tomaarsen/mpnet-base-nq-cgist-2-gte

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
• 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}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

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/mpnet-base-nq-cgist-2-gte")
# Run inference
sentences = [
    'where does the last name francisco come from',
    'Francisco Francisco is the Spanish and Portuguese form of the masculine given name Franciscus (corresponding to English Francis).',
    'Book of Esther The Book of Esther, also known in Hebrew as "the Scroll" (Megillah), is a book in the third section (Ketuvim, "Writings") of the Jewish Tanakh (the Hebrew Bible) and in the Christian Old Testament. It is one of the five Scrolls (Megillot) in the Hebrew Bible. It relates the story of a Hebrew woman in Persia, born as Hadassah but known as Esther, who becomes queen of Persia and thwarts a genocide of her people. The story forms the core of the Jewish festival of Purim, during which it is read aloud twice: once in the evening and again the following morning. The books of Esther and Song of Songs are the only books in the Hebrew Bible that do not explicitly mention God.[2]',
]
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

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

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
cosine_accuracy@1	0.16	0.52	0.28	0.14	0.32	0.14	0.22	0.14	0.78	0.28	0.18	0.3	0.4898
cosine_accuracy@3	0.34	0.62	0.5	0.32	0.44	0.28	0.3	0.24	0.88	0.42	0.52	0.34	0.7347
cosine_accuracy@5	0.56	0.7	0.52	0.36	0.48	0.34	0.34	0.32	0.9	0.52	0.64	0.42	0.8163
cosine_accuracy@10	0.64	0.78	0.62	0.46	0.58	0.44	0.36	0.48	0.94	0.62	0.88	0.5	0.9388
cosine_precision@1	0.16	0.52	0.28	0.14	0.32	0.14	0.22	0.14	0.78	0.28	0.18	0.3	0.4898
cosine_precision@3	0.12	0.36	0.1667	0.1333	0.1733	0.0933	0.1533	0.08	0.36	0.2267	0.1733	0.12	0.4014
cosine_precision@5	0.128	0.364	0.108	0.1	0.116	0.068	0.124	0.064	0.24	0.2	0.128	0.092	0.3673
cosine_precision@10	0.082	0.322	0.064	0.07	0.068	0.044	0.096	0.05	0.132	0.124	0.088	0.056	0.3102
cosine_recall@1	0.06	0.0337	0.28	0.0693	0.16	0.14	0.0071	0.13	0.6807	0.0587	0.18	0.265	0.0365
cosine_recall@3	0.1217	0.0601	0.48	0.2032	0.26	0.28	0.0129	0.22	0.8347	0.1407	0.52	0.315	0.0858
cosine_recall@5	0.2483	0.1119	0.51	0.2277	0.29	0.34	0.0203	0.29	0.8793	0.2057	0.64	0.4	0.1256
cosine_recall@10	0.3157	0.1975	0.6	0.3235	0.34	0.44	0.0256	0.46	0.9367	0.2557	0.88	0.485	0.2065
cosine_ndcg@10	0.228	0.373	0.4359	0.2272	0.305	0.276	0.117	0.2707	0.8529	0.2491	0.5102	0.3689	0.3575
cosine_mrr@10	0.3094	0.5887	0.3857	0.2399	0.3991	0.2249	0.2652	0.2217	0.8324	0.3833	0.3946	0.3477	0.6281
cosine_map@100	0.1655	0.2525	0.3903	0.1836	0.263	0.2466	0.0304	0.2263	0.8202	0.2016	0.4002	0.3412	0.2783

Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with NanoBEIREvaluator

Metric	Value
cosine_accuracy@1	0.3038
cosine_accuracy@3	0.4565
cosine_accuracy@5	0.532
cosine_accuracy@10	0.6338
cosine_precision@1	0.3038
cosine_precision@3	0.197
cosine_precision@5	0.1615
cosine_precision@10	0.1159
cosine_recall@1	0.1616
cosine_recall@3	0.2718
cosine_recall@5	0.3299
cosine_recall@10	0.4205
cosine_ndcg@10	0.3516
cosine_mrr@10	0.4016
cosine_map@100	0.2923

Training Details

Training Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 50,000 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 11.74 tokens max: 24 tokens	min: 15 tokens mean: 137.2 tokens max: 508 tokens

• Samples:

  query	answer
  who is required to report according to the hmda	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]
  what is the definition of endoplasmic reticulum in biology	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...
  what does the ski mean in polish names	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.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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()
  ), 'temperature': 0.01}
  

Evaluation Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 100,231 evaluation samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 11.78 tokens max: 22 tokens	min: 11 tokens mean: 135.64 tokens max: 512 tokens

• Samples:

  query	answer
  difference between russian blue and british blue cat	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.
  who played the little girl on mrs doubtfire	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.
  what year did the movie the sound of music come out	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.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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()
  ), 'temperature': 0.01}
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 2048
• per_device_eval_batch_size: 2048
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 2048
• per_device_eval_batch_size: 2048
• 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: False
• 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: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoClimateFEVER_cosine_ndcg@10	NanoDBPedia_cosine_ndcg@10	NanoFEVER_cosine_ndcg@10	NanoFiQA2018_cosine_ndcg@10	NanoHotpotQA_cosine_ndcg@10	NanoMSMARCO_cosine_ndcg@10	NanoNFCorpus_cosine_ndcg@10	NanoNQ_cosine_ndcg@10	NanoQuoraRetrieval_cosine_ndcg@10	NanoSCIDOCS_cosine_ndcg@10	NanoArguAna_cosine_ndcg@10	NanoSciFact_cosine_ndcg@10	NanoTouche2020_cosine_ndcg@10	NanoBEIR_mean_cosine_ndcg@10
0.04	1	15.537	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2	5	11.6576	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4	10	7.1392	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6	15	5.0005	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8	20	4.0541	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0	25	3.4117	2.3797	0.2280	0.3730	0.4359	0.2272	0.3050	0.2760	0.1170	0.2707	0.8529	0.2491	0.5102	0.3689	0.3575	0.3516

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.153 kWh
• Carbon Emitted: 0.059 kg of CO2
• Hours Used: 0.396 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: 3.4.0.dev0
• Transformers: 4.46.2
• PyTorch: 2.5.0+cu121
• Accelerate: 0.35.0.dev0
• Datasets: 2.20.0
• 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",
}