checkpoint-258/README.md

metadata

base_model: microsoft/deberta-v3-base
datasets:
  - tals/vitaminc
  - allenai/scitail
  - allenai/sciq
  - allenai/qasc
  - sentence-transformers/msmarco-msmarco-distilbert-base-v3
  - sentence-transformers/natural-questions
  - sentence-transformers/trivia-qa
  - sentence-transformers/gooaq
  - google-research-datasets/paws
language:
  - en
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:123245
  - loss:CachedGISTEmbedLoss
widget:
  - source_sentence: what type of inheritance does haemochromatosis
    sentences:
      - >-
        Nestled on the tranquil banks of the Pamlico River, Moss Landing is a
        vibrant new community of thoughtfully conceived, meticulously crafted
        single-family homes in Washington, North Carolina. Washington is
        renowned for its historic architecture and natural beauty.
      - >-
        1 Microwave on high for 8 to 10 minutes or until tender, turning the
        yams once. 2  To microwave sliced yams: Wash, peel, and cut off the
        woody portions and ends. 3  Cut yams into quarters. 4  Place the yams
        and 1/2 cup water in a microwave-safe casserole.ake the Yams. 1  Place
        half the yams in a 1-quart casserole. 2  Layer with half the brown sugar
        and half the margarine. 3  Repeat the layers. 4  Bake, uncovered, in a
        375 degree F oven for 30 to 35 minutes or until the yams are glazed,
        spooning the liquid over the yams once or twice during cooking.
      - >-
        Types 1, 2, and 3 hemochromatosis are inherited in an autosomal
        recessive pattern, which means both copies of the gene in each cell have
        mutations. Most often, the parents of an individual with an autosomal
        recessive condition each carry one copy of the mutated gene but do not
        show signs and symptoms of the condition.Type 4 hemochromatosis is
        distinguished by its autosomal dominant inheritance pattern.With this
        type of inheritance, one copy of the altered gene in each cell is
        sufficient to cause the disorder. In most cases, an affected person has
        one parent with the condition.ype 1, the most common form of the
        disorder, and type 4 (also called ferroportin disease) begin in
        adulthood. Men with type 1 or type 4 hemochromatosis typically develop
        symptoms between the ages of 40 and 60, and women usually develop
        symptoms after menopause. Type 2 hemochromatosis is a juvenile-onset
        disorder.
  - source_sentence: >-
      More than 273 people have died from the 2019-20 coronavirus outside
      mainland China .
    sentences:
      - >-
        More than 3,700 people have died : around 3,100 in mainland China and
        around 550 in all other countries combined .
      - >-
        More than 3,200 people have died : almost 3,000 in mainland China and
        around 275 in other countries .
      - more than 4,900 deaths have been attributed to COVID-19 .
  - source_sentence: >-
      The male reproductive system consists of structures that produce sperm and
      secrete testosterone.
    sentences:
      - What does the male reproductive system consist of?
      - What facilitates the diffusion of ions across a membrane?
      - >-
        Autoimmunity can develop with time, and its causes may be rooted in
        this?
  - source_sentence: Nitrogen gas comprises about three-fourths of earth's atmosphere.
    sentences:
      - What do all cells have in common?
      - What gas comprises about three-fourths of earth's atmosphere?
      - >-
        What do you call an animal in which the embryo, often termed a joey, is
        born immature and must complete its development outside the mother's
        body?
  - source_sentence: What device is used to regulate a person's heart rate?
    sentences:
      - >-
        Marie Antoinette and the French Revolution    .   Famous Faces    .  
        Mad Max: Maximilien Robespierre   |   PBS Extended Interviews >
        Resources > For Educators > Mad Max: Maximilien Robespierre Maximilien
        Robespierre was born May 6, 1758 in Arras, France. Educated at the Lycée
        Louis-le-Grand in Paris as a lawyer, Robespierre became a disciple of
        philosopher Jean-Jacques Rousseau and a passionate advocate for the
        poor. Called "the Incorruptible" because of his unwavering dedication to
        the Revolution, Robespierre joined the Jacobin Club and earned a loyal
        following. In contrast to the more republican Girondins and Marie
        Antoinette, Robespierre fiercely opposed declaring war on Austria,
        feeling it would distract from revolutionary progress in France.
        Robespierre's exemplary oratory skills influenced the National
        Convention in 1792 to avoid seeking public opinion about the
        Convention’s decision to execute King Louis XVI.  In 1793, the
        Convention elected Robespierre to the Committee of Public Defense. He
        was a highly controversial member, developing radical policies, warning
        of conspiracies, and suggesting restructuring the Convention. This
        behavior eventually led to his downfall, and he was guillotined without
        trial on 10th Thermidor An II (July 28, 1794), marking the end of the
        Reign of Terror. Famous Faces
      - >-
        Devices for Arrhythmia Devices for Arrhythmia Updated:Dec 21,2016 In a
        medical emergency, life-threatening arrhythmias may be stopped by giving
        the heart an electric shock (as with a defibrillator ). For people with
        recurrent arrhythmias, medical devices such as a pacemaker and
        implantable cardioverter defibrillator (ICD) can help by continuously
        monitoring the heart's electrical system and providing automatic
        correction when an arrhythmia starts to occur. This section covers
        everything you need to know about these devices. Implantable
        Cardioverter Defibrillator (ICD)
      - >-
        vintage cleats | eBay vintage cleats: 1 2 3 4 5 eBay determines this
        price through a machine learned model of the product's sale prices
        within the last 90 days. eBay determines trending price through a
        machine learned model of the product’s sale prices within the last 90
        days. "New" refers to a brand-new, unused, unopened, undamaged item, and
        "Used" refers to an item that has been used previously. Top Rated Plus
        Sellers with highest buyer ratings Returns, money back Sellers with
        highest buyer ratings Returns, money back
model-index:
  - name: SentenceTransformer based on microsoft/deberta-v3-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.4297034177530014
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.49463792972220844
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.4527271663445909
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.46803254405357775
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.4381297122634254
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.455142390722399
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.3153020725919898
            name: Pearson Dot
          - type: spearman_dot
            value: 0.31075978504991664
            name: Spearman Dot
          - type: pearson_max
            value: 0.4527271663445909
            name: Pearson Max
          - type: spearman_max
            value: 0.49463792972220844
            name: Spearman Max
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: allNLI dev
          type: allNLI-dev
        metrics:
          - type: cosine_accuracy
            value: 0.693359375
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.9488164782524109
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.5440613026819924
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.8723046779632568
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.4068767908309456
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8208092485549133
            name: Cosine Recall
          - type: cosine_ap
            value: 0.5017454777328199
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.673828125
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 668.8308715820312
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.5069124423963134
            name: Dot F1
          - type: dot_f1_threshold
            value: 449.8724365234375
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.34518828451882844
            name: Dot Precision
          - type: dot_recall
            value: 0.953757225433526
            name: Dot Recall
          - type: dot_ap
            value: 0.3969704201342592
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.689453125
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 127.58004760742188
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.5362035225048923
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 221.26995849609375
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.40532544378698226
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.791907514450867
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.5053834291774996
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.6875
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 7.274426460266113
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.5429141716566867
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 12.62590217590332
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.4146341463414634
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.7861271676300579
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.5011125896179964
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.693359375
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 668.8308715820312
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.5440613026819924
            name: Max F1
          - type: max_f1_threshold
            value: 449.8724365234375
            name: Max F1 Threshold
          - type: max_precision
            value: 0.4146341463414634
            name: Max Precision
          - type: max_recall
            value: 0.953757225433526
            name: Max Recall
          - type: max_ap
            value: 0.5053834291774996
            name: Max Ap
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Qnli dev
          type: Qnli-dev
        metrics:
          - type: cosine_accuracy
            value: 0.6328125
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.8666848540306091
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.6366366366366366
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.7626283168792725
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.4930232558139535
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8983050847457628
            name: Cosine Recall
          - type: cosine_ap
            value: 0.6314460649736229
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.6015625
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 507.15960693359375
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.638680659670165
            name: Dot F1
          - type: dot_f1_threshold
            value: 389.59454345703125
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.494199535962877
            name: Dot Precision
          - type: dot_recall
            value: 0.902542372881356
            name: Dot Recall
          - type: dot_ap
            value: 0.5696093250757446
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.6328125
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 210.99937438964844
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.6392961876832844
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 295.44036865234375
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.48878923766816146
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.923728813559322
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.6305567474066167
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.626953125
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 11.648075103759766
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.6362098138747886
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 14.59055233001709
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.5295774647887324
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.7966101694915254
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.630384295725278
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.6328125
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 507.15960693359375
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.6392961876832844
            name: Max F1
          - type: max_f1_threshold
            value: 389.59454345703125
            name: Max F1 Threshold
          - type: max_precision
            value: 0.5295774647887324
            name: Max Precision
          - type: max_recall
            value: 0.923728813559322
            name: Max Recall
          - type: max_ap
            value: 0.6314460649736229
            name: Max Ap

SentenceTransformer based on microsoft/deberta-v3-base

This is a sentence-transformers model finetuned from microsoft/deberta-v3-base on the negation-triplets, vitaminc-pairs, scitail-pairs-qa, scitail-pairs-pos, xsum-pairs, sciq_pairs, qasc_pairs, openbookqa_pairs, msmarco_pairs, nq_pairs, trivia_pairs, gooaq_pairs, paws-pos and global_dataset datasets. 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/deberta-v3-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity
• Training Datasets:
  • negation-triplets
  • vitaminc-pairs
  • scitail-pairs-qa
  • scitail-pairs-pos
  • xsum-pairs
  • sciq_pairs
  • qasc_pairs
  • openbookqa_pairs
  • msmarco_pairs
  • nq_pairs
  • trivia_pairs
  • gooaq_pairs
  • paws-pos
  • global_dataset
• Language: en

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("bobox/DeBERTa3-base-STr-CosineWaves-checkpoints-tmp")
# Run inference
sentences = [
    "What device is used to regulate a person's heart rate?",
    "Devices for Arrhythmia Devices for Arrhythmia Updated:Dec 21,2016 In a medical emergency, life-threatening arrhythmias may be stopped by giving the heart an electric shock (as with a defibrillator ). For people with recurrent arrhythmias, medical devices such as a pacemaker and implantable cardioverter defibrillator (ICD) can help by continuously monitoring the heart's electrical system and providing automatic correction when an arrhythmia starts to occur. This section covers everything you need to know about these devices. Implantable Cardioverter Defibrillator (ICD)",
    'vintage cleats | eBay vintage cleats: 1 2 3 4 5 eBay determines this price through a machine learned model of the product\'s sale prices within the last 90 days. eBay determines trending price through a machine learned model of the product’s sale prices within the last 90 days. "New" refers to a brand-new, unused, unopened, undamaged item, and "Used" refers to an item that has been used previously. Top Rated Plus Sellers with highest buyer ratings Returns, money back Sellers with highest buyer ratings Returns, money back',
]
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

Semantic Similarity

• Dataset: sts-test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4297
spearman_cosine	0.4946
pearson_manhattan	0.4527
spearman_manhattan	0.468
pearson_euclidean	0.4381
spearman_euclidean	0.4551
pearson_dot	0.3153
spearman_dot	0.3108
pearson_max	0.4527
spearman_max	0.4946

Binary Classification

• Dataset: allNLI-dev
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.6934
cosine_accuracy_threshold	0.9488
cosine_f1	0.5441
cosine_f1_threshold	0.8723
cosine_precision	0.4069
cosine_recall	0.8208
cosine_ap	0.5017
dot_accuracy	0.6738
dot_accuracy_threshold	668.8309
dot_f1	0.5069
dot_f1_threshold	449.8724
dot_precision	0.3452
dot_recall	0.9538
dot_ap	0.397
manhattan_accuracy	0.6895
manhattan_accuracy_threshold	127.58
manhattan_f1	0.5362
manhattan_f1_threshold	221.27
manhattan_precision	0.4053
manhattan_recall	0.7919
manhattan_ap	0.5054
euclidean_accuracy	0.6875
euclidean_accuracy_threshold	7.2744
euclidean_f1	0.5429
euclidean_f1_threshold	12.6259
euclidean_precision	0.4146
euclidean_recall	0.7861
euclidean_ap	0.5011
max_accuracy	0.6934
max_accuracy_threshold	668.8309
max_f1	0.5441
max_f1_threshold	449.8724
max_precision	0.4146
max_recall	0.9538
max_ap	0.5054

Binary Classification

• Dataset: Qnli-dev
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.6328
cosine_accuracy_threshold	0.8667
cosine_f1	0.6366
cosine_f1_threshold	0.7626
cosine_precision	0.493
cosine_recall	0.8983
cosine_ap	0.6314
dot_accuracy	0.6016
dot_accuracy_threshold	507.1596
dot_f1	0.6387
dot_f1_threshold	389.5945
dot_precision	0.4942
dot_recall	0.9025
dot_ap	0.5696
manhattan_accuracy	0.6328
manhattan_accuracy_threshold	210.9994
manhattan_f1	0.6393
manhattan_f1_threshold	295.4404
manhattan_precision	0.4888
manhattan_recall	0.9237
manhattan_ap	0.6306
euclidean_accuracy	0.627
euclidean_accuracy_threshold	11.6481
euclidean_f1	0.6362
euclidean_f1_threshold	14.5906
euclidean_precision	0.5296
euclidean_recall	0.7966
euclidean_ap	0.6304
max_accuracy	0.6328
max_accuracy_threshold	507.1596
max_f1	0.6393
max_f1_threshold	389.5945
max_precision	0.5296
max_recall	0.9237
max_ap	0.6314

Training Details

Training Datasets

negation-triplets

• Dataset: negation-triplets
• Size: 6,700 training samples
• Columns: anchor, entailment, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	entailment	negative
  type	string	string	string
  details	min: 5 tokens mean: 22.48 tokens max: 83 tokens	min: 4 tokens mean: 14.16 tokens max: 45 tokens	min: 5 tokens mean: 14.41 tokens max: 40 tokens

• Samples:

  anchor	entailment	negative
  Gà raudot is a commune of the Aube dà partement in the north-central part of France .	Gà raudot is a commune in the Aube department in north-central France .	Gà raudot is a city in the Aube department in south-central France.
  Jamie S. Rich from DVD Talk said , `` In addition to the solid writing , Avatar the Last Airbender also has amazing animation .	Jamie S. Rich from DVD Talk remarked , `` In addition to the solid writing , Avatar the Last Airbender also has amazing animation .	Jamie S. Rich from DVD Talk remarked, "In addition to the weak writing, Avatar the Last Airbender also has poor animation.
  A person working with an artichoke in a bowl on a counter.	a person putting some grapes in a bowl	a person taking some grapes out of a bowl

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

vitaminc-pairs

• Dataset: vitaminc-pairs at be6febb
• Size: 6,700 training samples
• Columns: claim and evidence
• Approximate statistics based on the first 1000 samples:

  	claim	evidence
  type	string	string
  details	min: 7 tokens mean: 16.54 tokens max: 44 tokens	min: 9 tokens mean: 38.33 tokens max: 184 tokens

• Samples:

  claim	evidence
  William Ingraham Koch is an American billionaire .	William Ingraham Koch ( ; born May 3 , 1940 ) is an American billionaire businessman , sailor , and collector .
  The single was number 9 on US Billboard Hot 100 and number 10 in the United Kingdom .	The album 's fourth single '' Loyal '' '' became its most successful , by peaking at number 9 on the US Billboard Hot 100 and at number 10 in the United Kingdom . ''
  In Sucker Punch , Amber and Blondie are shot .	He shoots Amber and Blondie and attempts to rape Babydoll , but she stabs him with the kitchen knife and steals his master key .

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

scitail-pairs-qa

• Dataset: scitail-pairs-qa at 0cc4353
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 7 tokens mean: 15.9 tokens max: 41 tokens	min: 6 tokens mean: 15.07 tokens max: 33 tokens

• Samples:

  sentence1	sentence2
  A heterocyclic compound contains atoms of two or more different elements in its ring structure.	What type of compound contains atoms of two or more different elements in its ring structure?
  Tamiflu inhibits spread of virus.	What effect does tamiflu have on viruses and cells?
  Dependent variable is the term for the affected factor in an experiment.	What is the term for the affected factor in an experiment?

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

scitail-pairs-pos

• Dataset: scitail-pairs-pos at 0cc4353
• Size: 5,762 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 23.5 tokens max: 67 tokens	min: 7 tokens mean: 15.57 tokens max: 39 tokens

• Samples:

  sentence1	sentence2
  This stored energy is called potential energy.	Energy that is stored in a person or object is called potential energy.
  Although tornadoes may occur at any time of the year, peak tornado occurrence in Arkansas is during the spring.	Tornadoes can occur in any.
  The sun is the ultimate source of energy in most terrestrial and marine ecosystems.	Ultimately, most life forms get their energy from the sun.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

xsum-pairs

• Dataset: xsum-pairs
• Size: 6,700 training samples
• Columns: document and summary
• Approximate statistics based on the first 1000 samples:

  	document	summary
  type	string	string
  details	min: 55 tokens mean: 217.03 tokens max: 410 tokens	min: 12 tokens mean: 25.26 tokens max: 53 tokens

• Samples:

  document	summary
  Ferry operator the Steam Packet Company said 29,241 people visited during the fortnight - up 6.3% on 2015. Figures also showed 4,013 fans brought a motorbike - an increase of 4.5%. The fortnight-long motorcycling festival, includes the Classic TT and Manx Grand Prix races - both held on the Mountain Course. Steam Packet Chief Executive Mark Woodward said the figures were "very encouraging".	Nearly 30,000 passengers travelled to the Isle of Man by ferry for this year's Festival of Motorcycling, according to the latest figures.
  Rakhat Aliyev, a former ambassador to Austria, is accused of killing two bank managers in his home country in 2007. Kazakhstan has attempted to have him extradited to face trial, but Austria has twice refused because of the former Soviet republic's human rights record. Instead, Austrian prosecutors opened their own murder investigation in 2011. Mr Aliyev has denounced the case against him as politically motivated. However, in June he flew voluntarily to Vienna from his home in Malta and handed himself in to the Austrian authorities. Since then, he has been held in "investigative custody". On Tuesday, a court in Vienna said Mr Aliyev had been charged. A spokeswoman for the court told the Reuters news agency that the judge had not set any bail option and that Mr Aliyev's lawyers had two weeks to appeal against the charges. He faces at least 10 years in prison if found guilty of murder. If extradited to Kazakhstan he could face a sentence of up to 40 years. Mr Aliyev was once married to Kazakh President Nursultan Nazarbayev's eldest daughter, Dariga. A businessman with extensive contacts among the Kazakh elite, he spoke out against Mr Nazarbayev after being sacked as ambassador to Austria.	A former son-in-law of Kazakhstan's president who later became a prominent opponent has been charged with murder by prosecutors in Austria.
  Four people are reported to have pushed three trolleys containing more than £1,350 worth of Lego out of a Toys R Us store in Poole, Dorset Police said. Similar thefts were also reported at Smyths Toy Superstore in Bournemouth and a Tesco store in Poole. Officers said the offences could be linked to similar thefts in surrounding counties and CCTV images of two men and two women have been released. The Poole thefts at Tesco on Tower Park and Toys R Us on Nuffield Road took place within 10 minutes of each other on the evening of 15 May. Batman Lego was among the items taken, police said. The offenders made off in a silver Vauxhall Vectra with the registration BK56 XOB - known to be a false number plate from a stolen vehicle, police said. The theft at Smyths Toy Superstore on Mallard Road Retail Park, Bournemouth was on the afternoon of 10 May. Anyone who recognises the people in the images is urged to call the force.	Almost £3,000 worth of Lego has been stolen in targeted raids on toy shops.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

sciq_pairs

• Dataset: sciq_pairs at 2c94ad3
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 6 tokens mean: 16.6 tokens max: 57 tokens	min: 2 tokens mean: 84.49 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  What is an upward force that fluids exert on any object that is placed in them?	Buoyant force is an upward force that fluids exert on any object that is placed in them. The ability of fluids to exert this force is called buoyancy . What explains buoyant force? A fluid exerts pressure in all directions, but the pressure is greater at greater depth. Therefore, the fluid below an object, where the fluid is deeper, exerts greater pressure on the object than the fluid above it. You can see in the Figure below how this works. Buoyant force explains why the girl pictured above can float in water.
  The most abundant formed elements in blood, erythrocytes are red, biconcave disks packed with an oxygen-carrying compound called this?	18.3 Erythrocytes The most abundant formed elements in blood, erythrocytes are red, biconcave disks packed with an oxygen-carrying compound called hemoglobin. The hemoglobin molecule contains four globin proteins bound to a pigment molecule called heme, which contains an ion of iron. In the bloodstream, iron picks up oxygen in the lungs and drops it off in the tissues; the amino acids in hemoglobin then transport carbon dioxide from the tissues back to the lungs. Erythrocytes live only 120 days on average, and thus must be continually replaced. Worn-out erythrocytes are phagocytized by macrophages and their hemoglobin is broken down. The breakdown products are recycled or removed as wastes: Globin is broken down into amino acids for synthesis of new proteins; iron is stored in the liver or spleen or used by the bone marrow for production of new erythrocytes; and the remnants of heme are converted into bilirubin, or other waste products that are taken up by the liver and excreted in the bile or removed by the kidneys. Anemia is a deficiency of RBCs or hemoglobin, whereas polycythemia is an excess of RBCs.
  What is the process by which plants and animals increase in size?

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

qasc_pairs

• Dataset: qasc_pairs at a34ba20
• Size: 5,177 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 11.37 tokens max: 23 tokens	min: 16 tokens mean: 33.9 tokens max: 63 tokens

• Samples:

  sentence1	sentence2
  What is required before a chemical change?	All chemical reactions require activation energy to get started.. Chemical changes are a result of chemical reactions. Activation energy must be used before a chemical change happens.
  Endocrine hormones move from place to place through the	Endocrine hormones travel throughout the body in the blood.. For the tourists, there are many places to travel. Endocrine hormones move from place to place in the body through the blood.
  Soil nutrition can be what?	Soil can be depleted of nutrients.. For the nonrenewable resources, depletion means extraction of the available natural resources. soil nutrition can be extracted

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

openbookqa_pairs

• Dataset: openbookqa_pairs
• Size: 3,029 training samples
• Columns: question and fact
• Approximate statistics based on the first 1000 samples:

  	question	fact
  type	string	string
  details	min: 4 tokens mean: 13.72 tokens max: 65 tokens	min: 5 tokens mean: 11.4 tokens max: 31 tokens

• Samples:

  question	fact
  What causes direct damage to the lungs?	smoking causes direct damage to the lungs
  Feces on the ground is an indicator of a nearby	an organism is a source of organic material
  What time are you most likely to see a rainbow	sunlight and rain can cause a rainbow

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

msmarco_pairs

• Dataset: msmarco_pairs at 28ff31e
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 4 tokens mean: 8.51 tokens max: 23 tokens	min: 16 tokens mean: 75.53 tokens max: 258 tokens

• Samples:

  sentence1	sentence2
  can olive oil cure ear infection	Olive oil with all its below mentioned properties, helps to prevent the ear pain and infection very efficiently. 1 Olive oil, when applied on the ear, helps to decrease the irritation in the outer and inner ear to ease the pain.
  who was william vale	Squadron Leader William Cherry Vale DFC & Bar, AFC (3 June 1914 – 29 November 1981) was a Royal Air Force (RAF) pilot who, during the Second World War, claimed 30 enemy aircraft shot down and shared in the destruction of three others, and also claiming 6 damaged and another two shared damaged.
  what is swamp fever	Equine Infectious Anemia (Swamp Fever) Table of Contents. General Description. Equine infectious anemia (EIA), also known as swamp fever, is a potentially fatal disease caused by a virus that can infect all types of equines, including horses, mules, zebras and donkeys.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

nq_pairs

• Dataset: nq_pairs at f9e894e
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 9 tokens mean: 11.91 tokens max: 23 tokens	min: 17 tokens mean: 135.35 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  who plays harry from harry and the hendersons	Kevin Peter Hall Kevin Peter Hall (May 9, 1955 – April 10, 1991) was an American actor best known for his roles as the title character in the first two films in the Predator franchise and the title character of Harry in the film and television series, Harry and the Hendersons. He also appeared in the television series Misfits of Science and 227 along with the film, Without Warning.
  where does the eustachian tube drain in the throat	Eustachian tube The Eustachian tube also drains mucus from the middle ear. Upper respiratory tract infections or allergies can cause the Eustachian tube, or the membranes surrounding its opening to become swollen, trapping fluid, which serves as a growth medium for bacteria, causing ear infections. This swelling can be reduced through the use of decongestants such as pseudoephedrine, oxymetazoline, and phenylephrine.[7] Ear infections are more common in children because the tube is horizontal and shorter, making bacterial entry easier, and it also has a smaller diameter, making the movement of fluid more difficult. In addition, children's developing immune systems and poor hygiene habits make them more prone to upper respiratory infections.
  who played boss hogg on the dukes of hazzard	Sorrell Booke Sorrell Booke (January 4, 1930 – February 11, 1994) was an American actor who performed on stage, screen, and television. He is best known for his role as corrupt politician Jefferson Davis "Boss" Hogg in the television show The Dukes of Hazzard.[1]

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

trivia_pairs

• Dataset: trivia_pairs at a7c36e3
• Size: 3,749 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 8 tokens mean: 17.79 tokens max: 64 tokens	min: 20 tokens mean: 209.39 tokens max: 498 tokens

• Samples:

  query	answer
  Which singer and songwriter of the 1970s and 1980s was the first to have three consecutive double albums hit #1 on the Billboard charts, and was the first female artist to have four number-one singles in a thirteen-month period?	Donna Summer - Music on Google Play Donna Summer About the artist LaDonna Adrian Gaines, known by her stage name Donna Summer, was an American singer, songwriter, painter, and actress. She gained prominence during the disco era of the late-1970s. A five-time Grammy Award winner, she was the first artist to have three consecutive double albums reach No. 1 on the United States Billboard 200 chart and charted four number-one singles in the U.S. within a 12-month period. Summer has reportedly sold over 140 million records, making her one of the world's best-selling artists of all time. She also charted two number-one singles on the R&B charts in the U.S. and one number-one in the U.K. Summer earned a total of 32 hit singles on the U.S. Billboard Hot 100 chart in her lifetime, with 14 of those reaching the top ten. She claimed a top 40 hit every year between 1975 and 1984, and from her first top ten hit in 1976, to the end of 1982, she had 12 top ten hits; more than any other act. She returned to the Hot 100's top five in 1983, and claimed her final top ten hit in 1989 with "This Time I Know It's for Real". Her most recent Hot 100 hit came in 1999 with "I Will Go With You".
  What type of car did Burt Reynolds drive in the 1977 film ‘Smokey and the Bandit’?	What Cars Did They Drive In 'Smokey and The Bandit' Share on Twitter Perhaps more famous then the actual actors themselves, was the car driven by Burt Reynold’s character Bo Darville the “Bandit”. We got a call this morning from  a woman who had claimed they had a car for sale that was the same car that Jackie Gleason’s character Sheriff Buford T. Justice.We decided to do some digging around the Internet to see exactly what kind of cars they were driving. Bo Darville The “Bandit” Flickr Well it turns out there is some debate raging across the Internet about whether or not Burt Reynolds was driving a 1976 or a 1977. But there was never any doubt to the model. Burt cruised through the movie inside a Pontiac Trans Am, with the now iconic Black and Gold paint scheme.   1 Sheriff Buford T. Justice What’s The Bandit with out being chased by the Sheriff? Of course Buford had to have something that could almost keep up with the Bandit as they raced across several states. The Sheriff’s vehicle was a 1977 Ponitac LeMans.
  In 1985, which funny man was the first UK citizen to make a mobile phone call?	The call that changed our world: Blue plaque to mark site where a mobile phone was first used in the UK – The Sun SMARTPHONES may have changed the way we communicate and view the world – but the first mobile phone, which was heavier than a new-born baby, was no less groundbreaking. On New Year’s Day in 1985, the UK’s first official mobile call was made by comedian Ernie Wise from St Katharine Docks in London to the Vodafone offices in Newbury, Berkshire 65 miles away. This historic moment, which marked the start of the mobile age, is to be commemorated with a blue plaque in the town of Berkshire where Vodafone was founded and still resides today. Vodafone Newbury Town Council has applied for formal planning permission for the plaque, which will be placed at Thames Court, and will feature the wording “The first official mobile telephone call in the UK was made to Vodafone offices close to this site on January 1, 1985.” The phone which TV favourite Ernie, one half of legendary double act Morecambe and Wise, used to call Vodafone’s Sir Michael Harrison bears little comparison to the sophisticated devices we carry today. Weighing an incredible 11lbs, the equivalent of five bags of sugar, and costing the equivalent of £5,000, no one standing next to the diminutive funny man could have known the significance of what they were witnessing.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

gooaq_pairs

• Dataset: gooaq_pairs at b089f72
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 11.34 tokens max: 19 tokens	min: 15 tokens mean: 57.57 tokens max: 143 tokens

• Samples:

  sentence1	sentence2
  why is my urine bright yellow when pregnant?	It can range from an intense bright yellow to a darker, almost orange-yellow colour. The colour of the urine is caused by the pigment urochrome, which is also known as urobilin. Urobilin is made when the body breaks down haemoglobin from dead red blood cells.
  are vw beetles being discontinued?	Volkswagen is discontinuing the iconic Beetle after 80 years on the market. Volkswagen announced it will stop worldwide production of the iconic Beetle by summer 2019. The move comes as the auto market continues its march toward SUVs and crossover vehicles.
  do seth and summer break up?	Summer and Seth broke up quite a few times for numerous reasons including Seth running away and Summer moving on and starting a relationship with Zach, Summer thinking Seth was seeing Anna again when really she was just trying to help him get into college to be near Summer, in the end they get back together and end up ...

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

paws-pos

• Dataset: paws-pos at 161ece9
• Size: 6,700 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 9 tokens mean: 25.71 tokens max: 56 tokens	min: 9 tokens mean: 25.7 tokens max: 54 tokens

• Samples:

  sentence1	sentence2
  The bay ends at Quinte West ( Trenton ) and the Trent River , both also on the north side .	The bay ends at Trenton ( Quinte West ) and the Trent River , both on the north side .
  The first main span was positioned in 1857 and the finished bridge was opened on 2 May 1859 by Prince Albert .	The first main span was positioned in 1857 and the completed bridge was opened by Prince Albert on 2 May 1859 .
  The reactance is defined as the imaginary part of electrical impedance and is equal , but generally not analogous to reversing the susceptance .	Reactance is defined as the imaginary part of Electrical impedance , and is equal but not generally analogous to the inverse of the susceptance .

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

global_dataset

• Dataset: global_dataset
• Size: 45,228 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 4 tokens mean: 29.03 tokens max: 329 tokens	min: 2 tokens mean: 51.81 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  what is emla cream used for	EMLA cream for local anaesthesia. This leaflet is about the use of EMLA cream. The cream is used to make an area of skin numb, which is called local anaesthesia. It may be used before taking blood with a needle or putting in a drip (cannula), or before a small surgical procedure that might be painful.
  Adana Province , Turkey is a village in the District of Yüreğir , Düzce .	The province of Adana , Turkey is a village in the district of Yüreğir , Düzce .
  A second factor is the journalistic culture of the news conference, which rewards zinger questions that provoke news--and discourages anything that courts televised dullness.	One of the factors is the culture of journalistic news conferences which discourages dullness.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

Evaluation Datasets

vitaminc-pairs

• Dataset: vitaminc-pairs at be6febb
• Size: 128 evaluation samples
• Columns: claim and evidence
• Approximate statistics based on the first 1000 samples:

  	claim	evidence
  type	string	string
  details	min: 9 tokens mean: 21.42 tokens max: 41 tokens	min: 11 tokens mean: 35.55 tokens max: 79 tokens

• Samples:

  claim	evidence
  Dragon Con had over 5000 guests .	Among the more than 6000 guests and musical performers at the 2009 convention were such notables as Patrick Stewart , William Shatner , Leonard Nimoy , Terry Gilliam , Bruce Boxleitner , James Marsters , and Mary McDonnell .
  COVID-19 has reached more than 185 countries .	As of , more than cases of COVID-19 have been reported in more than 190 countries and 200 territories , resulting in more than deaths .
  In March , Italy had 3.6x times more cases of coronavirus than China .	As of 12 March , among nations with at least one million citizens , Italy has the world 's highest per capita rate of positive coronavirus cases at 206.1 cases per million people ( 3.6x times the rate of China ) and is the country with the second-highest number of positive cases as well as of deaths in the world , after China .

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

negation-triplets

• Dataset: negation-triplets
• Size: 128 evaluation samples
• Columns: anchor, entailment, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	entailment	negative
  type	string	string	string
  details	min: 8 tokens mean: 14.66 tokens max: 35 tokens	min: 6 tokens mean: 12.3 tokens max: 22 tokens	min: 6 tokens mean: 12.62 tokens max: 23 tokens

• Samples:

  anchor	entailment	negative
  An open door leading to a bathroom toilet, with a shower rack and bureau visible.	A bathroom has a red circular rug by the toilet.	A bathroom has no red circular rug by the toilet.
  A child wearing a red top is standing behind a blond headed child sitting in a wheelbarrow.	A child wearing a red top is standing behind a blond headed child	A child wearing a red top is standing far from a blond headed child
  Two women waiting at a bench next to a street.	A woman sitting on a bench and a woman standing waiting for the bus.	A woman sitting on a bench and a woman walking away from the bus stop.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

scitail-pairs-pos

• Dataset: scitail-pairs-pos at 0cc4353
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 9 tokens mean: 20.28 tokens max: 56 tokens	min: 8 tokens mean: 15.48 tokens max: 23 tokens

• Samples:

  sentence1	sentence2
  humans normally have 23 pairs of chromosomes.	Humans typically have 23 pairs pairs of chromosomes.
  A solution is a homogenous mixture of two or more substances that exist in a single phase.	Solution is the term for a homogeneous mixture of two or more substances.
  Upwelling The physical process in near-shore ocean systems of rising of nutrients and colder bottom waters to the surface because of constant wind patterns along the shoreline.	Upwelling is the term for when deep ocean water rises to the surface.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

scitail-pairs-qa

• Dataset: scitail-pairs-qa at 0cc4353
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 7 tokens mean: 15.95 tokens max: 37 tokens	min: 8 tokens mean: 15.4 tokens max: 34 tokens

• Samples:

  sentence1	sentence2
  A lipid is one of a highly diverse group of compounds made up mostly of hydrocarbons.	A lipid is one of a highly diverse group of compounds made up mostly of what?
  Sugar crystals dissolving in water is an example of the formation of a mixture.	Which of the following is an example of the formation of a mixture?
  Starches are complex carbohydrates that are the polymers of glucose.	What complex carbohydrates are the polymers of glucose?

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

xsum-pairs

• Dataset: xsum-pairs
• Size: 128 evaluation samples
• Columns: document and summary
• Approximate statistics based on the first 1000 samples:

  	document	summary
  type	string	string
  details	min: 64 tokens mean: 223.53 tokens max: 399 tokens	min: 13 tokens mean: 25.44 tokens max: 46 tokens

• Samples:

  document	summary
  Former Northampton South MP Tony Clarke said he feared that if the petition was successful the council could lose the £10.25m it is owed by the club. HM Revenue and Customs is owed £166,000 by the club. The borough council said it was seeking a meeting with HMRC. Last week it was revealed that players and staff at Northampton Town Football Club have not been paid due to its financial problems. Manager Chris Wilder paid tribute to the attitude of people who work at the League Two club, saying it has brought them all "much closer together". Mr Clarke, who is also a former director of the club, said: "It absolutely imperative the council objects to the winding-up petition in two weeks time. "If they don't and Northampton Town Football Club goes into receivership then the council won't recover any of its money." He called for the council to be "positive" and "ask for an adjournment" to the winding-up hearing so the club supporters and staff have more time to help save the club. On Monday, councillors backed a motion calling for it to do "whatever we can to help" the football club and the Supporters Trust. It also called for the £10.25m of public money to be "retrieved" and for its audit committee to review its policies and practices.	A former MP has called on Northampton Borough Council to oppose a winding-up petition sought by HM Revenue and Customs (HMCRC) against the town's football club.
  Tokyo's Nikkei 225 closed down 1.32% to 16,819.59 points as a stronger yen against the dollar hurt the country's big exporters for a second day. Toyota and Honda shares finished the day down about 2%, while Mazda shed nearly 5%. At the close of trade, Toyota reported a 4.7% rise in net income for the three months to December. However, the firm's operating profit for the quarter fell by 5.3%, missing forecasts. Australia's S&P/ASX 200 spent the day in negative territory and closed flat, down 0.08% to 16,819.59. The country's big lenders had weighed on the market and analysts said traders were being cautious ahead of a US jobs report due out later. Energy firms regained lost territory late in the day, however, with Woodside finishing up 0.41% and rival Santos up 2.2%. Mining giant BHP finished up close to 5%. Official numbers released earlier showed Australia's retail sales had come in flat for the month of December - a 0.4% gain was expected. But analysts said the numbers still supported economic growth. "December quarter real retail sales rose by 0.6%, which was less than expected, but similar to the last few quarters," said AMP Capital's head economist Shane Oliver. "It implies that consumer spending has again helped support December quarter GDP growth," he added. In Hong Kong, the Hang Seng was up 0.4% to 19,255.88 points in afternoon trade, while the mainland's benchmark Shanghai Composite closed down 0.63% to 2,763.49. South Korea's Kospi index closed flat, up just 0.08% to 1,917.79.	Shares in Asia were in mixed territory on Friday ahead of a closely watched US monthly jobs report.
  In February, Badminton was among seven Olympic sports to lose funding despite Chris Langridge and Marcus Ellis winning doubles bronze at Rio 2016. "We are working through an unprecedented financial situation as a consequence of the recent funding decisions," Badminton England performance director Jon Austin said. The Sudirman Cup starts on 21 May. The event in Gold Coast, Australia, is seen as an unofficial test event for English players ahead of next year's Commonwealth Games to be held in the same city. England finished ninth in the last edition of the World Mixed Team Championships, which take place every two years. "We have had to consider the investments we make very carefully," Austin added. "The pressures we are facing right now, both through the people resource and financial investment needed, means we are regrettably not in a position to commit to the Sudirman Cup this year." Badminton England received around £5.5m between London 2012 and 2016 and was left "staggered" when it had its funding pulled, despite beating a Rio Games performance target set by elite sport funding body UK Sport.	Badminton England has withdrawn from May's World Mixed Team Championships citing government funding cuts.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

sciq_pairs

• Dataset: sciq_pairs at 2c94ad3
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 16.32 tokens max: 42 tokens	min: 2 tokens mean: 89.04 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  Poetically speaking, nature reserves are islands of what, in a sea of habitat degraded by human activity?
  Multiplying the linear momentum of a spinning object by the radius calculates what?	The angular momentum of a spinning object can be found in two equivalent ways. Just like linear momentum, one way, shown in the first equation, is to multiply the moment of inertia, the rotational analog of mass, with the angular velocity. The other way is simply multiplying the linear momentum by the radius, as shown in the second equation.
  What is the term for the intentional release or spread of agents of disease?	Bioterrorism is the intentional release or spread of agents of disease.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

qasc_pairs

• Dataset: qasc_pairs at a34ba20
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 6 tokens mean: 11.82 tokens max: 22 tokens	min: 17 tokens mean: 34.68 tokens max: 57 tokens

• Samples:

  sentence1	sentence2
  Operating an automobile usually requires what from gasoline?	operating an automobile usually requires fossil fuels. Energy pollution Cars operate mainly on gasoline, a fossil fuel. Operating an automobile usually requires energy pollution from gasoline.
  Which unit could a graduated cylinder measure in?	a graduated cylinder is used to measure volume of a liquid. Liquid volume is measured using a unit called a liter. A graduated cyliner measures in liters
  What can decompose wood?	Fungi are the only organisms that can decompose wood.. Mushrooms are organisms known as fungi. mushrooms can decompose wood

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

openbookqa_pairs

• Dataset: openbookqa_pairs
• Size: 128 evaluation samples
• Columns: question and fact
• Approximate statistics based on the first 1000 samples:

  	question	fact
  type	string	string
  details	min: 3 tokens mean: 13.98 tokens max: 47 tokens	min: 4 tokens mean: 11.78 tokens max: 28 tokens

• Samples:

  question	fact
  The thermal production of a stove is generically used for	a stove generates heat for cooking usually
  What creates a valley?	a valley is formed by a river flowing
  when it turns day and night on a planet, what cause this?	a planet rotating causes cycles of day and night on that planet

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

msmarco_pairs

• Dataset: msmarco_pairs at 28ff31e
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 8.73 tokens max: 20 tokens	min: 26 tokens mean: 76.41 tokens max: 182 tokens

• Samples:

  sentence1	sentence2
  what is a normal osmolar gap	The osmolar gap is the difference between the calculated serum osmolarity and the measured serum osmolarity. The normal osmolar gap is 10-15 mmol/L H20 .The osmolar gap is increased in the presence of low molecular weight substances that are not included in the formula for calculating plasma osmolarity.
  how old is kendrick lamar	The 27-year-old rapper has a broad smile on his face. He seems almost as excited as the students, who just might be having their best day of school ... ever. Lamar is on top of the rap game at the moment. His latest album, To Pimp a Butterfly, came out earlier this year and debuted at No. 1 on Billboard's albums chart.
  modific definition	(ˌmɒdɪfɪˈkeɪʃən) n. 1. the act of modifying or the condition of being modified. 2. something modified; the result of a modification. 3. a small change or adjustment. 4. (Grammar) grammar the relation between a modifier and the word or phrase that it modifies. ˈmodifiˌcatory, ˈmodifiˌcative adj.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

nq_pairs

• Dataset: nq_pairs at f9e894e
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 10 tokens mean: 11.68 tokens max: 19 tokens	min: 25 tokens mean: 135.38 tokens max: 466 tokens

• Samples:

  sentence1	sentence2
  patch and kayla on days of our lives	Steve Johnson and Kayla Brady Steve "Patch" Earl Johnson and Dr. Kayla Caroline Brady are a supercouple on the American soap opera Days of Our Lives. Steve is portrayed by Stephen Nichols and Kayla is portrayed by Mary Beth Evans. On the Internet message boards[5] the couple is often referred to by the portmanteau "Stayla" (for Steve and Kayla). The couple was initially popular from 1986 through 1990 until the "death" of Steve. Both characters have recently returned: after Steve being presumed dead for 16 years, Steve returned to the show on June 9, 2006; Kayla returned on June 12, 2006. Steve and Kayla were dropped off canvas in February 2009. Kayla returned in December 2011. In August 2015, Steve returned to Salem, and the couple reunited soon after
  when does the tour de france usually start	Tour de France Traditionally, the race is held primarily in the month of July. While the route changes each year, the format of the race stays the same with the appearance of time trials,[1] the passage through the mountain chains of the Pyrenees and the Alps, and the finish on the Champs-Élysées in Paris.[7][8] The modern editions of the Tour de France consist of 21 day-long segments (stages) over a 23-day period and cover around 3,500 kilometres (2,200 mi).[9] The race alternates between clockwise and counterclockwise circuits of France.[10]
  what's a dell from farmer in the dell	The Farmer in the Dell A dell is a wooded valley. In the Dutch language, the word deel means, among other things, the workspace in a farmer's barn. The use of dell in this song may be a bastardisation of this term.[citation needed]

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

trivia_pairs

• Dataset: trivia_pairs at a7c36e3
• Size: 128 evaluation samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 8 tokens mean: 18.45 tokens max: 47 tokens	min: 38 tokens mean: 207.95 tokens max: 411 tokens

• Samples:

  query	answer
  Messer is German for which item of cutlery?	messer knife
  American Presidents assassinated in office?	Question - Number of Presidents Who Were Assassinated All four of them were killed by shooting. Interestingly enough, they were also all victims of Tecumseh's Curse . Learn More:
  Which Chicago building was formerly known as the Sears Tower?	Willis Tower DISCOVER THE WARM PERSONALITY OF THIS IMPRESSIVE ADDRESS. Welcome to Willis Tower, where there is more than meets the skyline. A bustling community of business, tourism and culture, Willis Tower is so much more than North America's tallest building. It’s home to large well-known companies as well as hundreds of thriving businesses run by smart, passionate people. More than an office building, it’s a cultural landmark and iconic Chicago tourist attraction. Willis Tower is a pivotal point of reference – from across town, from financial centers on both coasts, and from Europe, Asia, and the Middle East. It’s a building with retail and commercial office space at heart, but also inspires tens of thousands of visitors to take in the amazing views of the city and experience the breathtaking Ledge. 110 FLOORS. COUNTLESS STORIES.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

gooaq_pairs

• Dataset: gooaq_pairs at b089f72
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 11.48 tokens max: 18 tokens	min: 16 tokens mean: 58.07 tokens max: 108 tokens

• Samples:

  sentence1	sentence2
  what is the different kinds of antivirus?	['Malware signature antivirus. Malware, or malicious software, installs viruses and spyware on your computer or device without your knowledge. ... ', 'System monitoring antivirus. This is where system monitoring antivirus software comes into play. ... ', 'Machine learning antivirus.']
  1. what is the difference between quantitative and qualitative research proposal?	Qualitative research identifies abstract concepts while quantitative research collects numerical data. But the substantial difference is in the type of action applied and in the size of the sample (respondents).
  how to calculate efn finance?	Instead of preparing a set of forecasted financial statements, you can also calculate your external financing needs (EFN) by using a formula that looks at three changes: 1. Required increases to assets given a change in sales. Formula = (A/S) x (Δ Sales).

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

paws-pos

• Dataset: paws-pos at 161ece9
• Size: 128 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 10 tokens mean: 25.72 tokens max: 42 tokens	min: 10 tokens mean: 25.55 tokens max: 41 tokens

• Samples:

  sentence1	sentence2
  They were there to enjoy us and they were there to pray for us .	They were there for us to enjoy and they were there for us to pray .
  After the end of the war in June 1902 , Higgins left Southampton in the `` SSBavarian '' in August , returning to Cape Town the following month .	In August , after the end of the war in June 1902 , Higgins Southampton left the `` SSBavarian '' and returned to Cape Town the following month .
  From the merger of the Four Rivers Council and the Audubon Council , the Shawnee Trails Council was born .	Shawnee Trails Council was formed from the merger of the Four Rivers Council and the Audubon Council .

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

global_dataset

• Dataset: global_dataset
• Size: 416 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 31.67 tokens max: 399 tokens	min: 2 tokens mean: 58.97 tokens max: 503 tokens

• Samples:

  sentence1	sentence2
  More than 478,000 cases and more than 21,500 deaths have been reported worldwide .	more than 478,000 cases have been reported worldwide ; more than 21,500 people have died and more than 114,000 have recovered.
  Solutions are homogenous mixtures of two or more substances.	Solution is the term for a homogeneous mixture of two or more substances.
  What celestial object has been visited by manned spacecraft and is easily seen from earth?	The Moon is easily seen from Earth. Early astronomers used telescopes to study and map its surface. The Moon has also seen a great number of satellites, rovers, and orbiters. After all, it is relatively easy to get spacecraft to the satellite. Also, before humans could be safely sent to the Moon, many studies and experiments had to be completed.

• Loss: CachedGISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
    (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})
    (2): Normalize()
  ), 'temperature': 0.025}
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 96
• per_device_eval_batch_size: 68
• learning_rate: 3.5e-05
• weight_decay: 0.0005
• num_train_epochs: 2
• lr_scheduler_type: cosine_with_min_lr
• lr_scheduler_kwargs: {'num_cycles': 3.5, 'min_lr': 1.5e-05}
• warmup_ratio: 0.33
• save_safetensors: False
• fp16: True
• push_to_hub: True
• hub_model_id: bobox/DeBERTa3-base-STr-CosineWaves-checkpoints-tmp
• hub_strategy: all_checkpoints
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 96
• per_device_eval_batch_size: 68
• 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: 3.5e-05
• weight_decay: 0.0005
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 2
• max_steps: -1
• lr_scheduler_type: cosine_with_min_lr
• lr_scheduler_kwargs: {'num_cycles': 3.5, 'min_lr': 1.5e-05}
• warmup_ratio: 0.33
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: False
• 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: True
• resume_from_checkpoint: None
• hub_model_id: bobox/DeBERTa3-base-STr-CosineWaves-checkpoints-tmp
• hub_strategy: all_checkpoints
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	negation-triplets loss	vitaminc-pairs loss	sciq pairs loss	openbookqa pairs loss	msmarco pairs loss	paws-pos loss	qasc pairs loss	scitail-pairs-pos loss	trivia pairs loss	scitail-pairs-qa loss	nq pairs loss	gooaq pairs loss	global dataset loss	xsum-pairs loss	Qnli-dev_max_ap	allNLI-dev_max_ap	sts-test_spearman_cosine
0.0008	1	6.6871	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0016	2	5.8546	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0023	3	6.576	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0031	4	6.8301	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0039	5	5.2308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0047	6	6.3588	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0054	7	6.8417	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0062	8	10.3916	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0070	9	5.5136	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0078	10	7.4726	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0085	11	5.5414	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0093	12	4.8507	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0101	13	4.9058	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0109	14	6.2301	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0116	15	7.9813	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0124	16	5.5269	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0132	17	10.0786	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0140	18	9.6075	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0147	19	4.671	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0155	20	6.945	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0163	21	6.233	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0171	22	5.5828	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0178	23	6.6991	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0186	24	5.9928	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0194	25	4.8443	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0202	26	11.0738	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0209	27	6.4076	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0217	28	6.2668	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0225	29	5.092	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0233	30	5.9955	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0240	31	6.6071	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0248	32	4.7984	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0256	33	6.173	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0264	34	5.9604	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0272	35	6.3435	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0279	36	6.0394	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0287	37	6.0135	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0295	38	8.0721	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0303	39	6.2283	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0310	40	5.365	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0318	41	6.0378	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0326	42	6.5136	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0334	43	5.6955	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0341	44	6.1769	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0349	45	6.302	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0357	46	6.0792	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0365	47	5.4317	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0372	48	5.7632	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0380	49	4.6767	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0388	50	6.1871	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0396	51	5.572	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0403	52	7.351	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0411	53	5.6907	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0419	54	5.7986	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0427	55	5.9598	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0434	56	6.024	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0442	57	5.328	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0450	58	5.5545	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0458	59	5.3813	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0465	60	5.3023	5.3504	3.9951	0.9480	5.4622	8.8025	2.7421	6.7080	2.7031	6.3097	3.3195	7.8914	6.8511	5.3453	5.5659	0.6173	0.3812	0.2096
0.0473	61	3.5705	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0481	62	5.8784	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0489	63	8.5966	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0497	64	5.9225	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0504	65	4.6667	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0512	66	6.12	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0520	67	5.2713	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0528	68	6.9483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0535	69	3.6892	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0543	70	7.5618	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0551	71	5.8086	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0559	72	6.517	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0566	73	5.5826	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0574	74	6.5543	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0582	75	6.5721	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0590	76	5.4454	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0597	77	6.3208	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0605	78	6.5299	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0613	79	7.1424	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0621	80	5.1799	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0628	81	6.3358	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0636	82	7.9256	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0644	83	5.4606	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0652	84	5.6861	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0659	85	3.6595	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0667	86	5.3626	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0675	87	5.7214	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0683	88	3.7724	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0690	89	6.8782	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0698	90	7.1858	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0706	91	6.1052	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0714	92	5.6906	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0721	93	6.3279	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0729	94	6.6561	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0737	95	5.634	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0745	96	5.6729	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0753	97	5.1085	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0760	98	6.7441	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0768	99	6.2151	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0776	100	6.6636	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0784	101	5.3276	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0791	102	5.1297	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0799	103	5.0139	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0807	104	5.029	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0815	105	5.605	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0822	106	5.0171	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0830	107	3.6544	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0838	108	5.9355	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0846	109	5.7908	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0853	110	5.2447	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0861	111	6.5699	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0869	112	4.8604	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0877	113	5.6599	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0884	114	4.9483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0892	115	5.7634	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0900	116	5.0934	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0908	117	4.5253	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0915	118	4.6447	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0923	119	5.5944	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0931	120	4.4379	5.2776	3.9060	0.8786	5.2407	6.3303	2.6328	5.1705	2.5746	5.4142	3.3100	5.9142	5.5463	4.5579	5.1207	0.6152	0.4023	0.2319
0.0939	121	4.9112	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0946	122	4.6273	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0954	123	5.5262	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0962	124	4.837	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0970	125	6.3641	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0978	126	4.6542	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0985	127	3.2895	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0993	128	5.5488	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1001	129	6.3668	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1009	130	6.0549	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1016	131	4.7537	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1024	132	4.245	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1032	133	4.3526	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1040	134	2.9629	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1047	135	4.4471	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1055	136	4.5066	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1063	137	4.7698	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1071	138	4.706	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1078	139	4.4883	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1086	140	6.0553	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1094	141	5.8958	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1102	142	4.1842	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1109	143	6.3887	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1117	144	4.0725	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1125	145	4.6545	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1133	146	6.1092	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1140	147	3.7272	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1148	148	4.1651	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1156	149	3.8952	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1164	150	4.6196	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1171	151	3.7705	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1179	152	6.073	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1187	153	3.7738	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1195	154	3.6523	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1202	155	5.4226	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1210	156	4.5508	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1218	157	3.9043	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1226	158	3.66	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1234	159	6.0984	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1241	160	3.9498	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1249	161	4.4688	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1257	162	3.6255	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1265	163	3.658	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1272	164	3.4856	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1280	165	5.3092	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1288	166	3.7321	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1296	167	3.2995	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1303	168	5.1161	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1311	169	3.614	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1319	170	4.0901	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1327	171	3.4437	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1334	172	5.0212	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1342	173	1.3904	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1350	174	5.6536	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1358	175	5.0981	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1365	176	4.7528	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1373	177	5.4556	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1381	178	2.8553	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1389	179	5.4703	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1396	180	4.7665	4.8691	3.7699	0.7544	5.3407	5.4312	0.5739	4.1874	1.6041	5.0353	1.6546	4.6816	4.4876	3.1652	4.0281	0.6266	0.4411	0.2932
0.1404	181	4.0213	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1412	182	4.6874	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1420	183	3.1823	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1427	184	3.1686	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1435	185	2.8957	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1443	186	4.5781	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1451	187	3.7329	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1458	188	3.4419	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1466	189	5.6953	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1474	190	3.1869	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1482	191	3.6055	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1490	192	4.6231	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1497	193	4.2417	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1505	194	5.2779	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1513	195	4.3213	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1521	196	3.1158	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1528	197	2.27	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1536	198	3.5041	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1544	199	2.6007	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1552	200	2.4875	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1559	201	5.3046	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1567	202	3.0582	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1575	203	4.9347	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1583	204	2.855	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1590	205	1.7434	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1598	206	3.4045	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1606	207	3.4427	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1614	208	3.3483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1621	209	1.5883	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1629	210	5.3066	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1637	211	0.6047	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1645	212	0.8018	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1652	213	2.8775	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1660	214	0.5198	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1668	215	3.1591	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1676	216	2.7381	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1683	217	5.5722	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1691	218	3.998	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1699	219	2.2858	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1707	220	1.556	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1715	221	2.5352	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1722	222	3.1682	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1730	223	2.9073	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1738	224	2.547	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1746	225	4.1815	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1753	226	3.7504	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1761	227	5.033	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1769	228	5.2809	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1777	229	2.5598	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1784	230	0.4476	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1792	231	3.4592	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1800	232	2.9202	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1808	233	1.9092	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1815	234	1.9204	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1823	235	2.083	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1831	236	3.0433	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1839	237	1.5429	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1846	238	0.3347	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1854	239	1.8698	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1862	240	0.3031	3.8406	3.9217	0.4412	3.9774	3.6929	0.1191	2.3104	0.5979	3.7268	0.5432	3.8184	3.0682	1.8652	2.5906	0.6314	0.5054	0.4946
0.1870	241	3.2076	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1877	242	2.684	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1885	243	2.234	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1893	244	3.0141	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1901	245	0.271	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1908	246	1.878	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1916	247	2.4108	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1924	248	3.6327	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1932	249	2.9108	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	250	4.425	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1947	251	2.6128	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1955	252	3.1872	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1963	253	1.9839	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1971	254	5.0317	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1978	255	1.8456	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1986	256	2.7799	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1994	257	2.4114	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2002	258	1.2619	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 3.0.1
• Transformers: 4.44.0
• PyTorch: 2.4.0
• Accelerate: 0.33.0
• Datasets: 2.21.0
• 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",
}