Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,1215 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:46338
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: Alibaba-NLP/gte-modernbert-base
+widget:
+- source_sentence: What are the specific points and subparagraphs mentioned in the
+    context of Article 4(3) that relate to the introductory wording and how do they
+    connect to the provisions outlined in Article 3(1)?
+  sentences:
+  - 51 - Article 2, points 52, 53,54, 55 and 56 - Article 3 - Article 4(1) Article
+    3(1), first subparagraph Article 4(2), first subparagraph Article 4(2), second
+    subparagraph Article 3(1), second subparagraph, introductory wording Article 4(3),
+    first subparagraph, introductory wording Article 3(1), second subparagraph, points
+    (a) and (b) Article 4(3), first subparagraph, points (a) and (b) Article 3(1),
+    second subparagraph, point (c) - Article 3(1), second subparagraph, point (d)
+    Article 4(3), first subparagraph, point (c) Article 3(1), third subparagraph,
+    introductory wording - - Article 4(3), first subparagraph, point (d), introductory
+    wording - Article 4(3), first subparagraph, points (d)(i), (ii) and (iii) Article
+    3(1), third subparagraph, point (a) Article 4(3), first subparagraph, point (d)(iv)
+    - Article 4(3), first subparagraph, point (e), introductory wording Article 3(1),
+    third subparagraph, point (b) Article 4(3), first subparagraph, point (e)(i) Article
+    3(1), third subparagraph, point (c) Article 4(3), first subparagraph, point (e)(ii)
+    Article 3(1), third subparagraph, point (d) Article 4(3), first subparagraph,
+    point (e)(iii) Article 3(1), third subparagraph, point (e) - - Article 4(3), first
+    subparagraph, point (e)(iv) Article 3(2) and (3) - Article 3(4) Article 35(6)
+    Article 3(5) and (6) - - Article 4(4) - Article 4(5) Article 4(6) Article 4(7)
+    - Article 5 Article 5(1), first subparagraph Article 6(1), first subparagraph
+    Article 5(1), second subparagraph Article 6(1), fifth subparagraph - Article 6(1),
+    second and third subparagraph Article 5(1), third subparagraph Article 6(1), fourth
+    subparagraph Article 5(1), fourth and fifth subparagraph - Article 5(2) - Article
+    6(2) Article 6(2), second subparagraph Article 5(3) Article 6(3) Article 5(4)
+    Article 6(4) Article 5(5) Article 6(5) Article 5(5), first subparagraph, point
+    (b) Article 6(5), second subparagraph, point (c) - Article 6(5), second subparagraph,
+    point (b) Article 5(6) Article 6(6) - Article 6(6), second subparagraph, point
+    (a) Article 5(6), second subparagraph Article 6(6), second subparagraph, point
+    (b) Article 5(6), third subparagraph Article 6(6), third subparagraph Article
+    5(7) - Article 6(1), first subparagraph Article 7(1), first
+  - 'ii.
+
+
+    measures to protect against retaliation its own workers who are whistleblowers
+    in accordance with the applicable law transposing Directive (EU) 2019/1937 of
+    the European Parliament and of the Council ( 121 );
+
+
+    (d)
+
+
+    where the undertaking has no policies on the protection of whistle-blowers ( 122
+    ), it shall state this and whether it has plans to implement them and the timetable
+    for implementation;
+
+
+    (e)
+
+
+    beyond the procedures to follow-up on reports by whistleblowers in accordance
+    with the applicable law transposing Directive (EU) 2019/1937, whether the undertaking
+    has procedures to investigate business conduct incidents , including incidents
+    of corruption and bribery , promptly, independently and objectively;
+
+
+    (f)
+
+
+    where applicable, whether the undertaking has in place policies with respect to
+    animal welfare;
+
+
+    (g)
+
+
+    the undertaking’s policy for training within the organisation on business conduct,
+    including target audience, frequency and depth of coverage; and
+
+
+    (h)
+
+
+    the functions within the undertaking that are most at risk in respect of corruption
+    and bribery .
+
+
+    Undertakings that are subject to legal requirements under national law transposing
+    Directive (EU) 2019/1937, or to equivalent legal requirements with regard to the
+    protection of whistle-blowers, may comply with the disclosure specified in paragraph
+    10 (d) by stating that they are subject to those legal requirements.
+
+
+    Disclosure Requirement G1-2 – Management of relationships with suppliers
+
+
+    The undertaking shall provide information about the management of its relationships
+    with its suppliers and its impacts on its supply chain.
+
+
+    The objective of this Disclosure Requirement is to provide an understanding of
+    the undertaking’s management of its procurement process including fair behaviour
+    with suppliers .
+
+
+    The undertaking shall provide a description of its policy to prevent late payments,
+    specifically to SMEs.
+
+
+    The disclosure required under paragraph 12 shall include the following information:
+
+
+    (a)
+
+
+    the undertaking’s approach to its relationships with its suppliers , taking account
+    of risks to the undertaking related to its supply chain and of impacts on sustainability
+    matters ; and
+
+
+    (b)
+
+
+    whether and how it takes into account social and environmental criteria for the
+    selection of its suppliers.
+
+
+    Disclosure Requirement G1-3 – Prevention and detection of corruption and bribery
+
+
+    The undertaking shall provide information about its system to prevent and detect,
+    investigate, and respond to allegations or incidents relating to corruption and
+    bribery including the related training.
+
+
+    The objective of this Disclosure Requirement is to provide transparency on the
+    key procedures of the undertaking to prevent, detect, and address allegations
+    about corruption and bribery . This includes the training provided to own workers
+    and/or information provided internally or to suppliers .
+
+
+    The disclosure required under paragraph 16 shall include the following information:
+
+
+    (a)
+
+
+    a description of the procedures in place to prevent, detect, and address allegations
+    or incidents of corruption and bribery ;
+
+
+    (b)
+
+
+    whether the investigators or investigating committee are separate from the chain
+    of management involved in the matter; and
+
+
+    (c)
+
+
+    the process, if any, to report outcomes to the administrative, management and
+    supervisory bodies .
+
+
+    Where the undertaking has no such procedures in place, it shall disclose this
+    fact and, where applicable, its plans to adopt them.
+
+
+    The disclosures required by paragraph 16 shall include information about how the
+    undertaking communicates its policies to those for whom they are relevant to ensure
+    that the policy is accessible and that they understand its implications.
+
+
+    The disclosure required by paragraph 16 shall include information about the following
+    with respect to training:
+
+
+    (a)
+
+
+    the nature, scope and depth of anti- corruption and anti- bribery training programmes
+    offered or required by the undertaking;
+
+
+    (b)
+
+
+    the percentage of functions-at-risk covered by training programmes; and
+
+
+    (c)
+
+
+    the extent to which training is given to members of the administrative, management
+    and supervisory bodies.
+
+
+    Metrics and targets
+
+
+    Disclosure Requirement G1-4 – Incidents of corruption or bribery
+
+
+    The undertaking shall provide information on incidents of corruption or bribery
+    during the reporting period.'
+  - '(39)
+
+
+    ‘algorithmic trading’ means trading in financial instruments where a computer
+    algorithm automatically determines individual parameters of orders such as whether
+    to initiate the order, the timing, price or quantity of the order or how to manage
+    the order after its submission, with limited or no human intervention, and does
+    not include any system that is only used for the purpose of routing orders to
+    one or more trading venues or for the processing of orders involving no determination
+    of any trading parameters or for the confirmation of orders or the post-trade
+    processing of executed transactions;
+
+
+    (40)
+
+
+    ‘high-frequency algorithmic trading technique’ means an algorithmic trading technique
+    characterised by:
+
+
+    (a)'
+- source_sentence: What action does the Commission take if the scheme owner fails
+    to address the deficiencies and the scheme no longer meets the criteria in Annex
+    IV?
+  sentences:
+  - '2.
+
+
+    Implementing partners shall fill out the Scoreboard for their proposals for financing
+    and investment operations.
+
+
+    3.
+
+
+    The Scoreboard shall cover the following elements:
+
+
+    (a)
+
+
+    a description of the proposed financing or investment operation;
+
+
+    (b)
+
+
+    how the proposed financing or investment operation contributes to EU policy objectives;
+
+
+    (c)
+
+
+    a description of additionality;
+
+
+    (d)
+
+
+    a description of the market failure or suboptimal investment situation;
+
+
+    (e)
+
+
+    the financial and technical contribution by the implementing partner;
+
+
+    (f)
+
+
+    the impact of the investment;
+
+
+    (g)
+
+
+    the financial profile of the financing or investment operation;
+
+
+    (h)
+
+
+    complementary indicators.
+
+
+    4.
+
+
+    The Commission is empowered to adopt delegated acts in accordance with Article
+    34 in order to supplement this Regulation by establishing additional elements
+    of the Scoreboard, including detailed rules for the Scoreboard to be used by the
+    implementing partners.
+
+
+    Article 23
+
+
+    Policy check
+
+
+    1.
+
+
+    The Commission shall conduct a check to confirm that the financing and investment
+    operations proposed by the implementing partners other than the EIB comply with
+    Union law and policies.
+
+
+    2.
+
+
+    EIB financing and investment operations that fall within the scope of this Regulation
+    shall not be covered by the EU guarantee where the Commission delivers an unfavourable
+    opinion within the framework of the procedure provided for in Article 19 of the
+    EIB Statute.
+
+
+    ▼M1
+
+
+    3.
+
+
+    In the context of the procedures referred to in paragraphs 1 and 2 of this Article,
+    the Commission shall take into account any Sovereignty Seal awarded in accordance
+    with Article 4 of Regulation (EU) 2024/795 to a project.
+
+
+    ▼B
+
+
+    Article 24
+
+
+    Investment Committee
+
+
+    1.
+
+
+    A fully independent investment committee shall be established for the InvestEU
+    Fund (the ‘Investment Committee’). The Investment Committee shall:
+
+
+    (a)
+
+
+    examine the proposals for financing and investment operations submitted by implementing
+    partners for coverage under the EU guarantee that have passed the policy check
+    referred to in Article 23(1) of this Regulation or that have received a favourable
+    opinion within the framework of the procedure provided for in Article 19 of the
+    EIB Statute;
+
+
+    (b)'
+  - (6) |  The maritime transport sector is subject to strong international competition.
+    Major differences in regulatory burdens across flag states have often led to unwanted
+    practices such as the reflagging of ships. The sector’s intrinsic global character
+    underlines the importance of a flag-neutral approach and of a favourable regulatory
+    environment, which would help to attract new investment and safeguard the competitiveness
+    of Union ports, shipowners and ship operators.
+  - '8.
+
+
+    Where the scheme owner fails or refuses to take the necessary remedial action
+    and where the Commission has determined that the deficiencies referred to in paragraph
+    6 of this Article mean that the scheme no longer fulfils the criteria laid down
+    in Annex IV, or of the recognised subset of those criteria, the Commission shall
+    withdraw the recognition of the scheme by means of implementing acts. Those implementing
+    acts shall be adopted in accordance with the examination procedure referred to
+    in Article 39(3).
+
+
+    9.'
+- source_sentence: What roles do upstream and downstream business partners play in
+    the overall production and distribution process as described?
+  sentences:
+  - (25) The chain of activities should cover activities of a company’s upstream business
+    partners related to the production of goods or the provision of services by the
+    company, including the design, extraction, sourcing, manufacture, transport, storage
+    and supply of raw materials, products or parts of the products and development
+    of the product or the service, and activities of a company’s downstream business
+    partners related to the distribution, transport and storage of the product, where
+    the business partners carry out those activities for the company or on behalf
+    of the company. This Directive should not cover the disposal of the product. In
+    addition, under this Directive the chain of activities should not encompass the
+    distribution,
+  - '7.
+
+
+    Any actor in the supply chain who is required to prepare a chemical safety report
+    according to Articles 14 or 37 shall place the relevant exposure scenarios (including
+    use and exposure categories where appropriate) in an annex to the safety data
+    sheet covering identified uses and including specific conditions resulting from
+    the application of Section 3 of Annex XI.
+
+
+    Any downstream user shall include relevant exposure scenarios, and use other relevant
+    information, from the safety data sheet supplied to him when compiling his own
+    safety data sheet for identified uses.'
+  - '8.
+
+
+    Authorisations shall be subject to a time-limited review without prejudice to
+    any decision on a future review period and shall normally be subject to conditions,
+    including monitoring. The duration of the time-limited review for any authorisation
+    shall be determined on a case-by-case basis taking into account all relevant information
+    including the elements listed in paragraph 4(a) to (d), as appropriate.
+
+
+    9.
+
+
+    The authorisation shall specify:
+
+
+    (a)
+
+
+    the person(s) to whom the authorisation is granted;
+
+
+    (b)
+
+
+    the identity of the substance(s);
+
+
+    (c)
+
+
+    the use(s) for which the authorisation is granted;
+
+
+    (d)
+
+
+    any conditions under which the authorisation is granted;
+
+
+    (e)
+
+
+    the time-limited review period;
+
+
+    (f)
+
+
+    any monitoring arrangement.
+
+
+    10.'
+- source_sentence: What conditions must be met for the stability study in organic
+    solvents to be deemed unnecessary for a substance?
+  sentences:
+  - 'AR 23. When disclosing information required under paragraph 29 for the purpose
+    of setting targets the undertaking shall consider the need for an informed and
+    willing consent of local and indigenous peoples , the need for appropriate consultations
+    and the need to respect the decisions of these communities.
+
+
+    AR 24. The targets related to material impacts may be presented in a table as
+    illustrated below:
+
+
+    Type of target according to mitigation hierarchy Baseline value and base year
+    Target value and geographical scope Connected policy or legislation if relevant
+    2025 2030 Up to 2050 Avoidance Minimisation Rehabilitation and restoration Compensation
+    or offsets'
+  - '1.
+
+
+    Member States shall, in accordance with paragraph 2, draw up a register of producers,
+    including producers supplying EEE by means of distance communication. That register
+    shall serve to monitor compliance with the requirements of this Directive.
+
+
+    Producers supplying EEE by means of distance communication as defined in Article
+    3(1)(f)(iv) shall be registered in the Member State that they sell to. Where such
+    producers are not registered in the Member State that they are selling to, they
+    shall be registered through their authorised representatives as referred to in
+    Article 17(2).
+
+
+    2.
+
+
+    Member States shall ensure that:
+
+
+    (a)
+
+
+    each producer, or each authorised representative where appointed under Article
+    17, is registered as required and has the possibility of entering online in their
+    national register all relevant information reflecting that producer’s activities
+    in that Member State;
+
+
+    (b)
+
+
+    upon registering, each producer, or each authorised representative where appointed
+    under Article 17, provides the information set out in Annex X, Part A, undertaking
+    to update it as appropriate;
+
+
+    (c)
+
+
+    each producer, or each authorised representative where appointed under Article
+    17, provides the information set out in Annex X, Part B;
+
+
+    (d)
+
+
+    national registers provide links to other national registers on their website
+    to facilitate, in all Member States, registration of producers or, where appointed
+    under Article 17, authorised representatives.
+
+
+    3.
+
+
+    In order to ensure uniform conditions for the implementation of this Article,
+    the Commission shall adopt implementing acts establishing the format for registration
+    and reporting and the frequency of reporting to the register. Those implementing
+    acts shall be adopted in accordance with the examination procedure referred to
+    in Article 21(2).
+
+
+    4.
+
+
+    Member States shall collect information, including substantiated estimates, on
+    an annual basis, on the quantities and categories of EEE placed on their markets,
+    collected through all routes, prepared for re-use, recycled and recovered within
+    the Member State, and on separately collected WEEE exported, by weight.
+
+
+    ▼M1 —————
+
+
+    ▼M1
+
+
+    6.'
+  - 'COLUMN 1 STANDARD INFORMATION REQUIRED COLUMN 2 SPECIFIC RULES FOR ADAPTATION
+    FROM COLUMN 1 7.15. Stability in organic solvents and identity of relevant degradation
+    products Only required if stability of the substance is considered to be critical.
+    7.15. The study does not need to be conducted if the substance is inorganic. 7.16.
+    Dissociation constant 7.16. The study does not need to be conducted if: — the
+    substance is hydrolytically unstable (half-life less than 12 hours) or is readily
+    oxidisable in water, or ►M70 ◄ ►M64 — or based on the structure, the substance
+    does not have any chemical group that can dissociate. ◄ 7.17. Viscosity ►M64 For
+    hydrocarbon substances the kinematic viscosity shall be determined at 40 °C. ◄'
+- source_sentence: How is 'associated undertaking' defined, and what criteria determine
+    the significant influence of one undertaking over another in terms of voting rights?
+  sentences:
+  - '▼B
+
+
+    (6)
+
+
+    ‘purchase price’ means the price payable and any incidental expenses minus any
+    incidental reductions in the cost of acquisition;
+
+
+    (7)
+
+
+    ‘production cost’ means the purchase price of raw materials, consumables and other
+    costs directly attributable to the item in question. Member States shall permit
+    or require the inclusion of a reasonable proportion of fixed or variable overhead
+    costs indirectly attributable to the item in question, to the extent that they
+    relate to the period of production. Distribution costs shall not be included;
+
+
+    (8)
+
+
+    ‘value adjustment’ means the adjustments intended to take account of changes in
+    the values of individual assets established at the balance sheet date, whether
+    the change is final or not;
+
+
+    (9)
+
+
+    ‘parent undertaking’ means an undertaking which controls one or more subsidiary
+    undertakings;
+
+
+    (10)
+
+
+    ‘subsidiary undertaking’ means an undertaking controlled by a parent undertaking,
+    including any subsidiary undertaking of an ultimate parent undertaking;
+
+
+    (11)
+
+
+    ‘group’ means a parent undertaking and all its subsidiary undertakings;
+
+
+    (12)
+
+
+    ‘affiliated undertakings’ means any two or more undertakings within a group;
+
+
+    (13)
+
+
+    ‘associated undertaking’ means an undertaking in which another undertaking has
+    a participating interest, and over whose operating and financial policies that
+    other undertaking exercises significant influence. An undertaking is presumed
+    to exercise a significant influence over another undertaking where it has 20 %
+    or more of the shareholders'' or members'' voting rights in that other undertaking;
+
+
+    (14)
+
+
+    ‘investment undertakings’ means:
+
+
+    (a)
+
+
+    undertakings the sole object of which is to invest their funds in various securities,
+    real property and other assets, with the sole aim of spreading investment risks
+    and giving their shareholders the benefit of the results of the management of
+    their assets,
+
+
+    (b)
+
+
+    undertakings associated with investment undertakings with fixed capital, if the
+    sole object of those associated undertakings is to acquire fully paid shares issued
+    by those investment undertakings without prejudice to point (h) of Article 22(1)
+    of Directive 2012/30/EU;
+
+
+    (15)'
+  - and non-European non-financial corporations not subject to the disclosure obligations
+    laid down in Directive 2013/34/EU. That information may be disclosed only once,
+    based on counterparties’ turnover alignment for the general-purpose lending loans,
+    as in the case of the GAR. The first disclosure reference date of this template
+    is as of 31 December 2024. Institutions are not required to disclose this information
+    before 1 January 2025. ---|---|---
+  - 'ANNEX II
+
+
+    Due diligence statement
+
+
+    Information to be contained in the due diligence statement in accordance with
+    Article 4(2):
+
+
+    1.
+
+
+    Operator’s name, address and, in the event of relevant commodities and relevant
+    products entering or leaving the market, the Economic Operators Registration and
+    Identification (EORI) number in accordance with Article 9 of Regulation (EU) No
+    952/2013.
+
+
+    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: SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6910063870188158
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9109269808389435
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9461418953909891
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9742793026065941
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6910063870188158
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30364232694631454
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18922837907819778
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09742793026065939
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6910063870188158
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9109269808389435
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9461418953909891
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9742793026065941
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8471731447814336
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.804833419644399
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8061197699360279
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision bc02f0a92d1b6dd82108036f6cb4b7b423fb7434 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "How is 'associated undertaking' defined, and what criteria determine the significant influence of one undertaking over another in terms of voting rights?",
+    "▼B\n\n(6)\n\n‘purchase price’ means the price payable and any incidental expenses minus any incidental reductions in the cost of acquisition;\n\n(7)\n\n‘production cost’ means the purchase price of raw materials, consumables and other costs directly attributable to the item in question. Member States shall permit or require the inclusion of a reasonable proportion of fixed or variable overhead costs indirectly attributable to the item in question, to the extent that they relate to the period of production. Distribution costs shall not be included;\n\n(8)\n\n‘value adjustment’ means the adjustments intended to take account of changes in the values of individual assets established at the balance sheet date, whether the change is final or not;\n\n(9)\n\n‘parent undertaking’ means an undertaking which controls one or more subsidiary undertakings;\n\n(10)\n\n‘subsidiary undertaking’ means an undertaking controlled by a parent undertaking, including any subsidiary undertaking of an ultimate parent undertaking;\n\n(11)\n\n‘group’ means a parent undertaking and all its subsidiary undertakings;\n\n(12)\n\n‘affiliated undertakings’ means any two or more undertakings within a group;\n\n(13)\n\n‘associated undertaking’ means an undertaking in which another undertaking has a participating interest, and over whose operating and financial policies that other undertaking exercises significant influence. An undertaking is presumed to exercise a significant influence over another undertaking where it has 20 % or more of the shareholders' or members' voting rights in that other undertaking;\n\n(14)\n\n‘investment undertakings’ means:\n\n(a)\n\nundertakings the sole object of which is to invest their funds in various securities, real property and other assets, with the sole aim of spreading investment risks and giving their shareholders the benefit of the results of the management of their assets,\n\n(b)\n\nundertakings associated with investment undertakings with fixed capital, if the sole object of those associated undertakings is to acquire fully paid shares issued by those investment undertakings without prejudice to point (h) of Article 22(1) of Directive 2012/30/EU;\n\n(15)",
+    'and non-European non-financial corporations not subject to the disclosure obligations laid down in Directive 2013/34/EU. That information may be disclosed only once, based on counterparties’ turnover alignment for the general-purpose lending loans, as in the case of the GAR. The first disclosure reference date of this template is as of 31 December 2024. Institutions are not required to disclose this information before 1 January 2025. ---|---|---',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.691      |
+| cosine_accuracy@3   | 0.9109     |
+| cosine_accuracy@5   | 0.9461     |
+| cosine_accuracy@10  | 0.9743     |
+| cosine_precision@1  | 0.691      |
+| cosine_precision@3  | 0.3036     |
+| cosine_precision@5  | 0.1892     |
+| cosine_precision@10 | 0.0974     |
+| cosine_recall@1     | 0.691      |
+| cosine_recall@3     | 0.9109     |
+| cosine_recall@5     | 0.9461     |
+| cosine_recall@10    | 0.9743     |
+| **cosine_ndcg@10**  | **0.8472** |
+| cosine_mrr@10       | 0.8048     |
+| cosine_map@100      | 0.8061     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 46,338 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                           |
+  |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                               |
+  | details | <ul><li>min: 13 tokens</li><li>mean: 34.18 tokens</li><li>max: 251 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 231.33 tokens</li><li>max: 2146 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How is 'energy efficiency' defined in the context of Directive (EU) 2018/2001?</code>                                                                                               | <code>of Directive (EU) 2018/2001; --- --- (8) ‘energy efficiency’ means the ratio of output of performance, service, goods or energy to input of energy; --- --- (9) ‘energy savings’ means an amount of saved energy determined by measuring or estimating consumption, or both,, before and after the implementation of an energy efficiency improvement measure, whilst ensuring normalisation for external conditions that affect energy consumption; --- --- (10) ‘energy efficiency improvement’ means an increase in energy efficiency as a result of any technological, behavioural or economic changes; --- --- (11) ‘energy service’ means the physical benefit, utility or good derived from a combination of energy with energy-efficient technology or with action,</code>            |
+  | <code>What are the sources of information that the external experts will use to create the list of conflict-affected and high-risk areas?</code>                                          | <code>2.<br><br>The Commission shall call upon external expertise that will provide an indicative, non-exhaustive, regularly updated list of conflict-affected and high-risk areas. That list shall be based on the external experts' analysis of the handbook referred to in paragraph 1 and existing information from, inter alia, academics and supply chain due diligence schemes. Union importers sourcing from areas which are not mentioned on that list shall also maintain their responsibility to comply with the due diligence obligations under this Regulation.<br><br>Article 15<br><br>Committee procedure<br><br>1.<br><br>The Commission shall be assisted by a committee. That committee shall be a committee within the meaning of Regulation (EU) No 182/2011.<br><br>2.</code> |
+  | <code>What is the maximum time frame for completing the undertaking according to the technical specifications set out in Annexes II and III after the Directive enters into force?</code> | <code>is undertaken according to the technical specifications set out in Annexes II and III and that it is completed at the latest four years after the date of entry into force of this Directive.<br><br>2. The analyses and reviews mentioned under paragraph 1 shall be reviewed, and if necessary updated at the latest 13 years after the date of entry into force of this Directive and every six years thereafter.<br><br>Article 6<br><br>Register of protected areas</code>                                                                                                                                                                                                                                                                                                               |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 4
+- `num_train_epochs`: 4
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 4
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | cosine_ndcg@10 |
+|:------:|:-----:|:-------------:|:--------------:|
+| 0.0432 | 500   | 0.358         | -              |
+| 0.0863 | 1000  | 0.1048        | -              |
+| 0.1295 | 1500  | 0.0827        | -              |
+| 0.1726 | 2000  | 0.067         | 0.7969         |
+| 0.2158 | 2500  | 0.0491        | -              |
+| 0.2590 | 3000  | 0.0831        | -              |
+| 0.3021 | 3500  | 0.062         | -              |
+| 0.3453 | 4000  | 0.0657        | 0.8050         |
+| 0.3884 | 4500  | 0.0522        | -              |
+| 0.4316 | 5000  | 0.049         | -              |
+| 0.4748 | 5500  | 0.0426        | -              |
+| 0.5179 | 6000  | 0.0708        | 0.8215         |
+| 0.5611 | 6500  | 0.0236        | -              |
+| 0.6042 | 7000  | 0.024         | -              |
+| 0.6474 | 7500  | 0.0256        | -              |
+| 0.6905 | 8000  | 0.041         | 0.8105         |
+| 0.7337 | 8500  | 0.0285        | -              |
+| 0.7769 | 9000  | 0.0249        | -              |
+| 0.8200 | 9500  | 0.0368        | -              |
+| 0.8632 | 10000 | 0.0588        | 0.8118         |
+| 0.9063 | 10500 | 0.0386        | -              |
+| 0.9495 | 11000 | 0.0456        | -              |
+| 0.9927 | 11500 | 0.0399        | -              |
+| 1.0    | 11585 | -             | 0.8184         |
+| 1.0358 | 12000 | 0.0424        | 0.8239         |
+| 1.0790 | 12500 | 0.0107        | -              |
+| 1.1221 | 13000 | 0.0279        | -              |
+| 1.1653 | 13500 | 0.0236        | -              |
+| 1.2085 | 14000 | 0.024         | 0.8193         |
+| 1.2516 | 14500 | 0.0143        | -              |
+| 1.2948 | 15000 | 0.0118        | -              |
+| 1.3379 | 15500 | 0.0078        | -              |
+| 1.3811 | 16000 | 0.023         | 0.8217         |
+| 1.4243 | 16500 | 0.0239        | -              |
+| 1.4674 | 17000 | 0.0335        | -              |
+| 1.5106 | 17500 | 0.0119        | -              |
+| 1.5537 | 18000 | 0.0411        | 0.8292         |
+| 1.5969 | 18500 | 0.0168        | -              |
+| 1.6401 | 19000 | 0.0059        | -              |
+| 1.6832 | 19500 | 0.0234        | -              |
+| 1.7264 | 20000 | 0.0184        | 0.8366         |
+| 1.7695 | 20500 | 0.0128        | -              |
+| 1.8127 | 21000 | 0.0166        | -              |
+| 1.8558 | 21500 | 0.0181        | -              |
+| 1.8990 | 22000 | 0.0148        | 0.8353         |
+| 1.9422 | 22500 | 0.0225        | -              |
+| 1.9853 | 23000 | 0.0158        | -              |
+| 2.0    | 23170 | -             | 0.8360         |
+| 2.0285 | 23500 | 0.0123        | -              |
+| 2.0716 | 24000 | 0.0173        | 0.8329         |
+| 2.1148 | 24500 | 0.0167        | -              |
+| 2.1580 | 25000 | 0.0125        | -              |
+| 2.2011 | 25500 | 0.013         | -              |
+| 2.2443 | 26000 | 0.0079        | 0.8338         |
+| 2.2874 | 26500 | 0.007         | -              |
+| 2.3306 | 27000 | 0.0171        | -              |
+| 2.3738 | 27500 | 0.0058        | -              |
+| 2.4169 | 28000 | 0.0048        | 0.8405         |
+| 2.4601 | 28500 | 0.005         | -              |
+| 2.5032 | 29000 | 0.0141        | -              |
+| 2.5464 | 29500 | 0.0132        | -              |
+| 2.5896 | 30000 | 0.006         | 0.8461         |
+| 2.6327 | 30500 | 0.0095        | -              |
+| 2.6759 | 31000 | 0.0061        | -              |
+| 2.7190 | 31500 | 0.0107        | -              |
+| 2.7622 | 32000 | 0.0157        | 0.8451         |
+| 2.8054 | 32500 | 0.005         | -              |
+| 2.8485 | 33000 | 0.0087        | -              |
+| 2.8917 | 33500 | 0.0064        | -              |
+| 2.9348 | 34000 | 0.005         | 0.8449         |
+| 2.9780 | 34500 | 0.0115        | -              |
+| 3.0    | 34755 | -             | 0.8451         |
+| 3.0211 | 35000 | 0.0079        | -              |
+| 3.0643 | 35500 | 0.0045        | -              |
+| 3.1075 | 36000 | 0.0029        | 0.8443         |
+| 3.1506 | 36500 | 0.0161        | -              |
+| 3.1938 | 37000 | 0.0144        | -              |
+| 3.2369 | 37500 | 0.0076        | -              |
+| 3.2801 | 38000 | 0.0157        | 0.8500         |
+| 3.3233 | 38500 | 0.0039        | -              |
+| 3.3664 | 39000 | 0.0045        | -              |
+| 3.4096 | 39500 | 0.0033        | -              |
+| 3.4527 | 40000 | 0.0064        | 0.8434         |
+| 3.4959 | 40500 | 0.0054        | -              |
+| 3.5391 | 41000 | 0.0061        | -              |
+| 3.5822 | 41500 | 0.0051        | -              |
+| 3.6254 | 42000 | 0.0019        | 0.8472         |
+
+
+### Framework Versions
+- Python: 3.10.15
+- Sentence Transformers: 3.4.1
+- Transformers: 4.49.0
+- PyTorch: 2.6.0+cu126
+- Accelerate: 1.5.2
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@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
+```bibtex
+@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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-modernbert-base",
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "reference_compile": false,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 50368
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.6.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d142207c04c435aad0e65bb57b4edb7fa82de7f409696c6b50576caceb655c
+size 596070136

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25837551c5ea01836209ba69f40aff854c8e38884c5d12027898dd74731bea30
+size 1192227066

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d239e3621d79502a0429d2f66b0ee1d9d87731a0b30b289302595590195e7ae0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127f06add1ffec77cf1dbfde5d47abb256ba37206b1fb51a0c26d412c7203b0e
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,945 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,1083 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.6253776435045317,
+  "eval_steps": 2000,
+  "global_step": 42000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04315925766076824,
+      "grad_norm": 30.676715850830078,
+      "learning_rate": 2.1579628830384117e-06,
+      "loss": 0.358,
+      "step": 500
+    },
+    {
+      "epoch": 0.08631851532153648,
+      "grad_norm": 19.524194717407227,
+      "learning_rate": 4.3159257660768235e-06,
+      "loss": 0.1048,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1294777729823047,
+      "grad_norm": 0.00297492160461843,
+      "learning_rate": 6.473888649115235e-06,
+      "loss": 0.0827,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17263703064307295,
+      "grad_norm": 8.900677680969238,
+      "learning_rate": 8.631851532153647e-06,
+      "loss": 0.067,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17263703064307295,
+      "eval_cosine_accuracy@1": 0.6191955808734679,
+      "eval_cosine_accuracy@10": 0.9514931814258588,
+      "eval_cosine_accuracy@3": 0.8606939409632315,
+      "eval_cosine_accuracy@5": 0.909891248058001,
+      "eval_cosine_map@100": 0.748128574680106,
+      "eval_cosine_mrr@10": 0.7459635876906734,
+      "eval_cosine_ndcg@10": 0.7968614059582585,
+      "eval_cosine_precision@1": 0.6191955808734679,
+      "eval_cosine_precision@10": 0.09514931814258587,
+      "eval_cosine_precision@3": 0.28689798032107716,
+      "eval_cosine_precision@5": 0.18197824961160017,
+      "eval_cosine_recall@1": 0.6191955808734679,
+      "eval_cosine_recall@10": 0.9514931814258588,
+      "eval_cosine_recall@3": 0.8606939409632315,
+      "eval_cosine_recall@5": 0.909891248058001,
+      "eval_runtime": 468.0233,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.21579628830384118,
+      "grad_norm": 0.12022869288921356,
+      "learning_rate": 1.0789814415192059e-05,
+      "loss": 0.0491,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2589555459646094,
+      "grad_norm": 0.07568053156137466,
+      "learning_rate": 1.294777729823047e-05,
+      "loss": 0.0831,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3021148036253776,
+      "grad_norm": 0.0246192067861557,
+      "learning_rate": 1.5105740181268884e-05,
+      "loss": 0.062,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3452740612861459,
+      "grad_norm": 0.009853623807430267,
+      "learning_rate": 1.7263703064307294e-05,
+      "loss": 0.0657,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3452740612861459,
+      "eval_cosine_accuracy@1": 0.6362851717590196,
+      "eval_cosine_accuracy@10": 0.9523562920766442,
+      "eval_cosine_accuracy@3": 0.8606939409632315,
+      "eval_cosine_accuracy@5": 0.9110996029691006,
+      "eval_cosine_map@100": 0.7589134849598074,
+      "eval_cosine_mrr@10": 0.756632799848751,
+      "eval_cosine_ndcg@10": 0.8050365772218437,
+      "eval_cosine_precision@1": 0.6362851717590196,
+      "eval_cosine_precision@10": 0.09523562920766442,
+      "eval_cosine_precision@3": 0.28689798032107716,
+      "eval_cosine_precision@5": 0.1822199205938201,
+      "eval_cosine_recall@1": 0.6362851717590196,
+      "eval_cosine_recall@10": 0.9523562920766442,
+      "eval_cosine_recall@3": 0.8606939409632315,
+      "eval_cosine_recall@5": 0.9110996029691006,
+      "eval_runtime": 467.8258,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 0.38843331894691413,
+      "grad_norm": 0.017763391137123108,
+      "learning_rate": 1.9421665947345706e-05,
+      "loss": 0.0522,
+      "step": 4500
+    },
+    {
+      "epoch": 0.43159257660768235,
+      "grad_norm": 21.21623420715332,
+      "learning_rate": 1.982446885041485e-05,
+      "loss": 0.049,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4747518342684506,
+      "grad_norm": 0.13613158464431763,
+      "learning_rate": 1.958467219797612e-05,
+      "loss": 0.0426,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5179110919292188,
+      "grad_norm": 0.1645500212907791,
+      "learning_rate": 1.9344875545537384e-05,
+      "loss": 0.0708,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5179110919292188,
+      "eval_cosine_accuracy@1": 0.6526842741239427,
+      "eval_cosine_accuracy@10": 0.9642672190574831,
+      "eval_cosine_accuracy@3": 0.8865872604867944,
+      "eval_cosine_accuracy@5": 0.9287070602451234,
+      "eval_cosine_map@100": 0.7759321604397249,
+      "eval_cosine_mrr@10": 0.7742270364616298,
+      "eval_cosine_ndcg@10": 0.8214808830487713,
+      "eval_cosine_precision@1": 0.6526842741239427,
+      "eval_cosine_precision@10": 0.0964267219057483,
+      "eval_cosine_precision@3": 0.2955290868289315,
+      "eval_cosine_precision@5": 0.1857414120490247,
+      "eval_cosine_recall@1": 0.6526842741239427,
+      "eval_cosine_recall@10": 0.9642672190574831,
+      "eval_cosine_recall@3": 0.8865872604867944,
+      "eval_cosine_recall@5": 0.9287070602451234,
+      "eval_runtime": 467.7458,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 6000
+    },
+    {
+      "epoch": 0.561070349589987,
+      "grad_norm": 0.3336288332939148,
+      "learning_rate": 1.9105078893098655e-05,
+      "loss": 0.0236,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6042296072507553,
+      "grad_norm": 0.011359921656548977,
+      "learning_rate": 1.886528224065992e-05,
+      "loss": 0.024,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6473888649115235,
+      "grad_norm": 0.0021573721896857023,
+      "learning_rate": 1.8625485588221192e-05,
+      "loss": 0.0256,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6905481225722918,
+      "grad_norm": 0.024769997224211693,
+      "learning_rate": 1.8385688935782457e-05,
+      "loss": 0.041,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6905481225722918,
+      "eval_cosine_accuracy@1": 0.6390471258415329,
+      "eval_cosine_accuracy@10": 0.9573623338511997,
+      "eval_cosine_accuracy@3": 0.8693250474710857,
+      "eval_cosine_accuracy@5": 0.9195580873467979,
+      "eval_cosine_map@100": 0.7640704294756044,
+      "eval_cosine_mrr@10": 0.762041421091137,
+      "eval_cosine_ndcg@10": 0.8104943817099518,
+      "eval_cosine_precision@1": 0.6390471258415329,
+      "eval_cosine_precision@10": 0.09573623338511995,
+      "eval_cosine_precision@3": 0.2897750158236953,
+      "eval_cosine_precision@5": 0.18391161746935958,
+      "eval_cosine_recall@1": 0.6390471258415329,
+      "eval_cosine_recall@10": 0.9573623338511997,
+      "eval_cosine_recall@3": 0.8693250474710857,
+      "eval_cosine_recall@5": 0.9195580873467979,
+      "eval_runtime": 467.5761,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 8000
+    },
+    {
+      "epoch": 0.73370738023306,
+      "grad_norm": 0.001473304582759738,
+      "learning_rate": 1.8145892283343725e-05,
+      "loss": 0.0285,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7768666378938283,
+      "grad_norm": 0.002119662007316947,
+      "learning_rate": 1.7906095630904994e-05,
+      "loss": 0.0249,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8200258955545965,
+      "grad_norm": 0.035019177943468094,
+      "learning_rate": 1.7666298978466262e-05,
+      "loss": 0.0368,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8631851532153647,
+      "grad_norm": 0.2664908468723297,
+      "learning_rate": 1.742650232602753e-05,
+      "loss": 0.0588,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8631851532153647,
+      "eval_cosine_accuracy@1": 0.6407733471431037,
+      "eval_cosine_accuracy@10": 0.9589159330226135,
+      "eval_cosine_accuracy@3": 0.8734679785948558,
+      "eval_cosine_accuracy@5": 0.9204211979975833,
+      "eval_cosine_map@100": 0.7652575174635105,
+      "eval_cosine_mrr@10": 0.7632412818974197,
+      "eval_cosine_ndcg@10": 0.811775458664963,
+      "eval_cosine_precision@1": 0.6407733471431037,
+      "eval_cosine_precision@10": 0.09589159330226135,
+      "eval_cosine_precision@3": 0.2911559928649519,
+      "eval_cosine_precision@5": 0.18408423959951664,
+      "eval_cosine_recall@1": 0.6407733471431037,
+      "eval_cosine_recall@10": 0.9589159330226135,
+      "eval_cosine_recall@3": 0.8734679785948558,
+      "eval_cosine_recall@5": 0.9204211979975833,
+      "eval_runtime": 467.8166,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9063444108761329,
+      "grad_norm": 0.032082412391901016,
+      "learning_rate": 1.71867056735888e-05,
+      "loss": 0.0386,
+      "step": 10500
+    },
+    {
+      "epoch": 0.9495036685369012,
+      "grad_norm": 8.98410415649414,
+      "learning_rate": 1.6946909021150067e-05,
+      "loss": 0.0456,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9926629261976694,
+      "grad_norm": 0.002887778216972947,
+      "learning_rate": 1.6707112368711332e-05,
+      "loss": 0.0399,
+      "step": 11500
+    },
+    {
+      "epoch": 1.0358221838584376,
+      "grad_norm": 0.039170317351818085,
+      "learning_rate": 1.6467315716272604e-05,
+      "loss": 0.0424,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0358221838584376,
+      "eval_cosine_accuracy@1": 0.6606248921111687,
+      "eval_cosine_accuracy@10": 0.9654755739685827,
+      "eval_cosine_accuracy@3": 0.8808907301916106,
+      "eval_cosine_accuracy@5": 0.9300880372863801,
+      "eval_cosine_map@100": 0.7789505370634054,
+      "eval_cosine_mrr@10": 0.7772537463112309,
+      "eval_cosine_ndcg@10": 0.8239196088222247,
+      "eval_cosine_precision@1": 0.6606248921111687,
+      "eval_cosine_precision@10": 0.09654755739685827,
+      "eval_cosine_precision@3": 0.2936302433972035,
+      "eval_cosine_precision@5": 0.186017607457276,
+      "eval_cosine_recall@1": 0.6606248921111687,
+      "eval_cosine_recall@10": 0.9654755739685827,
+      "eval_cosine_recall@3": 0.8808907301916106,
+      "eval_cosine_recall@5": 0.9300880372863801,
+      "eval_runtime": 467.7683,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0789814415192058,
+      "grad_norm": 0.07316175103187561,
+      "learning_rate": 1.622751906383387e-05,
+      "loss": 0.0107,
+      "step": 12500
+    },
+    {
+      "epoch": 1.122140699179974,
+      "grad_norm": 0.03618592023849487,
+      "learning_rate": 1.598772241139514e-05,
+      "loss": 0.0279,
+      "step": 13000
+    },
+    {
+      "epoch": 1.1652999568407423,
+      "grad_norm": 0.023356635123491287,
+      "learning_rate": 1.5747925758956405e-05,
+      "loss": 0.0236,
+      "step": 13500
+    },
+    {
+      "epoch": 1.2084592145015105,
+      "grad_norm": 0.002293772529810667,
+      "learning_rate": 1.5508129106517674e-05,
+      "loss": 0.024,
+      "step": 14000
+    },
+    {
+      "epoch": 1.2084592145015105,
+      "eval_cosine_accuracy@1": 0.6506128085620576,
+      "eval_cosine_accuracy@10": 0.9640945969273261,
+      "eval_cosine_accuracy@3": 0.8803728638011393,
+      "eval_cosine_accuracy@5": 0.9266355946832384,
+      "eval_cosine_map@100": 0.7732572758885798,
+      "eval_cosine_mrr@10": 0.7715017303313533,
+      "eval_cosine_ndcg@10": 0.8192838549207232,
+      "eval_cosine_precision@1": 0.6506128085620576,
+      "eval_cosine_precision@10": 0.09640945969273261,
+      "eval_cosine_precision@3": 0.29345762126704644,
+      "eval_cosine_precision@5": 0.18532711893664763,
+      "eval_cosine_recall@1": 0.6506128085620576,
+      "eval_cosine_recall@10": 0.9640945969273261,
+      "eval_cosine_recall@3": 0.8803728638011393,
+      "eval_cosine_recall@5": 0.9266355946832384,
+      "eval_runtime": 467.8783,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 14000
+    },
+    {
+      "epoch": 1.2516184721622787,
+      "grad_norm": 0.007560160476714373,
+      "learning_rate": 1.5268332454078942e-05,
+      "loss": 0.0143,
+      "step": 14500
+    },
+    {
+      "epoch": 1.2947777298230472,
+      "grad_norm": 0.004202102776616812,
+      "learning_rate": 1.5028535801640209e-05,
+      "loss": 0.0118,
+      "step": 15000
+    },
+    {
+      "epoch": 1.3379369874838152,
+      "grad_norm": 0.00022126469411887228,
+      "learning_rate": 1.4788739149201479e-05,
+      "loss": 0.0078,
+      "step": 15500
+    },
+    {
+      "epoch": 1.3810962451445836,
+      "grad_norm": 0.011956814676523209,
+      "learning_rate": 1.4548942496762745e-05,
+      "loss": 0.023,
+      "step": 16000
+    },
+    {
+      "epoch": 1.3810962451445836,
+      "eval_cosine_accuracy@1": 0.6533747626445711,
+      "eval_cosine_accuracy@10": 0.9642672190574831,
+      "eval_cosine_accuracy@3": 0.8826169514931814,
+      "eval_cosine_accuracy@5": 0.9302606594165372,
+      "eval_cosine_map@100": 0.7763076224553367,
+      "eval_cosine_mrr@10": 0.7745393318153555,
+      "eval_cosine_ndcg@10": 0.8216976031852626,
+      "eval_cosine_precision@1": 0.6533747626445711,
+      "eval_cosine_precision@10": 0.0964267219057483,
+      "eval_cosine_precision@3": 0.2942056504977271,
+      "eval_cosine_precision@5": 0.18605213188330738,
+      "eval_cosine_recall@1": 0.6533747626445711,
+      "eval_cosine_recall@10": 0.9642672190574831,
+      "eval_cosine_recall@3": 0.8826169514931814,
+      "eval_cosine_recall@5": 0.9302606594165372,
+      "eval_runtime": 467.7532,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 16000
+    },
+    {
+      "epoch": 1.4242555028053516,
+      "grad_norm": 0.008947977796196938,
+      "learning_rate": 1.4309145844324015e-05,
+      "loss": 0.0239,
+      "step": 16500
+    },
+    {
+      "epoch": 1.46741476046612,
+      "grad_norm": 0.20168237388134003,
+      "learning_rate": 1.4069349191885282e-05,
+      "loss": 0.0335,
+      "step": 17000
+    },
+    {
+      "epoch": 1.510574018126888,
+      "grad_norm": 0.003233299357816577,
+      "learning_rate": 1.3829552539446552e-05,
+      "loss": 0.0119,
+      "step": 17500
+    },
+    {
+      "epoch": 1.5537332757876565,
+      "grad_norm": 0.013063711114227772,
+      "learning_rate": 1.3589755887007819e-05,
+      "loss": 0.0411,
+      "step": 18000
+    },
+    {
+      "epoch": 1.5537332757876565,
+      "eval_cosine_accuracy@1": 0.6644225789746245,
+      "eval_cosine_accuracy@10": 0.9680649059209391,
+      "eval_cosine_accuracy@3": 0.8898670809597791,
+      "eval_cosine_accuracy@5": 0.9335404798895218,
+      "eval_cosine_map@100": 0.7848911785594413,
+      "eval_cosine_mrr@10": 0.7833323743214994,
+      "eval_cosine_ndcg@10": 0.8292454833247894,
+      "eval_cosine_precision@1": 0.6644225789746245,
+      "eval_cosine_precision@10": 0.09680649059209388,
+      "eval_cosine_precision@3": 0.2966223603199264,
+      "eval_cosine_precision@5": 0.18670809597790436,
+      "eval_cosine_recall@1": 0.6644225789746245,
+      "eval_cosine_recall@10": 0.9680649059209391,
+      "eval_cosine_recall@3": 0.8898670809597791,
+      "eval_cosine_recall@5": 0.9335404798895218,
+      "eval_runtime": 467.9161,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 18000
+    },
+    {
+      "epoch": 1.5968925334484245,
+      "grad_norm": 3.0231621265411377,
+      "learning_rate": 1.3349959234569087e-05,
+      "loss": 0.0168,
+      "step": 18500
+    },
+    {
+      "epoch": 1.640051791109193,
+      "grad_norm": 0.08278048038482666,
+      "learning_rate": 1.3110162582130355e-05,
+      "loss": 0.0059,
+      "step": 19000
+    },
+    {
+      "epoch": 1.6832110487699612,
+      "grad_norm": 0.10015950351953506,
+      "learning_rate": 1.2870365929691622e-05,
+      "loss": 0.0234,
+      "step": 19500
+    },
+    {
+      "epoch": 1.7263703064307294,
+      "grad_norm": 2.1657984256744385,
+      "learning_rate": 1.263056927725289e-05,
+      "loss": 0.0184,
+      "step": 20000
+    },
+    {
+      "epoch": 1.7263703064307294,
+      "eval_cosine_accuracy@1": 0.6768513723459347,
+      "eval_cosine_accuracy@10": 0.969963749352667,
+      "eval_cosine_accuracy@3": 0.897807698947005,
+      "eval_cosine_accuracy@5": 0.9369929224926635,
+      "eval_cosine_map@100": 0.7938770196077543,
+      "eval_cosine_mrr@10": 0.7923516066188262,
+      "eval_cosine_ndcg@10": 0.8365875778541227,
+      "eval_cosine_precision@1": 0.6768513723459347,
+      "eval_cosine_precision@10": 0.09699637493526668,
+      "eval_cosine_precision@3": 0.29926923298233504,
+      "eval_cosine_precision@5": 0.1873985844985327,
+      "eval_cosine_recall@1": 0.6768513723459347,
+      "eval_cosine_recall@10": 0.969963749352667,
+      "eval_cosine_recall@3": 0.897807698947005,
+      "eval_cosine_recall@5": 0.9369929224926635,
+      "eval_runtime": 467.8044,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 20000
+    },
+    {
+      "epoch": 1.7695295640914976,
+      "grad_norm": 1.5666255950927734,
+      "learning_rate": 1.2390772624814159e-05,
+      "loss": 0.0128,
+      "step": 20500
+    },
+    {
+      "epoch": 1.8126888217522659,
+      "grad_norm": 0.00032274972181767225,
+      "learning_rate": 1.2150975972375427e-05,
+      "loss": 0.0166,
+      "step": 21000
+    },
+    {
+      "epoch": 1.855848079413034,
+      "grad_norm": 0.051935628056526184,
+      "learning_rate": 1.1911179319936694e-05,
+      "loss": 0.0181,
+      "step": 21500
+    },
+    {
+      "epoch": 1.8990073370738023,
+      "grad_norm": 0.02546406351029873,
+      "learning_rate": 1.1671382667497964e-05,
+      "loss": 0.0148,
+      "step": 22000
+    },
+    {
+      "epoch": 1.8990073370738023,
+      "eval_cosine_accuracy@1": 0.6744346625237355,
+      "eval_cosine_accuracy@10": 0.9697911272225099,
+      "eval_cosine_accuracy@3": 0.8971172104263767,
+      "eval_cosine_accuracy@5": 0.9388917659243915,
+      "eval_cosine_map@100": 0.792274316391964,
+      "eval_cosine_mrr@10": 0.7907476593261165,
+      "eval_cosine_ndcg@10": 0.8353359235071491,
+      "eval_cosine_precision@1": 0.6744346625237355,
+      "eval_cosine_precision@10": 0.09697911272225099,
+      "eval_cosine_precision@3": 0.2990390701421256,
+      "eval_cosine_precision@5": 0.1877783531848783,
+      "eval_cosine_recall@1": 0.6744346625237355,
+      "eval_cosine_recall@10": 0.9697911272225099,
+      "eval_cosine_recall@3": 0.8971172104263767,
+      "eval_cosine_recall@5": 0.9388917659243915,
+      "eval_runtime": 467.8952,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 22000
+    },
+    {
+      "epoch": 1.9421665947345705,
+      "grad_norm": 0.009108115918934345,
+      "learning_rate": 1.143158601505923e-05,
+      "loss": 0.0225,
+      "step": 22500
+    },
+    {
+      "epoch": 1.9853258523953388,
+      "grad_norm": 0.06883949786424637,
+      "learning_rate": 1.1191789362620497e-05,
+      "loss": 0.0158,
+      "step": 23000
+    },
+    {
+      "epoch": 2.028485110056107,
+      "grad_norm": 0.00019052527204621583,
+      "learning_rate": 1.0951992710181767e-05,
+      "loss": 0.0123,
+      "step": 23500
+    },
+    {
+      "epoch": 2.071644367716875,
+      "grad_norm": 0.005655207671225071,
+      "learning_rate": 1.0712196057743034e-05,
+      "loss": 0.0173,
+      "step": 24000
+    },
+    {
+      "epoch": 2.071644367716875,
+      "eval_cosine_accuracy@1": 0.6718453305713793,
+      "eval_cosine_accuracy@10": 0.9685827723114103,
+      "eval_cosine_accuracy@3": 0.8934921456930779,
+      "eval_cosine_accuracy@5": 0.9383738995339203,
+      "eval_cosine_map@100": 0.7895192117982024,
+      "eval_cosine_mrr@10": 0.7879250134946668,
+      "eval_cosine_ndcg@10": 0.832874525127316,
+      "eval_cosine_precision@1": 0.6718453305713793,
+      "eval_cosine_precision@10": 0.09685827723114103,
+      "eval_cosine_precision@3": 0.297830715231026,
+      "eval_cosine_precision@5": 0.18767477990678402,
+      "eval_cosine_recall@1": 0.6718453305713793,
+      "eval_cosine_recall@10": 0.9685827723114103,
+      "eval_cosine_recall@3": 0.8934921456930779,
+      "eval_cosine_recall@5": 0.9383738995339203,
+      "eval_runtime": 468.4558,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 24000
+    },
+    {
+      "epoch": 2.1148036253776437,
+      "grad_norm": 0.1119648739695549,
+      "learning_rate": 1.0472399405304304e-05,
+      "loss": 0.0167,
+      "step": 24500
+    },
+    {
+      "epoch": 2.1579628830384117,
+      "grad_norm": 0.03796195238828659,
+      "learning_rate": 1.023260275286557e-05,
+      "loss": 0.0125,
+      "step": 25000
+    },
+    {
+      "epoch": 2.20112214069918,
+      "grad_norm": 0.012651159428060055,
+      "learning_rate": 9.992806100426838e-06,
+      "loss": 0.013,
+      "step": 25500
+    },
+    {
+      "epoch": 2.244281398359948,
+      "grad_norm": 0.0021349990274757147,
+      "learning_rate": 9.753009447988107e-06,
+      "loss": 0.0079,
+      "step": 26000
+    },
+    {
+      "epoch": 2.244281398359948,
+      "eval_cosine_accuracy@1": 0.669255998619023,
+      "eval_cosine_accuracy@10": 0.9709994821336095,
+      "eval_cosine_accuracy@3": 0.8950457448644916,
+      "eval_cosine_accuracy@5": 0.9390643880545486,
+      "eval_cosine_map@100": 0.7897457483356454,
+      "eval_cosine_mrr@10": 0.7882845059308039,
+      "eval_cosine_ndcg@10": 0.8337888145070348,
+      "eval_cosine_precision@1": 0.669255998619023,
+      "eval_cosine_precision@10": 0.09709994821336093,
+      "eval_cosine_precision@3": 0.29834858162149724,
+      "eval_cosine_precision@5": 0.18781287761090973,
+      "eval_cosine_recall@1": 0.669255998619023,
+      "eval_cosine_recall@10": 0.9709994821336095,
+      "eval_cosine_recall@3": 0.8950457448644916,
+      "eval_cosine_recall@5": 0.9390643880545486,
+      "eval_runtime": 467.762,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 26000
+    },
+    {
+      "epoch": 2.2874406560207166,
+      "grad_norm": 0.4521012306213379,
+      "learning_rate": 9.513212795549375e-06,
+      "loss": 0.007,
+      "step": 26500
+    },
+    {
+      "epoch": 2.3305999136814846,
+      "grad_norm": 0.0015283157117664814,
+      "learning_rate": 9.273416143110643e-06,
+      "loss": 0.0171,
+      "step": 27000
+    },
+    {
+      "epoch": 2.373759171342253,
+      "grad_norm": 0.0033215314615517855,
+      "learning_rate": 9.033619490671912e-06,
+      "loss": 0.0058,
+      "step": 27500
+    },
+    {
+      "epoch": 2.416918429003021,
+      "grad_norm": 4.302379131317139,
+      "learning_rate": 8.793822838233178e-06,
+      "loss": 0.0048,
+      "step": 28000
+    },
+    {
+      "epoch": 2.416918429003021,
+      "eval_cosine_accuracy@1": 0.6825479026411186,
+      "eval_cosine_accuracy@10": 0.9718625927843949,
+      "eval_cosine_accuracy@3": 0.8993612981184188,
+      "eval_cosine_accuracy@5": 0.9390643880545486,
+      "eval_cosine_map@100": 0.7983751737002095,
+      "eval_cosine_mrr@10": 0.7969948679166703,
+      "eval_cosine_ndcg@10": 0.8405363983140419,
+      "eval_cosine_precision@1": 0.6825479026411186,
+      "eval_cosine_precision@10": 0.09718625927843948,
+      "eval_cosine_precision@3": 0.2997870993728063,
+      "eval_cosine_precision@5": 0.18781287761090973,
+      "eval_cosine_recall@1": 0.6825479026411186,
+      "eval_cosine_recall@10": 0.9718625927843949,
+      "eval_cosine_recall@3": 0.8993612981184188,
+      "eval_cosine_recall@5": 0.9390643880545486,
+      "eval_runtime": 467.6926,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 28000
+    },
+    {
+      "epoch": 2.4600776866637895,
+      "grad_norm": 0.001049822778441012,
+      "learning_rate": 8.554026185794447e-06,
+      "loss": 0.005,
+      "step": 28500
+    },
+    {
+      "epoch": 2.5032369443245575,
+      "grad_norm": 0.0011170560028403997,
+      "learning_rate": 8.314229533355715e-06,
+      "loss": 0.0141,
+      "step": 29000
+    },
+    {
+      "epoch": 2.546396201985326,
+      "grad_norm": 0.0026090971659868956,
+      "learning_rate": 8.074432880916982e-06,
+      "loss": 0.0132,
+      "step": 29500
+    },
+    {
+      "epoch": 2.5895554596460943,
+      "grad_norm": 7.936817564768717e-05,
+      "learning_rate": 7.83463622847825e-06,
+      "loss": 0.006,
+      "step": 30000
+    },
+    {
+      "epoch": 2.5895554596460943,
+      "eval_cosine_accuracy@1": 0.6911790091489729,
+      "eval_cosine_accuracy@10": 0.9735888140859659,
+      "eval_cosine_accuracy@3": 0.9092007595373727,
+      "eval_cosine_accuracy@5": 0.9442430519592612,
+      "eval_cosine_map@100": 0.8050289389600185,
+      "eval_cosine_mrr@10": 0.8036913735515502,
+      "eval_cosine_ndcg@10": 0.8461133955612519,
+      "eval_cosine_precision@1": 0.6911790091489729,
+      "eval_cosine_precision@10": 0.09735888140859657,
+      "eval_cosine_precision@3": 0.3030669198457909,
+      "eval_cosine_precision@5": 0.18884861039185225,
+      "eval_cosine_recall@1": 0.6911790091489729,
+      "eval_cosine_recall@10": 0.9735888140859659,
+      "eval_cosine_recall@3": 0.9092007595373727,
+      "eval_cosine_recall@5": 0.9442430519592612,
+      "eval_runtime": 467.8028,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 30000
+    },
+    {
+      "epoch": 2.6327147173068624,
+      "grad_norm": 0.014025676064193249,
+      "learning_rate": 7.5948395760395184e-06,
+      "loss": 0.0095,
+      "step": 30500
+    },
+    {
+      "epoch": 2.6758739749676304,
+      "grad_norm": 0.0240753386169672,
+      "learning_rate": 7.355042923600787e-06,
+      "loss": 0.0061,
+      "step": 31000
+    },
+    {
+      "epoch": 2.719033232628399,
+      "grad_norm": 0.051389552652835846,
+      "learning_rate": 7.115246271162055e-06,
+      "loss": 0.0107,
+      "step": 31500
+    },
+    {
+      "epoch": 2.7621924902891672,
+      "grad_norm": 0.0053047193214297295,
+      "learning_rate": 6.875449618723323e-06,
+      "loss": 0.0157,
+      "step": 32000
+    },
+    {
+      "epoch": 2.7621924902891672,
+      "eval_cosine_accuracy@1": 0.689452787847402,
+      "eval_cosine_accuracy@10": 0.9723804591748663,
+      "eval_cosine_accuracy@3": 0.9074745382358018,
+      "eval_cosine_accuracy@5": 0.9442430519592612,
+      "eval_cosine_map@100": 0.8041420474637542,
+      "eval_cosine_mrr@10": 0.8027525694667068,
+      "eval_cosine_ndcg@10": 0.8451171490975874,
+      "eval_cosine_precision@1": 0.689452787847402,
+      "eval_cosine_precision@10": 0.09723804591748661,
+      "eval_cosine_precision@3": 0.3024915127452673,
+      "eval_cosine_precision@5": 0.18884861039185225,
+      "eval_cosine_recall@1": 0.689452787847402,
+      "eval_cosine_recall@10": 0.9723804591748663,
+      "eval_cosine_recall@3": 0.9074745382358018,
+      "eval_cosine_recall@5": 0.9442430519592612,
+      "eval_runtime": 467.7248,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 32000
+    },
+    {
+      "epoch": 2.8053517479499352,
+      "grad_norm": 0.005983938928693533,
+      "learning_rate": 6.635652966284592e-06,
+      "loss": 0.005,
+      "step": 32500
+    },
+    {
+      "epoch": 2.8485110056107033,
+      "grad_norm": 0.006458807270973921,
+      "learning_rate": 6.395856313845859e-06,
+      "loss": 0.0087,
+      "step": 33000
+    },
+    {
+      "epoch": 2.8916702632714717,
+      "grad_norm": 0.00440911203622818,
+      "learning_rate": 6.1560596614071276e-06,
+      "loss": 0.0064,
+      "step": 33500
+    },
+    {
+      "epoch": 2.93482952093224,
+      "grad_norm": 0.0034452094696462154,
+      "learning_rate": 5.916263008968395e-06,
+      "loss": 0.005,
+      "step": 34000
+    },
+    {
+      "epoch": 2.93482952093224,
+      "eval_cosine_accuracy@1": 0.6884170550664596,
+      "eval_cosine_accuracy@10": 0.9725530813050233,
+      "eval_cosine_accuracy@3": 0.9083376488865873,
+      "eval_cosine_accuracy@5": 0.9463145175211463,
+      "eval_cosine_map@100": 0.8037708008346327,
+      "eval_cosine_mrr@10": 0.8023887614773162,
+      "eval_cosine_ndcg@10": 0.8449160090668899,
+      "eval_cosine_precision@1": 0.6884170550664596,
+      "eval_cosine_precision@10": 0.0972553081305023,
+      "eval_cosine_precision@3": 0.30277921629552906,
+      "eval_cosine_precision@5": 0.18926290350422922,
+      "eval_cosine_recall@1": 0.6884170550664596,
+      "eval_cosine_recall@10": 0.9725530813050233,
+      "eval_cosine_recall@3": 0.9083376488865873,
+      "eval_cosine_recall@5": 0.9463145175211463,
+      "eval_runtime": 467.6593,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 34000
+    },
+    {
+      "epoch": 2.977988778593008,
+      "grad_norm": 1.5224103927612305,
+      "learning_rate": 5.6764663565296625e-06,
+      "loss": 0.0115,
+      "step": 34500
+    },
+    {
+      "epoch": 3.0211480362537766,
+      "grad_norm": 0.007577585522085428,
+      "learning_rate": 5.436669704090931e-06,
+      "loss": 0.0079,
+      "step": 35000
+    },
+    {
+      "epoch": 3.0643072939145446,
+      "grad_norm": 0.01359875500202179,
+      "learning_rate": 5.196873051652199e-06,
+      "loss": 0.0045,
+      "step": 35500
+    },
+    {
+      "epoch": 3.107466551575313,
+      "grad_norm": 0.005014342721551657,
+      "learning_rate": 4.9570763992134675e-06,
+      "loss": 0.0029,
+      "step": 36000
+    },
+    {
+      "epoch": 3.107466551575313,
+      "eval_cosine_accuracy@1": 0.6875539444156741,
+      "eval_cosine_accuracy@10": 0.972035214914552,
+      "eval_cosine_accuracy@3": 0.9067840497151735,
+      "eval_cosine_accuracy@5": 0.9442430519592612,
+      "eval_cosine_map@100": 0.8031759037555115,
+      "eval_cosine_mrr@10": 0.8017571836836468,
+      "eval_cosine_ndcg@10": 0.8443043752760462,
+      "eval_cosine_precision@1": 0.6875539444156741,
+      "eval_cosine_precision@10": 0.09720352149145518,
+      "eval_cosine_precision@3": 0.3022613499050578,
+      "eval_cosine_precision@5": 0.18884861039185225,
+      "eval_cosine_recall@1": 0.6875539444156741,
+      "eval_cosine_recall@10": 0.972035214914552,
+      "eval_cosine_recall@3": 0.9067840497151735,
+      "eval_cosine_recall@5": 0.9442430519592612,
+      "eval_runtime": 467.7266,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 36000
+    },
+    {
+      "epoch": 3.150625809236081,
+      "grad_norm": 0.015572451055049896,
+      "learning_rate": 4.717279746774736e-06,
+      "loss": 0.0161,
+      "step": 36500
+    },
+    {
+      "epoch": 3.1937850668968495,
+      "grad_norm": 0.004311546217650175,
+      "learning_rate": 4.477483094336003e-06,
+      "loss": 0.0144,
+      "step": 37000
+    },
+    {
+      "epoch": 3.2369443245576175,
+      "grad_norm": 0.0009289888548664749,
+      "learning_rate": 4.237686441897272e-06,
+      "loss": 0.0076,
+      "step": 37500
+    },
+    {
+      "epoch": 3.280103582218386,
+      "grad_norm": 0.0010557913919910789,
+      "learning_rate": 3.997889789458539e-06,
+      "loss": 0.0157,
+      "step": 38000
+    },
+    {
+      "epoch": 3.280103582218386,
+      "eval_cosine_accuracy@1": 0.6977386500949422,
+      "eval_cosine_accuracy@10": 0.9747971689970655,
+      "eval_cosine_accuracy@3": 0.909891248058001,
+      "eval_cosine_accuracy@5": 0.9470050060417745,
+      "eval_cosine_map@100": 0.809749193191093,
+      "eval_cosine_mrr@10": 0.8084805416498834,
+      "eval_cosine_ndcg@10": 0.8499994995327701,
+      "eval_cosine_precision@1": 0.6977386500949422,
+      "eval_cosine_precision@10": 0.09747971689970651,
+      "eval_cosine_precision@3": 0.30329708268600036,
+      "eval_cosine_precision@5": 0.18940100120835487,
+      "eval_cosine_recall@1": 0.6977386500949422,
+      "eval_cosine_recall@10": 0.9747971689970655,
+      "eval_cosine_recall@3": 0.909891248058001,
+      "eval_cosine_recall@5": 0.9470050060417745,
+      "eval_runtime": 467.9009,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 38000
+    },
+    {
+      "epoch": 3.323262839879154,
+      "grad_norm": 0.002490697894245386,
+      "learning_rate": 3.7580931370198075e-06,
+      "loss": 0.0039,
+      "step": 38500
+    },
+    {
+      "epoch": 3.3664220975399224,
+      "grad_norm": 0.0011037011863663793,
+      "learning_rate": 3.518296484581076e-06,
+      "loss": 0.0045,
+      "step": 39000
+    },
+    {
+      "epoch": 3.4095813552006904,
+      "grad_norm": 0.008491401560604572,
+      "learning_rate": 3.2784998321423433e-06,
+      "loss": 0.0033,
+      "step": 39500
+    },
+    {
+      "epoch": 3.452740612861459,
+      "grad_norm": 0.0002366910339333117,
+      "learning_rate": 3.0387031797036116e-06,
+      "loss": 0.0064,
+      "step": 40000
+    },
+    {
+      "epoch": 3.452740612861459,
+      "eval_cosine_accuracy@1": 0.6832383911617469,
+      "eval_cosine_accuracy@10": 0.97393405834628,
+      "eval_cosine_accuracy@3": 0.9062661833247022,
+      "eval_cosine_accuracy@5": 0.9464871396513033,
+      "eval_cosine_map@100": 0.8011659555812971,
+      "eval_cosine_mrr@10": 0.7998895081365299,
+      "eval_cosine_ndcg@10": 0.8433601615941685,
+      "eval_cosine_precision@1": 0.6832383911617469,
+      "eval_cosine_precision@10": 0.097393405834628,
+      "eval_cosine_precision@3": 0.30208872777490076,
+      "eval_cosine_precision@5": 0.18929742793026064,
+      "eval_cosine_recall@1": 0.6832383911617469,
+      "eval_cosine_recall@10": 0.97393405834628,
+      "eval_cosine_recall@3": 0.9062661833247022,
+      "eval_cosine_recall@5": 0.9464871396513033,
+      "eval_runtime": 467.6658,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 40000
+    },
+    {
+      "epoch": 3.495899870522227,
+      "grad_norm": 0.0015487176133319736,
+      "learning_rate": 2.7989065272648796e-06,
+      "loss": 0.0054,
+      "step": 40500
+    },
+    {
+      "epoch": 3.5390591281829953,
+      "grad_norm": 1.1207655668258667,
+      "learning_rate": 2.559109874826148e-06,
+      "loss": 0.0061,
+      "step": 41000
+    },
+    {
+      "epoch": 3.5822183858437633,
+      "grad_norm": 0.0002378961944486946,
+      "learning_rate": 2.319313222387416e-06,
+      "loss": 0.0051,
+      "step": 41500
+    },
+    {
+      "epoch": 3.6253776435045317,
+      "grad_norm": 0.0002853251644410193,
+      "learning_rate": 2.0795165699486837e-06,
+      "loss": 0.0019,
+      "step": 42000
+    },
+    {
+      "epoch": 3.6253776435045317,
+      "eval_cosine_accuracy@1": 0.6910063870188158,
+      "eval_cosine_accuracy@10": 0.9742793026065941,
+      "eval_cosine_accuracy@3": 0.9109269808389435,
+      "eval_cosine_accuracy@5": 0.9461418953909891,
+      "eval_cosine_map@100": 0.8061197699360279,
+      "eval_cosine_mrr@10": 0.804833419644399,
+      "eval_cosine_ndcg@10": 0.8471731447814336,
+      "eval_cosine_precision@1": 0.6910063870188158,
+      "eval_cosine_precision@10": 0.09742793026065939,
+      "eval_cosine_precision@3": 0.30364232694631454,
+      "eval_cosine_precision@5": 0.18922837907819778,
+      "eval_cosine_recall@1": 0.6910063870188158,
+      "eval_cosine_recall@10": 0.9742793026065941,
+      "eval_cosine_recall@3": 0.9109269808389435,
+      "eval_cosine_recall@5": 0.9461418953909891,
+      "eval_runtime": 467.6854,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "step": 42000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 46340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8adee61c42569acda3b6148ffcf73faf677af58c325f10f3d4798bf52f61a30e
+size 5624