DrishtiSharma's picture
Add new SentenceTransformer model.
73b4039 verified
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:22291
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-small-en
widget:
  - source_sentence: >-
      What rights and obligations does an Authorised Person have if a storage
      facility holding Accepted Spot Commodities becomes insolvent?
    sentences:
      - "MTF (using Virtual Assets): using third-party issued fiat tokens as a payment/transaction mechanism:\n\ni.\tIn the context of using third party fiat tokens, the Authorised Person must directly meet the requirements of the Accepted Virtual Assets, Technology Governance and AML/CFT sections of this Guidance.\n\nii.\tFor the related fiat currency custody activities, FSRA preference is to have the MTF utilise a Virtual Asset/Fiat Custodian authorised on the basis of paragraphs 139 - 145 or 166(b) above.\n\niii.\tIn relation to the issuance of the related fiat token, in circumstances where the issuer is not authorised under paragraph 166(a) above, it is expected that the Authorised Person undertake the same due diligence as that it would apply for the purposes of determining Accepted Virtual Assets (focusing on Technology Governance requirements, the seven factors used to determine an Accepted Virtual Asset, and requirements relating to reporting and reconciliation).\n"
      - >
        Valuation adjustments. The Regulator expects the following valuation
        adjustments to be formally considered at a minimum: unearned credit
        spreads, close out costs, Operational Risks, early termination,
        investing and funding costs, and future administrative costs and, where
        appropriate, model risk.
      - "Storage Facilities. An Authorised Person must have arrangements in place for the approval, management, monitoring and control for Accepted Spot Commodities and the storage facilities operated by itself or by third parties, including in relation to:\n(a)\tsecurity arrangements;\n(b)\tperiodic stock reports;\n(c)\tperiodic inventory audits;\n(d)\tdispute resolution procedures where the storage facility materially fails to meet any of its obligations to the title holder;\n(e)\tstorage or other fees; and\n(f)\trights and obligations in the event of storage facility insolvency, as per the rules, terms, conditions and other obligations of the Authorised Person."
  - source_sentence: >-
      Regarding GEN Rule 3.3, can you provide examples of what constitutes
      effective and responsible management of an Authorised Person's affairs in
      the context of Virtual Assets?
    sentences:
      - >
        REGULATORY REQUIREMENTS - SPOT COMMODITY ACTIVITIES

        Custody

        Due to their psychical nature, Spot Commodities may require specialist
        Custody arrangements, with the holding of Accepted Spot Commodities
        introducing additional operational risks.  For example, the safekeeping
        of gold bullion would require a custodian with appropriate secure vault
        facilities.
      - "Measurement of E for pre settlement Counterparty Exposures arising from SFTs. An Authorised Person must determine E, for a pre settlement Counterparty Exposure arising from an SFT which is not covered by a qualifying cross product Netting agreement as follows:\n(a)\tin the case where the Authorised Person has lent Securities to a Counterparty or sold Securities to a Counterparty with a commitment to repurchase those Securities at a specified price on a specified future date, the latest fair value of the Securities lent or sold; and\n(b)\tin the case where the Authorised Person has lent cash to a Counterparty through the borrowing of Securities from the Counterparty or paid cash for the purchase of Securities from a Counterparty with a commitment to resell those Securities at a specified price on a specified future date, the amount of cash lent or paid."
      - "The base figure for the size factor component is determined by aggregating the following components, for the Long Term Insurance Fund:\n(a)\tthe default risk components determined in accordance with Rule ‎A8.4;\n(b)\tthe investment volatility risk component determined in accordance with Rule ‎A8.5; and\n(c)\tthe concentration risk component determined in accordance with Rule ‎A8.8."
  - source_sentence: >-
      In the case of non-compliance with Part 17 of FSMR, what are the typical
      steps or actions the ADGM might take against an authorised firm?
    sentences:
      - >
        The Regulatory Authority shall, within thirty (30) days of the date of
        the notification mentioned in subparagraph (2), notify the Account
        Holder or the Controlling Person of the violation, the amount of the
        fine and the payment request of the fine within no later than thirty
        (30) days from receipt of the notice.
      - "When employing an eKYC System to assist with CDD, a Relevant Person should:\na.\tensure that it has a thorough understanding of the eKYC System itself and the risks of eKYC, including those outlined by relevant guidance from FATF and other international standard setting bodies;\nb.\tcomply with all the Rules of the Regulator relevant to eKYC including, but not limited to, applicable requirements regarding the business risk assessment, as per Rule ‎6.1, and outsourcing, as per Rule ‎9.3;\nc.\tcombine eKYC with transaction monitoring, anti-fraud and cyber-security measures to support a wider framework preventing applicable Financial Crime; and\nd.\ttake appropriate steps to identify, assess and mitigate the risk of the eKYC system being misused for the purposes of Financial Crime."
      - >-
        This Chapter deals with the regulatory requirements arising out of the
        need for Authorised Persons to carry out a self assessment of their risk
        which can be reviewed and assessed by the Regulator. This Chapter
        details the Rules stipulating the need to complete internal risk
        assessments by Authorised Persons in defined frequencies and the
        Regulator's role in reviewing the results of such assessments. In the
        case of Authorised Persons facing financial risks, the requirements in
        this Chapter mandate completion of an Internal Capital Adequacy
        Assessment Process. The Regulator will review the results of such
        internal risk assessments. This Chapter also sets out how the Regulator
        may impose an additional Capital Requirement on a firm specific basis in
        addition to the minimum requirement specified in Chapter 3 of these
        Rules to address higher-than-normal risk.
  - source_sentence: >-
      In terms of basis risk, are there any preferred methods or models that the
      ADGM recommends for assessing the impact of divergences in market rates,
      such as the prime rate versus deposit and benchmark rates?
    sentences:
      - "In performing its functions and exercising its powers, the Regulator shall pursue the following objectives—\n(a)\tto foster and maintain fairness, transparency and efficiency in the Abu Dhabi Global Market;\n(b)\tto foster and maintain confidence in the Abu Dhabi Global Market;\n(c)\tto ensure that the financial markets in the Abu Dhabi Global Market are supported by safe and efficient infrastructure;\n(d)\tto foster and maintain financial stability in the Abu Dhabi Global Market, including the reduction of systemic risk;\n(e)\tto promote and enhance the integrity of the Abu Dhabi Global Market Financial System;\n(f)\tto prevent, detect and restrain conduct that causes or may cause damage to the reputation of the Abu Dhabi Global Market through appropriate means including the imposition of sanctions;\n(g)\tto secure an appropriate degree of protection for direct and indirect users, and prospective users of the Abu Dhabi Global Market;\n(h)\tto promote public understanding of the regulation of the Abu Dhabi Global Market;\n(i)\tto further the interests of the Abu Dhabi Global Market;\n(j)\tto promote the safety and soundness of Authorised Persons and Recognised Bodies; and\n(k)\tto pursue any other objectives as the Board may set."
      - >-
        Two-year validity period. During the two-year validity period, the
        Regulator will engage with and support the FinTech Participant and
        ensure the FinTech Participant operates within the parameters as set and
        agreed to prior to the grant of the FSP.
      - "Without limiting compliance with Rules ‎6.1.1 and ‎6.1.2, prior to launching any new product, service, or business practice, or using a new or developing technology, a Relevant Person must take reasonable steps to ensure that it has:\n(a)\tassessed and identified the money laundering risks relating to the product, service, business practice or technology; and\n(b)\ttaken appropriate steps to mitigate or eliminate the risks identified under (a)."
  - source_sentence: >-
      How should an Authorised Person document and justify any deviations when
      mapping activities into business lines for Operational Risk capital
      purposes, particularly when they differ from regulatory capital
      calculations in other risk categories?
    sentences:
      - "For the purposes of ‎8.1.2(1), in determining when it is appropriate to apply CDD measures in relation to existing customers, a Relevant Person must take into account, amongst other things:\n(a)\tany indication that the identity of the customer, or the customer’s Beneficial Owners, has changed;\n(b)\tany Transactions that are not reasonably consistent with the Relevant Person’s knowledge of the customer;\n(c)\tany change in the purpose or intended nature of the Relevant Person’s relationship with the customer; or\n(d)\tany other matter that might affect the Relevant Person’s risk assessment of the customer."
      - >-
        Principles for business line mapping. The mapping of activities into
        business lines for Operational Risk capital purposes should be
        consistent with the definitions of business lines used for regulatory
        capital calculations in other risk categories, i.e. credit and Market
        Risk. Any deviations from this principle should be clearly motivated and
        documented.
      - >
        REGULATORY REQUIREMENTS FOR AUTHORISED PERSONS ENGAGED IN REGULATED
        ACTIVITIES IN RELATION TO VIRTUAL ASSETS

        Planned and Unplanned system outages

        Authorised Persons should have a programme of planned systems outages to
        provide for adequate opportunities to perform updates and testing.
        Authorised Persons should also have multiple communication channels to
        ensure that its Clients are informed, ahead of time, of any outages
        which may affect them.
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
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
model-index:
  - name: SentenceTransformer based on BAAI/bge-small-en
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.6255380200860832
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7517934002869441
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.793400286944046
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8368005738880918
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6255380200860832
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26410808225729315
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1703012912482066
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09314921090387374
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5488103778096605
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.670468675274988
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7117168818747011
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7628347680535629
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.6800021713111875
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6975649609437263
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6393436933673565
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.6255380200860832
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7517934002869441
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.793400286944046
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8368005738880918
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6255380200860832
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26410808225729315
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1703012912482066
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09314921090387374
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5488103778096605
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.670468675274988
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.7117168818747011
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7628347680535629
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6800021713111875
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6975649609437263
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6393436933673565
            name: Dot Map@100

SentenceTransformer based on BAAI/bge-small-en

This is a sentence-transformers model finetuned from BAAI/bge-small-en. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

  • Model Type: Sentence Transformer
  • Base model: BAAI/bge-small-en
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 384 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("DrishtiSharma/bge-small-en-obliqa-5-epochs")
# Run inference
sentences = [
    'How should an Authorised Person document and justify any deviations when mapping activities into business lines for Operational Risk capital purposes, particularly when they differ from regulatory capital calculations in other risk categories?',
    'Principles for business line mapping. The mapping of activities into business lines for Operational Risk capital purposes should be consistent with the definitions of business lines used for regulatory capital calculations in other risk categories, i.e. credit and Market Risk. Any deviations from this principle should be clearly motivated and documented.',
    'REGULATORY REQUIREMENTS FOR AUTHORISED PERSONS ENGAGED IN REGULATED ACTIVITIES IN RELATION TO VIRTUAL ASSETS\nPlanned and Unplanned system outages\nAuthorised Persons should have a programme of planned systems outages to provide for adequate opportunities to perform updates and testing. Authorised Persons should also have multiple communication channels to ensure that its Clients are informed, ahead of time, of any outages which may affect them.\n',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Information Retrieval

Metric Value
cosine_accuracy@1 0.6255
cosine_accuracy@3 0.7518
cosine_accuracy@5 0.7934
cosine_accuracy@10 0.8368
cosine_precision@1 0.6255
cosine_precision@3 0.2641
cosine_precision@5 0.1703
cosine_precision@10 0.0931
cosine_recall@1 0.5488
cosine_recall@3 0.6705
cosine_recall@5 0.7117
cosine_recall@10 0.7628
cosine_ndcg@10 0.68
cosine_mrr@10 0.6976
cosine_map@100 0.6393
dot_accuracy@1 0.6255
dot_accuracy@3 0.7518
dot_accuracy@5 0.7934
dot_accuracy@10 0.8368
dot_precision@1 0.6255
dot_precision@3 0.2641
dot_precision@5 0.1703
dot_precision@10 0.0931
dot_recall@1 0.5488
dot_recall@3 0.6705
dot_recall@5 0.7117
dot_recall@10 0.7628
dot_ndcg@10 0.68
dot_mrr@10 0.6976
dot_map@100 0.6393

Training Details

Training Dataset

Unnamed Dataset

  • Size: 22,291 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: 14 tokens
    • mean: 34.77 tokens
    • max: 68 tokens
    • min: 12 tokens
    • mean: 113.08 tokens
    • max: 369 tokens
  • Samples:
    sentence_0 sentence_1
    Could you outline the process for obtaining an ADGM Green Fund Designation or an ADGM Climate Transition Fund Designation, and what are the ongoing compliance obligations associated with these designations? AUTHORISED PERSONS CONDUCTING A REGULATED ACTIVITY IN RELATION TO VIRTUAL ASSETS – EXTENSION INTO TO DIGITAL SECURITIES ACTIVITIES
    MTFs using Virtual Assets – Becoming a Digital Securities RIE
    Migration of a Virtual Assets MTF to a RIE is more complex than the extension of a Virtual Assets MTF into Digital Securities (as dealt with in paragraphs 63 - 67 above). This is due to a number of factors, including that a RIE is required to meet the full suite of requirements in Chapters 2 and 3 of MIR, and the primary market considerations associated with operating a RIE (e.g., requirement for Approved Prospectuses, admission to the Official List of Securities, and the ongoing technical/operational and regulatory requirements related to Digital Securities being admitted to trading and admitted to the Official List).
    Can the ADGM provide examples of effective internal risk control and reporting mechanisms that ensure an accurate assessment of a Reporting Entity's financial position and prospects, as per Rule 9.2.8? Risk control. Authorised Persons should recognise and control the Credit Risk arising from their new products and services. Well in advance of entering into business transactions involving new types of products and activities, they should ensure that they understand the risks fully and have established appropriate Credit Risk policies, procedures and controls, which should be approved by the Governing Body or its appropriate delegated committee. A formal risk assessment of new products and activities should also be performed and documented.
    What are the specific criteria used by the FSRA to determine whether a company's ESG disclosures align with a globally recognized standard? The Regulator may refuse to grant an application for an ADGM Green Bond Designation or an ADGM Sustainability-Linked Bond Designation if it is not satisfied that the requirements of this section have been met or will be met on an ongoing basis.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 10
  • per_device_eval_batch_size: 10
  • num_train_epochs: 5
  • 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: 10
  • per_device_eval_batch_size: 10
  • 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: 5
  • 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: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • dispatch_batches: None
  • split_batches: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • eval_use_gather_object: False
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step Training Loss cosine_map@100
0.0897 200 - 0.5994
0.1794 400 - 0.6027
0.2242 500 0.925 -
0.2691 600 - 0.6053
0.3587 800 - 0.6123
0.4484 1000 0.5995 0.5981
0.5381 1200 - 0.6230
0.6278 1400 - 0.6236
0.6726 1500 0.5963 -
0.7175 1600 - 0.6082
0.8072 1800 - 0.6192
0.8969 2000 0.5078 0.6128
0.9865 2200 - 0.6159
1.0 2230 - 0.6235
1.0762 2400 - 0.6232
1.1211 2500 0.4599 -
1.1659 2600 - 0.6122
1.2556 2800 - 0.6242
1.3453 3000 0.4054 0.6246
1.4350 3200 - 0.6364
1.5247 3400 - 0.6260
1.5695 3500 0.4197 -
1.6143 3600 - 0.6230
1.7040 3800 - 0.6324
1.7937 4000 0.3896 0.6384
1.8834 4200 - 0.6346
1.9731 4400 - 0.6279
2.0 4460 - 0.6296
2.0179 4500 0.3875 -
2.0628 4600 - 0.6263
2.1525 4800 - 0.6326
2.2422 5000 0.3117 0.6306
2.3318 5200 - 0.6351
2.4215 5400 - 0.6330
2.4664 5500 0.3327 -
2.5112 5600 - 0.6355
2.6009 5800 - 0.6323
2.6906 6000 0.3017 0.6249
2.7803 6200 - 0.6324
2.8700 6400 - 0.6326
2.9148 6500 0.2971 -
2.9596 6600 - 0.6306
3.0 6690 - 0.6368
3.0493 6800 - 0.6351
3.1390 7000 0.2755 0.6308
3.2287 7200 - 0.6372
3.3184 7400 - 0.6390
3.3632 7500 0.2639 -
3.4081 7600 - 0.6326
3.4978 7800 - 0.6351
3.5874 8000 0.2474 0.6377
3.6771 8200 - 0.6375
3.7668 8400 - 0.6380
3.8117 8500 0.2402 -
3.8565 8600 - 0.6407
3.9462 8800 - 0.6401
4.0 8920 - 0.6433
4.0359 9000 0.2628 0.6452
4.1256 9200 - 0.6432
4.2152 9400 - 0.6426
4.2601 9500 0.2318 -
4.3049 9600 - 0.6404
4.3946 9800 - 0.6390
4.4843 10000 0.2246 0.6389
4.5740 10200 - 0.6394
4.6637 10400 - 0.6388
4.7085 10500 0.2054 -
4.7534 10600 - 0.6396
4.8430 10800 - 0.6389
4.9327 11000 0.2194 0.6394
5.0 11150 - 0.6393

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.1.1
  • Transformers: 4.45.2
  • PyTorch: 2.5.1+cu121
  • Accelerate: 1.2.0.dev0
  • Datasets: 3.1.0
  • Tokenizers: 0.20.3

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",
}

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}
}