metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:46338
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-m-v2.0
widget:
  - source_sentence: >-
      What is the definition of 'Union processing capacity' and how does it
      relate to the location of processing operations for strategic raw
      materials?
    sentences:
      - >-
        (9)


        ‘Union processing capacity’ means an aggregate of the maximum annual
        production volumes of processing operations for strategic raw materials,
        excluding such operations that are typically located at or near the
        extraction site, located in the Union;


        (10)


        ‘recycling’ means recycling as defined in Article 3, point (17), of
        Directive 2008/98/EC;


        (11)


        ‘Union recycling capacity’ means an aggregate of the maximum annual
        production volume of recycling operations for strategic raw materials
        after re- processing, including the sorting and pre-treatment of waste,
        and its processing into secondary raw materials, located in the Union;


        (12)
      - >-
        206-44-0 205-912-4 Fluoranthene (16) 118-74-1 204-273-9
        Hexachlorobenzene X (17) 87-68-3 201-765-5 Hexachlorobutadiene X (18)
        608-73-1 210-168-9 Hexachlorocyclohexane X (19) 34123-59-6 251-835-4
        Isoproturon (20) 7439-92-1 231-100-4 Lead and its compounds (21)
        7439-97-6 231-106-7 Mercury and its compounds X (22) 91-20-3 202-049-5
        Naphthalene (23) 7440-02-0 231-111-4 Nickel and its compounds (24) not
        applicable not applicable Nonylphenols X (5) (25) not applicable not
        applicable Octylphenols (6) (26) 608-93-5 210-172-0 Pentachlorobenzene X
        (27) 87-86-5 201-778-6 Pentachlorophenol (28) not applicable not
        applicable Polyaromatic hydrocarbons (PAH) (7) X (29) 122-34-9 204-535-2
        Simazine (30) not applicable not applicable Tributyltin compounds X
      - >-
        7.


        The principles governing public procurement procedures, including the
        principles of proportionality, non-discrimination, equal treatment,
        transparency and competition, shall be observed as regards all economic
        operators involved in the public procurement procedure. The
        investigation of foreign subsidies pursuant to this Regulation shall not
        result in the contracting authority or the contracting entity treating
        the economic operators concerned in a way that is contrary to those
        principles. Environmental, social and labour requirements shall apply to
        economic operators in accordance with Directives 2014/23/EU, 2014/24/EU
        and 2014/25/EU, or other Union law.


        8.
  - source_sentence: >-
      What types of services are one-stop shops or similar mechanisms expected
      to provide to households and small non-household entities regarding energy
      efficiency?
    sentences:
      - >-
        Low boiling point cat-reformed naphtha; 649-302-00-X 270-687-1
        68476-47-1 P Residues (petroleum), C6-8 catalytic reformer; Low boiling
        point cat-reformed naphtha; [A complex residuum from the catalytic
        reforming of C6-8 feed. It consists of hydrocarbons having carbon
        numbers predominantly in the range of C2 through C6.] 649-303-00-5
        270-794-3 68478-15-9 P Naphtha (petroleum), light catalytic reformed,
        arom.-free; Low boiling point cat-reformed naphtha; [A complex
        combination of hydrocarbons obtained from distillation of products from
        a catalytic reforming process. It consists predominantly of hydrocarbons
        having carbon numbers predominantly in the range of C5 through C8 and
        boiling in the range of approximately 35 °C to 120 °C (95 °F to
      - >-
        The undertaking may disclose by head count or full time equivalent (FTE)
        the following information:


        (a)


        full-time employees , and breakdowns by gender and by region; and


        (b)


        part-time employees, and breakdowns by gender and by region.


        Disclosure Requirement S1-7 – Characteristics of non-employees in the
        undertaking’s own workforce


        The undertaking shall describe key characteristics of non-employees in
        its own workforce.
      - >-
        (a) the creation of one-stop shops or similar mechanisms for the
        provision of technical, administrative and financial advice and
        assistance on energy efficiency, such as energy checks for households,
        energy renovations of buildings, information on the replacement of old
        and inefficient heating systems with modern and more efficient
        appliances and the take-up of renewable energy and energy storage for
        buildings to final customers and final users, especially household and
        small non-household ones, including SMEs and microenterprises; (b)
        cooperation with private actors that provide services such as energy
        audits and energy consumption assessments, financing solutions and
        execution of energy renovations; --- --- (c) the communication of
  - source_sentence: >-
      What procedures must competent authorities follow to verify compliance of
      operators and traders with the specified regulations regarding products
      they place or intend to place on the market?
    sentences:
      - >-
        1.


        The competent authorities shall carry out checks within their territory
        to establish whether operators and traders established in the Union
        comply with this Regulation. The competent authorities shall carry out
        checks within their territory to establish whether the relevant products
        that the operator or trader has placed or intends to place on the
        market, has made available or intends to make available on the market or
        has exported or intends to export comply with this Regulation.


        2.


        The checks referred to in paragraph 1 of this Article shall be carried
        out in accordance with Articles 18 and 19.


        3.
      - >-
        ▼M2 —————


        ▼B


        7.


        Implementing bodies, other than executive agencies, and entities to
        which the management of the Innovation Fund revenues has been delegated
        pursuant Article 20(3) shall provide the Commission with the following:


        (a)


        by 15 February, unaudited financial statements covering the preceding
        financial year, which shall run from 1 January to 31 December, in
        respect of the activities delegated to those implementing bodies and
        entities;


        (b)


        by 15 March of the year of the transmission of the unaudited financial
        statements, the audited financial statements covering the preceding
        financial year, which shall run from 1 January to 31 December, in
        respect of the activities delegated to those implementing bodies and
        entities.
      - >-
        (44) Where a company cannot prevent, mitigate, bring to an end or
        minimise the extent of all the identified actual and potential adverse
        impacts at the same time to the full extent, it should prioritise the
        adverse impacts based on their severity and likelihood. The severity of
        an adverse impact should be assessed based on the scale, scope or
        irremediable character of the adverse impact, taking into account the
        gravity of the impact, including the number of individuals that are or
        will be affected, the extent to which the environment is or may be
        damaged or otherwise affected, its irreversibility and the limits on the
        ability to restore affected individuals or the environment to a
        situation equivalent to their situation prior to the impact
  - source_sentence: >-
      What are the possible outcomes for a testing proposal that does not comply
      with the requirements outlined in Annexes IX, X, and XI?
    sentences:
      - >-
        3.


        Where the competent authority of the Member State of reference considers
        that an authorised non-EU AIFM is in breach of its obligations under
        this Directive, it shall notify ESMA, setting out full reasons as soon
        as possible.


        4.


        Member States shall ensure that the competent authorities have the
        powers necessary to take all measures required in order to ensure the
        orderly functioning of markets in those cases where the activity of one
        or more AIFs in the market for a financial instrument could jeopardise
        the orderly functioning of that market.


        Article 47


        Powers and competences of ESMA


        1.
      - >-
        40.


        not chemically modified substance: means a substance whose chemical
        structure remains unchanged, even if it has undergone a chemical process
        or treatment, or a physical mineralogical transformation, for instance
        to remove impurities;


        41.


        alloy: means a metallic material, homogenous on a macroscopic scale,
        consisting of two or more elements so combined that they cannot be
        readily separated by mechanical means.


        Article 4


        General provision
      - >-
        (c)


        a decision in accordance with points (a), (b) or (d) but requiring
        registrant(s) or downstream user(s) to carry out one or more additional
        tests in cases of non-compliance of the testing proposal with Annexes
        IX, X and XI;


        (d)


        a decision rejecting the testing proposal;


        (e)
  - source_sentence: >-
      What conditions must a new registrant meet in order to refer to previously
      submitted study summaries for a substance that has already been
      registered?
    sentences:
      - >-
        5.


        If a substance has already been registered, a new registrant shall be
        entitled to refer to the study summaries or robust study summaries, for
        the same substance submitted earlier, provided that he can show that the
        substance that he is now registering is the same as the one previously
        registered, including the degree of purity and the nature of impurities,
        and that the previous registrant(s) have given permission to refer to
        the full study reports for the purpose of registration.


        A new registrant shall not refer to such studies in order to provide the
        information required in Section 2 of Annex VI.


        Article 14


        Chemical safety report and duty to apply and recommend risk reduction
        measures


        1.
      - >-
        of high boiling fractions from bituminous coal high temperature tar
        and/or pitch coke oil, with a softening point of 140 to 170 °C according
        to DIN 52025. Composed primarily of tri- and polynuclear aromatic
        compounds which also contain heteroatoms.) 648-057-00-6 302-650-3
        94114-13-3 M Residues (coal tar), pitch distillation; Pitch redistillate
        (Residue from the fractional distillation of pitch distillate boiling in
        the range of approximately 400 to 470 °C. Composed primarily of
        polynuclear aromatic hydrocarbons, and heterocyclic compounds.)
        648-058-00-1 295-507-9 92061-94-4 M Tar, coal, high-temperature,
        distillation and storage residues; Coal tar solids residue (Coke- and
        ash-containing solid residues that separate on distillation and thermal
        treatment of bituminous coal high temperature tar in distillation
        installations and storage vessels. Consists predominantly of carbon and
        contains a small quantity of hetero compounds as well as ash
        components.) 648-059-00-7 295-535-1 92062-20-9 M Tar, coal, storage
        residues; Coal tar solids residue (The deposit removed from crude coal
        tar storages. Composed primarily of coal tar and carbonaceous
        particulate matter.) 648-060-00-2 293-764-1 91082-50-7 M Tar, coal,
        high-temperature, residues; Coal tar solids residue (Solids formed
        during the coking of bituminous coal to produce crude bituminous coal
        high temperature tar. Composed primarily of coke and coal particles,
        highly aromatised compounds and mineral substances.) 648-061-00-8
        309-726-5 100684-51-3 M Tar, coal, high-temperature, high-solids; Coal
        tar solids residue (The condensation product obtained by cooling, to
        approximately ambient temperature, the gas evolved in the high
        temperature (greater than 700 °C) destructive distillation of coal.
        Composed primarily of a complex mixture of condensed ring aromatic
        hydrocarbons with a high solid content of coal-type materials.)
        648-062-00-3 273-615-7 68990-61-4 M Waste solids, coal-tar pitch coking;
        Coal tar solids residue (The combination of wastes formed by the coking
        of bituminous coal tar pitch. It consists predominantly of carbon.)
        648-063-00-9 295-549-8 92062-34-5 M Extract residues (coal), brown; Coal
        tar extract (The residue from extraction of dried coal.)
      - >-
        4. Member States shall establish a network of experts from various
        sectors such as the health, building and social sectors, or entrust an
        existing network, to develop strategies to support local and national
        decision makers in implementing energy efficiency improvement measures,
        technical assistance and financial tools aiming to alleviate energy
        poverty. Member States shall strive to ensure that the composition of
        the network of experts ensures gender balance and reflects the
        perspectives of all people.


        Member States may entrust the network of experts to offer advice on:
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-v2.0
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.7203521491455205
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.923701018470568
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9554634904194718
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9796305886414638
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7203521491455205
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3079003394901893
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1910926980838943
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09796305886414639
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7203521491455205
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.923701018470568
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9554634904194718
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9796305886414638
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8635032698612493
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8247555204831233
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8257385664756074
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-m-v2.0

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-m-v2.0. 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-v2.0
Maximum Sequence Length: 8192 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': 8192, 'do_lower_case': False}) with Transformer model: GteModel 
  (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 conditions must a new registrant meet in order to refer to previously submitted study summaries for a substance that has already been registered?',
    '5.\n\nIf a substance has already been registered, a new registrant shall be entitled to refer to the study summaries or robust study summaries, for the same substance submitted earlier, provided that he can show that the substance that he is now registering is the same as the one previously registered, including the degree of purity and the nature of impurities, and that the previous registrant(s) have given permission to refer to the full study reports for the purpose of registration.\n\nA new registrant shall not refer to such studies in order to provide the information required in Section 2 of Annex VI.\n\nArticle 14\n\nChemical safety report and duty to apply and recommend risk reduction measures\n\n1.',
    'of high boiling fractions from bituminous coal high temperature tar and/or pitch coke oil, with a softening point of 140 to 170 °C according to DIN 52025. Composed primarily of tri- and polynuclear aromatic compounds which also contain heteroatoms.) 648-057-00-6 302-650-3 94114-13-3 M Residues (coal tar), pitch distillation; Pitch redistillate (Residue from the fractional distillation of pitch distillate boiling in the range of approximately 400 to 470 °C. Composed primarily of polynuclear aromatic hydrocarbons, and heterocyclic compounds.) 648-058-00-1 295-507-9 92061-94-4 M Tar, coal, high-temperature, distillation and storage residues; Coal tar solids residue (Coke- and ash-containing solid residues that separate on distillation and thermal treatment of bituminous coal high temperature tar in distillation installations and storage vessels. Consists predominantly of carbon and contains a small quantity of hetero compounds as well as ash components.) 648-059-00-7 295-535-1 92062-20-9 M Tar, coal, storage residues; Coal tar solids residue (The deposit removed from crude coal tar storages. Composed primarily of coal tar and carbonaceous particulate matter.) 648-060-00-2 293-764-1 91082-50-7 M Tar, coal, high-temperature, residues; Coal tar solids residue (Solids formed during the coking of bituminous coal to produce crude bituminous coal high temperature tar. Composed primarily of coke and coal particles, highly aromatised compounds and mineral substances.) 648-061-00-8 309-726-5 100684-51-3 M Tar, coal, high-temperature, high-solids; Coal tar solids residue (The condensation product obtained by cooling, to approximately ambient temperature, the gas evolved in the high temperature (greater than 700 °C) destructive distillation of coal. Composed primarily of a complex mixture of condensed ring aromatic hydrocarbons with a high solid content of coal-type materials.) 648-062-00-3 273-615-7 68990-61-4 M Waste solids, coal-tar pitch coking; Coal tar solids residue (The combination of wastes formed by the coking of bituminous coal tar pitch. It consists predominantly of carbon.) 648-063-00-9 295-549-8 92062-34-5 M Extract residues (coal), brown; Coal tar extract (The residue from extraction of dried coal.)',
]
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	0.7204
cosine_accuracy@3	0.9237
cosine_accuracy@5	0.9555
cosine_accuracy@10	0.9796
cosine_precision@1	0.7204
cosine_precision@3	0.3079
cosine_precision@5	0.1911
cosine_precision@10	0.098
cosine_recall@1	0.7204
cosine_recall@3	0.9237
cosine_recall@5	0.9555
cosine_recall@10	0.9796
cosine_ndcg@10	0.8635
cosine_mrr@10	0.8248
cosine_map@100	0.8257

Training Details

Training Dataset

Unnamed Dataset

Size: 46,338 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 12 tokens
mean: 42.34 tokens
max: 246 tokens

min: 6 tokens
mean: 260.86 tokens
max: 2053 tokens

	sentence_0	sentence_1
type	string	string
details	min: 12 tokens mean: 42.34 tokens max: 246 tokens	min: 6 tokens mean: 260.86 tokens max: 2053 tokens

Samples:

sentence_0	sentence_1
`What actions can a Member State take if it believes urgent measures are necessary to protect human health or the environment regarding a substance, and what are the requirements for informing other entities about these actions?`	1. Where a Member State has justifiable grounds for believing that urgent action is essential to protect human health or the environment in respect of a substance, on its own, in a ►M3 mixture ◄ or in an article, even if satisfying the requirements of this Regulation, it may take appropriate provisional measures. The Member State shall immediately inform the Commission, the Agency and the other Member States thereof, giving reasons for its decision and submitting the scientific or technical information on which the provisional measure is based. 2.
`Under what circumstances can Member States extend the time limits for the permit-granting process for Strategic Projects, and what is the maximum extension period allowed?`	(b) 12 months for Strategic Projects involving only processing or recycling. 3. Where an environmental impact assessment is required pursuant to Directive 2011/92/EU, the step of the assessment referred to in Article 1(2), point (g)(i), of that Directive shall not be included in the duration for permit- granting process referred to in paragraphs 1 and 2 of this Article. 4. In exceptional cases, where the nature, complexity, location or size of the Strategic Project so require, Member States may extend, before their expiry and on a case-by-case basis, the time limits referred to in: (a) paragraph 1, point (a), and paragraph 2, point (a), by a maximum of six months; (b)
`What types of compounds primarily compose the distillates mentioned in the context?`	(86 °F to 572 °F). Composed primarily of partly hydrogenated condensed-ring aromatic hydrocarbons, aromatic compounds containing nitrogen, oxygen and sulfur, and their alkyl derivatives having carbon numbers predominantly in the range of C4 through C14.] 648-148-00-0 302-688-0 94114-52-0 J Distillates (coal), solvent extn., hydrocracked; [Distillate obtained by hydrocracking of coal extract or solution produced by the liquid solvent extraction or supercritical gas extraction processes and boiling in the range of approximately 30 °C to 300 °C (86 °F to 572 °F). Composed primarily of aromatic, hydrogenated aromatic and naphthenic compounds, their alkyl derivatives and alkanes with carbon numbers predominantly in the range of C4 through C14.

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
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: 8
per_device_eval_batch_size: 8
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: 3
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

Epoch	Step	Training Loss	cosine_ndcg@10
0.0863	500	0.2243	0.8154
0.1726	1000	0.1242	0.8270
0.2589	1500	0.0877	0.8298
0.3452	2000	0.0823	0.8284
0.4316	2500	0.0627	0.8351
0.5179	3000	0.0636	0.8385
0.6042	3500	0.0587	0.8356
0.6905	4000	0.0746	0.8398
0.7768	4500	0.05	0.8440
0.8631	5000	0.0495	0.8441
0.9494	5500	0.0569	0.8451
1.0	5793	-	0.8432
1.0357	6000	0.0368	0.8458
1.1220	6500	0.0267	0.8501
1.2084	7000	0.0402	0.8451
1.2947	7500	0.0261	0.8524
1.3810	8000	0.0304	0.8503
1.4673	8500	0.0345	0.8521
1.5536	9000	0.0337	0.8551
1.6399	9500	0.0221	0.8525
1.7262	10000	0.0287	0.8560
1.8125	10500	0.0291	0.8549
1.8988	11000	0.0315	0.8577
1.9852	11500	0.0226	0.8577
2.0	11586	-	0.8578
2.0715	12000	0.0162	0.8552
2.1578	12500	0.0161	0.8561
2.2441	13000	0.0224	0.8550
2.3304	13500	0.0277	0.8601
2.4167	14000	0.0238	0.8591
2.5030	14500	0.0155	0.8593
2.5893	15000	0.0164	0.8598
2.6756	15500	0.0259	0.8624
2.7620	16000	0.0114	0.8617
2.8483	16500	0.025	0.8635

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

@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}
}