - - -
2.3241 460 1.0464 - - - - -
2.3747 470 3.3324 - - - - -
2.4253 480 1.7592 - - - - -
2.4759 490 1.3254 - - - - -
2.5266 500 0.9768 - - - - -
2.5772 510 3.603 - - - - -
2.6278 520 1.0011 - - - - -
2.6785 530 1.1125 - - - - -
2.7291 540 1.3817 - - - - -
2.7797 550 1.2609 - - - - -
2.8304 560 0.5562 - - - - -
2.8810 570 2.1196 - - - - -
2.9316 580 2.9498 - - - - -
2.9823 590 1.8963 - - - - -
3.0 594 - 0.4875 0.4863 0.4686 0.4493 0.4139
3.0304 600 1.1573 - - - - -
3.0810 610 1.2194 - - - - -
3.1316 620 0.5912 - - - - -
3.1823 630 1.0336 - - - - -
3.2329 640 1.4426 - - - - -
3.2835 650 1.5099 - - - - -
3.3342 660 1.0995 - - - - -
3.3848 670 1.0333 - - - - -
3.4354 680 1.8372 - - - - -
3.4861 690 1.0771 - - - - -
3.5367 700 0.2972 - - - - -
3.5873 710 0.7128 - - - - -
3.6380 720 0.9087 - - - - -
3.6886 730 2.1019 - - - - -
3.7392 740 1.1736 - - - - -
3.7899 750 1.8183 - - - - -
3.8405 760 1.5602 - - - - -
3.8911 770 1.5488 - - - - -
3.9418 780 2.9643 - - - - -
3.9924 790 0.965 - - - - -
4.0 792 - 0.4893 0.4956 0.4825 0.4549 0.4159
-1 -1 - 0.5077 0.5097 0.4754 0.4573 0.4028
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.11.13
  • Sentence Transformers: 4.1.0
  • Transformers: 4.51.3
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.8.1
  • Datasets: 4.0.0
  • Tokenizers: 0.21.2

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}
}