checkpoint-178/README.md

metadata

base_model: bobox/DeBERTa-small-ST-v1-test-step2
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:279409
  - loss:CachedGISTEmbedLoss
widget:
  - source_sentence: what is acetylcholinesterase in biochemistry
    sentences:
      - >-
        The Arkansas was the last nuclear powered cruiser built by the United
        States. (Click here for detailed information about the USS Arkansas) USS
        Enterprise (CVN-65) The USS Enterprise was the Navy's first nuclear
        powered aircraft carrier and from 1961 to 1972 she was the biggest
        warship in the world.
      - >-
        The staph infection may also live on the skin of a dog as a parasite or
        in the respiratory system of a dog. In some cases if a dog is not
        treated right away the dog could become very ill or even die. In some
        cases where a dog is infected with staph a dog may have one or several
        different symptoms. These signs may be a reason to have a dog seen by a
        veterinarian; typically this disease may make a dog very sick. Some
        symptoms of staph infection may include but are not limited to.
      - >-
        Acetylcholinesterase (HGNC symbol ACHE), also known as AChE or
        acetylhydrolase, is the primary cholinesterase in the body.It is an
        enzyme that catalyzes the breakdown of acetylcholine and of some other
        choline esters that function as neurotransmitters.AChE is found at
        mainly neuromuscular junctions and in chemical synapses of the
        cholinergic type, where its activity serves to terminate synaptic
        transmission.uring neurotransmission, ACh is released from the nerve
        into the synaptic cleft and binds to ACh receptors on the post-synaptic
        membrane, relaying the signal from the nerve. AChE, also located on the
        post-synaptic membrane, terminates the signal transmission by
        hydrolyzing ACh.
  - source_sentence: >-
      More than 169 countries had reported over 212,000 COVID-19 cases before
      March 19 , 2020 .
    sentences:
      - >-
        As of 23 March , more than 341,000 cases of COVID-19 have been reported
        in 192 countries and territories , resulting in more than 14,700 deaths
        and 99,000 recoveries .
      - >-
        As of 21 March , more than 278,000 cases of COVID-19 have been reported
        in over 186 countries and territories , resulting in more than 11,500
        deaths and 92,000 recoveries.  virus seems to mostly spread between
        people via respiratory droplets .
      - >-
        As of 18 March 2020 , more than 212,000 cases of COVID-19 have been
        reported in at least 170 countries and territories , with major
        outbreaks in China , Iran and the European Union .
  - source_sentence: The brain is harmed if you get meningitis.
    sentences:
      - Which organ of our body is harmed if you get meningitis?
      - >-
        What is the rate at which a specific allele appears within a population
        called?
      - What is the term for the application of science to solve problems?
  - source_sentence: >-
      Electrical energy can be converted into kinetic energy and heat energy by
      an electric motor.
    sentences:
      - >-
        Solution is the term for a homogeneous mixture of two or more
        substances.
      - >-
        Solution is the term for a homogeneous mixture of two or more
        substances.
      - Electric motors transform electrical energy into kinetic energy.
  - source_sentence: where was the first hudson bay company post
    sentences:
      - >-
        Hudson's Bay Company Hudson's Bay Company's first inland trading post
        was established by Samuel Hearne in 1774 in Cumberland House,
        Saskatchewan.[38][39]
      - >-
        Another Mother for Peace Los Angeles artist Lorraine Art Schneider
        donated the use of a striking illustration for the Mother's Day peace
        cards--a sunflower on yellow background amid the slogan “War is not
        healthy for children and other living things.” [1]
      - >-
        Steven Ogg Steven Ogg is a Canadian actor.[1] He is best known for his
        roles as Trevor Philips in the 2013 video game Grand Theft Auto V and
        Simon in The Walking Dead.[2] He has also appeared in television series
        such as Better Call Saul, Law & Order, Person of Interest, Broad City,
        and Westworld.
model-index:
  - name: SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.8812438499723412
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9049742835092648
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.9035516699922166
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.9002747745455083
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9036940037118162
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.9003956924537878
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8695651753004092
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8707925987895928
            name: Spearman Dot
          - type: pearson_max
            value: 0.9036940037118162
            name: Pearson Max
          - type: spearman_max
            value: 0.9049742835092648
            name: Spearman Max
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: VitaminC
          type: VitaminC
        metrics:
          - type: cosine_accuracy
            value: 0.560546875
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.7956135272979736
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.6684709066305818
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.40466147661209106
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.5061475409836066
            name: Cosine Precision
          - type: cosine_recall
            value: 0.9840637450199203
            name: Cosine Recall
          - type: cosine_ap
            value: 0.5505565383154402
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.5546875
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 312.2774658203125
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.6684856753069577
            name: Dot F1
          - type: dot_f1_threshold
            value: 157.33203125
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.508298755186722
            name: Dot Precision
          - type: dot_recall
            value: 0.9760956175298805
            name: Dot Recall
          - type: dot_ap
            value: 0.5365135091766033
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.5546875
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 241.22061157226562
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.6649006622516557
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 510.2530212402344
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.498015873015873
            name: Manhattan Precision
          - type: manhattan_recall
            value: 1
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.5494156168773414
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.5546875
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 12.184114456176758
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.6649006622516557
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 23.68879508972168
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.498015873015873
            name: Euclidean Precision
          - type: euclidean_recall
            value: 1
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.5517706579195627
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.560546875
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 312.2774658203125
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.6684856753069577
            name: Max F1
          - type: max_f1_threshold
            value: 510.2530212402344
            name: Max F1 Threshold
          - type: max_precision
            value: 0.508298755186722
            name: Max Precision
          - type: max_recall
            value: 1
            name: Max Recall
          - type: max_ap
            value: 0.5517706579195627
            name: Max Ap

SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step2

This is a sentence-transformers model finetuned from bobox/DeBERTa-small-ST-v1-test-step2 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 and paws-pos 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: bobox/DeBERTa-small-ST-v1-test-step2
• 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
• 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/DeBERTa-small-ST-v1-test-step3-checkpoints-tmp")
# Run inference
sentences = [
    'where was the first hudson bay company post',
    "Hudson's Bay Company Hudson's Bay Company's first inland trading post was established by Samuel Hearne in 1774 in Cumberland House, Saskatchewan.[38][39]",
    'Steven Ogg Steven Ogg is a Canadian actor.[1] He is best known for his roles as Trevor Philips in the 2013 video game Grand Theft Auto V and Simon in The Walking Dead.[2] He has also appeared in television series such as Better Call Saul, Law & Order, Person of Interest, Broad City, and Westworld.',
]
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	0.8812
spearman_cosine	0.905
pearson_manhattan	0.9036
spearman_manhattan	0.9003
pearson_euclidean	0.9037
spearman_euclidean	0.9004
pearson_dot	0.8696
spearman_dot	0.8708
pearson_max	0.9037
spearman_max	0.905

Binary Classification

• Dataset: VitaminC
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.5605
cosine_accuracy_threshold	0.7956
cosine_f1	0.6685
cosine_f1_threshold	0.4047
cosine_precision	0.5061
cosine_recall	0.9841
cosine_ap	0.5506
dot_accuracy	0.5547
dot_accuracy_threshold	312.2775
dot_f1	0.6685
dot_f1_threshold	157.332
dot_precision	0.5083
dot_recall	0.9761
dot_ap	0.5365
manhattan_accuracy	0.5547
manhattan_accuracy_threshold	241.2206
manhattan_f1	0.6649
manhattan_f1_threshold	510.253
manhattan_precision	0.498
manhattan_recall	1.0
manhattan_ap	0.5494
euclidean_accuracy	0.5547
euclidean_accuracy_threshold	12.1841
euclidean_f1	0.6649
euclidean_f1_threshold	23.6888
euclidean_precision	0.498
euclidean_recall	1.0
euclidean_ap	0.5518
max_accuracy	0.5605
max_accuracy_threshold	312.2775
max_f1	0.6685
max_f1_threshold	510.253
max_precision	0.5083
max_recall	1.0
max_ap	0.5518

Training Details

Training Datasets

negation-triplets

• Dataset: negation-triplets
• Size: 35,750 training samples
• Columns: anchor, entailment, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	entailment	negative
  type	string	string	string
  details	min: 4 tokens mean: 21.52 tokens max: 101 tokens	min: 5 tokens mean: 14.34 tokens max: 47 tokens	min: 5 tokens mean: 14.62 tokens max: 44 tokens

• Samples:

  anchor	entailment	negative
  Brunette woman in a white bikini pouring a drink into a man's cup.	A woman is serving a beverage to a man.	A woman is not serving a beverage to a man.
  People under a tent at a reception.	People are outside.	People are inside.
  A man is smoking at sunset.	The time in the picture is probably somewhere between 3PM and 9PM.	The time in the picture is probably not somewhere between 3PM and 9PM.

• 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': 0.05}
  

vitaminc-pairs

• Dataset: vitaminc-pairs at be6febb
• Size: 34,375 training samples
• Columns: claim and evidence
• Approximate statistics based on the first 1000 samples:

  	claim	evidence
  type	string	string
  details	min: 7 tokens mean: 18.14 tokens max: 54 tokens	min: 6 tokens mean: 37.45 tokens max: 192 tokens

• Samples:

  claim	evidence
  Dora and the Lost City of Gold grossed more than $ 58 million in North America , more than $ 40 million in other territories , and more than $ 98 million globally .	, Dora and the Lost City of Gold has grossed $ 58.4 million in the United States and Canada , and $ 40.4 million in other territories , for a worldwide total of $ 98.8 million , against a production budget of $ 49 million .
  After Juan Antonio and Vicky Cristina have sex , they go to bed .	Afterwards , Juan Antonio lets her know he thinks she 's beautiful , and they make love , and eventually go to bed .
  Tove Lo 's single `` Disco Tits '' reached number 55 in Sweden .	Its lead single , '' Disco Tits '' '' , peaked at number 55 in Sweden. ''

• 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': 0.05}
  

scitail-pairs-qa

• Dataset: scitail-pairs-qa at 0cc4353
• Size: 14,237 training samples
• Columns: sentence2 and question
• Approximate statistics based on the first 1000 samples:

  	sentence2	question
  type	string	string
  details	min: 7 tokens mean: 16.29 tokens max: 41 tokens	min: 8 tokens mean: 15.21 tokens max: 35 tokens

• Samples:

  sentence2	question
  When an atom gains or loses an electron it becames a(n) ion.	When an atom gains or loses an electron it becames an?
  The stratosphere is the layer above the troposphere.	What is the layer above the troposphere?
  Solar and wind are still expensive compared to fossil fuels.	Solar and wind are still expensive compared to what?

• 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': 0.05}
  

scitail-pairs-pos

• Dataset: scitail-pairs-pos at 0cc4353
• Size: 8,600 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 7 tokens mean: 23.52 tokens max: 71 tokens	min: 7 tokens mean: 15.54 tokens max: 39 tokens

• Samples:

  sentence1	sentence2
  Ozone is a molecule formed of THREE oxygen atoms.	Three oxygen ions make up an ozone molecule.
  Animals live by eating the energy produced by plants (herbivores), or live by eating animals that eat plants (carnivores) Let's take the human being (a polyhagous animal) as an example and ponder upon it.	Herbivores is the term for animals that eat producers to get energy.
  Fertilization triggers Meiosis II, and then the sperm nucleus unites with the resulting egg nucleus.	When a sperm penetrates the egg, it triggers the egg to complete meiosis.

• 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': 0.05}
  

xsum-pairs

• Dataset: xsum-pairs
• Size: 38,500 training samples
• Columns: document and summary
• Approximate statistics based on the first 1000 samples:

  	document	summary
  type	string	string
  details	min: 40 tokens mean: 223.77 tokens max: 443 tokens	min: 13 tokens mean: 25.9 tokens max: 45 tokens

• Samples:

  document	summary
  William Heath, 12, from Earls Barton, has so far disguised himself as Ali G, Hercule Poirot and Groucho Marx as part of his Movember campaign. He is raising money in memory of his grandfather, who died from cancer in February. William came up with the idea as he cannot grow a moustache himself. His granddad, Robin Wickham, died from pancreatic, testicular and prostate cancer, and William is now asking people to donate to The Movember Foundation, via his own "Mo Space" page. William has already dressed as seven famous moustachioed men, including Biggles, Keith Lemon and Magnum PI. His costumes were sourced from a combination of a local fancy dress shop and items around the home. "My granddad and I were very close," he said. "He used to come on holiday with us and was always having fun." His mum Clare said William had wanted to do something that would help, but was also fun. She said: "We needed to fill 30 days. When you try to think of 30 people with moustaches it is harder than you think. "The overriding thing is that it has been fun, but it has serious implications." William said his favourite character so far had been Ali G, but he had struggled to create a successful Ned Flanders outfit. He said: "I tried to paint my face yellow, but it didn't really work."	A schoolboy has decided to raise money for a men's health charity by dressing up as a different moustachioed famous face every day for a month.
  Media playback is not supported on this device The Daily Mail claimed a £10m offer was made to owner Owen Oyston despite him stating the club was not for sale at a recent public meeting with fans. Oyston was heckled throughout over the way the club is being run. "The owners of the club have received no approach whatsoever, from any investor or third party," said a statement. The Blackpool Supporters Trust launched a £16m bid to buy the club July 2015 but Oyston, whose son Karl is chairman, eventually ended those takeover talks. The Seasiders, who will play in the fourth tier for the first time since 2000-01 this season, have also announced the signing of midfielder Danny Pugh. The 33-year-old former Manchester United trainee joins on a free transfer after his release by Bury and has signed a one-year deal, with further 12-month option. "He brings a wealth of experience to the team and will be a strong, vocal presence in the middle of the park," said boss Gary Bowyer.	League Two club Blackpool have denied claims they were subject of a new takeover offer.
  The Cochrane Collaboration carried out a systematic review of eight exercise trials involving more than 300 patients living at home or in care. Exercise did little for patients' moods, the research concluded. But it did help them carry out daily activities such as rising from a chair, and boosted their cognitive skills. Whether these benefits improve quality of life is still unclear, but the study authors say the findings are reason for optimism. Dementia affects some 800,000 people in the UK. And the number of people with the condition is steadily increasing because people are living longer. It is estimated that by 2021, the number of people with dementia in the UK will have increased to around one million. With no cure, ways to improve the lives of those living with the condition are vital. Researcher Dorothy Forbes, of the University of Alberta, and colleagues who carried out the Cochrane review, said: "Clearly, further research is needed to be able to develop best practice guidelines to enable healthcare providers to advise people with dementia living at home or in institutions. "We also need to understand what level and intensity of exercise is beneficial for someone with dementia." Dr Laura Phipps of Alzheimer's Research UK said: "We do know that exercise is an important part of keeping healthy, and though we can't say that exercise will prevent dementia, evidence does suggest it can help reduce the risk of the condition as part of a healthy lifestyle."	People with dementia who exercise improve their thinking abilities and everyday life, a body of medical research concludes.

• 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': 0.05}
  

sciq_pairs

• Dataset: sciq_pairs at 2c94ad3
• Size: 11,095 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 7 tokens mean: 16.92 tokens max: 54 tokens	min: 2 tokens mean: 85.56 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  The bright color of poison dart frogs serves what purpose?	Poison dart frogs have toxins in their skin. Their bright colors warn potential predators not to take a bite!.
  What term describes motion that repeats itself at regular time intervals, such as exhibited by a vibrating guitar string?	When you pluck a guitar string, the resulting sound has a steady tone and lasts a long time. Each successive vibration of the string takes the same time as the previous one. We define periodic motion to be a motion that repeats itself at regular time intervals, such as exhibited by the guitar string or by an object on a spring moving up and down. The time to complete one oscillation remains constant and is called the period T . Its units are usually seconds, but may be any convenient unit of time. The word period refers to the time for some event whether repetitive or not; but we shall be primarily interested in periodic motion, which is by definition repetitive. A concept closely related to period is the frequency of an event. For example, if you get a paycheck twice a month, the frequency of payment is two per month and the period between checks is half a month. Frequency f is defined to be the number of events per unit time. For periodic motion, frequency is the number of oscillations per unit time. The relationship between frequency and period is.
  What do stored fats provide our body with for later use?	Fats are one type of lipid. Stored fat gives your body energy to use for later. It’s like having money in a savings account: it’s there in case you need it. Stored fat also cushions and protects internal organs. In addition, it insulates the body. It helps keep you warm in cold weather.

• 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': 0.05}
  

qasc_pairs

• Dataset: qasc_pairs at a34ba20
• Size: 7,727 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 4 tokens mean: 11.4 tokens max: 22 tokens	min: 16 tokens mean: 34.47 tokens max: 67 tokens

• Samples:

  sentence1	sentence2
  What do geologists use to determine the age of rock layers?	radioactive dating is used to determine the age of fossils. Geologists use fossils to determine the age of the rock layer that it was found in.. Geologists use radioactive dating to determine the age of rock layers.
  Air pollution can cause a decrease in what?	air pollution can cause the pH of soil to decrease. Research has shown that soil pH less than 6.0 can decrease crop yields.. Air pollution can cause a decrease in crop yields.
  What organism uses their sense of smell to find a mate?	Most salamanders use their sense of smell to find a mate.. Salamanders are a type of amphibian.. Some amphibians use their sense of smell to find a mate.

• 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': 0.05}
  

openbookqa_pairs

• Dataset: openbookqa_pairs
• Size: 4,522 training samples
• Columns: question and fact
• Approximate statistics based on the first 1000 samples:

  	question	fact
  type	string	string
  details	min: 3 tokens mean: 13.8 tokens max: 78 tokens	min: 4 tokens mean: 11.5 tokens max: 30 tokens

• Samples:

  question	fact
  What is animal competition?	if two animals eat the same prey then those animals compete for that pey
  If you wanted to make a metal bed frame, where would you start?	alloys are made of two or more metals
  Places lacking warmth have few what	cold environments contain few organisms

• 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': 0.05}
  

msmarco_pairs

• Dataset: msmarco_pairs at 28ff31e
• Size: 30,250 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 4 tokens mean: 8.65 tokens max: 31 tokens	min: 17 tokens mean: 76.38 tokens max: 207 tokens

• Samples:

  sentence1	sentence2
  propria definition	The lamina propria is a constituent of the moist linings known as mucous membranes or mucosa, which line various tubes in the body.The lamina propria is a thin layer of loose connective tissue which lies beneath the epithelium and together with the epithelium constitutes the mucosa.As its Latin name indicates it is a characteristic component of the mucosa, the mucosa's own special layer.he lamina propria is a constituent of the moist linings known as mucous membranes or mucosa, which line various tubes in the body.
  what family is the common bullfrog in	The American bullfrog (Rana catesbeiana), often simply known as the bullfrog in Canada and the United States, is an aquatic frog, a member of the family Ranidae, or “true frogs”. This frog has an olive green back and sides blotched with brownish markings and a whitish belly spotted with yellow or grey.
  why does well pump cycle on and off	1 When a well pump turns on every time a water-using fixture’s valve is opened, or if it turns on and off rapidly while the fixture is in use, that’s short cycling. It is typically caused by a water pressure tank that has lost it built-in cushion of pressurized air.

• 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': 0.05}
  

nq_pairs

• Dataset: nq_pairs at f9e894e
• Size: 30,250 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 10 tokens mean: 11.81 tokens max: 22 tokens	min: 16 tokens mean: 135.28 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  who established the republic of china in 1912 ce	Republic of China (1912–1949) The Republic of China was a sovereign state in East Asia, that occupied the territories of modern China and for part of its history Mongolia and Taiwan. It was founded in 1912, after the Qing dynasty, the last imperial dynasty, was overthrown in the Xinhai Revolution. The Republic's first president, Sun Yat-sen, served only briefly before handing over the position to Yuan Shikai, former leader of the Beiyang Army. His party, then led by Song Jiaoren, won the parliamentary election held in December 1912. Song was assassinated shortly after, and the Beiyang Army led by Yuan Shikai maintained full control of the government in Beijing. Between late 1915 and early 1916, Yuan tried to reinstate the monarchy, before resigning after popular unrest. After Yuan's death in 1916, members of cliques in the former Beiyang Army claimed their autonomy and clashed with each other. During this period, the authority of the republican government was weakened by a restoration of the Qing government.
  what is the message in john lennon's imagine	Imagine (John Lennon song) "Imagine" is a song written and performed by English musician John Lennon. The best-selling single of his solo career, its lyrics encourage the listener to imagine a world at peace without the barriers of borders or the divisions of religion and nationality, and to consider the possibility that the whole of humanity would live unattached to material possessions.
  who is the original singer for these boots are made for walking	These Boots Are Made for Walkin' "These Boots Are Made for Walkin'" is a hit song written by Lee Hazlewood and recorded by Nancy Sinatra. It charted January 22, 1966,[3] and reached No. 1 in the United States Billboard Hot 100 and in the UK Singles Chart.[2]

• 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': 0.05}
  

trivia_pairs

• Dataset: trivia_pairs at a7c36e3
• Size: 12,024 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 7 tokens mean: 17.49 tokens max: 61 tokens	min: 12 tokens mean: 200.72 tokens max: 482 tokens

• Samples:

  query	answer
  What is the name of 'Bob the Builder's' cement mixer?	BOB the BUILDER DIZZY the CEMENT MIXER BOB the BUILDER DIZZY THE CEMENT MIXER Large Friction Action Dizzy the Cement Mixer and clicky noise turn by hand Mixer from the Large Bob The Builder Friction toy Collection  Measures 5" x  4" High  in EXCELLENT Played with Condition �8.00 .. US $15.60  .. EUROS 12.00 Ref # 0845
  Which cartoon character, who cooks at the Krusty Krab, lives in a pineapple under the sea?	SpongeBob SquarePants from SpongeBob SquarePants
  Chinese Democracy was the long awaited 2008 album release of which band?	Guns N Roses 'Chinese Democracy' Set For Wal-Mart Release

• 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': 0.05}
  

gooaq_pairs

• Dataset: gooaq_pairs at b089f72
• Size: 30,250 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 11.37 tokens max: 24 tokens	min: 13 tokens mean: 56.7 tokens max: 154 tokens

• Samples:

  sentence1	sentence2
  do namibians need a visa for london?	The Embassy is closed every Friday. Namibia tourist visa is not required for citizens of United Kingdom for a stay up to 90 days. Sounds good!
  what is the meaning of personal finance?	Personal finance is a term that covers managing your money as well as saving and investing. ... It often refers to the entire industry that provides financial services to individuals and households and advises them about financial and investment opportunities.
  what are trim tabs for?	Trim tabs are either flat plates or vertical blades fitted either side of the boat and attached to the transom. They are used to trim or level the boat, both fore and aft and side to side. Trim tabs are controlled up and downwards by either a hydraulic, or electric ram system on the transom.

• 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': 0.05}
  

paws-pos

• Dataset: paws-pos at 161ece9
• Size: 21,829 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 9 tokens mean: 25.63 tokens max: 68 tokens	min: 10 tokens mean: 25.55 tokens max: 68 tokens

• Samples:

  sentence1	sentence2
  Thompson was born in Hendon , North London , Dena Holmes in 1960 and worked for a building society bank .	Thompson was born Dena Holmes in 1960 in Hendon , North London . She worked for a building society .
  One of his first cousins was Elizabeth , aka Lady Elizabeth Hervey , aka Bess Foster , Duchess of Devonshire . His younger brother married Lord Bishop Foster .	One of his first cousins was Elizabeth , alias Lady Elizabeth Hervey , alias Bess Foster , Duchess of Devonshire , his younger brother married Lord Bishop Foster .
  At the executive level , EEAA represents the central arm of the Ministry .	At executive level , EEAA represents the central arm of the ministry .

• 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': 0.05}
  

Evaluation Datasets

vitaminc-pairs

• Dataset: vitaminc-pairs at be6febb
• Size: 108 evaluation samples
• Columns: claim and evidence
• Approximate statistics based on the first 1000 samples:

  	claim	evidence
  type	string	string
  details	min: 9 tokens mean: 21.36 tokens max: 41 tokens	min: 11 tokens mean: 36.11 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': 0.05}
  

negation-triplets

• Dataset: negation-triplets
• Size: 64 evaluation samples
• Columns: anchor, entailment, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	entailment	negative
  type	string	string	string
  details	min: 11 tokens mean: 13.64 tokens max: 19 tokens	min: 9 tokens mean: 13.23 tokens max: 21 tokens	min: 10 tokens mean: 13.52 tokens max: 22 tokens

• Samples:

  anchor	entailment	negative
  Set of toy animals sitting in front of a red wooden wagon.	Several toy animals - a bull, giraffe, deer and parakeet.	Several toy animals - a cow, lion, wolf and canary.
  A bathroom with a toilette with it's seat down.	A bathroom with a sink and a toilet	A bathroom without a sink or a toilet
  A striped plane flying up into the sky as the sun shines behind it.	An airplane is ascending into the white sky	An airplane is descending into the black sky

• 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': 0.05}
  

scitail-pairs-pos

• Dataset: scitail-pairs-pos at 0cc4353
• Size: 54 evaluation samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 9 tokens mean: 20.81 tokens max: 45 tokens	min: 10 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': 0.05}
  

scitail-pairs-qa

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

  	sentence2	question
  type	string	string
  details	min: 7 tokens mean: 15.31 tokens max: 33 tokens	min: 7 tokens mean: 14.91 tokens max: 26 tokens

• Samples:

  sentence2	question
  It takes earth one week to rotate on its axis seven times.	How long does it take for Earth to rotate on its axis seven times?
  Both hurricanes and tornadoes always have high winds.	Both hurricanes and tornadoes always
  Seeds of a pine cone are easily carried by the wind and dispersed because seeds have wings.	Why are seeds of a pine cone easily carried by the wind and dispersed?

• 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': 0.05}
  

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: 63 tokens mean: 214.16 tokens max: 341 tokens	min: 15 tokens mean: 25.86 tokens max: 43 tokens

• Samples:

  document	summary
  The rescue on Monday afternoon involved a challenging winch down to the casualty by a coastguard helicopter's paramedic. The Inverness Airport-based helicopter could not be brought too close in case its downdraft blew the man and his fellow walkers off the ridge. The walker was taken to hospital for treatment. The alarm was raised at 14:25 on Monday after the man became unwell on Carn Mor Dearg. He was airlifted to Torlundy and from there was taken to hospital by ambulance. Scott Sharman, paramedic winchman, said: "It was an extremely steep ridge and we needed to make sure we kept at a safe distance because the downdraft could very easily have blown them over the ridge."	A walker had to be rescued from a 1,000m (3,500ft) ridge near Ben Nevis after he became ill.
  The 23-year-old, who did not make a senior appearances during a year with the Hornets, has signed a two-year deal with the O's. Woods began his career in Cambridge United's youth set-up and subsequently joined Manchester United's academy. He moved to Doncaster Rovers in 2009 and went on to make 82 appearances, before leaving the club last summer. Woods, a former England Under-19 international, will provide competition for fellow new arrival Adam Legzdins.	League One side Leyton Orient have signed goalkeeper Gary Woods following his departure from Watford.
  The 32-year-old, the number one ranked Test bowler, has been out of action with a groin strain since the first Test against India in early November. But in Cape Town this week he was able to complete two bowling spells at match intensity in the nets, run sprints and do agility tests and fielding drills. The first of the four-match Test series begins in Durban on 26 December. Proteas team manager, Dr Mohammed Moosajee said: "Dale has put a lot of work into his training and rehab since his return from India so we are very happy to have him back from injury. "He was put through a thorough fitness test on Thursday by physiotherapist, Shane Jabaar, he came through the tests without any discomfort and will be available for selection for the first Test match against England." Steyn has taken 402 wickets in 81 Tests at an average of 22.56, including 46 in 11 matches against England. South Africa remain at the top of the Test rankings despite a 3-0 defeat in India this month.	South Africa paceman Dale Steyn will be fit for the Test series with England after passing a fitness test.

• 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': 0.05}
  

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: 16.72 tokens max: 36 tokens	min: 2 tokens mean: 73.28 tokens max: 332 tokens

• Samples:

  sentence1	sentence2
  The skull is a part of a vertebrate endoskeleton that encloses and protects what organ?	part of a vertebrate endoskeleton that encloses and protects the brain; also called the skull.
  The action of sunlight on the skin triggers the body to produce what vitamin?	Milk and other dairy foods are not the only sources of calcium. This important nutrient is also found in green leafy vegetables, broccoli, and intact salmon and canned sardines with their soft bones. Nuts, beans, seeds, and shellfish provide calcium in smaller quantities. Except for fatty fish like salmon and tuna, or fortified milk or cereal, vitamin D is not found naturally in many foods. The action of sunlight on the skin triggers the body to produce its own vitamin D (Figure 6.22), but many people, especially those of darker complexion and those living in northern latitudes where the sun’s rays are not as strong, are deficient in vitamin D. In cases of deficiency, a doctor can prescribe a vitamin D supplement.
  What phenomenon is essential in order for evolution to occur because it increases genetic variation and the potential for individuals to differ?	Mutations are essential for evolution to occur because they increase genetic variation and the potential for individuals to differ. The majority of mutations are neutral in their effects on the organisms in which they occur. Beneficial mutations may become more common through natural selection. Harmful mutations may cause genetic disorders or cancer.

• 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': 0.05}
  

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: 4 tokens mean: 11.34 tokens max: 25 tokens	min: 18 tokens mean: 35.58 tokens max: 66 tokens

• Samples:

  sentence1	sentence2
  What designed for swimming are used for moving faster through water?	webbed feet are used for moving faster through water by aquatic animals. Ducks have webbed feet, designed for swimming.. Feet designed for swimming are used for moving faster through water.
  what falls making sunlight available to surrounding plants?	if a tree falls then sunlight becomes available to the surrounding plants. Oak trees are found throughout.. if an oak falls then sunlight becomes available to surrounding plants
  What is the term used for an individual who is learning ethology?	Ethologists usually study how animals behave in their natural environment.. Ethology is the study of behavior.. Ethologists learn ethology

• 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': 0.05}
  

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': 0.05}
  

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: 4 tokens mean: 8.91 tokens max: 20 tokens	min: 26 tokens mean: 80.7 tokens max: 195 tokens

• Samples:

  sentence1	sentence2
  when did young american by david bowie come out	Young Americans (song) Young Americans is a single by English singer and songwriter David Bowie, released in 1975. It is included in the album of the same name. The song was a massive breakthrough in the United States, where glam rock had never really become very popular outside the major cities.
  are investment commissions tax deductible	You typically pay a commission when you buy, and you pay another commission when you sell. The IRS does not consider investment commissions to be a tax-deductible expense. Instead, the commission becomes part of the investment's cost basis, which still provides you with some tax relief.
  does photosynthesis occur in prokaryotes	Animal cells do not undergo photosynthesis, but in a plant cell, the site of photosynthesis is the chloroplast. Prokaryotes are more primitive-they have no nucleus for a start, and also have no chloroplasts.They are bacterial cells and so do not undergo photosynthesis.ating Newest Oldest. Best Answer: Actually, some procaryotes have photosynthesis. The thing is, as they don't have organelles, it doesn't occur in a differentiated structure, like choroplasts in eucaryotes. It happens along the plasma membrane.

• 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': 0.05}
  

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: 18 tokens	min: 31 tokens mean: 127.79 tokens max: 326 tokens

• Samples:

  sentence1	sentence2
  who played gimli in the lord of the rings movies	John Rhys-Davies John Rhys-Davies (born 5 May 1944) is a Welsh actor and voice actor known for his portrayal of Gimli in The Lord of the Rings trilogy and the charismatic Arab excavator Sallah in the Indiana Jones films. He also played Agent Michael Malone in the 1993 remake of the 1950s television series The Untouchables, Pilot Vasco Rodrigues in the mini-series Shōgun, Professor Maximillian Arturo in Sliders, King Richard I in Robin of Sherwood, General Leonid Pushkin in the James Bond film The Living Daylights, and Macro in I, Claudius. Additionally, he provided the voices of Cassim in Disney's Aladdin and the King of Thieves, Macbeth in Gargoyles, Man Ray in SpongeBob SquarePants, Hades in Justice League and Tobias in the computer game Freelancer.
  why did the red sea get its name	Red Sea Red Sea is a direct translation of the Greek Erythra Thalassa (Ερυθρὰ Θάλασσα), Latin Mare Rubrum (alternatively Sinus Arabicus, literally "Arabian Gulf"), Arabic: البحر الأحمر‎, translit. Al-Baḥr Al-Aḥmar (alternatively بحر القلزم Baḥr Al-Qulzum, literally "the Sea of Clysma"), Somali Badda Cas and Tigrinya Qeyyiḥ bāḥrī (ቀይሕ ባሕሪ). The name of the sea may signify the seasonal blooms of the red-coloured Trichodesmium erythraeum near the water's surface.[5] A theory favored by some modern scholars is that the name red is referring to the direction south, just as the Black Sea's name may refer to north. The basis of this theory is that some Asiatic languages used color words to refer to the cardinal directions.[6] Herodotus on one occasion uses Red Sea and Southern Sea interchangeably.[7]
  when is the new president of mexico announced	Mexican general election, 2018 López Obrador won the election on 1 July 2018 with over 50% of the popular vote. In terms of states won, López Obrador won in a landslide, carrying 31 out of 32 of the country's states,[5] the most states won by a candidate since Ernesto Zedillo won every state in the 1994 election.

• 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': 0.05}
  

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: 16.72 tokens max: 42 tokens	min: 20 tokens mean: 211.76 tokens max: 512 tokens

• Samples:

  query	answer
  Who sang '99 Red Balloons'?	99 red ballons - Nena - YouTube 99 red ballons - Nena Want to watch this again later? Sign in to add this video to a playlist. Need to report the video? Sign in to report inappropriate content. Rating is available when the video has been rented. This feature is not available right now. Please try again later. Uploaded on Jul 29, 2006 This is the video 99 red ballons (english version) by nena Category
  Who is the patron saint of doctors, surgeons, painters and artists?	St. Luke Medals St. Luke Medals St. Luke is the Patron Saint of artists, brewers, butchers, doctors, glassworks, painters, physicians and surgeons. Luke is symbolically portrayed as an animal of sacrifice, the ox, because he begins his Gospel with the history of Zachary, the priest offering sacrifice to God, and because throughout his Gospel he accentuates the universal priesthood of Christ. St. Luke�s Gospel includes six miracles and 18 parables not found elsewhere in the Bible.
  Vande Mataram (I praise thee, Mother) is the national song of which BRIC nation?	'Vande Mataram' Real National Anthem: RSS Leader- The New Indian Express 'Vande Mataram' Real National Anthem: RSS Leader By PTI

• 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': 0.05}
  

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: 11.34 tokens max: 15 tokens	min: 19 tokens mean: 57.08 tokens max: 112 tokens

• Samples:

  sentence1	sentence2
  which gases are emitted from vehicles?	['Particulate matter (PM). One type of particulate matter is the soot seen in vehicle exhaust. ... ', 'Volatile Organic Compounds (VOCs). ... ', 'Nitrogen oxides (NOx). ... ', 'Carbon monoxide (CO). ... ', 'Sulfur dioxide (SO2). ... ', 'Greenhouse gases.']
  how long does it take for someone to not be drunk?	It takes 30 minutes to feel the effects of alcohol. Drinking more than one drink every 30 minutes means you are probably drinking too much, too fast. Slow yourself down, and if you find yourself feeling thirsty before those 30 minutes have passed, try a glass of water first.
  is ssdi taxable in ohio?	Social Security retirement benefits are fully exempt from state income taxes in Ohio. Any income from retirement accounts (like a 401(k) or an IRA) or pensions is taxed as regular income (but there are credits available). Social security benefits, if taxable on the federal return, are deducted on Ohio schedule A.

• 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': 0.05}
  

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': 0.05}
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 640
• per_device_eval_batch_size: 64
• learning_rate: 3.5e-05
• weight_decay: 5e-05
• num_train_epochs: 2
• lr_scheduler_type: cosine_with_min_lr
• lr_scheduler_kwargs: {'num_cycles': 0.5, 'min_lr': 6.999999999999999e-06}
• warmup_ratio: 0.2
• save_safetensors: False
• fp16: True
• push_to_hub: True
• hub_model_id: bobox/DeBERTa-small-ST-v1-test-step3-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: 640
• per_device_eval_batch_size: 64
• 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: 5e-05
• 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': 0.5, 'min_lr': 6.999999999999999e-06}
• warmup_ratio: 0.2
• 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/DeBERTa-small-ST-v1-test-step3-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	paws-pos loss	trivia pairs loss	scitail-pairs-pos loss	scitail-pairs-qa loss	qasc pairs loss	sciq pairs loss	openbookqa pairs loss	msmarco pairs loss	nq pairs loss	vitaminc-pairs loss	xsum-pairs loss	gooaq pairs loss	negation-triplets loss	VitaminC_max_ap	sts-test_spearman_cosine
0.0022	1	0.8103	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0045	2	0.8803	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0067	3	0.8219	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0090	4	0.0574	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0112	5	0.3044	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0135	6	0.3306	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0157	7	0.759	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0180	8	0.0472	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0202	9	0.7782	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0225	10	0.0757	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0247	11	0.7778	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0270	12	0.7111	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0292	13	0.6598	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0315	14	0.8901	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0337	15	0.3206	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0360	16	0.3408	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0382	17	0.5623	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0404	18	0.0758	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0427	19	0.994	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0449	20	2.4196	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0472	21	0.0561	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0494	22	0.0827	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0517	23	0.7405	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0539	24	0.9656	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0562	25	0.7855	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0584	26	0.6349	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0607	27	0.8087	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0629	28	0.9282	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0652	29	0.3377	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0674	30	0.3289	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0697	31	0.6314	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0719	32	0.0611	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0742	33	0.8942	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0764	34	0.0701	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0787	35	0.8506	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0809	36	0.3386	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0831	37	0.0701	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0854	38	0.8042	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0876	39	0.8744	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0899	40	0.8644	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0921	41	0.8647	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0944	42	0.7916	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0966	43	0.8599	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0989	44	0.0523	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1011	45	0.6968	0.0245	0.5306	0.0737	0.0016	0.0908	0.0154	0.6755	0.1599	0.0959	1.7274	0.0382	0.2968	0.9175	0.5544	0.9038
0.1034	46	0.3376	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1056	47	0.5174	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1079	48	0.8162	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1101	49	0.3545	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1124	50	0.315	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1146	51	0.0627	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1169	52	0.8851	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1191	53	0.8382	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1213	54	0.733	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1236	55	0.7173	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1258	56	0.7659	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1281	57	0.793	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1303	58	0.5426	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1326	59	0.7641	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1348	60	0.0657	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1371	61	0.7836	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1393	62	0.9306	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1416	63	0.8673	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1438	64	0.9296	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1461	65	0.8211	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1483	66	0.7685	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1506	67	0.7139	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1528	68	0.8241	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1551	69	0.6256	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1573	70	0.8842	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1596	71	0.804	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1618	72	0.0989	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1640	73	0.332	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1663	74	0.5736	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1685	75	0.8285	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1708	76	0.9561	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1730	77	0.0633	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1753	78	0.0848	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1775	79	0.8325	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1798	80	1.0011	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1820	81	0.8697	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1843	82	0.8344	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1865	83	0.9967	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1888	84	0.4638	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1910	85	0.8994	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1933	86	0.7789	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1955	87	0.0555	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1978	88	0.3778	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2	89	0.708	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2022	90	0.0689	0.0245	0.5192	0.0654	0.0016	0.0911	0.0158	0.7133	0.1517	0.0965	1.6142	0.0399	0.3071	0.9220	0.5542	0.9046
0.2045	91	2.3489	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2067	92	0.741	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2090	93	0.7729	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2112	94	0.0631	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2135	95	0.9342	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2157	96	0.8581	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2180	97	0.5198	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2202	98	0.846	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2225	99	0.6581	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2247	100	0.3579	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2270	101	0.908	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2292	102	0.0664	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2315	103	0.5411	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2337	104	0.9163	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2360	105	0.7975	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2382	106	0.37	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2404	107	0.8495	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2427	108	0.8073	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2449	109	0.7563	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2472	110	0.6585	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2494	111	0.3246	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2517	112	0.9718	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2539	113	0.8584	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2562	114	0.3385	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2584	115	0.323	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2607	116	0.3359	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2629	117	0.6955	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2652	118	0.0539	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2674	119	0.0507	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2697	120	0.314	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2719	121	1.0339	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2742	122	0.3158	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2764	123	0.7809	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2787	124	0.9516	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2809	125	0.3117	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2831	126	0.8366	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2854	127	0.8033	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2876	128	0.7253	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2899	129	0.8345	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2921	130	0.7532	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2944	131	0.8247	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2966	132	0.5175	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2989	133	0.7813	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3011	134	0.6582	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3034	135	0.3484	0.0242	0.5458	0.0738	0.0015	0.0924	0.0162	0.6892	0.1677	0.0974	1.5520	0.0366	0.3082	0.9212	0.5518	0.9050
0.3056	136	0.7648	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3079	137	0.7554	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3101	138	0.0753	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3124	139	0.4987	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3146	140	0.8543	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3169	141	0.9425	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3191	142	0.0472	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3213	143	0.848	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3236	144	0.8946	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3258	145	0.7841	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3281	146	0.6653	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3303	147	0.3522	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3326	148	0.4853	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3348	149	0.4726	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3371	150	0.8693	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3393	151	0.8124	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3416	152	0.8206	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3438	153	0.9406	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3461	154	0.7944	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3483	155	0.0766	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3506	156	0.8609	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3528	157	1.0533	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3551	158	0.8396	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3573	159	0.7865	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3596	160	2.4616	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3618	161	0.0556	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3640	162	0.3758	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3663	163	0.9312	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3685	164	0.7993	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3708	165	0.8104	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3730	166	0.8199	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3753	167	1.0724	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3775	168	0.3521	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3798	169	0.8536	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3820	170	0.872	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3843	171	0.8009	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3865	172	0.7798	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3888	173	0.5953	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3910	174	0.7562	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3933	175	0.7227	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3955	176	0.8953	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3978	177	0.7102	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4	178	0.0667	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-

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",
}