README.md

metadata

base_model: microsoft/mdeberta-v3-base
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:110575
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: plant-based diets
    sentences:
      - >-
        Effect of a low-fat high-carbohydrate diet on symptoms of cyclical
        mastopathy. 21 patients with severe persistent cyclical mastopathy of at
        least 5 years' duration were randomised to a control group who received
        general dietary advice or to an intervention group who were taught how
        to reduce the fat content of their diet to 15% of calories while
        increasing complex carbohydrate consumption to maintain caloric intake.
        Both groups were followed for 6 months with food records and measurement
        of plasma hormone and lipid levels. Severity of symptoms was recorded
        with daily diaries and patients were assessed at the beginning and end
        of the study by a physician who was unaware of their dietary regimen.
        After 6 months there was a significant reduction in the intervention
        group in the severity of premenstrual breast tenderness and swelling.
        Physical examination showed reduced breast swelling, tenderness, and
        nodularity in 6 of 10 patients in the intervention group and 2 of 9
        patients in the control group.
      - >-
        Cranberries and cranberry products: powerful in vitro, ex vivo, and in
        vivo sources of antioxidants. Cranberry products and especially
        cranberry juice (CJ) have been consumed for health reasons primarily due
        to their effect on urinary tract infections. We investigated the
        quantity of both free and total (after hydrolysis) phenolic antioxidants
        in cranberry products using the Folin assay. The order of amount of
        total polyphenols in cranberry foods on a fresh weight basis was as
        follows: dried > frozen > sauce > jellied sauce. On a serving size basis
        for all cranberry products, the order was as follows: frozen > 100%
        juice > dried > 27% juice > sauce > jellied sauce. High fructose corn
        syrup (HFCS) is a major source of sugar consumption in the U.S. and
        contains both glucose and fructose, potential mediators of oxidative
        stress. We investigated the effect of the consumption of HFCS and
        ascorbate with CJ antioxidants or without CJ (control) given to 10
        normal individuals after an overnight fast. Plasma antioxidant capacity,
        glucose, triglycerides, and ascorbate were measured 6 times over 7 h
        after the consumption of a single 240 mL serving of the two different
        beverages. The control HFCS caused a slight decrease in plasma
        antioxidant capacity at all time points and thus an oxidative stress in
        spite of the presence of ascorbate. CJ produced an increase in plasma
        antioxidant capacity that was significantly greater than control HFCS at
        all time points. Postprandial triglycerides, due to fructose in the
        beverages, were mainly responsible for the oxidative stress and were
        significantly correlated with the oxidative stress as measured by the
        antioxidant capacity. Cranberries are an excellent source of high
        quality antioxidants and should be examined in human supplementation
        studies.
      - >-
        Açai Palm Fruit (Euterpe oleracea Mart.) Pulp Improves Survival of Flies
        on a High Fat Diet Reducing oxidative damage is thought to be an
        effective aging intervention. Açai, a fruit indigenous to the Amazon, is
        rich in phytochemicals that possesses high anti-oxidant activities, and
        has anti-inflammatory, anti-cancer and anti-cardiovascular disease
        properties. However, little is known about its potential anti-aging
        properties especially at the organismal level. Here we evaluated the
        effect of açai pulp on modulating lifespan in Drosophila melanogaster.
        We found that açai supplementation at 2% in the food increased the
        lifespan of female flies fed a high fat diet compared to the
        non-supplemented control. We measured transcript changes induced by açai
        for age-related genes. Although transcript levels of most genes tested
        were not altered, açai increased the transcript level of l(2)efl, a
        small heat-shock-related protein, and two detoxification genes, gstD1
        and mtnA, while decreasing the transcript level of phosphoenolpyruvate
        carboxykinase (Pepck), a key gene involved in gluconeogenesis.
        Furthermore, açai increased the lifespan of oxidative stressed females
        caused by sod1 RNAi. This suggests that açai improves survival of flies
        fed a high fat diet through activation of stress response pathways and
        suppression of Pepck expression. Açai has the potential to antagonize
        the detrimental effect of fat in the diet and alleviate oxidative stress
        in aging.
  - source_sentence: reproductive health
    sentences:
      - >-
        Do national advisories serve local consumers: an assessment of mercury
        in economically important North Carolina fish. Consumption of marine
        fish provides both benefits (lean protein, omega-3 fatty acids and
        essential nutrients) and risks (main source of mercury (Hg) exposure for
        humans). Mercury is a potent neurotoxin and the source of more fish
        advisories nationwide than any other toxicant. Despite the widespread
        nature of Hg, it is unknown whether local Hg contamination reflects
        national and regional levels often used as bases to inform consumers of
        potential fish consumption risk. Thus, the objectives of our study were
        to examine Hg levels of six commonly consumed marine species harvested
        locally off the North Carolina coast and to compare our results to
        published regional (Monterey Bay Aquarium's Seafood Watch List) and
        national (Environmental Protection Agency, EPA, and Food and Drug
        Administration, FDA) Hg averages, action levels, and guidelines. We
        found significant differences in Hg concentrations among collected
        species, and we identified correlations between Hg concentration and
        fish length and trophic levels. Collected mahi mahi and triggerfish were
        below the EPA fish tissue action level (0.3ppm). Wahoo and grouper
        exceeded the EPA action level but were below the FDA action level
        (1.0ppm). King mackerel had the highest Hg concentration among targeted
        species, exceeding both EPA and FDA action levels. Further, our local
        results were not always consistent with calculated averages from EPA and
        FDA databases for the same species, and although many of our findings
        were consistent with Monterey Bay Aquarium's Seafood Watch List
        (southeast region), recommendations based on Hg levels would conflict
        with recommendations they provide based on sustainability. We find
        regional and national averages are not always reflective of local Hg
        contamination and suggest local data may be needed to accurately assess
        consumer risk.
      - >-
        Purple rice (Oryza sativa L.) extract and its constituents inhibit
        VEGF-induced angiogenesis. The study evaluated the protective effects of
        purple rice (Oryza sativa L.) bran extract (PRE) and its constituents,
        cyanidin and peonidin, against angiogenesis induced by vascular
        endothelial growth factor (VEGF). The effects of VEGF and PRE were
        examined by in vitro tube formation assays and following 14-day
        co-culture of human umbilical vein endothelial cells (HUVECs) and
        fibroblasts. The antiangiogenic mechanism of PRE was evaluated by
        VEGF-induced proliferation and migration of HUVECs and/or human retinal
        microvascular endothelial cells (HRMECs) and phosphorylation of
        extracellular signal-regulated kinase (ERK) and p38. The PRE
        significantly suppressed VEGF-induced tube formation, proliferation and
        migration in HUVECs and HRMECs as well as phosphorylation of ERK and
        p38. Cyanidin and peonidin also suppressed the proliferation and
        migration induced by VEGF. These findings indicate that PRE and
        anthocyanidins suppress VEGF-induced angiogenesis by inhibiting
        proliferation and migration and suggest that the inhibition of
        phosphorylated-ERK and -p38 may be involved in the underlying mechanism.
        Copyright © 2011 John Wiley & Sons, Ltd.
      - >-
        Endurance exercise results in DNA damage as detected by the comet assay.
        To determine if 6 weeks of supplementation with antioxidants could
        alleviate exercise-induced DNA damage, we studied 21 runners during a 50
        km ultramarathon. Subjects were randomly assigned to one of two groups:
        (1) placebos (PL) or (2) antioxidants (AO) (1000 mg vitamin C and 400 IU
        RRR-alpha-tocopheryl acetate). The comet assay was used to assess DNA
        damage in circulating leukocytes at selected time points: pre-, mid-,
        and 2 h postrace and daily for 6 days postrace. All subjects completed
        the race: run time 7.1 +/- 0.1 h, energy expenditure 5008 +/- 80 kcal
        for women (n = 10) and 6932 +/- 206 kcal for men (n = 11). Overall, the
        percentage DNA damage increased at midrace (p <.02), but returned to
        baseline by 2 h postrace, indicating that the exercise bout induced
        nonpersistent DNA damage. There was a gender x treatment x time
        interaction (p <.01). One day postrace, women taking AO had 62% less DNA
        damage than women taking PL (p <.0008). In contrast, there were no
        statistically significant differences between the two treatment groups
        of men at any time point. Thus, endurance exercise resulted in DNA
        damage as shown by the comet assay and AO seemed to enhance recovery in
        women but not in men.
  - source_sentence: immune function
    sentences:
      - >-
        Relationship between the prenatal exposure to low-level of mercury and
        the size of a newborn's cerebellum. Exposure to methylmercury at any
        stage of central nervous system development could induce alterations and
        result in severe congenital abnormalities. Total mercury level in
        maternal hair during pregnancy correlates well with blood levels of
        methylmercury and with total mercury levels in fetal brain. A
        prospective study has been conducted and a total of 137 childbearing
        women living at the coastal region with term, normal pregnancies were
        included and their newborns evaluated by ultrasonography. Mothers and
        their newborns are divided in two groups according to their hair mercury
        levels; examined group with high body levels of mercury (≥ 1 μg/g) and
        control group with low body levels of mercury (<1 μg/g).
        Neurosonographic examination was conducted to all newborns. Two
        dimensions of cerebellum in the sagital-medial plane have been measured:
        maximum height and width starting from the roof of the fourth chamber.
        Majority of mothers had hair mercury levels lower than 1 μg/g (N = 107).
        Mean value was 0.88 μg/g (SD 1.24), ranging from 0.02 to 8.71 μg/g.
        There was no significant difference between the two groups when it comes
        to the width of cerebellum (Mann-Whitney test: Z = 1471; p = 0.141).
        However, comparison related to the length of cerebellum shows
        statistically significant smaller cerebellum in newborns whose mother
        had hair mercury levels higher than 1 μg/g (Mann-Whitney test: Z = 2329;
        p = 0.019). Our results lead to a conclusion that prenatal exposure to,
        what we consider to be, low-levels of methylmercury does influence fetal
        brain development detected as decreased size of newborn's cerebellum.
        From a clinical point of view, a question related to the influence of
        prenatal low-level methylmercury exposure on fetal neurodevelopment
        remains open. Our further objectives are to direct the research towards
        performing detailed neuropshychological tests on children at the age of
        18 months. Such tests could indicate the presence of subtle neurological
        or neuropsychological deficits. Copyright © 2010 Elsevier Ltd. All
        rights reserved.
      - >-
        Radioprotective effects of Zingiber officinale Roscoe (ginger): past,
        present and future. Radiation is an important modality in treating
        people with cancer especially when surgical intervention is
        impracticable or might debilitate the patient. However, effective use of
        ionizing radiation is compromised by the side effects that result from
        radiation-induced damage to normal tissue. The use of radioprotective
        compounds, which can selectively protect normal tissues against
        radiation injury is of immense use because in addition to association
        with protecting the normal tissue, it will also permits use of higher
        doses of radiation to obtain better cancer control and possible cure.
        However, till date no ideal radioprotectors are available as most
        synthetic compounds are toxic at their optimal concentrations. Plants
        commonly used as dietary and or therapeutic agents have recently been
        the focus of attention since in most cases they are non-toxic and are
        easily accepted for human use. Ginger, the rhizomes of Zingiber
        officinale Roscoe (Zingiberaceae), has widely been used as both culinary
        and medicinal agent. Preclinical studies carried out in the last decade
        has shown that ginger and its phytochemicals dehydrozingerone, zingerone
        possess radioprotective effects in laboratory animals and in cultured
        cells in vitro. The hydroalcoholic extract of ginger rhizome when
        administered either through intraperitoneal or oral route was effective
        in protecting against gamma radiation-induced sickness and mortality.
        The phytochemicals dehydrogingerone and zingerone present in ginger are
        also shown to protect mice against radiation-induced sickness and
        mortality. Mechanistic studies have indicated that the free radical
        scavenging, antioxidant affects, anti-inflammatory and anti-clastogenic
        effects may contribute towards the observed protection. Additionally,
        studies with tumor bearing mice have also shown that zingerone
        selectively protects the normal tissues against the tumoricidal effects
        of radiation. This review for the first time summarizes the results
        related to the radioprotective properties and also emphasizes the
        aspects that warrant future research to establish its activity and
        utility as a radioprotective agent.
      - >-
        Traditional non-Western diets. In traditional cultures, balancing health
        with a balanced lifestyle was a core belief. The diseases of modern
        civilization were rare. Indigenous people have patterns of illness very
        different from Western civilization; yet, they rapidly develop diseases
        once exposed to Western foods and lifestyles. Food and medicine were
        interwoven. All cultures used special or functional foods to prevent
        disease. Food could be used at different times either as food or
        medicine. Foods, cultivation, and cooking methods maximized community
        health and well-being. With methods passed down through generations,
        cooking processes were utilized that enhanced mineral and nutrient
        bioavailability. This article focuses on what researchers observed about
        the food traditions of indigenous people, their disease patterns, the
        use of specific foods, and the environmental factors that affect people
        who still eat traditional foods.
  - source_sentence: ginger
    sentences:
      - >-
        Xeno-estrogenic compounds in precipitation. The exposure to some
        chemicals can lead to hormone disrupting effects. Presently, much
        attention is focused on so-called xeno-estrogens, synthetic compounds
        that interact with hormone receptors causing a number of reactions that
        eventually lead to effects related to reproduction and development. The
        current study was initiated to investigate the presence of a number of
        such compounds in precipitation as a follow-up on a previous study in
        which pesticide concentrations in air and precipitation were determined.
        Rainwater samples were collected at about 50 locations in The
        Netherlands in a four week period. The samples were analysed for
        bisphenol-A, alkylphenols and alkylphenol ethoxylates, phthalates, flame
        retardants and synthetic musk compounds. The results clearly indicated
        the presence of these compounds in precipitation. The concentrations
        ranged from the low ng l(-1) range for flame retardants to several
        thousands of ng l(-1) for the phthalates. Bisphenol-A was found in 30%
        of the samples in concentrations up to 130 ng l(-1), while alkylphenols
        and alkylphenol ethoxylates were found in virtually all locations in
        concentrations up to 920 ng l(-1) for the individual compounds.
        Phthalates were by far the most abundant xeno-estrogens in the
        precipitation samples and were found in every sample. Di-isodecyl
        phthalate was found in a surprisingly high concentration of almost 100
        000 ng l(-1). Polybrominated flame retardants were found in the low ng
        l(-1) range and generally in less than 20% of the samples. Noticeable
        was the finding of hexabromocyclododecane, a replacement for the
        polybrominted diphenyl ethers at one location in a concentration of
        almost 2000 ng l(-1). Finally, as expected, synthetic musk compounds
        were detected in almost all samples. This is especially true for the
        polycyclic musks HHCB and AHTN. Nitro musks were found, but only on a
        few locations. Kriging techniques were used to calculate precipitation
        concentrations in between actual sampling locations to produce contour
        plots for a number of compounds. These plots clearly show located
        emission sources for a number of compounds such as bisphenol-A,
        nonylphenol ethoxylate, phthalates and AHTN. On the contrary, the
        results for HHCB and some phthalates indicated diffuse emission
        patterns, probably as the result of the use of consumer products
        containing these compounds.
      - >-
        The state of US health, 1990-2010: burden of diseases, injuries, and
        risk factors. IMPORTANCE: Understanding the major health problems in the
        United States and how they are changing over time is critical for
        informing national health policy. OBJECTIVES: To measure the burden of
        diseases, injuries, and leading risk factors in the United States from
        1990 to 2010 and to compare these measurements with those of the 34
        countries in the Organisation for Economic Co-operation and Development
        (OECD) countries. DESIGN: We used the systematic analysis of descriptive
        epidemiology of 291 diseases and injuries, 1160 sequelae of these
        diseases and injuries, and 67 risk factors or clusters of risk factors
        from 1990 to 2010 for 187 countries developed for the Global Burden of
        Disease 2010 Study to describe the health status of the United States
        and to compare US health outcomes with those of 34 OECD countries. Years
        of life lost due to premature mortality (YLLs) were computed by
        multiplying the number of deaths at each age by a reference life
        expectancy at that age. Years lived with disability (YLDs) were
        calculated by multiplying prevalence (based on systematic reviews) by
        the disability weight (based on population-based surveys) for each
        sequela; disability in this study refers to any short- or long-term loss
        of health. Disability-adjusted life-years (DALYs) were estimated as the
        sum of YLDs and YLLs. Deaths and DALYs related to risk factors were
        based on systematic reviews and meta-analyses of exposure data and
        relative risks for risk-outcome pairs. Healthy life expectancy (HALE)
        was used to summarize overall population health, accounting for both
        length of life and levels of ill health experienced at different ages.
        RESULTS: US life expectancy for both sexes combined increased from 75.2
        years in 1990 to 78.2 years in 2010; during the same period, HALE
        increased from 65.8 years to 68.1 years. The diseases and injuries with
        the largest number of YLLs in 2010 were ischemic heart disease, lung
        cancer, stroke, chronic obstructive pulmonary disease, and road injury.
        Age-standardized YLL rates increased for Alzheimer disease, drug use
        disorders, chronic kidney disease, kidney cancer, and falls. The
        diseases with the largest number of YLDs in 2010 were low back pain,
        major depressive disorder, other musculoskeletal disorders, neck pain,
        and anxiety disorders. As the US population has aged, YLDs have
        comprised a larger share of DALYs than have YLLs. The leading risk
        factors related to DALYs were dietary risks, tobacco smoking, high body
        mass index, high blood pressure, high fasting plasma glucose, physical
        inactivity, and alcohol use. Among 34 OECD countries between 1990 and
        2010, the US rank for the age-standardized death rate changed from 18th
        to 27th, for the age-standardized YLL rate from 23rd to 28th, for the
        age-standardized YLD rate from 5th to 6th, for life expectancy at birth
        from 20th to 27th, and for HALE from 14th to 26th. CONCLUSIONS AND
        RELEVANCE: From 1990 to 2010, the United States made substantial
        progress in improving health. Life expectancy at birth and HALE
        increased, all-cause death rates at all ages decreased, and age-specific
        rates of years lived with disability remained stable. However, morbidity
        and chronic disability now account for nearly half of the US health
        burden, and improvements in population health in the United States have
        not kept pace with advances in population health in other wealthy
        nations.
      - >-
        Curcumin as "Curecumin": from kitchen to clinic. Although turmeric
        (Curcuma longa; an Indian spice) has been described in Ayurveda, as a
        treatment for inflammatory diseases and is referred by different names
        in different cultures, the active principle called curcumin or
        diferuloylmethane, a yellow pigment present in turmeric (curry powder)
        has been shown to exhibit numerous activities. Extensive research over
        the last half century has revealed several important functions of
        curcumin. It binds to a variety of proteins and inhibits the activity of
        various kinases. By modulating the activation of various transcription
        factors, curcumin regulates the expression of inflammatory enzymes,
        cytokines, adhesion molecules, and cell survival proteins. Curcumin also
        downregulates cyclin D1, cyclin E and MDM2; and upregulates p21, p27,
        and p53. Various preclinical cell culture and animal studies suggest
        that curcumin has potential as an antiproliferative, anti-invasive, and
        antiangiogenic agent; as a mediator of chemoresistance and
        radioresistance; as a chemopreventive agent; and as a therapeutic agent
        in wound healing, diabetes, Alzheimer disease, Parkinson disease,
        cardiovascular disease, pulmonary disease, and arthritis. Pilot phase I
        clinical trials have shown curcumin to be safe even when consumed at a
        daily dose of 12g for 3 months. Other clinical trials suggest a
        potential therapeutic role for curcumin in diseases such as familial
        adenomatous polyposis, inflammatory bowel disease, ulcerative colitis,
        colon cancer, pancreatic cancer, hypercholesteremia, atherosclerosis,
        pancreatitis, psoriasis, chronic anterior uveitis and arthritis. Thus,
        curcumin, a spice once relegated to the kitchen shelf, has moved into
        the clinic and may prove to be "Curecumin".
  - source_sentence: hot dogs
    sentences:
      - >-
        Occurrence of pharmaceuticals and personal care products in fish:
        results of a national pilot study in the United States. Pharmaceuticals
        and personal care products are being increasingly reported in a variety
        of biological matrices, including fish tissue; however, screening
        studies have presently not encompassed broad geographical areas. A
        national pilot study was initiated in the United States to assess the
        accumulation of pharmaceuticals and personal care products in fish
        sampled from five effluent-dominated rivers that receive direct
        discharge from wastewater treatment facilities in Chicago, Illinois;
        Dallas, Texas; Orlando, Florida; Phoenix, Arizona; and West Chester,
        Pennsylvania, USA. Fish were also collected from the Gila River, New
        Mexico, USA, as a reference condition expected to be minimally impacted
        by anthropogenic influence. High performance liquid
        chromatography-tandem mass spectrometry analysis of pharmaceuticals
        revealed the presence of norfluoxetine, sertraline, diphenhydramine,
        diltiazem, and carbamazepine at nanogram-per-gram concentrations in
        fillet composites from effluent-dominated sampling locations; the
        additional presence of fluoxetine and gemfibrozil was confirmed in liver
        tissue. Sertraline was detected at concentrations as high as 19 and 545
        ng/g in fillet and liver tissue, respectively. Gas chromatography-tandem
        mass spectrometry analysis of personal care products in fillet
        composites revealed the presence of galaxolide and tonalide at maximum
        concentrations of 2,100 and 290 ng/g, respectively, and trace levels of
        triclosan. In general, more pharmaceuticals were detected at higher
        concentrations and with greater frequency in liver than in fillet
        tissues. Higher lipid content in liver tissue could not account for this
        discrepancy as no significant positive correlations were found between
        accumulated pharmaceutical concentrations and lipid content for either
        tissue type from any sampling site. In contrast, accumulation of the
        personal care products galaxolide and tonalide was significantly related
        to lipid content. Results suggest that the detection of pharmaceuticals
        and personal care products was dependent on the degree of wastewater
        treatment employed.
      - >-
        Dietary modification of human macular pigment density. PURPOSE: The
        retinal carotenoids lutein (L) and zeaxanthin (Z) that form the macular
        pigment (MP) may help to prevent neovascular age-related macular
        degeneration. The purpose of this study was to determine whether MP
        density in the retina could be raised by increasing dietary intake of L
        and Z from foods. METHODS: Macular pigment was measured psychophysically
        for 13 subjects. Serum concentrations of L, Z, and beta-carotene were
        measured by high-performance liquid chromatography. Eleven subjects
        modified their usual daily diets by adding 60 g of spinach (10.8 mg L,
        0.3 mg Z, 5 mg beta-carotene) and ten also added 150 g of corn (0.3 mg
        Z, 0.4 mg L); two other subjects were given only corn. Dietary
        modification lasted up to 15 weeks. RESULTS: For the subjects fed
        spinach or spinach and corn, three types of responses to dietary
        modification were identified: Eight "retinal responders" had increases
        in serum L (mean, 33%; SD, 22%) and in MP density (mean, 19%; SD, 11%);
        two "retinal nonresponders" showed substantial increases in serum L
        (mean, 31%) but not in MP density (mean, -11%); one "serum and retinal
        nonresponder" showed no changes in serum L, Z, or beta-carotene and no
        change in MP density. For the two subjects given only corn, serum L
        changed little (+11%, -6%), but in one subject serum Z increased (70%)
        and MP density increased (25%). CONCLUSIONS: Increases in MP density
        were obtained within 4 weeks of dietary modification for most, but not
        all, subjects. When MP density increased with dietary modification, it
        remained elevated for at least several months after resuming an
        unmodified diet. Augmentation of MP for both experimental and clinical
        investigation appears to be feasible for many persons.
      - >-
        Habitual physical exercise has beneficial effects on telomere length in
        postmenopausal women. OBJECTIVE: It has been reported that women benefit
        from the maintenance of telomere length by estrogen. Exercise may
        favorably influence telomere length, although results are inconsistent
        regarding the duration and type of exercise and the cell type used to
        measure telomere length. The purpose of this study was to investigate
        the relationship between habitual physical exercise and telomere length
        in peripheral blood mononuclear cells (PBMCs) in postmenopausal women.
        Postmenopausal women were chosen as study participants because they are
        typically estrogen deficient. METHODS: This experimental-control,
        cross-sectional study included 44 healthy, nondiabetic, nonsmoking,
        postmenopausal women. Habitual exercisers and sedentary participants
        were matched for age and body mass index. Body weight, height, blood
        pressure, and waist and hip circumference were measured. Mitochondrial
        DNA copy number and telomere length in PBMCs were determined, and
        biochemical tests were performed. Habitual physical exercise was defined
        as combined aerobic and resistance exercise performed for at least 60
        minutes per session more than three times a week for more than 12
        months. RESULTS: The mean age of all participants was 58.11 ± 6.84
        years, and participants in the habitual exercise group had been
        exercising more than three times per week for an average of 19.23 ± 5.15
        months. Serum triglyceride levels (P = 0.01), fasting insulin
        concentrations (P < 0.01), and homeostasis model assessment of insulin
        resistance (P < 0.01) were significantly lower and high-density
        lipoprotein cholesterol levels (P < 0.01), circulating adiponectin (P <
        0.01), mitochondrial DNA copy number (P < 0.01), and telomere length (P
        < 0.01) were significantly higher in the habitual exercise group than in
        the sedentary group. In a stepwise multiple regression analysis,
        habitual exercise (β = 0.522, P < 0.01) and adiponectin levels (β =
        0.139, P = 0.03) were the independent factors associated with the
        telomere length of PBMCs in postmenopausal women. CONCLUSIONS: Habitual
        physical exercise is associated with greater telomere length in
        postmenopausal women. This finding suggests that habitual physical
        exercise in postmenopausal women may reduce telomere attrition.
model-index:
  - name: SentenceTransformer based on microsoft/mdeberta-v3-base
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: eval
          type: eval
        metrics:
          - type: cosine_accuracy@1
            value: 0.19753086419753085
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3117283950617284
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.36728395061728397
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.4074074074074074
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.19753086419753085
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.17901234567901234
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18271604938271604
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.15987654320987654
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.012537229433577907
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.028172357070419075
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.04616926987049525
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.07464352973292211
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.1771093240394393
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2604485106799922
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.10892177775157068
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.1419753086419753
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.2345679012345679
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.26851851851851855
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.33024691358024694
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.1419753086419753
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.13786008230452673
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.13950617283950617
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1308641975308642
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.005321414264515094
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.019846033299858425
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.029084171632431998
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.049244765309017405
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.13684384060235508
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.19590192043895757
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.08815891364299847
            name: Dot Map@100

SentenceTransformer based on microsoft/mdeberta-v3-base

This is a sentence-transformers model finetuned from microsoft/mdeberta-v3-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: microsoft/mdeberta-v3-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• 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': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
  (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("BlackBeenie/mdeberta-v3-base-sbert")
# Run inference
sentences = [
    'hot dogs',
    'Habitual physical exercise has beneficial effects on telomere length in postmenopausal women. OBJECTIVE: It has been reported that women benefit from the maintenance of telomere length by estrogen. Exercise may favorably influence telomere length, although results are inconsistent regarding the duration and type of exercise and the cell type used to measure telomere length. The purpose of this study was to investigate the relationship between habitual physical exercise and telomere length in peripheral blood mononuclear cells (PBMCs) in postmenopausal women. Postmenopausal women were chosen as study participants because they are typically estrogen deficient. METHODS: This experimental-control, cross-sectional study included 44 healthy, nondiabetic, nonsmoking, postmenopausal women. Habitual exercisers and sedentary participants were matched for age and body mass index. Body weight, height, blood pressure, and waist and hip circumference were measured. Mitochondrial DNA copy number and telomere length in PBMCs were determined, and biochemical tests were performed. Habitual physical exercise was defined as combined aerobic and resistance exercise performed for at least 60 minutes per session more than three times a week for more than 12 months. RESULTS: The mean age of all participants was 58.11 ± 6.84 years, and participants in the habitual exercise group had been exercising more than three times per week for an average of 19.23 ± 5.15 months. Serum triglyceride levels (P = 0.01), fasting insulin concentrations (P < 0.01), and homeostasis model assessment of insulin resistance (P < 0.01) were significantly lower and high-density lipoprotein cholesterol levels (P < 0.01), circulating adiponectin (P < 0.01), mitochondrial DNA copy number (P < 0.01), and telomere length (P < 0.01) were significantly higher in the habitual exercise group than in the sedentary group. In a stepwise multiple regression analysis, habitual exercise (β = 0.522, P < 0.01) and adiponectin levels (β = 0.139, P = 0.03) were the independent factors associated with the telomere length of PBMCs in postmenopausal women. CONCLUSIONS: Habitual physical exercise is associated with greater telomere length in postmenopausal women. This finding suggests that habitual physical exercise in postmenopausal women may reduce telomere attrition.',
    'Dietary modification of human macular pigment density. PURPOSE: The retinal carotenoids lutein (L) and zeaxanthin (Z) that form the macular pigment (MP) may help to prevent neovascular age-related macular degeneration. The purpose of this study was to determine whether MP density in the retina could be raised by increasing dietary intake of L and Z from foods. METHODS: Macular pigment was measured psychophysically for 13 subjects. Serum concentrations of L, Z, and beta-carotene were measured by high-performance liquid chromatography. Eleven subjects modified their usual daily diets by adding 60 g of spinach (10.8 mg L, 0.3 mg Z, 5 mg beta-carotene) and ten also added 150 g of corn (0.3 mg Z, 0.4 mg L); two other subjects were given only corn. Dietary modification lasted up to 15 weeks. RESULTS: For the subjects fed spinach or spinach and corn, three types of responses to dietary modification were identified: Eight "retinal responders" had increases in serum L (mean, 33%; SD, 22%) and in MP density (mean, 19%; SD, 11%); two "retinal nonresponders" showed substantial increases in serum L (mean, 31%) but not in MP density (mean, -11%); one "serum and retinal nonresponder" showed no changes in serum L, Z, or beta-carotene and no change in MP density. For the two subjects given only corn, serum L changed little (+11%, -6%), but in one subject serum Z increased (70%) and MP density increased (25%). CONCLUSIONS: Increases in MP density were obtained within 4 weeks of dietary modification for most, but not all, subjects. When MP density increased with dietary modification, it remained elevated for at least several months after resuming an unmodified diet. Augmentation of MP for both experimental and clinical investigation appears to be feasible for many persons.',
]
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

• Dataset: eval
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1975
cosine_accuracy@3	0.3117
cosine_accuracy@5	0.3673
cosine_accuracy@10	0.4074
cosine_precision@1	0.1975
cosine_precision@3	0.179
cosine_precision@5	0.1827
cosine_precision@10	0.1599
cosine_recall@1	0.0125
cosine_recall@3	0.0282
cosine_recall@5	0.0462
cosine_recall@10	0.0746
cosine_ndcg@10	0.1771
cosine_mrr@10	0.2604
cosine_map@100	0.1089
dot_accuracy@1	0.142
dot_accuracy@3	0.2346
dot_accuracy@5	0.2685
dot_accuracy@10	0.3302
dot_precision@1	0.142
dot_precision@3	0.1379
dot_precision@5	0.1395
dot_precision@10	0.1309
dot_recall@1	0.0053
dot_recall@3	0.0198
dot_recall@5	0.0291
dot_recall@10	0.0492
dot_ndcg@10	0.1368
dot_mrr@10	0.1959
dot_map@100	0.0882

Training Details

Training Dataset

Unnamed Dataset

• Size: 110,575 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	int
  details	min: 3 tokens mean: 6.46 tokens max: 19 tokens	min: 27 tokens mean: 394.71 tokens max: 512 tokens	1: 100.00%

• Samples:

  sentence_0	sentence_1	label
  chronic diseases	Role of antioxidants in cancer therapy. Oxidative stress is a key component in linking environmental toxicity to the multistage carcinogenic process. Reactive oxygen species (ROS) are generated in response to both endogenous and exogenous stimuli. To counterbalance ROS-mediated injury, an endogenous antioxidants defense system exists; however, when oxidation exceeds the control mechanisms, oxidative stress arises. Chronic and cumulative oxidative stress induces deleterious modifications to a variety of macromolecular components, such as DNA, lipids, and proteins. A primary mechanism of many chemotherapy drugs against cancer cells is the formation of ROS, or free radicals. Radiotherapy is based on the fact that ionizing radiation destroys tumor cells. Radiotherapy induces direct lesions in the DNA or biological molecules, which eventually affect DNA. Free radicals produced by oncology therapy are often a source of serious side effects as well. The objective of this review is to provide information about the effects of antioxidants during oncology treatments and to discuss the possible events and efficacy. Much debate has arisen about whether antioxidant supplementation alters the efficacy of cancer chemotherapy. There is still limited evidence in both quality and sample size, suggesting that certain antioxidant supplements may reduce adverse reactions and toxicities. Significant reductions in toxicity may alleviate dose-limiting toxicities so that more patients are able to complete prescribed chemotherapy regimens and thus, in turn, improve the potential for success in terms of tumor response and survival. Copyright © 2013 Elsevier Inc. All rights reserved.	1
  plant-based diets	Diet, infection and wheezy illness: lessons from adults. An increase in asthma and atopic disease has been recorded in many countries where society has become more prosperous. We have investigated two possible explanations: a reduction in childhood infections and a change in diet. In a cohort of people followed up since 1964, originally selected as a random sample of primary school children, we have investigated the relevance of family size and the common childhood infectious diseases to development of eczema, hay fever and asthma. Although membership of a large family reduced risks of hay fever and eczema (but not asthma), this was not explained by the infections the child had suffered. Indeed, the more infections the child had had, the greater the likelihood of asthma, although measles gave a modest measure of protection. We have investigated dietary factors in two separate studies. In the first, we have shown the risks of bronchial hyper-reactivity are increased seven-fold among those with the lowest intake of vitamin C, while the lowest intake of saturated fats gave a 10-fold protection. In the second, we have shown that the risk of adult-onset wheezy illness is increased five-fold by the lowest intake of vitamin E and doubled by the lowest intake of vitamin C. These results were supported by direct measurements of the vitamins and triglycerides in plasma. We have proposed that changes in the diet of pregnant women may have reflected those observed in the population as a whole and that these may have resulted in the birth of cohorts of children predisposed to atopy and asthma. The direct test of this is to study the diet and nutritional status of a large cohort of pregnant women and to follow their offspring forward. This is our current research.	1
  liver health	Effect of a very-high-fiber vegetable, fruit, and nut diet on serum lipids and colonic function. We tested the effects of feeding a diet very high in fiber from fruit and vegetables. The levels fed were those, which had originally inspired the dietary fiber hypothesis related to colon cancer and heart disease prevention and also may have been eaten early in human evolution. Ten healthy volunteers each took 3 metabolic diets of 2 weeks duration. The diets were: high-vegetable, fruit, and nut (very-high-fiber, 55 g/1,000 kcal); starch-based containing cereals and legumes (early agricultural diet); or low-fat (contemporary therapeutic diet). All diets were intended to be weight-maintaining (mean intake, 2,577 kcal/d). Compared with the starch-based and low-fat diets, the high-fiber vegetable diet resulted in the largest reduction in low-density lipoprotein (LDL) cholesterol (33% +/- 4%, P <.001) and the greatest fecal bile acid output (1.13 +/- 0.30 g/d, P =.002), fecal bulk (906 +/- 130 g/d, P <.001), and fecal short-chain fatty acid outputs (78 +/- 13 mmol/d, P <.001). Nevertheless, due to the increase in fecal bulk, the actual concentrations of fecal bile acids were lowest on the vegetable diet (1.2 mg/g wet weight, P =.002). Maximum lipid reductions occurred within 1 week. Urinary mevalonic acid excretion increased (P =.036) on the high-vegetable diet reflecting large fecal steroid losses. We conclude that very high-vegetable fiber intakes reduce risk factors for cardiovascular disease and possibly colon cancer. Vegetable and fruit fibers therefore warrant further detailed investigation. Copyright 2001 by W.B. Saunders Company	1

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 32
• per_device_eval_batch_size: 32
• 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: 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	eval_cosine_map@100
0.1447	500	3.4744	-
0.2894	1000	3.3463	-
0.4340	1500	3.2119	-
0.5787	2000	3.0852	-
0.7234	2500	2.9736	-
0.8681	3000	2.8964	-
1.0	3456	-	0.0628
1.0127	3500	2.8117	-
1.1574	4000	2.7464	-
1.3021	4500	2.6987	-
1.4468	5000	2.6423	0.0795
1.5914	5500	2.584	-
1.7361	6000	2.5438	-
1.8808	6500	2.4891	-
2.0	6912	-	0.0948
2.0255	7000	2.4555	-
2.1701	7500	2.442	-
2.3148	8000	2.4161	-
2.4595	8500	2.3882	-
2.6042	9000	2.3545	-
2.7488	9500	2.3274	-
2.8935	10000	2.3134	0.1082
3.0	10368	-	0.1089

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Accelerate: 0.34.2
• Datasets: 3.0.0
• Tokenizers: 0.19.1

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",
}

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}
}