README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:26299
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-m-v1.5
widget:
  - source_sentence: >-
      What are the conditions that must be met for the appointment of a
      depositary established in a third country for non-EU AIFs?
    sentences:
      - >-
        (a)


        for EU AIFs, in the home Member State of the AIF;


        (b)


        for non-EU AIFs, in the third country where the AIF is established or in
        the home Member State of the AIFM managing the AIF or in the Member
        State of reference of the AIFM managing the AIF.


        6.


        Without prejudice to the requirements set out in paragraph 3, the
        appointment of a depositary established in a third country shall, at all
        times, be subject to the following conditions:


        (a)
      - >-
        (c)


        the financial soundness of the proposed acquirer, in particular in
        relation to the type of business pursued and envisaged in the investment
        firm in which the acquisition is proposed;


        (d)


        whether the investment firm will be able to comply and continue to
        comply with the prudential requirements based on this Directive and,
        where applicable, other Directives, in particular Directives 2002/87/EC
        and 2013/36/EU, in particular, whether the group of which it will become
        a part has a structure that makes it possible to exercise effective
        supervision, effectively exchange information among the competent
        authorities and determine the allocation of responsibilities among the
        competent authorities;


        (e)
      - >-
        (f)


        the undertaking shall describe the expected decarbonisation levers and
        their overall quantitative contributions to achieve the GHG emission
        reduction targets (e.g., energy or material efficiency and consumption
        reduction, fuel switching, use of renewable energy , phase out or
        substitution of product and process).


        Disclosure Requirement E1-5 – Energy consumption and mix


        The undertaking shall provide information on its energy consumption and
        mix.


        The objective of this Disclosure Requirement is to provide an
        understanding of the undertaking’s total energy consumption in absolute
        value, improvement in energy efficiency, exposure to coal, oil and
        gas-related activities, and the share of renewable energy in its overall
        energy mix.
  - source_sentence: >-
      What factors should be considered when assessing the risk of human rights
      being affected in a specific case?
    sentences:
      - >-
        of eligible new assets as referred to in the instructions corresponding
        to column (h) of Template 7. The denominator of the KPI shall be the
        gross carrying amount of new covered assets from those assets, as
        referred to in the instructions corresponding to column (a) of Template
        7. x | Of which: specialised lending Institutions shall disclose the
        proportion of new assets (i.e. assets originated within the current
        disclosure period) categorised as specialised lending funding
        environmentally sustainable activities for the objective of climate
        change adaptation in total new eligible assets (i.e. assets originated
        within the current disclosure period) funding environmentally
        sustainable activities. New eligible assets shall be calculated net of
      - >-
        the risk that such human right may be affected, taking into account the
        circumstances of the specific case, including the nature and extent of
        the company’s business operations and its chain of activities, the
        characteristics of the economic sector and the geographical and
        operational context; ---|--- (d) | ‘adverse impact’ means an adverse
        environmental impact or adverse human rights impact; ---|--- (e) |
        ‘subsidiary’ means a legal person, as defined in Article 2, point (10),
        of Directive 2013/34/EU, and a legal person through which the activity
        of a controlled undertaking, as defined in Article 2(1), point (f), of
        Directive 2004/109/EC of the European Parliament and of the Council
        (46), is exercised; ---|--- (f) | ‘business partner’
      - >-
        (f)


        the undertaking shall describe the expected decarbonisation levers and
        their overall quantitative contributions to achieve the GHG emission
        reduction targets (e.g., energy or material efficiency and consumption
        reduction, fuel switching, use of renewable energy , phase out or
        substitution of product and process).


        Disclosure Requirement E1-5 – Energy consumption and mix


        The undertaking shall provide information on its energy consumption and
        mix.


        The objective of this Disclosure Requirement is to provide an
        understanding of the undertaking’s total energy consumption in absolute
        value, improvement in energy efficiency, exposure to coal, oil and
        gas-related activities, and the share of renewable energy in its overall
        energy mix.
  - source_sentence: >-
      Can you list the different types of fluorescent lamps referenced,
      including any specific categories of high intensity discharge lamps?
    sentences:
      - >-
        and other products or equipment for the purpose of recording or
        reproducing sound or images, including signals or other technologies for
        the distribution of sound and image than by telecommunications


        Photovoltaic panels


        5. LIGHTING EQUIPMENT


        Luminaires for fluorescent lamps with the exception of luminaires in
        households


        Straight fluorescent lamps


        Compact fluorescent lamps


        High intensity discharge lamps, including pressure sodium lamps and
        metal halide lamps


        Low pressure sodium lamps


        Other lighting or equipment for the purpose of spreading or controlling
        light with the exception of filament bulbs


        6. ELECTRICAL AND ELECTRONIC TOOLS (WITH THE EXCEPTION OF LARGE-SCALE
        STATIONARY INDUSTRIAL TOOLS)


        Drills


        Saws


        Sewing machines
      - >-
        the principle of recovery of the costs of water use in accordance with
        Article 9; ---|--- 7.3. | a summary of the measures taken to meet the
        requirements of Article 7; ---|--- 7.4. | a summary of the controls on
        abstraction and impoundment of water, including reference to the
        registers and identifications of the cases where exemptions have been
        made under Article 11(3)(e); ---|--- 7.5. | a summary of the controls
        adopted for point source discharges and other activities with an impact
        on the status of water in accordance with the provisions of Article
        11(3)(g) and 11(3)(i); ---|--- 7.6. | an identification of the cases
        where direct discharges to groundwater have been authorised in
        accordance with the provisions of Article 11(3)(j); ---|---
      - >-
        (158) Member States should have the right to take into account the
        recycling of metals separated after incineration of waste in proportion
        to the share of the packaging waste incinerated, provided that the
        recycled metals meet certain quality criteria laid down in Commission
        Implementing Decision (EU) 2019/1004 (41).


        (159) In the case of exports of packaging waste from the Union for
        recycling, Regulation (EC) No 1013/2006 of the European Parliament and
        of the Council (42) and Regulation (EU) 2024/1157 of the European
        Parliament and of the Council (43) apply.
  - source_sentence: >-
      What are the requirements for cooperation between competent authorities in
      Member States regarding the supervision of financial institutions and
      other entities as outlined in the provided text?
    sentences:
      - >-
        AR 9. In Phase 3, to assesses its material risks and opportunities based
        on the results of Phases 1 and 2, the undertaking may consider the
        following categories:


        (a)


        physical risks :


        i.


        acute risks (e.g., natural disasters exacerbated by loss of coastal
        protection from ecosystems , leading to costs of storm damage to coastal
        infrastructure, disease or pests affecting the species or variety of
        crop the undertaking relies on, especially in the case of no or low
        genetic diversity, species loss and ecosystem degradation ); and


        ii.
      - >-
        necessary to demonstrate the conformity of packaging in one or more
        languages which can be easily understood by that authority; ---|--- (d)
        | upon a request from a competent national authority, make available
        relevant documents within 10 days of the receipt of such a request;
        ---|--- (e) | terminate the mandate if the manufacturer acts contrary to
        its obligations under this Regulation. ---|---
      - >-
        Each Member State shall require that such cooperation also take place
        between the competent authorities for the purposes of this Directive or
        of Regulation (EU) No 600/2014 and the competent authorities responsible
        in that Member State for the supervision of credit and other financial
        institutions, pension funds, UCITS, insurance and reinsurance
        intermediaries and insurance undertakings.


        Member States shall require that competent authorities exchange any
        information which is essential or relevant to the exercise of their
        functions and duties.


        Article 69


        Supervisory powers


        1.
  - source_sentence: >-
      What types of substances or mixtures should be listed in relation to their
      potential to react and create hazardous situations, and what additional
      information is required to manage the associated risks?
    sentences:
      - >-
        The undertaking shall specify as part of the contextual information,
        whether the targets that it has set and presented are mandatory
        (required by legislation) or voluntary.


        Disclosure Requirement E2-4 – Pollution of air, water and soil


        The undertaking shall disclose the pollutants that it emits through its
        own operations, as well as the microplastics it generates or uses.


        The objective of this Disclosure Requirement is to provide an
        understanding of the emissions that the undertaking generates to air,
        water and soil in its own operations, and of its generation and use of
        microplastics.


        The undertaking shall disclose the amounts of:


        (a)
      - >-
        Families of substances or mixtures or specific substances, such as
        water, air, acids, bases, oxidising agents, with which the substance or
        mixture could react to produce a hazardous situation (like an explosion,
        a release of toxic or flammable materials, or a liberation of excessive
        heat), shall be listed and if appropriate a brief description of
        measures to be taken to manage risks associated with such hazards shall
        be given.


        10.6. Hazardous decomposition products


        Known and reasonably anticipated hazardous decomposition products
        produced as a result of use, storage, spill and heating shall be listed.
        Hazardous combustion products shall be included in section 5 of the
        safety data sheet.


        11. SECTION 11: Toxicological information
      - >-
        4. In order for a district heating and cooling system to qualify as
        efficient, Member States shall ensure that where it is built or its
        supply units are substantially refurbished, the district heating or
        cooling system meet the criteria set out in paragraph 1 or 2 applicable
        at the time when it starts or continues its operation after the
        refurbishment. In addition, Member States shall ensure that when a
        district heating and cooling system is built or its supply units are
        substantially refurbished:
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.7467552067612436
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8988831874434048
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9305765167521883
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9604587986718985
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7467552067612436
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29962772914780156
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1861153033504377
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09604587986718985
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7467552067612436
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8988831874434048
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9305765167521883
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9604587986718985
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8608067216595782
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8280703960827729
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.829841633884875
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.7530938726230003
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9079384243887715
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9402354361605796
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9680048294597042
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7530938726230003
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30264614146292385
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1880470872321159
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09680048294597042
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7530938726230003
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9079384243887715
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9402354361605796
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9680048294597042
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8682167825620759
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.835408970913047
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8367990198438501
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.8397223060670087
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.955629338967703
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9746453365529731
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9897373981285844
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8397223060670087
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3185431129892343
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19492906731059462
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09897373981285845
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8397223060670087
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.955629338967703
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9746453365529731
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9897373981285844
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9225924304434711
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.900205659283534
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9007567489649001
            name: Cosine Map@100

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

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-m-v1.5. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Snowflake/snowflake-arctic-embed-m-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

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

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'What types of substances or mixtures should be listed in relation to their potential to react and create hazardous situations, and what additional information is required to manage the associated risks?',
    'Families of substances or mixtures or specific substances, such as water, air, acids, bases, oxidising agents, with which the substance or mixture could react to produce a hazardous situation (like an explosion, a release of toxic or flammable materials, or a liberation of excessive heat), shall be listed and if appropriate a brief description of measures to be taken to manage risks associated with such hazards shall be given.\n\n10.6. Hazardous decomposition products\n\nKnown and reasonably anticipated hazardous decomposition products produced as a result of use, storage, spill and heating shall be listed. Hazardous combustion products shall be included in section 5 of the safety data sheet.\n\n11. SECTION 11: Toxicological information',
    'The undertaking shall specify as part of the contextual information, whether the targets that it has set and presented are mandatory (required by legislation) or voluntary.\n\nDisclosure Requirement E2-4 – Pollution of air, water and soil\n\nThe undertaking shall disclose the pollutants that it emits through its own operations, as well as the microplastics it generates or uses.\n\nThe objective of this Disclosure Requirement is to provide an understanding of the emissions that the undertaking generates to air, water and soil in its own operations, and of its generation and use of microplastics.\n\nThe undertaking shall disclose the amounts of:\n\n(a)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7468
cosine_accuracy@3	0.8989
cosine_accuracy@5	0.9306
cosine_accuracy@10	0.9605
cosine_precision@1	0.7468
cosine_precision@3	0.2996
cosine_precision@5	0.1861
cosine_precision@10	0.096
cosine_recall@1	0.7468
cosine_recall@3	0.8989
cosine_recall@5	0.9306
cosine_recall@10	0.9605
cosine_ndcg@10	0.8608
cosine_mrr@10	0.8281
cosine_map@100	0.8298

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7531
cosine_accuracy@3	0.9079
cosine_accuracy@5	0.9402
cosine_accuracy@10	0.968
cosine_precision@1	0.7531
cosine_precision@3	0.3026
cosine_precision@5	0.188
cosine_precision@10	0.0968
cosine_recall@1	0.7531
cosine_recall@3	0.9079
cosine_recall@5	0.9402
cosine_recall@10	0.968
cosine_ndcg@10	0.8682
cosine_mrr@10	0.8354
cosine_map@100	0.8368

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8397
cosine_accuracy@3	0.9556
cosine_accuracy@5	0.9746
cosine_accuracy@10	0.9897
cosine_precision@1	0.8397
cosine_precision@3	0.3185
cosine_precision@5	0.1949
cosine_precision@10	0.099
cosine_recall@1	0.8397
cosine_recall@3	0.9556
cosine_recall@5	0.9746
cosine_recall@10	0.9897
cosine_ndcg@10	0.9226
cosine_mrr@10	0.9002
cosine_map@100	0.9008

Training Details

Training Dataset

Unnamed Dataset

• Size: 26,299 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 16 tokens mean: 38.67 tokens max: 215 tokens	min: 5 tokens mean: 251.42 tokens max: 512 tokens

• Samples:

  sentence_0	sentence_1
  What are the key considerations the Commission must evaluate when assessing the feasibility of including municipal waste incineration installations in the EU ETS by 31 July 2026?	By 31 July 2026, the Commission shall present a report to the European Parliament and to the Council in which it shall assess the feasibility of including municipal waste incineration installations in the EU ETS, including with a view to their inclusion from 2028 and with an assessment of the potential need for an option for a Member State to opt out until 31 December 2030. In that regard, the Commission shall take into account the importance of all sectors contributing to emission reductions and potential diversion of waste towards disposal by landfilling in the Union and waste exports to third countries. The Commission shall in addition take into account relevant criteria such as the effects on the internal market, potential distortions
  What are the conditions under which a registrant can withhold certain information from disclosure, and what steps must they take to justify this decision?	NOTES Note 1: If it is not technically possible, or if it does not appear scientifically necessary to give information, the reasons shall be clearly stated, in accordance with the relevant provisions. Note 2: The registrant may wish to declare that certain information submitted in the registration dossier is commercially sensitive and its disclosure might harm him commercially. If this is the case, he shall list the items and provide a justification. ▼C1 INFORMATION REFERRED TO IN ARTICLE 10(a) (i) TO (v) 1. GENERAL REGISTRANT INFORMATION 1.1. Registrant ▼M70 1.1.1. Name, address, telephone number and email address ▼C1 1.1.2. Contact person 1.1.3. Location of the registrant's production and own use site(s), as appropriate ▼M70
  What are the specific color indices and chemical identifiers for Pigment Red 112 and Pigment Yellow 14, and what is their respective concentration percentage?	17 (PR17)/CI 12390 229-681-4 6655-84-1 0,1 % Pigment Red 112 (PR112)/CI 12370 229-440-3 6535-46-2 0,1 % Pigment Yellow 14 (PY14)/CI 21095 226-789-3 5468-75-7 0,1 % Pigment Yellow 55 (PY55)/CI 21096 226-789-3 6358-37-8 0,1 % Pigment Red 2 (PR2)/CI 12310 227-930-1 6041-94-7 0,1 % Pigment Red 22 (PR22)/CI 12315 229-245-3 6448-95-9 0,1 % Pigment Red 146 (PR146)/CI 12485 226-103-2 5280-68-2 0,1 % Pigment Red 269 (PR269)/CI 12466 268-028-8 67990-05-0 0,1 % Pigment Orange16 (PO16)/CI 21160 229-388-1 6505-28-8 0,1 % Pigment Yellow 1 (PY1)/CI 11680 219-730-8 2512-29-0 0,1 % Pigment Yellow 12 (PY12)/CI 21090 228-787-8 6358-85-6 0,1 % Pigment Yellow 87 (PY87)/CI 21107:1 239-160-3 15110-84-6, 14110-84-6 0,1 % Pigment Yellow 97 (PY97)/CI 11767

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 6
• per_device_eval_batch_size: 6
• num_train_epochs: 4
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 6
• per_device_eval_batch_size: 6
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 4
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss	cosine_ndcg@10
0.0228	100	-	0.6723
0.0456	200	-	0.7870
0.0684	300	-	0.8397
0.0912	400	-	0.8608
0.1141	500	0.4135	-
0.0228	100	-	0.8669
0.0456	200	-	0.8682
0.0228	100	-	0.8699
0.0456	200	-	0.8733
0.0684	300	-	0.8759
0.0912	400	-	0.8802
0.1141	500	0.1122	0.8823
0.1369	600	-	0.8847
0.1597	700	-	0.8835
0.1825	800	-	0.8862
0.2053	900	-	0.8864
0.2281	1000	0.1299	0.8860
0.2509	1100	-	0.8837
0.2737	1200	-	0.8861
0.2965	1300	-	0.8882
0.3193	1400	-	0.8850
0.3422	1500	0.123	0.8916
0.3650	1600	-	0.8866
0.3878	1700	-	0.8917
0.4106	1800	-	0.8918
0.4334	1900	-	0.8904
0.4562	2000	0.0769	0.8896
0.4790	2100	-	0.8876
0.5018	2200	-	0.8956
0.5246	2300	-	0.8964
0.5474	2400	-	0.8901
0.5703	2500	0.0697	0.8888
0.5931	2600	-	0.8872
0.6159	2700	-	0.8839
0.6387	2800	-	0.8891
0.6615	2900	-	0.8890
0.6843	3000	0.0537	0.8867
0.7071	3100	-	0.8907
0.7299	3200	-	0.8916
0.7527	3300	-	0.8933
0.7755	3400	-	0.8933
0.7984	3500	0.0772	0.8924
0.8212	3600	-	0.8946
0.8440	3700	-	0.8953
0.8668	3800	-	0.8941
0.8896	3900	-	0.8939
0.9124	4000	0.065	0.8953
0.9352	4100	-	0.8969
0.9580	4200	-	0.8993
0.9808	4300	-	0.9020
1.0	4384	-	0.9040
1.0036	4400	-	0.9044
1.0265	4500	0.0329	0.9015
1.0493	4600	-	0.8999
1.0721	4700	-	0.9005
1.0949	4800	-	0.8976
1.1177	4900	-	0.9001
1.1405	5000	0.024	0.9014
1.1633	5100	-	0.8995
1.1861	5200	-	0.9022
1.2089	5300	-	0.9030
1.2318	5400	-	0.9027
1.2546	5500	0.016	0.9024
1.2774	5600	-	0.9012
1.3002	5700	-	0.9011
1.3230	5800	-	0.9049
1.3458	5900	-	0.9094
1.3686	6000	0.0553	0.9094
1.3914	6100	-	0.9028
1.4142	6200	-	0.9113
1.4370	6300	-	0.9118
1.4599	6400	-	0.9139
1.4827	6500	0.0416	0.9112
1.5055	6600	-	0.9102
1.5283	6700	-	0.9092
1.5511	6800	-	0.9098
1.5739	6900	-	0.9101
1.5967	7000	0.0283	0.9107
1.6195	7100	-	0.9114
1.6423	7200	-	0.9131
1.6651	7300	-	0.9130
1.6880	7400	-	0.9144
1.7108	7500	0.0268	0.9126
1.7336	7600	-	0.9119
1.7564	7700	-	0.9125
1.7792	7800	-	0.9111
1.8020	7900	-	0.9100
1.8248	8000	0.0252	0.9110
1.8476	8100	-	0.9151
1.8704	8200	-	0.9123
1.8932	8300	-	0.9118
1.9161	8400	-	0.9103
1.9389	8500	0.0288	0.9110
1.9617	8600	-	0.9106
1.9845	8700	-	0.9109
2.0	8768	-	0.9126
2.0073	8800	-	0.9117
2.0301	8900	-	0.9114
2.0529	9000	0.0232	0.9123
2.0757	9100	-	0.9113
2.0985	9200	-	0.9095
2.1214	9300	-	0.9086
2.1442	9400	-	0.9109
2.1670	9500	0.0188	0.9124
2.1898	9600	-	0.9125
2.2126	9700	-	0.9121
2.2354	9800	-	0.9122
2.2582	9900	-	0.9132
2.2810	10000	0.0182	0.9125
2.3038	10100	-	0.9142
2.3266	10200	-	0.9135
2.3495	10300	-	0.9084
2.3723	10400	-	0.9147
2.3951	10500	0.0111	0.9170
2.4179	10600	-	0.9142
2.4407	10700	-	0.9158
2.4635	10800	-	0.9174
2.4863	10900	-	0.9176
2.5091	11000	0.0153	0.9166
2.5319	11100	-	0.9172
2.5547	11200	-	0.9171
2.5776	11300	-	0.9168
2.6004	11400	-	0.9176
2.6232	11500	0.0241	0.9170
2.6460	11600	-	0.9177
2.6688	11700	-	0.9184
2.6916	11800	-	0.9196
2.7144	11900	-	0.9211
2.7372	12000	0.0172	0.9209
2.7600	12100	-	0.9212
2.7828	12200	-	0.9201
2.8057	12300	-	0.9194
2.8285	12400	-	0.9205
2.8513	12500	0.013	0.9202
2.8741	12600	-	0.9213
2.8969	12700	-	0.9210
2.9197	12800	-	0.9203
2.9425	12900	-	0.9200
2.9653	13000	0.03	0.9209
2.9881	13100	-	0.9212
3.0	13152	-	0.9200
3.0109	13200	-	0.9198
3.0338	13300	-	0.9192
3.0566	13400	-	0.9183
3.0794	13500	0.0133	0.9170
3.1022	13600	-	0.9181
3.125	13700	-	0.9180
3.1478	13800	-	0.9176
3.1706	13900	-	0.9168
3.1934	14000	0.0185	0.9175
3.2162	14100	-	0.9188
3.2391	14200	-	0.9182
3.2619	14300	-	0.9192
3.2847	14400	-	0.9199
3.3075	14500	0.0135	0.9195
3.3303	14600	-	0.9190
3.3531	14700	-	0.9187
3.3759	14800	-	0.9196
3.3987	14900	-	0.9202
3.4215	15000	0.0157	0.9214
3.4443	15100	-	0.9211
3.4672	15200	-	0.9211
3.4900	15300	-	0.9208
3.5128	15400	-	0.9195
3.5356	15500	0.015	0.9207
3.5584	15600	-	0.9210
3.5812	15700	-	0.9226

Framework Versions

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

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

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

MultipleNegativesRankingLoss

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