metadata

language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1453
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: nomic-ai/nomic-embed-text-v1.5
datasets: []
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
widget:
  - source_sentence: >-
      We therefore conducted a hospital based cross sectional study involving
      101 HCWs from two facilities in Kumasi, Ghana to assess the level of
      preparedness of HCWs to respond to any possible EVD. METHODS: We
      administered a face-to-face questionnaire using an adapted WHO (2015) and
      CDC (2014) Checklist for Ebola Preparedness and assessed overall knowledge
      gaps, and preparedness of the Ghanaian HCWs in selected health facilities
      of the Ashanti Region of Ghana from October to December 2015. RESULTS: A
      total 92 (91.09%) HCWs indicated they were not adequately trained to
      handle an EVD suspected case. Only 25.74% (n = 26) considered their
      facilities sufficiently equipped to handle and manage EVD patients. When
      asked which disinfectant to use after attending to and caring for a
      suspected patient with EVD, only 8.91% (n = 9) could correctly identify
      the right disinfectant (χ(2) = 28.52, p = 0.001). CONCLUSION: Our study
      demonstrates poor knowledge and ill preparedness and unwillingness of many
      HCWs to attend to EVD. Beyond knowledge acquisition, there is the need for
      more training from time to time to fully prepare HCWs to handle any
      possible EVD case. Text: During the last outbreak of Ebola Virus Disease
      (EVD) and its consequential massive epidemic with very high mortality [1]
      , many health systems and services in West Africa were overwhelmed and
      disrupted.
    sentences:
      - >-
        How many facilities believed they were adequately equipped to handle
        Ebla virus disease?
      - >-
        What  developments have been made possible by the study of B-cell
        repertoire?
      - Where does the NLRP3 inflammasome activate after a SARS-CoV infection?
  - source_sentence: >-
      All inﬂuenza A pandemics since that time, and indeed almost all cases of
      inﬂuenza A worldwide (except- ing human infections from avian Viruses such
      as H5N1 and H7N7), have been caused by descendants of the 1918 Virus,
      including “drifted” H1N1 Viruses and reassorted H2N2 and H3N2 Viruses. The
      latter are composed of key genes from the 1918 Virus, updated by
      subsequently-incor— porated avian inﬂuenza genes that code for novel
      surface   *Armed Forces Institute of Pathology, Rockville, Maryland, USA;
      and TNational Institutes of Health, Bethesda, Maryland, USA proteins,
      making the 1918 Virus indeed the “mother” of all pandemics. In 1918, the
      cause of human inﬂuenza and its links to avian and swine inﬂuenza were
      unknown. Despite clinical and epidemiologic similarities to inﬂuenza
      pandemics of 1889, 1847, and even earlier, many questioned whether such an
      explosively fatal disease could be inﬂuenza at all. That question did not
      begin to be resolved until the 1930s, when closely related inﬂuenza
      Viruses (now known to be H1N1 Viruses) were isolated, ﬁrst from pigs and
      shortly thereafter from humans. Seroepidemiologic studies soon linked both
      of these viruses to the 1918 pandemic (8). Subsequent research indicates
      that descendants of the 1918 Virus still persists enzootically in pigs.
      They probably also circulated continuously in humans, undergoing gradual
      antigenic drift and causing annual epidemics, until the 1950s.
    sentences:
      - What causes Q fever?
      - What was the mean length of the sequenced read?
      - >-
        When was it  determined that the 1918  pandemic was caused by the H1N1
        Influenza virus?
  - source_sentence: >-
      These results showed that CD3 + CD4 + T cells have obviously (P<0.01)
      increased ( Figure 5B ), nevertheless the CD3 + CD8 + T cells remarkably
      (P<0.05) declined ( Figure 5C ). After calculation, the ratio of CD4 +
      /CD8 + T cells increased ( Figure 5D ). This ratio could also further
      measure the immunity levels of piglets. Cytokine IL-1β and IL-10 levels
      were determined to evaluate cellular immune responses induced by B.
      subtilis-RC as shown in Figure 6A ,B. As we can see from the diagram,
      significantly (P<0.01) higher IL-1β and IL-10 were produced after oral
      administration with B. subtilis-RC than the other two groups. These all
      revealed that B. subtilis-RC could stimulate cytokines release to mediate
      communication with and between cells of the immune system, improving the
      mucosal immune response to PEDV infection. The PEDV neutralizing
      antibodies were detected by PRNT assay. Oral administration with B.
      subtilis-RC could effectively reduce the plaque-forming ability of PEDV
      (P<0.01) compared with other two groups in Figure 7 .
    sentences:
      - >-
        Why are antibody epitope based peptide vaccines are no longer an active
        research area?
      - What is a conclusion of  this study?
      - >-
        What is an effective indicator of a vaccine's ability to generate an
        immune response?
  - source_sentence: >-
      Many types of bacteriophage and engineered phage variants, including
      filamentous phage, have been proposed for prophylactic use ex vivo in food
      safety, either in the production pipeline (reviewed in Dalmasso et al.,
      2014) or for detection of foodborne pathogens post-production (reviewed in
      Schmelcher and Loessner, 2014) . Filamentous phage displaying a
      tetracysteine tag on pIII were used to detect E. coli cells through
      staining with biarsenical dye . M13 phage functionalized with metallic
      silver were highly bactericidal against E. coli and Staphylococcus
      epidermidis . Biosensors based on surface plasmon resonance (Nanduri et
      al., 2007) , piezoelectric transducers (Olsen et al., 2006) , linear
      dichroism (Pacheco-Gomez et al., 2012) , and magnetoelastic sensor
      technology (Lakshmanan et al., 2007; Huang et al., 2009) were devised
      using filamentous phage displaying scFv or conjugated to whole IgG against
      E. coli, Listeria monocytogenes, Salmonella typhimurium, and Bacillus
      anthracis with limits of detection on the order of 10 2 -10 6 bacterial
      cells/mL. Proof of concept has been demonstrated for use of such
      phage-based biosensors to detect bacterial contamination of live produce
      (Li et al., 2010b) and eggs (Chai et al., 2012) . The filamentous phage
      particle is enclosed by a rod-like protein capsid, ∼1000 nm long and 5 nm
      wide, made up almost entirely of overlapping pVIII monomers, each of which
      lies ∼27 angstroms from its nearest neighbor and exposes two amine groups
      as well as at least three carboxyl groups (Henry et al., 2011) . The
      regularity of the phage pVIII lattice and its diversity of chemically
      addressable groups make it an ideal scaffold for bioconjugation (Figure 3)
      . The most commonly used approach is functionalization of amine groups
      with NHS esters (van Houten et al., 2006 (van Houten et al., , 2010 Yacoby
      et al., 2006) , although this can result in unwanted acylation of pIII and
      any displayed biomolecules.
    sentences:
      - What is the contrast with SARS-COV and MERS=COV?
      - What is the structure of a filamentous phage particle?
      - Why do treatment and management vary in efficacy?
  - source_sentence: >-
      The monolayers were removed from their plastic surfaces and serially
      passaged whenever they became confluent. Cells were plated out onto
      96-well culture plates for cytotoxicity and anti-influenza assays, and
      propagated at 37 °C in an atmosphere of 5% CO 2 . The influenza strain
      A/Leningrad/134/17/1957 H2N2) was purchased from National Control
      Institute of Veterinary Bioproducts and Pharmaceuticals (Beijing, China).
      Virus was routinely grown on MDCK cells. The stock cultures were prepared
      from supernatants of infected cells and stored at −80 °C. The cellular
      toxicity of patchouli alcohol on MDCK cells was assessed by the MTT
      method. Briefly, cells were seeded on a microtiter plate in the absence or
      presence of various concentrations (20 µM -0.0098 µM) of patchouli alcohol
      (eight replicates) and incubated at 37 °C in a humidified atmosphere of 5%
      CO 2 for 72 h. The supernatants were discarded, washed with PBS twice and
      MTT reagent (5 mg/mL in PBS) was added to each well. After incubation at
      37 °C for 4 h, the supernatants were removed, then 200 μL DMSO was added
      and incubated at 37 °C for another 30 min.
    sentences:
      - >-
        What can be a factor in using common vectors for the delivery of
        vaccines?
      - ' What can  some of the other activities of N have, be linked to?'
      - What method was used to measure the inhibition of viral replication?
pipeline_tag: sentence-similarity
model-index:
  - name: nomic-text-embed COVID QA Matryoshka test
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.32098765432098764
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.6049382716049383
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7222222222222222
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8580246913580247
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.32098765432098764
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.20164609053497942
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14444444444444443
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08580246913580246
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.32098765432098764
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.6049382716049383
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7222222222222222
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8580246913580247
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5726476297998092
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4831545169508133
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4876624839192167
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.3395061728395062
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.6172839506172839
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.691358024691358
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8395061728395061
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3395061728395062
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.20576131687242796
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1382716049382716
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0839506172839506
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.3395061728395062
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.6172839506172839
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.691358024691358
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8395061728395061
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5769674187028887
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4942803252988438
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.49996505521200235
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.3148148148148148
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5864197530864198
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6604938271604939
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7901234567901234
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3148148148148148
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.19547325102880658
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.13209876543209875
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07901234567901234
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.3148148148148148
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5864197530864198
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6604938271604939
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7901234567901234
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5454859667021819
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.46796492259455236
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4775435566293839
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.2716049382716049
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5370370370370371
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.654320987654321
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7283950617283951
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.2716049382716049
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.17901234567901234
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1308641975308642
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0728395061728395
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.2716049382716049
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5370370370370371
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.654320987654321
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7283950617283951
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4965852195530764
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4220825984714875
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.43352458189921866
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.24074074074074073
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.47530864197530864
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5864197530864198
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6728395061728395
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.24074074074074073
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15843621399176952
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11728395061728394
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06728395061728394
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.24074074074074073
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.47530864197530864
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5864197530864198
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6728395061728395
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4508577703429953
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3797864001567706
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.39108804574508443
            name: Cosine Map@100

nomic-text-embed COVID QA Matryoshka test

This is a sentence-transformers model finetuned from nomic-ai/nomic-embed-text-v1.5. 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: nomic-ai/nomic-embed-text-v1.5
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
  (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("JerryO3/test")
# Run inference
sentences = [
    'The monolayers were removed from their plastic surfaces and serially passaged whenever they became confluent. Cells were plated out onto 96-well culture plates for cytotoxicity and anti-influenza assays, and propagated at 37 °C in an atmosphere of 5% CO 2 . The influenza strain A/Leningrad/134/17/1957 H2N2) was purchased from National Control Institute of Veterinary Bioproducts and Pharmaceuticals (Beijing, China). Virus was routinely grown on MDCK cells. The stock cultures were prepared from supernatants of infected cells and stored at −80 °C. The cellular toxicity of patchouli alcohol on MDCK cells was assessed by the MTT method. Briefly, cells were seeded on a microtiter plate in the absence or presence of various concentrations (20 µM -0.0098 µM) of patchouli alcohol (eight replicates) and incubated at 37 °C in a humidified atmosphere of 5% CO 2 for 72 h. The supernatants were discarded, washed with PBS twice and MTT reagent (5 mg/mL in PBS) was added to each well. After incubation at 37 °C for 4 h, the supernatants were removed, then 200 μL DMSO was added and incubated at 37 °C for another 30 min.',
    'What method was used to measure the inhibition of viral replication?',
    'What can be a factor in using common vectors for the delivery of vaccines?',
]
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: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.321
cosine_accuracy@3	0.6049
cosine_accuracy@5	0.7222
cosine_accuracy@10	0.858
cosine_precision@1	0.321
cosine_precision@3	0.2016
cosine_precision@5	0.1444
cosine_precision@10	0.0858
cosine_recall@1	0.321
cosine_recall@3	0.6049
cosine_recall@5	0.7222
cosine_recall@10	0.858
cosine_ndcg@10	0.5726
cosine_mrr@10	0.4832
cosine_map@100	0.4877

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.3395
cosine_accuracy@3	0.6173
cosine_accuracy@5	0.6914
cosine_accuracy@10	0.8395
cosine_precision@1	0.3395
cosine_precision@3	0.2058
cosine_precision@5	0.1383
cosine_precision@10	0.084
cosine_recall@1	0.3395
cosine_recall@3	0.6173
cosine_recall@5	0.6914
cosine_recall@10	0.8395
cosine_ndcg@10	0.577
cosine_mrr@10	0.4943
cosine_map@100	0.5

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.3148
cosine_accuracy@3	0.5864
cosine_accuracy@5	0.6605
cosine_accuracy@10	0.7901
cosine_precision@1	0.3148
cosine_precision@3	0.1955
cosine_precision@5	0.1321
cosine_precision@10	0.079
cosine_recall@1	0.3148
cosine_recall@3	0.5864
cosine_recall@5	0.6605
cosine_recall@10	0.7901
cosine_ndcg@10	0.5455
cosine_mrr@10	0.468
cosine_map@100	0.4775

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.2716
cosine_accuracy@3	0.537
cosine_accuracy@5	0.6543
cosine_accuracy@10	0.7284
cosine_precision@1	0.2716
cosine_precision@3	0.179
cosine_precision@5	0.1309
cosine_precision@10	0.0728
cosine_recall@1	0.2716
cosine_recall@3	0.537
cosine_recall@5	0.6543
cosine_recall@10	0.7284
cosine_ndcg@10	0.4966
cosine_mrr@10	0.4221
cosine_map@100	0.4335

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.2407
cosine_accuracy@3	0.4753
cosine_accuracy@5	0.5864
cosine_accuracy@10	0.6728
cosine_precision@1	0.2407
cosine_precision@3	0.1584
cosine_precision@5	0.1173
cosine_precision@10	0.0673
cosine_recall@1	0.2407
cosine_recall@3	0.4753
cosine_recall@5	0.5864
cosine_recall@10	0.6728
cosine_ndcg@10	0.4509
cosine_mrr@10	0.3798
cosine_map@100	0.3911

Training Details

Training Dataset

Unnamed Dataset

Size: 1,453 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 112 tokens
mean: 319.17 tokens
max: 778 tokens

min: 6 tokens
mean: 14.84 tokens
max: 65 tokens

	positive	anchor
type	string	string
details	min: 112 tokens mean: 319.17 tokens max: 778 tokens	min: 6 tokens mean: 14.84 tokens max: 65 tokens

Samples:

positive	anchor
We find that the slowing growth in daily reported deaths in Italy is consistent with a significant impact of interventions implemented several weeks earlier. In Italy, we estimate that the effective reproduction number, Rt, dropped to close to 1 around the time of Iockdown (11th March), although with a high level of uncertainty. Overall, we estimate that countries have managed to reduce their reproduction number. Our estimates have wide credible intervals and contain 1 for countries that have implemented a
[46] Where the biological samples are taken from also play a role in the sensitivity of these tests. For SARS-CoV and MERS-CoV, specimens collected from the lower respiratory tract such as sputum and tracheal aspirates have higher and more prolonged levels of viral RNA because of the tropism of the virus. MERS-CoV viral loads are also higher for severe cases and have longer viral shedding compared to mild cases. Although upper respiratory tract specimens such as nasopharyngeal or oropharyngeal swabs can be used, they have potentially lower viral loads and may have higher risk of false-negatives among the mild MERS and SARS cases [102, 103] , and likely among the 2019-nCoV cases. The existing practices in detecting genetic material of coronaviruses such as SARS-CoV and MERS-CoV include (a) reverse transcription-polymerase chain reaction (RT-PCR), (b) real-time RT-PCR (rRT-PCR), (c) reverse transcription loop-mediated isothermal amplification (RT-LAMP) and (d) real-time RT-LAMP [104] . Nucleic amplification tests (NAAT) are usually preferred as in the case of MERS-CoV diagnosis as it has the highest sensitivity at the earliest time point in the acute phase of infection [102] . Chinese health authorities have recently posted the full genome of 2019-nCoV in the GenBank and in GISAID portal to facilitate in the detection of the virus [11] . Several laboratory assays have been developed to detect the novel coronavirus in Wuhan, as highlighted in WHO's interim guidance on nCoV laboratory testing of suspected cases.	`Why are Nucleic amplification tests (NAAT) usually preferred as in the case of MERS-CoV diagnosis?`
By the time symptoms appear in HCPS, both strong antiviral responses, and, for the more virulent viral genotypes, viral RNA can be detected in blood plasma or nucleated blood cells respectively [63, 64] . At least three studies have correlated plasma viral RNA with disease severity for HCPS and HFRS, suggesting that the replication of the virus plays an ongoing and real-time role in viral pathogenesis [65] [66] [67] . Several hallmark pathologic changes have been identified that occur in both HFRS and HCPS. A critical feature of both is a transient (~ 1-5 days) capillary leak involving the kidney and retroperitoneal space in HFRS and the lungs in HCPS. The resulting leakage is exudative in character, with chemical composition high in protein and resembling plasma. The continued experience indicating the strong tissue tropism for endothelial cells, specifically, is among the several factors that make β3 integrin an especially attractive candidate as an important in vivo receptor for hantaviruses. It is likely that hantaviruses arrive at their target tissues through uptake by regional lymph nodes, perhaps with or within an escorting lung histiocyte. The virus seeds local endothelium, where the first few infected cells give rise, ultimately, to a primary viremia, a process that appears to take a long time for hantavirus infections [62, 63] .	`Which is an especially attractive candidate as an important in vivo receptor for hantaviruses?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
auto_find_batch_size: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
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: 4
max_steps: -1
lr_scheduler_type: cosine
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: 42
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: True
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: True
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_fused
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: True
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.0549	10	5.6725	-	-	-	-	-
0.1099	20	4.6781	-	-	-	-	-
0.1648	30	3.9597	-	-	-	-	-
0.2198	40	3.2221	-	-	-	-	-
0.2747	50	2.2144	-	-	-	-	-
0.3297	60	2.8916	-	-	-	-	-
0.3846	70	1.7038	-	-	-	-	-
0.4396	80	2.4738	-	-	-	-	-
0.4945	90	1.8951	-	-	-	-	-
0.5495	100	1.515	-	-	-	-	-
0.6044	110	1.5431	-	-	-	-	-
0.6593	120	2.4492	-	-	-	-	-
0.7143	130	1.656	-	-	-	-	-
0.7692	140	1.7953	-	-	-	-	-
0.8242	150	1.8679	-	-	-	-	-
0.8791	160	2.1551	-	-	-	-	-
0.9341	170	1.5363	-	-	-	-	-
0.9890	180	1.2529	-	-	-	-	-
1.0	182	-	0.3894	0.4585	0.4805	0.3287	0.4926
1.0440	190	1.319	-	-	-	-	-
1.0989	200	1.0985	-	-	-	-	-
1.1538	210	1.0403	-	-	-	-	-
1.2088	220	0.4363	-	-	-	-	-
1.2637	230	0.2102	-	-	-	-	-
1.3187	240	0.3584	-	-	-	-	-
1.3736	250	0.2683	-	-	-	-	-
1.4286	260	0.4438	-	-	-	-	-
1.4835	270	0.34	-	-	-	-	-
1.5385	280	0.4296	-	-	-	-	-
1.5934	290	0.2323	-	-	-	-	-
1.6484	300	0.3259	-	-	-	-	-
1.7033	310	0.4339	-	-	-	-	-
1.7582	320	0.1524	-	-	-	-	-
1.8132	330	0.0782	-	-	-	-	-
1.8681	340	0.4306	-	-	-	-	-
1.9231	350	0.312	-	-	-	-	-
1.9780	360	0.2112	-	-	-	-	-
2.0	364	-	0.4139	0.4526	0.4762	0.3761	0.4672
2.0330	370	0.2341	-	-	-	-	-
2.0879	380	0.1965	-	-	-	-	-
2.1429	390	0.3019	-	-	-	-	-
2.1978	400	0.1518	-	-	-	-	-
2.2527	410	0.0203	-	-	-	-	-
2.3077	420	0.0687	-	-	-	-	-
2.3626	430	0.0206	-	-	-	-	-
2.4176	440	0.3615	-	-	-	-	-
2.4725	450	0.4674	-	-	-	-	-
2.5275	460	0.0623	-	-	-	-	-
2.5824	470	0.0222	-	-	-	-	-
2.6374	480	0.1049	-	-	-	-	-
2.6923	490	0.4955	-	-	-	-	-
2.7473	500	0.439	-	-	-	-	-
2.8022	510	0.0052	-	-	-	-	-
2.8571	520	0.16	-	-	-	-	-
2.9121	530	0.0583	-	-	-	-	-
2.9670	540	0.0127	-	-	-	-	-
3.0	546	-	0.4427	0.4765	0.508	0.397	0.5021
3.0220	550	0.0143	-	-	-	-	-
3.0769	560	0.0228	-	-	-	-	-
3.1319	570	0.0704	-	-	-	-	-
3.1868	580	0.0086	-	-	-	-	-
3.2418	590	0.001	-	-	-	-	-
3.2967	600	0.002	-	-	-	-	-
3.3516	610	0.0016	-	-	-	-	-
3.4066	620	0.021	-	-	-	-	-
3.4615	630	0.0013	-	-	-	-	-
3.5165	640	0.0723	-	-	-	-	-
3.5714	650	0.0045	-	-	-	-	-
3.6264	660	0.0048	-	-	-	-	-
3.6813	670	0.1005	-	-	-	-	-
3.7363	680	0.0018	-	-	-	-	-
3.7912	690	0.0101	-	-	-	-	-
3.8462	700	0.0104	-	-	-	-	-
3.9011	710	0.0025	-	-	-	-	-
3.9560	720	0.014	-	-	-	-	-
4.0	728	-	0.4335	0.4775	0.5000	0.3911	0.4877

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.9
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.31.0
Datasets: 2.19.1
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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}