metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:12689
  - loss:TripletLossWithLogging
base_model: Alibaba-NLP/gte-modernbert-base
widget:
  - source_sentence: >-
      Which of the following statements is true regarding the properties of
      zinc-activated ion channels and quaternary carbon atoms?

      A. Quaternary carbon atoms are primarily involved in the activation of
      zinc-activated ion channels.

      B. Both zinc-activated ion channels and quaternary carbon atoms are unique
      to the rat genome.

      C. Zinc-activated ion channels are cation-permeable and can activate
      spontaneously, while quaternary carbon atoms are found in hydrocarbons
      with at least five carbon atoms.

      D. Zinc-activated ion channels are exclusively found in the human genome,
      while quaternary carbon atoms can only exist in linear alkanes.
    sentences:
      - >-
        A quaternary carbon is a carbon atom bound to four other carbon atoms.
        For this reason, quaternary carbon atoms are found only in hydrocarbons
        having at least five carbon atoms. Quaternary carbon atoms can occur in
        branched alkanes, but not in linear alkanes.


        Synthesis 

        The formation of chiral quaternary carbon centers has been a synthetic
        challenge. Chemists have developed asymmetric Diels–Alder reactions,
        Heck reaction, Enyne cyclization, cycloaddition reactions, C–H
        activation, Allylic substitution,  Pauson–Khand reaction,  etc. to
        construct asymmetric quaternary carbons.


        References 


        Chemical nomenclature

        Organic chemistry
      - >-
        Severe fever with thrombocytopenia syndrome (SFTS) is an emerging
        infectious disease caused by Dabie bandavirus also known as the SFTS
        virus, first reported between late March and mid-July 2009 in rural
        areas of Hubei and Henan provinces in Central China. SFTS has fatality
        rates ranging from 12% to as high as 30% in some areas. The major
        clinical symptoms of SFTS are fever, vomiting, diarrhea, multiple organ
        failure, thrombocytopenia (low platelet count), leucopenia (low white
        blood cell count), and elevated liver enzyme levels.


        Virology

        SFTS virus (SFTSV) is a virus in the order Bunyavirales.
        Person-to-person transmission was not noted in early reports but has
        since been documented.


        The life cycle of the SFTSV most likely involves arthropod vectors and
        animal hosts. Humans appear to be largely accidental hosts. SFTSV has
        been detected in Haemaphysalis longicornis ticks.


        Epidemiology

        SFTS occurs in China's rural areas from March to November with the
        majority of cases from April to July. In 2013, Japan and Korea also
        reported several cases with deaths.


        In July 2013, South Korea reported a total of eight deaths since August
        2012.


        In July 2017, Japanese doctors reported that a woman had died of SFTS
        after being bitten by a cat that may have itself infected by a tick. The
        woman had no visible tick bites, leading doctors to believe that the cat
        — which died as well — was the transmission vector.


        In early 2020 an outbreak occurred in East China, more than 37 people
        were found with SFTS in Jiangsu province, while 23 more were found
        infected in Anhui province in August 2020. Seven people have died.


        Evolution

        The virus originated 50–150 years ago and has undergone a recent
        population expansion.


        History

        In 2009 Xue-jie Yu and colleagues isolated the SFTS virus (SFTSV) from
        SFTS patients’ blood.


        References


        External links 


        Arthropod-borne viral fevers and viral haemorrhagic fevers

        Insect-borne diseases

        Zoonoses
      - >-
        Lecticans, also known as hyalectans, are a family of proteoglycans (a
        type protein that is attached to chains of negatively charged
        polysaccharides) that are components of the extracellular matrix.  There
        are four members of the lectican family: aggrecan, brevican, neurocan,
        and versican.  Lecticans interact with hyaluronic acid and tenascin-R to
        form a ternary complex.


        Tissue distribution 


        Aggrecan is a major component of extracellular matrix in cartilage
        whereas versican is widely expressed in a number of connective tissues
        including those in vascular smooth muscle, skin epithelial cells, and
        the cells of central and peripheral nervous system. The expression of
        neurocan and brevican is largely restricted to neural tissues.


        Structure 


        All four lecticans contain an N-terminal globular domain (G1 domain)
        that in turn contains an immunoglobulin V-set domain and a Link domain
        that binds hyaluronic acid; a long extended central domain (CS) that is
        modified with covalently attached sulfated glycosaminoglycan chains, and
        a C-terminal globular domain (G3 domain) containing of one or more EGF
        repeats, a C-type lectin domain and a CRP-like domain. Aggrecan has in
        addition a globular domain (G2 domain) that is situated between the G1
        and CS domains.


        See also 

        Hyaladherin


        References 


        Protein families
  - source_sentence: >-
      What is the primary physiological process that causes the corpora
      cavernosa to become engorged with blood during an erection?

      A. Tumescence

      B. Hyperemia

      C. Contraction

      D. Vasodilation
    sentences:
      - >-
        Leukotriene D4 (LTD4) is one of the leukotrienes. Its main function in
        the body is to induce the contraction of smooth muscle, resulting in
        bronchoconstriction and vasoconstriction. It also increases vascular
        permeability. LTD4 is released by basophils. Other leukotrienes that
        function in a similar manner are leukotrienes C4 and E4. Pharmacological
        agents that inhibit the function of these leukotrienes are leukotriene
        receptor antagonists (e.g. Zafirlukast, montelukast) and are useful for
        asthmatic individuals.


        References


        Eicosanoids
      - >-
        The Panasonic Lumix DMC-FZ45 (a.k.a. DMC-FZ40 in North American markets)
        is a superzoom bridge digital camera, replacing the similar Panasonic
        Lumix DMC-FZ38 and earlier Panasonic Lumix DMC-FZ28. The Panasonic Lumix
        DMC-FZ40/FZ45 superzoom slots in where the FZ38/35 left off, featuring
        the same 25-600mm equiv. lens as the FZ100, but with a 14.1MP CCD sensor
        and simpler 230K dot 3.0 inch fixed LCD (as opposed to the FZ100's CMOS
        sensor and high-res screen). The FZ40 also offers AVCHD Lite 720p HD
        video recording, manual shooting modes and the company’s Sonic Speed
        auto-focus system that offers the industry's fastest focus times.


        External links 

        Specs on panasonic.it

        Information regarding DMC-FZ45:
        https://www.dpreview.com/products/panasonic/compacts/panasonic_dmcfz40


        Bridge digital cameras

        Superzoom cameras

        FZ45
      - >-
        Erectile tissue is tissue in the body with numerous vascular spaces, or
        cavernous tissue, that may become engorged with blood. However, tissue
        that is devoid of or otherwise lacking erectile tissue (such as the
        labia minora, the vestibule/vagina and the urethra) may also be
        described as engorging with blood, often with regard to sexual arousal.


        In the clitoris and penis


        Erectile tissue exists in places such as the corpora cavernosa of the
        penis, and in the clitoris or in the bulbs of vestibule. During
        erection, the corpora cavernosa will become engorged with arterial
        blood, a process called tumescence. This may result from any of various
        physiological stimuli, also known as sexual arousal. The corpus
        spongiosum is a single tubular structure located just below the corpora
        cavernosa. This may also become slightly engorged with blood, but less
        so than the corpora cavernosa.


        Other types

        Erectile tissue is also found in the nose (turbinates), ear, urethral
        sponge and perineal sponge. The erection of nipples is not due to
        erectile tissue, but rather due to the contraction of smooth muscle
        under the control of the autonomic nervous system.


        References


        Sexual anatomy


        ru:Пещеристое тело
  - source_sentence: |-
      What is the primary function of the supratrochlear nerve?
      A. Sensory innervation to the lower jaw
      B. Motor function to the muscles of facial expression
      C. Motor innervation to the superior oblique muscle
      D. Sensory innervation to the skin of the forehead and upper eyelid
    sentences:
      - "A lung counter is a system consisting of a radiation detector, or detectors, and associated electronics that is used to measure radiation emitted from radioactive material that has been inhaled by a person and is sufficiently insoluble as to remain in the lung for weeks, months, or years.\n\nOften, such a system is housed in a low background counting chamber whose thick walls will be made of low-background steel (~20\_cm thick) and will be lined with ~1\_cm of lead, then perhaps thin layers of cadmium, or tin, with a final layer of copper.  The purpose of the lead, cadmium (or tin), and copper is to reduce the background in the low energy region of a gamma spectrum (typically less than 200 keV)\n\nCalibration \nAs a lung counter is primarily measuring radioactive materials that emit low energy gamma rays or x-rays, the phantom used to calibrate the system must be anthropometric. An example of such a phantom is the Lawrence Livermore National Laboratory Torso Phantom.\n\nSee also \n Bomab\n\nMedical equipment\nRadiobiology"
      - >-
        The supratrochlear nerve is a branch of the frontal nerve, itself a
        branch of the ophthalmic nerve (CN V1) from the trigeminal nerve (CN V).
        It provides sensory innervation to the skin of the forehead and the
        upper eyelid.


        Structure 

        The supratrochlear nerve is a branch of the frontal nerve, itself a
        branch of the ophthalmic nerve (CN V1) from the trigeminal nerve (CN V).
        It is smaller than the supraorbital nerve from the frontal nerve. It
        branches midway between the base and apex of the orbit. It passes above
        the trochlea of the superior oblique muscle. It then travels anteriorly
        above the levator palpebrae superioris muscle. It exits the orbit
        through the frontal notch in the superomedial margin of the orbit. It
        then ascends onto the forehead beneath the corrugator supercilii muscle
        and frontalis muscle. It then divides into sensory branches.


        The supratrochlear nerve travels with the supratrochlear artery, a
        branch of the ophthalmic artery.


        Function 

        The supratrochlear nerve provides sensory innervation to the skin of the
        lateral lower forehead, upper eyelid, and the conjunctiva. It may also
        supply sensation to the periosteum of part of the frontal bone of the
        skull.


        Clinical significance 

        The supratrochlear nerve may be anaesthetised for surgery of parts of
        the scalp. This can be used for small lesions of the scalp. It can also
        be used for more extensive injury to the scalp. It is often
        anaesthetised alongside the supraorbital artery.


        Etymology 

        The supratrochlear nerve is named for its passage above the trochlea of
        the superior oblique muscle.


        Additional images


        References


        External links 
         
         
          ()
          ()
         http://www.dartmouth.edu/~humananatomy/figures/chapter_47/47-2.HTM

        Ophthalmic nerve
      - >-
        A Y-SNP is a single-nucleotide polymorphism on the Y chromosome. Y-SNPs
        are often used in paternal genealogical DNA testing.


        SNP markers


        A single nucleotide polymorphism (SNP) is a change to a single
        nucleotide in a DNA sequence. The relative mutation rate for an SNP is
        extremely low. This makes them ideal for marking the history of the
        human genetic tree. SNPs are named with a letter code and a number. The
        letter indicates the lab or research team that discovered the SNP. The
        number indicates the order in which it was discovered. For example M173
        is the 173rd SNP documented by the Human Population Genetics Laboratory
        at Stanford University, which uses the letter M.


        See also 

        Mt-SNP

        Short tandem repeat

        Haplogroup

        Haplotype

        Genealogical DNA test


        Single-nucleotide polymorphisms
  - source_sentence: >-
      What is the primary function of the enzyme encoded by the GCNT2 gene in
      humans?

      A. Synthesis of hemoglobin

      B. Formation of the blood group I antigen

      C. Conversion of glucose to glycogen

      D. Degradation of fatty acids
    sentences:
      - >-
        N-acetyllactosaminide beta-1,6-N-acetylglucosaminyl-transferase is an
        enzyme that in humans is encoded by the GCNT2 gene.


        This gene encodes the enzyme responsible for formation of the blood
        group I antigen. The i and I antigens are distinguished by linear and
        branched poly-N-acetyllactosaminoglycans, respectively. The encoded
        protein is the I-branching enzyme, a
        beta-1,6-N-acetylglucosaminyltransferase responsible for the conversion
        of fetal i antigen to adult I antigen in erythrocytes during embryonic
        development. Mutations in this gene have been associated with adult i
        blood group phenotype. Alternatively spliced transcript variants
        encoding different isoforms have been described.


        References


        Further reading
      - >-
        Telapristone (), as telapristone acetate (proposed brand names Proellex,
        Progenta; former code name CDB-4124), is a synthetic, steroidal
        selective progesterone receptor modulator (SPRM) related to mifepristone
        which is under development by Repros Therapeutics for the treatment of
        breast cancer, endometriosis, and uterine fibroids. It was originally
        developed by the National Institutes of Health (NIH), and, as of 2017,
        is in phase II clinical trials for the aforementioned indications. In
        addition to its activity as an SPRM, the drug also has some
        antiglucocorticoid activity.


        See also
         List of investigational sex-hormonal agents § Progestogenics
         Aglepristone
         Lilopristone
         Onapristone
         Toripristone

        References


        External links
         Telapristone - AdisInsight

        Acetate esters

        Dimethylamino compounds

        Antiglucocorticoids

        Estranes

        Ketones

        Selective progesterone receptor modulators
      - >-
        Eclipse chasing is the pursuit of observing solar eclipses when they
        occur around the Earth. Solar eclipses must occur at least twice and as
        often as five times a year across the Earth. Total eclipses may occur
        multiple times every few years.


        A person who chases eclipses is known as a umbraphile, meaning shadow
        lover. Umbraphiles often travel for eclipses and use various tools to
        help view the sun including solar viewers also known as eclipse glasses,
        as well as telescopes.


        As of 2017, three New Yorkers, Glenn Schneider, Jay Pasachoff, and John
        Beattie have each seen 33 total solar eclipses, the current record.
        Donald Liebenberg, professor of astronomy at Clemson University in South
        Carolina has seen 26 traveling to Turkey, Zambia, China, the Cook
        Islands and others.


        History


        In the 19th century, Mabel Loomis Todd, an American editor and writer,
        and her husband David Peck Todd, a professor of astronomy at Amherst
        College, traveled around the world to view solar eclipses. During the
        solar eclipse of June 30, 1973, Donald Liebenberg and a group of eclipse
        experts observed the eclipse on board the Concorde and experienced 74
        minutes of totality.


        See also
         Solar eclipse
         Weather spotting
         Storm chasing

        References


        Observation hobbies

        2010s fads and trends
  - source_sentence: |-
      What is the primary role of davemaoite in Earth's lower mantle?
      A. It is the most abundant mineral in the crust.
      B. It acts as a catalyst for mineral formation.
      C. It serves as a primary source of diamonds.
      D. It contributes to heat flow through radioactive decay.
    sentences:
      - >-
        McKusick–Kaufman/Bardet–Biedl syndromes putative chaperonin is a protein
        that in humans is encoded by the MKKS gene.


        This gene encodes a protein with sequence similarity to the chaperonin
        family. The encoded protein may have a role in protein processing in
        limb, cardiac and reproductive system development. Mutations in this
        gene have been observed in patients with Bardet–Biedl syndrome type 6
        and McKusick–Kaufman syndrome. Two transcript variants encoding the same
        protein have been identified for this gene.


        References


        External links
         GeneReviews/NIH/NCBI/UW entry on Bardet–Biedl syndrome
         GeneReviews/NIH/NCBI/UW entry on McKusick–Kaufman syndrome

        Further reading
      - >-
        Davemaoite  is  a high-pressure calcium silicate perovskite (CaSiO3)
        mineral with a distinctive cubic crystal structure. It is named after
        geophysicist Ho-kwang (Dave) Mao, who pioneered in many discoveries in
        high-pressure geochemistry and geophysics.  


        It is one of three main minerals in Earth’s lower mantle, making up
        around 5–7% of the material there. Significantly, davemaoite can host
        uranium and thorium, radioactive isotopes which produce heat through
        radioactive decay and contribute greatly to heating within this region
        giving the material a major role in how heat flows deep below the
        earth's surface.


        Davemaoite has been artificially synthesized in the laboratory, but was
        thought to be too extreme to exist in the Earth's crust. Then in 2021,
        the mineral was discovered as specks within a diamond that formed
        between 660 and 900 km beneath the Earth's surface, within the mantle.
        The diamond had been extracted from the Orapa diamond mine in Botswana.
        The discovery was made  by focusing a high-energy beam of X-rays on
        precise spots within the diamond  using a technique known as synchrotron
        X-ray diffraction. 


        Calcium silicate is found in other forms, such as wollastonite in the
        crust and breyite in the middle and lower regions of the mantle.
        However, this version can exist only at very high pressure of around
        200,000 times that found at Earth’s surface.


        See also

         Perovskite (structure)
        List of minerals


        References 


        Perovskites

        Calcium minerals
      - >-
        In molecular biology, the calcipressin family of proteins negatively
        regulate calcineurin by direct binding. They are essential for the
        survival of T helper type 1 cells. Calcipressin 1 is a phosphoprotein
        that increases its capacity to inhibit calcineurin when phosphorylated
        at the conserved FLISPP motif; this phosphorylation also controls the
        half-life of calcipressin 1 by accelerating its degradation.


        In humans, the Calcipressins family of proteins is derived from three
        genes. Calcipressin 1 is also known as modulatory
        calcineurin-interacting protein 1 (MCIP1), Adapt78 and Down syndrome
        critical region 1 (DSCR1). Calcipressin 2 is variously known as MCIP2,
        ZAKI-4 and DSCR1-like 1. Calcipressin 3 is also called MCIP3 and
        DSCR1-like 2.


        References


        Protein families
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: validation
          type: validation
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy

SentenceTransformer based on Alibaba-NLP/gte-modernbert-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-modernbert-base. 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: Alibaba-NLP/gte-modernbert-base
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: ModernBertModel 
  (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})
)

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("anasse15/MNLP_M3_document_encoder")
# Run inference
sentences = [
    "What is the primary role of davemaoite in Earth's lower mantle?\nA. It is the most abundant mineral in the crust.\nB. It acts as a catalyst for mineral formation.\nC. It serves as a primary source of diamonds.\nD. It contributes to heat flow through radioactive decay.",
    "Davemaoite  is  a high-pressure calcium silicate perovskite (CaSiO3) mineral with a distinctive cubic crystal structure. It is named after geophysicist Ho-kwang (Dave) Mao, who pioneered in many discoveries in high-pressure geochemistry and geophysics.  \n\nIt is one of three main minerals in Earth’s lower mantle, making up around 5–7% of the material there. Significantly, davemaoite can host uranium and thorium, radioactive isotopes which produce heat through radioactive decay and contribute greatly to heating within this region giving the material a major role in how heat flows deep below the earth's surface.\n\nDavemaoite has been artificially synthesized in the laboratory, but was thought to be too extreme to exist in the Earth's crust. Then in 2021, the mineral was discovered as specks within a diamond that formed between 660 and 900 km beneath the Earth's surface, within the mantle. The diamond had been extracted from the Orapa diamond mine in Botswana. The discovery was made  by focusing a high-energy beam of X-rays on precise spots within the diamond  using a technique known as synchrotron X-ray diffraction. \n\nCalcium silicate is found in other forms, such as wollastonite in the crust and breyite in the middle and lower regions of the mantle. However, this version can exist only at very high pressure of around 200,000 times that found at Earth’s surface.\n\nSee also\n\n Perovskite (structure)\nList of minerals\n\nReferences \n\nPerovskites\nCalcium minerals",
    'In molecular biology, the calcipressin family of proteins negatively regulate calcineurin by direct binding. They are essential for the survival of T helper type 1 cells. Calcipressin 1 is a phosphoprotein that increases its capacity to inhibit calcineurin when phosphorylated at the conserved FLISPP motif; this phosphorylation also controls the half-life of calcipressin 1 by accelerating its degradation.\n\nIn humans, the Calcipressins family of proteins is derived from three genes. Calcipressin 1 is also known as modulatory calcineurin-interacting protein 1 (MCIP1), Adapt78 and Down syndrome critical region 1 (DSCR1). Calcipressin 2 is variously known as MCIP2, ZAKI-4 and DSCR1-like 1. Calcipressin 3 is also called MCIP3 and DSCR1-like 2.\n\nReferences\n\nProtein families',
]
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

Triplet

Dataset: validation
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	1.0

Training Details

Training Dataset

Unnamed Dataset

Size: 12,689 training samples
Columns: sentence_0, sentence_1, and sentence_2

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	sentence_2
type	string	string	string
details	min: 30 tokens mean: 84.52 tokens max: 198 tokens	min: 94 tokens mean: 261.34 tokens max: 818 tokens	min: 101 tokens mean: 257.86 tokens max: 752 tokens

Samples:

sentence_0	sentence_1	sentence_2
`What type of model is the TaiWan Ionospheric Model (TWIM)? A. A one-dimensional thermal model of the Earth's crust B. A two-dimensional statistical model of atmospheric pressure C. A four-dimensional quantum model of particle interactions D. A three-dimensional numerical and phenomenological model of ionospheric electron density`	The TaiWan Ionospheric Model (TWIM) developed in 2008 is a three-dimensional numerical and phenomenological model of ionospheric electron density (Ne). The TWIM has been constructed from global distributed ionosonde foF2 and foE data and vertical Ne profiles retrieved from FormoSat3/COSMIC GPS radio occultation measurements. The TWIM consists of vertically fitted α-Chapman-type layers, with distinct F2, F1, E, and D layers, for which the layer parameters such as peak density, peak density height, and scale height are represented by surface spherical harmonics. These results are useful for providing reliable radio propagation predictions and in investigation of near-Earth space and large-scale Ne distribution with diurnal and seasonal variations, along with geographic features such as the equatorial anomaly. This way the continuity of Ne and its derivatives is also maintained for practical schemes for providing reliable radio propagation predictions. References The information in thi...	Chandrasekhar–Kendall functions are the axisymmetric eigenfunctions of the curl operator, derived by Subrahmanyan Chandrasekhar and P.C. Kendall in 1957, in attempting to solve the force-free magnetic fields. The results were independently derived by both, but were agreed to publish the paper together. If the force-free magnetic field equation is written as with the assumption of divergence free field (), then the most general solution for axisymmetric case is where is a unit vector and the scalar function satisfies the Helmholtz equation, i.e., The same equation also appears in fluid dynamics in Beltrami flows where, vorticity vector is parallel to the velocity vector, i.e., . Derivation Taking curl of the equation and using this same equation, we get . In the vector identity , we can set since it is solenoidal, which leads to a vector Helmholtz equation, . Every solution of above equation is not the solution of original equation, but the converse is true. If is a scal...
`What is the primary function of the protein encoded by the PFN2 gene? A. Facilitating lipid metabolism B. Regulating actin polymerization C. Encoding DNA repair enzymes D. Transporting oxygen in blood`	Profilin-2 is a protein that in humans is encoded by the PFN2 gene. The protein encoded by this gene is a ubiquitous actin monomer-binding protein belonging to the profilin family. It is thought to regulate actin polymerization in response to extracellular signals. There are two alternatively spliced transcript variants encoding different isoforms described for this gene. Interactions PFN2 has been shown to interact with ROCK1, Vasodilator-stimulated phosphoprotein, CCDC113 and FMNL1. References Further reading External links	`Stearoyl-CoA is a coenzyme involved in the metabolism of fatty acids. Stearoyl-CoA is an 18-carbon long fatty acyl-CoA chain that participates in an unsaturation reaction. The reaction is catalyzed by the enzyme stearoyl-CoA desaturase, which is located in the endoplasmic reticulum. It forms a cis-double bond between the ninth and tenth carbons within the chain to form the product oleoyl-CoA. References Bibliography Metabolism Thioesters of coenzyme A`
`Which of the following statements is true regarding the properties of certain mathematical spaces and their relevance in functional analysis? A. Souslin spaces are always separable and complete metrizable. B. All Polish spaces are K-analytic but not all K-analytic spaces are Polish. C. The Borel graph theorem applies only to finite-dimensional spaces. D. The VEZF1 gene is involved in the continuity of linear maps in functional analysis.`	`Vascular endothelial zinc finger 1 is a protein that in humans is encoded by the VEZF1 gene. Function Transcriptional regulatory proteins containing tandemly repeated zinc finger domains are thought to be involved in both normal and abnormal cellular proliferation and differentiation. ZNF161 is a C2H2-type zinc finger protein (Koyano-Nakagawa et al., 1994 [PubMed 8035792]). See MIM 603971 for general information on zinc finger proteins. References Further reading`	`In mathematics, a trivial semigroup (a semigroup with one element) is a semigroup for which the cardinality of the underlying set is one. The number of distinct nonisomorphic semigroups with one element is one. If S = { a } is a semigroup with one element, then the Cayley table of S is {`

Loss: main.TripletLossWithLogging with these parameters:

{
    "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
    "triplet_margin": 5
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
fp16: True
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: 16
per_device_eval_batch_size: 16
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: 1
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: True
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
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	validation_cosine_accuracy
0.1259	100	-	1.0
0.2519	200	-	1.0
0.3778	300	-	1.0
0.5038	400	-	1.0
0.6297	500	0.1864	1.0
0.7557	600	-	1.0
0.8816	700	-	1.0
1.0	794	-	1.0

Framework Versions

Python: 3.12.8
Sentence Transformers: 4.1.0
Transformers: 4.52.3
PyTorch: 2.7.0+cu126
Accelerate: 1.3.0
Datasets: 3.6.0
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",
}

TripletLossWithLogging

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}