mpnet-base-nq-cls-last-split-pooling

MPNet base trained on Natural Questions pairs

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the natural-questions dataset. 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: microsoft/mpnet-base <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • natural-questions
• Language: en
• License: apache-2.0

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, 'architecture': 'MPNetModel'})
  (1): Router(
    (sub_modules): ModuleDict(
      (query): Sequential(
        (0): 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})
      )
      (document): Sequential(
        (0): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, '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': True, 'include_prompt': True})
      )
    )
  )
)

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("tomaarsen/cls-last-split-pooling")
# Run inference
queries = [
    "what is meaning of am and pm in time",
]
documents = [
    '12-hour clock The 12-hour clock is a time convention in which the 24 hours of the day are divided into two periods:[1] a.m. (from the Latin, ante meridiem, meaning before midday) and p.m. (post meridiem, meaning past midday).[2] Each period consists of 12 hours numbered: 12 (acting as zero),[3] 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11. The 24 hour/day cycle starts at 12 midnight (often indicated as 12 a.m.), runs through 12 noon (often indicated as 12 p.m.), and continues to the midnight at the end of the day. The 12-hour clock was developed over time from the mid-second millennium BC to the 16th century AD.',
    "America's Got Talent America's Got Talent (often abbreviated as AGT) is a televised American talent show competition, broadcast on the NBC television network. It is part of the global Got Talent franchise created by Simon Cowell, and is produced by Fremantle North America and SYCOtv, with distribution done by Fremantle. Since its premiere in June 2006, each season is run during the network's summer schedule, with the show having featured various hosts - it is currently hosted by Tyra Banks, since 2017.[2] It is the first global edition of the franchise, after plans for a British edition in 2005 were suspended, following a dispute between Paul O'Grady, the planned host, and the British broadcaster ITV; production of this edition later resumed in 2007.[3]",
    'Times Square Times Square is a major commercial intersection, tourist destination, entertainment center and neighborhood in the Midtown Manhattan section of New York City at the junction of Broadway and Seventh Avenue. It stretches from West 42nd to West 47th Streets.[1] Brightly adorned with billboards and advertisements, Times Square is sometimes referred to as "The Crossroads of the World",[2] "The Center of the Universe",[3] "the heart of The Great White Way",[4][5][6] and the "heart of the world".[7] One of the world\'s busiest pedestrian areas,[8] it is also the hub of the Broadway Theater District[9] and a major center of the world\'s entertainment industry.[10] Times Square is one of the world\'s most visited tourist attractions, drawing an estimated 50 million visitors annually.[11] Approximately 330,000 people pass through Times Square daily,[12] many of them tourists,[13] while over 460,000 pedestrians walk through Times Square on its busiest days.[7]',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.5485, 0.0270, 0.1584]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Datasets: NanoClimateFEVER, NanoDBPedia, NanoFEVER, NanoFiQA2018, NanoHotpotQA, NanoMSMARCO, NanoNFCorpus, NanoNQ, NanoQuoraRetrieval, NanoSCIDOCS, NanoArguAna, NanoSciFact and NanoTouche2020
• Evaluated with <code>InformationRetrievalEvaluator</code>

Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with <code>NanoBEIREvaluator</code> with these parameters:

  {
      "dataset_names": [
          "climatefever",
          "dbpedia",
          "fever",
          "fiqa2018",
          "hotpotqa",
          "msmarco",
          "nfcorpus",
          "nq",
          "quoraretrieval",
          "scidocs",
          "arguana",
          "scifact",
          "touche2020"
      ]
  }
  

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 99,231 training samples
• Columns: <code>query</code> and <code>answer</code>
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	<ul><li>min: 10 tokens</li><li>mean: 11.74 tokens</li><li>max: 24 tokens</li></ul>	<ul><li>min: 15 tokens</li><li>mean: 137.2 tokens</li><li>max: 508 tokens</li></ul>

• Samples:

  query	answer
  <code>who is required to report according to the hmda</code>	<code>Home Mortgage Disclosure Act US financial institutions must report HMDA data to their regulator if they meet certain criteria, such as having assets above a specific threshold. The criteria is different for depository and non-depository institutions and are available on the FFIEC website.[4] In 2012, there were 7,400 institutions that reported a total of 18.7 million HMDA records.[5]</code>
  <code>what is the definition of endoplasmic reticulum in biology</code>	<code>Endoplasmic reticulum The endoplasmic reticulum (ER) is a type of organelle in eukaryotic cells that forms an interconnected network of flattened, membrane-enclosed sacs or tube-like structures known as cisternae. The membranes of the ER are continuous with the outer nuclear membrane. The endoplasmic reticulum occurs in most types of eukaryotic cells, but is absent from red blood cells and spermatozoa. There are two types of endoplasmic reticulum: rough and smooth. The outer (cytosolic) face of the rough endoplasmic reticulum is studded with ribosomes that are the sites of protein synthesis. The rough endoplasmic reticulum is especially prominent in cells such as hepatocytes. The smooth endoplasmic reticulum lacks ribosomes and functions in lipid manufacture and metabolism, the production of steroid hormones, and detoxification.[1] The smooth ER is especially abundant in mammalian liver and gonad cells. The lacy membranes of the endoplasmic reticulum were first seen in 1945 using elect...</code>
  <code>what does the ski mean in polish names</code>	<code>Polish name Since the High Middle Ages, Polish-sounding surnames ending with the masculine -ski suffix, including -cki and -dzki, and the corresponding feminine suffix -ska/-cka/-dzka were associated with the nobility (Polish szlachta), which alone, in the early years, had such suffix distinctions.[1] They are widely popular today.</code>

• Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 16,
      "gather_across_devices": false
  }
  

Evaluation Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 1,000 evaluation samples
• Columns: <code>query</code> and <code>answer</code>
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	<ul><li>min: 10 tokens</li><li>mean: 11.78 tokens</li><li>max: 22 tokens</li></ul>	<ul><li>min: 11 tokens</li><li>mean: 135.64 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  query	answer
  <code>difference between russian blue and british blue cat</code>	<code>Russian Blue The coat is known as a "double coat", with the undercoat being soft, downy and equal in length to the guard hairs, which are an even blue with silver tips. However, the tail may have a few very dull, almost unnoticeable stripes. The coat is described as thick, plush and soft to the touch. The feeling is softer than the softest silk. The silver tips give the coat a shimmering appearance. Its eyes are almost always a dark and vivid green. Any white patches of fur or yellow eyes in adulthood are seen as flaws in show cats.[3] Russian Blues should not be confused with British Blues (which are not a distinct breed, but rather a British Shorthair with a blue coat as the British Shorthair breed itself comes in a wide variety of colors and patterns), nor the Chartreux or Korat which are two other naturally occurring breeds of blue cats, although they have similar traits.</code>
  <code>who played the little girl on mrs doubtfire</code>	<code>Mara Wilson Mara Elizabeth Wilson[2] (born July 24, 1987) is an American writer and former child actress. She is known for playing Natalie Hillard in Mrs. Doubtfire (1993), Susan Walker in Miracle on 34th Street (1994), Matilda Wormwood in Matilda (1996) and Lily Stone in Thomas and the Magic Railroad (2000). Since retiring from film acting, Wilson has focused on writing.</code>
  <code>what year did the movie the sound of music come out</code>	<code>The Sound of Music (film) The film was released on March 2, 1965 in the United States, initially as a limited roadshow theatrical release. Although critical response to the film was widely mixed, the film was a major commercial success, becoming the number one box office movie after four weeks, and the highest-grossing film of 1965. By November 1966, The Sound of Music had become the highest-grossing film of all-time—surpassing Gone with the Wind—and held that distinction for five years. The film was just as popular throughout the world, breaking previous box-office records in twenty-nine countries. Following an initial theatrical release that lasted four and a half years, and two successful re-releases, the film sold 283 million admissions worldwide and earned a total worldwide gross of $286,000,000.</code>

• Loss: <code>CachedMultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 16,
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• batch_sampler: no_duplicates
• router_mapping: {'query': 'query', 'answer': 'document'}

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 12
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: 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
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {'query': 'query', 'answer': 'document'}
• learning_rate_mapping: {}

</details>

Training Logs

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.376 kWh
• Carbon Emitted: 0.100 kg of CO2
• Hours Used: 0.956 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 5.2.0.dev0
• Transformers: 4.56.0.dev0
• PyTorch: 2.7.1+cu126
• Accelerate: 1.6.0
• Datasets: 3.6.0
• 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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->