tasksource/ModernBERT-base-embed

SentenceTransformer based on answerdotai/ModernBERT-base

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-base on the tomaarsen/natural-questions-hard-negatives, tomaarsen/gooaq-hard-negatives, bclavie/msmarco-500k-triplets, sentence-transformers/all-nli, sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1, sentence-transformers/gooaq, sentence-transformers/natural-questions, merged-2l-nli, merged-3l-nli, zero-shot-label-nli, dataset_train_nli, paws/labeled_final, glue/mrpc, glue/qqp, fever-evidence-related, glue/stsb_0, glue/stsb_1, glue/stsb_2, sick/relatedness_0, sick/relatedness_1, sick/relatedness_2, sts-companion_0, sts-companion_1 and sts-companion_2 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: answerdotai/ModernBERT-base
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Datasets:
  • tomaarsen/natural-questions-hard-negatives
  • tomaarsen/gooaq-hard-negatives
  • bclavie/msmarco-500k-triplets
  • sentence-transformers/all-nli
  • sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
  • sentence-transformers/gooaq
  • sentence-transformers/natural-questions
  • merged-2l-nli
  • merged-3l-nli
  • zero-shot-label-nli
  • dataset_train_nli
  • paws/labeled_final
  • glue/mrpc
  • glue/qqp
  • fever-evidence-related
  • glue/stsb_0
  • glue/stsb_1
  • glue/stsb_2
  • sick/relatedness_0
  • sick/relatedness_1
  • sick/relatedness_2
  • sts-companion_0
  • sts-companion_1
  • sts-companion_2
• 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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tasksource/ModernBERT-base-embed")
# Run inference
sentences = [
    'A chef is preparing some food',
    'A chef is preparing a meal',
    'A dog is in a sandy area with the sand that is being stirred up into the air and several plants are in the background',
]
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]

Training Details

Training Datasets

tomaarsen/natural-questions-hard-negatives

• Dataset: tomaarsen/natural-questions-hard-negatives at 52dfa09
• Size: 96,658 training samples
• Columns: query, answer, negative_1, negative_2, negative_3, negative_4, and negative_5
• Approximate statistics based on the first 1000 samples:

  	query	answer	negative_1	negative_2	negative_3	negative_4	negative_5
  type	string	string	string	string	string	string	string
  details	min: 10 tokens mean: 12.52 tokens max: 26 tokens	min: 17 tokens mean: 137.85 tokens max: 556 tokens	min: 23 tokens mean: 144.11 tokens max: 1035 tokens	min: 13 tokens mean: 142.73 tokens max: 832 tokens	min: 15 tokens mean: 146.37 tokens max: 649 tokens	min: 19 tokens mean: 145.79 tokens max: 549 tokens	min: 19 tokens mean: 142.01 tokens max: 574 tokens

• Samples:

  query	answer	negative_1	negative_2	negative_3	negative_4	negative_5
  when did richmond last play in a preliminary final	Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...	Brisbane Bears However, the club was still struggling off-field. One of the Bears' biggest problems was its lack of support (both on and off the field) in Melbourne, the location of most of its away matches. In mid-1996, the struggling Fitzroy Football Club collapsed due to financial pressures and was seeking to merge its assets with another club. When a merger with North Melbourne in forming the North Fitzroy Kangaroos failed to win the support of the other AFL clubs, a deal for a merger was done between Fitzroy and the Bears. The new team was known as the Brisbane Lions, based at the Gabba, with Northey as the coach of the merged club. As such, the history of the Brisbane Bears as an individual entity ended after the 1996 season, with ten seasons of competition and the third-place finish in 1996 as its best performance. The Bears last match as a separate entity was a preliminary final on Saturday 21 September 1996 at the Melbourne Cricket Ground (where the Bears played their first VF...	Virginia Tech–West Virginia football rivalry Virginia Tech held the trophy in six of the nine years in which it was contested, but West Virginia leads the all-time series 28–23–1. The last game was played on September 3, 2017 at FedEx Field in Landover, MD; Virginia Tech won 31–24.	Martin Truex Jr. To start off the Round of 12, Truex scored his 6th win of the season at Charlotte after leading 91 out of 334 laps to secure a spot for the Round of 8. Just two weeks later, he scored another win at Kansas despite having a restart violation early in the race.	Adelaide Football Club Star midfielder for many years Patrick Dangerfield left the club at the end of the 2015 season (a season in which he won the club's best and fairest) and Don Pyke, a former premiership player and assistant coach with West Coast who had also been an assistant coach at Adelaide from 2005 to 2006, was appointed Adelaide's senior coach for at least three years.[9] Adelaide was widely tipped to slide out of the finals in 2016[27][28][29] but the Crows proved to be one of the successes of the season, comfortably qualifying for a home elimination final and defeating North Melbourne by 62 points, before being eliminated the next week by eventual beaten grand finalists, Sydney in the semi-finals. The club had a dominant 2017 season, winning their opening six games and never falling below second place for the entire season. Adelaide claimed their second McClelland Trophy as minor premiers.[30] The Adelaide Crows entered the 2017 finals series as favourites for the premiers...	Battle of Appomattox Court House The Battle of Appomattox Court House (Virginia, U.S.), fought on the morning of April 9, 1865, was one of the last battles of the American Civil War (1861–1865). It was the final engagement of Confederate States Army General-in-Chief, Robert E. Lee, and his Army of Northern Virginia before it surrendered to the Union Army of the Potomac under the Commanding General of the United States, Ulysses S. Grant. Lee, having abandoned the Confederate capital of Richmond, Virginia, after the nine and one-half month Siege of Petersburg and Richmond, retreated west, hoping to join his army with the remaining Confederate forces in North Carolina, the Army of Tennessee under Gen. Joseph E. Johnston. Union infantry and cavalry forces under Gen. Philip Sheridan pursued and cut off the Confederates' retreat at the central Virginia village of Appomattox Court House. Lee launched a last-ditch attack to break through the Union forces to his front, assuming the Union forc...
  who sang what in the world's come over you	Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.	Lover, You Should've Come Over "Lover, You Should've Come Over" is the seventh track on Jeff Buckley's album Grace. Inspired by the ending of the relationship between Buckley and Rebecca Moore,[1] it concerns the despondency of a young man growing older, finding that his actions represent a perspective he feels that he should have outgrown. Biographer and critic David Browne describes the lyrics as "confused and confusing" and the music as "a languid beauty."[1]	It's Christmas (All Over The World) "It's Christmas (All Over The World)" is a song recorded by Scottish singer Sheena Easton. It was released in November 1985 as the theme song from the soundtrack of Santa Claus: The Movie. The song was written by Bill House and John Hobbs.	The End of the World (Skeeter Davis song) "The End of the World" is a country pop song written by Arthur Kent and Sylvia Dee, for American singer Skeeter Davis. It had success in the 1960s and spawned many covers.	Israel Kamakawiwoʻole His voice became famous outside Hawaii when his album Facing Future was released in 1993. His medley of "Somewhere Over the Rainbow/What a Wonderful World" was released on his albums Ka ʻAnoʻi and Facing Future. It was subsequently featured in several films, television programs, and television commercials.	Make the World Go Away "Make the World Go Away'" is a country-popular music song composed by Hank Cochran. It has become a Top 40 popular success three times: for Timi Yuro (during 1963), for Eddy Arnold (1965), and for the brother-sister duo Donny and Marie Osmond (1975). The original version of the song was recorded by Ray Price during 1963. It has remained a country crooner standard ever since.
  who produces the most wool in the world	Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.	Baa, Baa, Black Sheep As with many nursery rhymes, attempts have been made to find origins and meanings for the rhyme, most which have no corroborating evidence.[1] Katherine Elwes Thomas in The Real Personages of Mother Goose (1930) suggested that the rhyme referred to resentment at the heavy taxation on wool.[5] This has particularly been taken to refer to the medieval English "Great" or "Old Custom" wool tax of 1275, which survived until the fifteenth century.[1] More recently the rhyme has been connected to the slave trade, particularly in the southern United States.[6] This explanation was advanced during debates over political correctness and the use and reform of nursery rhymes in the 1980s, but has no supporting historical evidence.[7] Rather than being negative, the wool of black sheep may have been prized as it could be made into dark cloth without dyeing.[6]	Raymond Group Raymond Group is an Indian branded fabric and fashion retailer, incorporated in 1925. It produces suiting fabric, with a capacity of producing 31 million meters of wool and wool-blended fabrics. Gautam Singhania is the chairman and managing director of the Raymond group.[3]	Silk in the Indian subcontinent Silk in the Indian subcontinent is a luxury good. In India, about 97% of the raw mulberry silk is produced in the five Indian states of Karnataka, Andhra Pradesh, Tamil Nadu, West Bengal and Jammu and Kashmir.[1] Mysore and North Bangalore, the upcoming site of a US$20 million "Silk City", contribute to a majority of silk production.[2] Another emerging silk producer is Tamil Nadu where mulberry cultivation is concentrated in Salem, Erode and Dharmapuri districts. Hyderabad, Andhra Pradesh and Gobichettipalayam, Tamil Nadu were the first locations to have automated silk reeling units.[3] yoyo quantity:::	F. W. Woolworth Company The two Woolworth brothers pioneered and developed merchandising, direct purchasing, sales, and customer service practices commonly used today. Despite its growing to be one of the largest retail chains in the world through most of the 20th century, increased competition led to its decline beginning in the 1980s, while its sporting goods division grew. The chain went out of business in July 1997, when the company decided to focus primarily on sporting goods and renamed itself Venator Group. By 2001, the company focused exclusively on the sporting goods market, changing its name to the present Foot Locker, Inc., changing its ticker symbol from its familiar Z in 2003 to its present ticker (NYSE: FL).	Silk Silk's absorbency makes it comfortable to wear in warm weather and while active. Its low conductivity keeps warm air close to the skin during cold weather. It is often used for clothing such as shirts, ties, blouses, formal dresses, high fashion clothes, lining, lingerie, pajamas, robes, dress suits, sun dresses and Eastern folk costumes. For practical use, silk is excellent as clothing that protects from many biting insects that would ordinarily pierce clothing, such as mosquitoes and horseflies.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

tomaarsen/gooaq-hard-negatives

• Dataset: tomaarsen/gooaq-hard-negatives at 87594a1
• Size: 500,000 training samples
• Columns: question, answer, negative_1, negative_2, negative_3, negative_4, and negative_5
• Approximate statistics based on the first 1000 samples:

  	question	answer	negative_1	negative_2	negative_3	negative_4	negative_5
  type	string	string	string	string	string	string	string
  details	min: 8 tokens mean: 11.99 tokens max: 22 tokens	min: 15 tokens mean: 57.82 tokens max: 138 tokens	min: 14 tokens mean: 57.42 tokens max: 125 tokens	min: 14 tokens mean: 56.84 tokens max: 120 tokens	min: 14 tokens mean: 57.08 tokens max: 155 tokens	min: 15 tokens mean: 57.54 tokens max: 129 tokens	min: 14 tokens mean: 58.23 tokens max: 195 tokens

• Samples:

  question	answer	negative_1	negative_2	negative_3	negative_4	negative_5
  is toprol xl the same as metoprolol?	Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.	Secondly, metoprolol and metoprolol ER have different brand-name equivalents: Brand version of metoprolol: Lopressor. Brand version of metoprolol ER: Toprol XL.	Pill with imprint 1 is White, Round and has been identified as Metoprolol Tartrate 25 mg.	Interactions between your drugs No interactions were found between Allergy Relief and metoprolol. This does not necessarily mean no interactions exist. Always consult your healthcare provider.	Metoprolol is a type of medication called a beta blocker. It works by relaxing blood vessels and slowing heart rate, which improves blood flow and lowers blood pressure. Metoprolol can also improve the likelihood of survival after a heart attack.	Metoprolol starts to work after about 2 hours, but it can take up to 1 week to fully take effect. You may not feel any different when you take metoprolol, but this doesn't mean it's not working. It's important to keep taking your medicine.
  are you experienced cd steve hoffman?	The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.	I Saw the Light. Showcasing the unique talent and musical influence of country-western artist Hank Williams, this candid biography also sheds light on the legacy of drug abuse and tormented relationships that contributes to the singer's legend.	(Read our ranking of his top 10.) And while Howard dresses the part of director, any notion of him as a tortured auteur or dictatorial taskmasker — the clichés of the Hollywood director — are tossed aside. He's very nice.	He was a music star too. Where're you people born and brought up? We 're born and brought up here in Anambra State at Nkpor town, near Onitsha.	At the age of 87 he has now retired from his live shows and all the traveling involved. And although he still picks up his Martin Guitar and does a show now and then, his life is now devoted to writing his memoirs.	The owner of the mysterious voice behind all these videos is a man who's seen a lot, visiting a total of 56 intimate celebrity spaces over the course of five years. His name is Joe Sabia — that's him in the photo — and he's currently the VP of creative development at Condé Nast Entertainment.
  how are babushka dolls made?	Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.	A quick scan of the auction and buy-it-now listings on eBay finds porcelain doll values ranging from around $5 and $10 to several thousand dollars or more but no dolls listed above $10,000.	Japanese dolls are called as ningyō in Japanese and literally translates to 'human form'.	Matyoo: All Fresno Girl dolls come just as real children are born.	As of September 2016, there are over 100 characters. The main toy line includes 13-inch Dolls, the mini-series, and a variety of mini play-sets and plush dolls as well as Lalaloopsy Littles, smaller siblings of the 13-inch dolls. A spin-off known as "Lala-Oopsies" came out in late 2012.	LOL dolls are little baby dolls that come wrapped inside a surprise toy ball. Each ball has layers that contain stickers, secret messages, mix and match accessories–and finally–a doll. ... The doll on the ball is almost never the doll inside. Dolls are released in series, so not every doll is available all the time.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

bclavie/msmarco-500k-triplets

• Dataset: bclavie/msmarco-500k-triplets at cb1a85c
• Size: 500,000 training samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative
  type	string	string	string
  details	min: 4 tokens mean: 9.31 tokens max: 31 tokens	min: 20 tokens mean: 82.19 tokens max: 216 tokens	min: 18 tokens mean: 78.99 tokens max: 209 tokens

• Samples:

  query	positive	negative
  the most important factor that influences k+ secretion is __________.	The regulation of K+ distribution between the intracellular and extracellular space is referred to as internal K+ balance. The most important factors regulating this movement under normal conditions are insulin and catecholamines (1).	They are both also important for secretion and flow of bile: 1 Cholecystokinin: The name of this hormone describes its effect on the biliary system-cholecysto = gallbladder and kinin = movement. 2 Secretin: This hormone is secreted in response to acid in the duodenum.
  how much did the mackinac bridge cost to build	The cost to design the project was $3,500,000 (Steinman Company). The cost to construct the bridge was $70, 268,500. Two primary contractors were hired to build the bridge: American Bridge for superstructure - $44,532,900; and Merritt-Chapman and Scott of New York for the foundations - $25,735,600.	When your child needs a dental tooth bridge, you need to know the average cost so you can factor the price into your budget. Several factors affect the price of a bridge, which can run between $700 to $1,500 per tooth. If you have insurance or your child is covered by Medicaid, part of the cost may be covered.
  when do concussion symptoms appear	Then you can get advice on what to do next. For milder symptoms, the doctor may recommend rest and ask you to watch your child closely for changes, such as a headache that gets worse. Symptoms of a concussion don't always show up right away, and can develop within 24 to 72 hours after an injury.	Concussion: A traumatic injury to soft tissue, usually the brain, as a result of a violent blow, shaking, or spinning. A brain concussion can cause immediate but temporary impairment of brain functions, such as thinking, vision, equilibrium, and consciousness. After a person has had a concussion, he or she is at increased risk for recurrence. Moreover, after a person has several concussions, less of a blow can cause injury, and the person can require more time to recover.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

sentence-transformers/all-nli

• Dataset: sentence-transformers/all-nli at d482672
• Size: 500,000 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 7 tokens mean: 10.46 tokens max: 46 tokens	min: 6 tokens mean: 12.91 tokens max: 40 tokens	min: 5 tokens mean: 13.49 tokens max: 51 tokens

• Samples:

  anchor	positive	negative
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	A person is at a diner, ordering an omelette.
  Children smiling and waving at camera	There are children present	The kids are frowning
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.	The boy skates down the sidewalk.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1

• Dataset: sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1 at 84ed2d3
• Size: 500,000 training samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative
  type	string	string	string
  details	min: 5 tokens mean: 9.87 tokens max: 16 tokens	min: 44 tokens mean: 85.25 tokens max: 211 tokens	min: 18 tokens mean: 81.18 tokens max: 227 tokens

• Samples:

  query	positive	negative
  what are the liberal arts?	liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.	Rather than preparing students for a specific career, liberal arts programs focus on cultural literacy and hone communication and analytical skills. They often cover various disciplines, ranging from the humanities to social sciences. 1 Program Levels in Liberal Arts: Associate degree, Bachelor's degree, Master's degree.
  what are the liberal arts?	liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.	Artes Liberales: The historical basis for the modern liberal arts, consisting of the trivium (grammar, logic, and rhetoric) and the quadrivium (arithmetic, geometry, astronomy, and music). General Education: That part of a liberal education curriculum that is shared by all students.
  what are the liberal arts?	liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.	Liberal Arts. Upon completion of the Liberal Arts degree, students will be able to express ideas in coherent, creative, and appropriate forms, orally and in writing. Students will be able to apply their reading abilities in order to interconnect an understanding of resources to academic, professional, and personal interests.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

sentence-transformers/gooaq

• Dataset: sentence-transformers/gooaq at b089f72
• Size: 500,000 training samples
• Columns: question and answer
• Approximate statistics based on the first 1000 samples:

  	question	answer
  type	string	string
  details	min: 8 tokens mean: 12.19 tokens max: 22 tokens	min: 13 tokens mean: 58.34 tokens max: 124 tokens

• Samples:

  question	answer
  is toprol xl the same as metoprolol?	Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.
  are you experienced cd steve hoffman?	The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.
  how are babushka dolls made?	Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

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

sentence-transformers/natural-questions

• Dataset: sentence-transformers/natural-questions at f9e894e
• Size: 100,231 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 12.47 tokens max: 23 tokens	min: 17 tokens mean: 138.32 tokens max: 556 tokens

• Samples:

  query	answer
  when did richmond last play in a preliminary final	Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...
  who sang what in the world's come over you	Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.
  who produces the most wool in the world	Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

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

merged-2l-nli

• Dataset: merged-2l-nli at af845c6
• Size: 425,243 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 72.83 tokens max: 1219 tokens	min: 5 tokens mean: 12.78 tokens max: 118 tokens	0: ~55.50% 1: ~44.50%

• Samples:

  sentence1	sentence2	label
  What type of food was cheese considered to be in Rome?	The staple foods were generally consumed around 11 o'clock, and consisted of bread, lettuce, cheese, fruits, nuts, and cold meat left over from the dinner the night before.[citation needed]	1
  No Weapons of Mass Destruction Found in Iraq Yet.	Weapons of Mass Destruction Found in Iraq.	0
  I stuck a pin through a carrot. When I pulled the pin out, it had a hole.	The carrot had a hole.	1

• Loss: SoftmaxLoss

merged-3l-nli

• Dataset: merged-3l-nli at e311b1f
• Size: 564,204 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 5 tokens mean: 154.01 tokens max: 8192 tokens	min: 2 tokens mean: 28.37 tokens max: 570 tokens	0: ~36.00% 1: ~31.50% 2: ~32.50%

• Samples:

  sentence1	sentence2	label
  Over the nave, the two hollow pyramids appear to be designed in the style of chimneys for a castle kitchen.	There are seven pyramids there.	2
  The Catch of the Season is an Edwardian musical comedy by Seymour Hicks and Cosmo Hamilton, with music by Herbert Haines and Evelyn Baker and lyrics by Charles H. Taylor, based on the fairy tale Cinderella. A debutante is engaged to a young aristocrat but loves a page.	Seymour Hicks was alive in 1975.	1
  A 3600 g infant is heavy. A 2400 g infant is light.	A 2220 g bicycle is light.	1

• Loss: SoftmaxLoss

zero-shot-label-nli

• Dataset: zero-shot-label-nli at b363c89
• Size: 1,090,333 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	int	string	string
  details	0: ~49.30% 2: ~50.70%	min: 3 tokens mean: 81.11 tokens max: 5802 tokens	min: 7 tokens mean: 8.08 tokens max: 17 tokens

• Samples:

  label	sentence1	sentence2
  2	okay	This example is reply_y.
  2	We retrospectively compared 2 methods that have been proposed to screen for IA [1, 2].	This example is background.
  2	PersonX puts it under PersonX's pillow PersonX then checks it again Person X suffers from obsessive compulsive disorder.	This example is weakener.

• Loss: SoftmaxLoss

dataset_train_nli

• Dataset: dataset_train_nli at 1e00964
• Size: 1,018,733 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 4 tokens mean: 95.56 tokens max: 1152 tokens	min: 8 tokens mean: 14.05 tokens max: 38 tokens	0: ~50.60% 1: ~49.40%

• Samples:

  sentence1	sentence2	label
  where is nayagara falls located	The example utterance is a query about music.	1
  Druyun gets nine-month prison sentence A former top Air Force acquisition executive today was sentenced to nine months in prison for conspiring to help Boeing Co. win a multibillion-dollar Pentagon contract.	This example news text is about world news	1
  Writing on the #39;wall #39; n Last edition of the Far Eastern Economic Review is shown on the streets of Hong Kong. The weekly news magazine is to fold in its current form with the loss of 80 jobs, the magazine #39;s publisher Dow Jones said yesterday.	This example news text is about science and technology	1

• Loss: SoftmaxLoss

paws/labeled_final

• Dataset: paws/labeled_final at 161ece9
• Size: 49,401 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 10 tokens mean: 27.44 tokens max: 51 tokens	min: 8 tokens mean: 27.44 tokens max: 51 tokens	0: ~55.60% 1: ~44.40%

• Samples:

  sentence1	sentence2	label
  In Paris , in October 1560 , he secretly met the English ambassador , Nicolas Throckmorton , asking him for a passport to return to England through Scotland .	In October 1560 , he secretly met with the English ambassador , Nicolas Throckmorton , in Paris , and asked him for a passport to return to Scotland through England .	0
  The NBA season of 1975 -- 76 was the 30th season of the National Basketball Association .	The 1975 -- 76 season of the National Basketball Association was the 30th season of the NBA .	1
  There are also specific discussions , public profile debates and project discussions .	There are also public discussions , profile specific discussions , and project discussions .	0

• Loss: SoftmaxLoss

glue/mrpc

• Dataset: glue/mrpc at bcdcba7
• Size: 3,668 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 10 tokens mean: 27.55 tokens max: 49 tokens	min: 12 tokens mean: 27.25 tokens max: 48 tokens	0: ~33.70% 1: ~66.30%

• Samples:

  sentence1	sentence2	label
  Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .	Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .	1
  Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .	Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .	0
  They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .	On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .	1

• Loss: SoftmaxLoss

glue/qqp

• Dataset: glue/qqp at bcdcba7
• Size: 363,846 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 15.9 tokens max: 53 tokens	min: 6 tokens mean: 15.73 tokens max: 72 tokens	0: ~61.90% 1: ~38.10%

• Samples:

  sentence1	sentence2	label
  What are reviews of Big Data University?	What is your review of Big Data University?	1
  What are glass bottles made of?	How is a glass bottle made?	0
  What do you really know about Algeria?	What do you know about Algeria?	1

• Loss: SoftmaxLoss

fever-evidence-related

• Dataset: fever-evidence-related at 14aba00
• Size: 403,218 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 13.63 tokens max: 39 tokens	min: 9 tokens mean: 353.0 tokens max: 5023 tokens	0: ~31.80% 1: ~68.20%

• Samples:

  sentence1	sentence2	label
  The Bridges of Madison County is a TV series.	Saulsbury is a town in Hardeman County , Tennessee .. Hardeman County. Hardeman County, Tennessee. Tennessee. Tennessee. County. List of counties in Tennessee. Hardeman. Hardeman County, Tennessee. The population was 99 at the 2000 census and 81 at the 2010 census showing a decrease of 18 .. United States Census, 2010. It is located along State Highway 57 in southwest Hardeman County .. Hardeman County. Hardeman County, Tennessee. State. Political divisions of the United States. County. List of counties in Tennessee. Hardeman. Hardeman County, Tennessee. State Highway 57. State Highway 57	1
  Jessica Lange's first film role was in Godzilla.	Haji Ahmadov -LRB- Hacı Əhmədov , born on 23 November 1993 in Baku , Soviet Union -RRB- is an Azerbaijani football defender who plays for AZAL .. Baku. Baku. AZAL. AZAL PFK. Soviet Union. Soviet Union. Azerbaijani. Azerbaijani people. football. football ( soccer ). defender. Defender ( football )	1
  Brad Pitt directed 12 Years a Slave.	The Bronze Bauhinia Star -LRB- , BBS -RRB- is the lowest rank in Order of the Bauhinia Star in Hong Kong , created in 1997 to replace the British honours system of the Order of the British Empire after the transfer of sovereignty to People 's Republic of China and the establishment of the Hong Kong Special Administrative Region -LRB- HKSAR -RRB- .. Order of the Bauhinia Star. Order of the Bauhinia Star. British honours system. British honours system. Order of the British Empire. Order of the British Empire. Special Administrative Region. Special Administrative Region of the People's Republic of China. It is awarded to persons who have given outstanding service over a long period of time , but in a more limited field or way than that required for the Silver Bauhinia Star .. Silver Bauhinia Star. Silver Bauhinia Star	1

• Loss: SoftmaxLoss

glue/stsb_0

• Dataset: glue/stsb_0 at bcdcba7
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 15.22 tokens max: 74 tokens	min: 6 tokens mean: 15.04 tokens max: 51 tokens	min: 0.0 mean: 2.74 max: 5.0

• Samples:

  sentence1	sentence2	label
  Snowden Hits Hurdles in Search for Asylum	Snowden's hits hurdles in search for asylum	5.0
  Ukrainian protesters back in streets for anti-government rally	Ukraine protesters topple Lenin statue in Kiev	2.5999999046325684
  "Biotech products, if anything, may be safer than conventional products because of all the testing," Fraley said, adding that 18 countries have adopted biotechnology.	"Biotech products, if anything, may be safer than conventional products because of all the testing," said Robert Fraley, Monsanto's executive vice president.	3.200000047683716

• Loss: AnglELoss with these parameters:

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

glue/stsb_1

• Dataset: glue/stsb_1 at bcdcba7
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 15.22 tokens max: 74 tokens	min: 6 tokens mean: 15.04 tokens max: 51 tokens	min: 0.0 mean: 2.74 max: 5.0

• Samples:

  sentence1	sentence2	label
  Snowden Hits Hurdles in Search for Asylum	Snowden's hits hurdles in search for asylum	5.0
  Ukrainian protesters back in streets for anti-government rally	Ukraine protesters topple Lenin statue in Kiev	2.5999999046325684
  "Biotech products, if anything, may be safer than conventional products because of all the testing," Fraley said, adding that 18 countries have adopted biotechnology.	"Biotech products, if anything, may be safer than conventional products because of all the testing," said Robert Fraley, Monsanto's executive vice president.	3.200000047683716

• Loss: CoSENTLoss with these parameters:

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

glue/stsb_2

• Dataset: glue/stsb_2 at bcdcba7
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 15.22 tokens max: 74 tokens	min: 6 tokens mean: 15.04 tokens max: 51 tokens	min: 0.0 mean: 2.74 max: 5.0

• Samples:

  sentence1	sentence2	label
  Snowden Hits Hurdles in Search for Asylum	Snowden's hits hurdles in search for asylum	5.0
  Ukrainian protesters back in streets for anti-government rally	Ukraine protesters topple Lenin statue in Kiev	2.5999999046325684
  "Biotech products, if anything, may be safer than conventional products because of all the testing," Fraley said, adding that 18 countries have adopted biotechnology.	"Biotech products, if anything, may be safer than conventional products because of all the testing," said Robert Fraley, Monsanto's executive vice president.	3.200000047683716

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

sick/relatedness_0

• Dataset: sick/relatedness_0
• Size: 4,439 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.17 tokens max: 30 tokens	min: 6 tokens mean: 12.06 tokens max: 27 tokens	min: 1.0 mean: 3.53 max: 5.0

• Samples:

  sentence1	sentence2	label
  The dark skinned male is standing on one hand in front of a yellow building	The dark skinned male is not standing on one hand in front of a yellow building	4.0
  A man is singing and playing a guitar	A boy is skillfully playing a piano	2.299999952316284
  A picture is being drawn by a man	The person is drawing	4.099999904632568

• Loss: AnglELoss with these parameters:

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

sick/relatedness_1

• Dataset: sick/relatedness_1
• Size: 4,439 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.17 tokens max: 30 tokens	min: 6 tokens mean: 12.06 tokens max: 27 tokens	min: 1.0 mean: 3.53 max: 5.0

• Samples:

  sentence1	sentence2	label
  The dark skinned male is standing on one hand in front of a yellow building	The dark skinned male is not standing on one hand in front of a yellow building	4.0
  A man is singing and playing a guitar	A boy is skillfully playing a piano	2.299999952316284
  A picture is being drawn by a man	The person is drawing	4.099999904632568

• Loss: CoSENTLoss with these parameters:

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

sick/relatedness_2

• Dataset: sick/relatedness_2
• Size: 4,439 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.17 tokens max: 30 tokens	min: 6 tokens mean: 12.06 tokens max: 27 tokens	min: 1.0 mean: 3.53 max: 5.0

• Samples:

  sentence1	sentence2	label
  The dark skinned male is standing on one hand in front of a yellow building	The dark skinned male is not standing on one hand in front of a yellow building	4.0
  A man is singing and playing a guitar	A boy is skillfully playing a piano	2.299999952316284
  A picture is being drawn by a man	The person is drawing	4.099999904632568

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

sts-companion_0

• Dataset: sts-companion_0 at fd8beff
• Size: 5,289 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.15 max: 5.0	min: 5 tokens mean: 18.78 tokens max: 79 tokens	min: 6 tokens mean: 16.68 tokens max: 71 tokens

• Samples:

  label	sentence1	sentence2
  4.6	As a matter of urgency, therefore, the staff complement of the Interdepartmental Group attached to the Commission Secretariat should be strengthened at the earliest possible opportunity in order to ensure that all proposals for acts which are general in scope are accompanied, when considered by the College of Commissioners and on the basis of Article 299(2), by a simplified sheet outlining their potential impact.	Thus, it is urgent that the inter-service group staff should be strengthened very quickly at the heart of the General Secretariat of the Commission, so that all proposals to act of general scope can be accompanied, during their examination by the college on the basis of Article 299(2), a detailed impact statement.
  4.0	Reiterating the calls made by the European Parliament in its resolution of 16 March 2000, what initiatives does the Presidency of the European Council propose to take with a view to playing a more active role so as to guarantee the full and complete application of the UN peace plan?	As requested by the European Parliament in its resolution of 16 March 2000, that these initiatives the presidency of the European Council is going to take to play a more active role in order to ensure the full implementation of the UN peace plan?
  3.2	Let us, as a Europe of 15 Member States, organise ourselves in order to be able to welcome those countries who are knocking at the door into the fold under respectable conditions.	Let us organise itself to 15 in order to be able to welcome the right conditions for countries which are knocking on our door.

• Loss: AnglELoss with these parameters:

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

sts-companion_1

• Dataset: sts-companion_1 at fd8beff
• Size: 5,289 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.15 max: 5.0	min: 5 tokens mean: 18.78 tokens max: 79 tokens	min: 6 tokens mean: 16.68 tokens max: 71 tokens

• Samples:

  label	sentence1	sentence2
  4.6	As a matter of urgency, therefore, the staff complement of the Interdepartmental Group attached to the Commission Secretariat should be strengthened at the earliest possible opportunity in order to ensure that all proposals for acts which are general in scope are accompanied, when considered by the College of Commissioners and on the basis of Article 299(2), by a simplified sheet outlining their potential impact.	Thus, it is urgent that the inter-service group staff should be strengthened very quickly at the heart of the General Secretariat of the Commission, so that all proposals to act of general scope can be accompanied, during their examination by the college on the basis of Article 299(2), a detailed impact statement.
  4.0	Reiterating the calls made by the European Parliament in its resolution of 16 March 2000, what initiatives does the Presidency of the European Council propose to take with a view to playing a more active role so as to guarantee the full and complete application of the UN peace plan?	As requested by the European Parliament in its resolution of 16 March 2000, that these initiatives the presidency of the European Council is going to take to play a more active role in order to ensure the full implementation of the UN peace plan?
  3.2	Let us, as a Europe of 15 Member States, organise ourselves in order to be able to welcome those countries who are knocking at the door into the fold under respectable conditions.	Let us organise itself to 15 in order to be able to welcome the right conditions for countries which are knocking on our door.

• Loss: CoSENTLoss with these parameters:

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

sts-companion_2

• Dataset: sts-companion_2 at fd8beff
• Size: 5,289 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.15 max: 5.0	min: 5 tokens mean: 18.78 tokens max: 79 tokens	min: 6 tokens mean: 16.68 tokens max: 71 tokens

• Samples:

  label	sentence1	sentence2
  4.6	As a matter of urgency, therefore, the staff complement of the Interdepartmental Group attached to the Commission Secretariat should be strengthened at the earliest possible opportunity in order to ensure that all proposals for acts which are general in scope are accompanied, when considered by the College of Commissioners and on the basis of Article 299(2), by a simplified sheet outlining their potential impact.	Thus, it is urgent that the inter-service group staff should be strengthened very quickly at the heart of the General Secretariat of the Commission, so that all proposals to act of general scope can be accompanied, during their examination by the college on the basis of Article 299(2), a detailed impact statement.
  4.0	Reiterating the calls made by the European Parliament in its resolution of 16 March 2000, what initiatives does the Presidency of the European Council propose to take with a view to playing a more active role so as to guarantee the full and complete application of the UN peace plan?	As requested by the European Parliament in its resolution of 16 March 2000, that these initiatives the presidency of the European Council is going to take to play a more active role in order to ensure the full implementation of the UN peace plan?
  3.2	Let us, as a Europe of 15 Member States, organise ourselves in order to be able to welcome those countries who are knocking at the door into the fold under respectable conditions.	Let us organise itself to 15 in order to be able to welcome the right conditions for countries which are knocking on our door.

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Datasets

merged-2l-nli

• Dataset: merged-2l-nli at af845c6
• Size: 4,053 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 75.82 tokens max: 1219 tokens	min: 5 tokens mean: 13.5 tokens max: 158 tokens	0: ~51.00% 1: ~49.00%

• Samples:

  sentence1	sentence2	label
  What happens to the norm when a number is multiplied by p?	While completing Q (roughly, filling the gaps) with respect to the absolute value yields the field of real numbers, completing with respect to the p-adic norm	−
  The abode of the Greek gods was on the summit of Mount Olympus, in Thessaly.	Mount Olympus is in Thessaly.	1
  The drain is clogged with hair. It has to be cleaned.	The hair has to be cleaned.	0

• Loss: SoftmaxLoss

merged-3l-nli

• Dataset: merged-3l-nli at e311b1f
• Size: 2,872 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 258.59 tokens max: 8192 tokens	min: 2 tokens mean: 23.6 tokens max: 430 tokens	0: ~38.20% 1: ~31.30% 2: ~30.50%

• Samples:

  sentence1	sentence2	label
  But if Congress opts for debt over taxation, you can count on thoughtless commentators to denounce the interest payments on that debt as a second, and separate, outrage.	Everybody considers the interest on the national debt an outrage.	1
  The 1997 KNVB Cup Final was a football match between Roda JC and Heerenveen on 8 May 1997 at De Kuip, Rotterdam. It was the final match of the 1996–97 KNVB Cup competition and the 79th KNVB Cup final. Roda won 4–2 after goals from Gerald Sibon, Ger Senden, Eric van der Luer and Maarten Schops. It was the side's first KNVB Cup trophy.	Roda JC kept the Cup trophy at their headquarters.	1
  Discover Financial Services, Inc. is an American financial services company, which issues the Discover Card and operates the Discover and Pulse networks, and owns Diners Club International. Discover Card is the third largest credit card brand in the United States, when measured by cards in force, with nearly 50 million cardholders.	Discover Card is a way to build credit for less than 50 million cardholders	0

• Loss: SoftmaxLoss

zero-shot-label-nli

• Dataset: zero-shot-label-nli at b363c89
• Size: 14,419 evaluation samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	int	string	string
  details	0: ~51.40% 2: ~48.60%	min: 3 tokens mean: 101.82 tokens max: 8192 tokens	min: 7 tokens mean: 8.01 tokens max: 23 tokens

• Samples:

  label	sentence1	sentence2
  2	Police suspected that Shaichat , 20 , had been abducted either by Palestinians or by Israeli Arabs . Nobody claimed responsibility for Schaichat 's death , but police suspect that the 20-year-old soldier was abducted either by Palestinians or Israeli Arabs .	This example is equivalent.
  2	Can immorality be achieved by blocking death genes? Can immortality be achieved by blocking death genes?	This example is not_duplicate.
  2	can a minor sit at a bar in nj	This example is False.

• Loss: SoftmaxLoss

dataset_train_nli

• Dataset: dataset_train_nli at 1e00964
• Size: 1,018,733 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 4 tokens mean: 96.94 tokens max: 1020 tokens	min: 8 tokens mean: 13.86 tokens max: 38 tokens	0: ~52.50% 1: ~47.50%

• Samples:

  sentence1	sentence2	label
  Ecoplug MAX® ECOPLUG MAX® is an efficient method to prevent regroth from leaf trees. - Provides 100 percent effective on all brushwood - Can be used all year round - Kills all unwanted leaf tree - Minimizes chemical diffusion - Kills the entire root system of the treated tree/stump - Fully selective method reduce chemical use up to 90% compared to previously used methods. - Can be used all year around. - Will exterminate: Alder, elm, aspen, birch, beech, lime, maple, mountain ash,sallow, poplar, ash, cherry, bird cherry, oak and more broad leafed trees - Minimize the use of chemicals during treatment of trees and stumps. - The product will kill off the entire root system, but only the root system. Neither people, animals or the enviromnent will be exposed to our product..	This text is about: root extermination	0
  can you start f. m. eight hundred and ninety radio channel	The intent of this example utterance is a datetime query.	1
  never again swings between false sentiment and unfunny madcap comedy and , along the way , expects the audience to invest in the central relationship as some kind of marriage of true minds .	The sentiment in this example rotten tomatoes movie review is negative	0

• Loss: SoftmaxLoss

paws/labeled_final

• Dataset: paws/labeled_final at 161ece9
• Size: 8,000 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 9 tokens mean: 27.86 tokens max: 51 tokens	min: 9 tokens mean: 27.83 tokens max: 52 tokens	0: ~54.90% 1: ~45.10%

• Samples:

  sentence1	sentence2	label
  Bradd Crellin represented BARLA Cumbria on a tour of Australia with 6 other players representing Britain , also on a tour of Australia .	Bradd Crellin also represented BARLA Great Britain on a tour through Australia on a tour through Australia with 6 other players representing Cumbria .	0
  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 .	1
  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 .	1

• Loss: SoftmaxLoss

glue/mrpc

• Dataset: glue/mrpc at bcdcba7
• Size: 408 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 408 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 14 tokens mean: 27.92 tokens max: 46 tokens	min: 11 tokens mean: 27.24 tokens max: 43 tokens	0: ~31.62% 1: ~68.38%

• Samples:

  sentence1	sentence2	label
  He said the foodservice pie business doesn 't fit the company 's long-term growth strategy .	" The foodservice pie business does not fit our long-term growth strategy .	1
  Magnarelli said Racicot hated the Iraqi regime and looked forward to using his long years of training in the war .	His wife said he was " 100 percent behind George Bush " and looked forward to using his years of training in the war .	0
  The dollar was at 116.92 yen against the yen , flat on the session , and at 1.2891 against the Swiss franc , also flat .	The dollar was at 116.78 yen JPY = , virtually flat on the session , and at 1.2871 against the Swiss franc CHF = , down 0.1 percent .	0

• Loss: SoftmaxLoss

glue/qqp

• Dataset: glue/qqp at bcdcba7
• Size: 40,430 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 3 tokens mean: 15.77 tokens max: 48 tokens	min: 6 tokens mean: 16.05 tokens max: 69 tokens	0: ~62.00% 1: ~38.00%

• Samples:

  sentence1	sentence2	label
  What happens to a question on Quora if it is marked as needing further improvement?	If Quora doesn't understand my question and marks it as needing improvement, can others still see it?	1
  What does the open blue circle in Facebook Messenger mean?	"what does ""delivered"" mean on Facebook messenger?"	0
  How do I cool my mind?	What is the best way to be cool?	0

• Loss: SoftmaxLoss

fever-evidence-related

• Dataset: fever-evidence-related at 14aba00
• Size: 54,578 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 7 tokens mean: 13.66 tokens max: 26 tokens	min: 33 tokens mean: 282.39 tokens max: 1713 tokens	0: ~28.10% 1: ~71.90%

• Samples:

  sentence1	sentence2	label
  Colin Kaepernick became a starting quarterback during the 49ers 63rd season in the National Football League.	RapidAdvance is a technology-powered financial services company that provides working capital to small and mid-sized businesses in the United States .. United States. United States. financial services. financial services. working capital. working capital. small and mid-sized businesses. Small and medium-sized enterprises. It offers small business loan programs for business owners in a variety of industries , including traditional retail establishments , brand name chain restaurants , automotive repair , manufacturing , trucking , and professional service providers .. Founded in 2005 and headquartered in Bethesda , Maryland , the company was acquired by Dan Gilbert 's Rockbridge Growth Equity , LLC in 2013 .. It is part of Rock Ventures `` family '' of companies that include the Cleveland Cavaliers , Fathead , Quicken Loans and Genius .. Rock Ventures. Rock Ventures. Cleveland Cavaliers. Cleveland Cavaliers. Fathead. Fathead ( brand ). Quicken Loans. Quicken Loans. Genius. Genius	1
  Colin Kaepernick became a starting quarterback during the 49ers 63rd season in the National Football League.	Arthur Herbert Copeland -LRB- June 22 , 1898 Rochester , New York -- July 6 , 1970 -RRB- was an American mathematician .. American. United States. He graduated from Harvard University in 1926 and taught at Rice University and the University of Michigan .. Rice University. Rice University. University of Michigan. University of Michigan. Harvard University. Harvard University. His main interest was in the foundations of probability .. probability. probability theory. He worked with Paul Erdos on the Copeland-Erdos constant .. Copeland-Erdos constant. Copeland-Erdos constant. Paul Erdos. Paul Erdos. His son , Arthur Herbert Copeland , Jr. , is also a mathematician .	1
  Tilda Swinton is a vegan.	Michael Ronald Taylor -LRB- 1 June 1938 , Ealing , West London - 19 January 1969 -RRB- was a British jazz composer , pianist and co-songwriter for the band Cream .. Ealing. Ealing. London. London. British. United Kingdom. Cream. Cream ( band ). Mike Taylor was brought up by his grandparents in London and Kent , and joined the RAF for his national service .. London. London. Having rehearsed and written extensively throughout the early 1960s , he recorded two albums for the Lansdowne series produced by Denis Preston : Pendulum -LRB- 1966 -RRB- with drummer Jon Hiseman , bassist Tony Reeves and saxophonist Dave Tomlin -RRB- and Trio -LRB- 1967 -RRB- with Hiseman and bassists Jack Bruce and Ron Rubin .. Denis Preston. Denis Preston. Jon Hiseman. Jon Hiseman. Dave Tomlin. Dave Tomlin ( musician ). Jack Bruce. Jack Bruce. They were issued on UK Columbia .. Columbia. Columbia Graphophone Company. During his brief recording career , several of Taylor 's pieces were played and recorded by his ...	1

• Loss: SoftmaxLoss

glue/stsb_0

• Dataset: glue/stsb_0 at bcdcba7
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 5 tokens mean: 16.46 tokens max: 44 tokens	min: 6 tokens mean: 16.47 tokens max: 44 tokens	min: 0.0 mean: 2.35 max: 5.0

• Samples:

  sentence1	sentence2	label
  The room used for defecation is almost always referred to by euphemism.	I'm English, and would probably use 'toilet' most of the time, and always in the context of a private home.	1.600000023841858
  The two-year note US2YT=RR fell 5/32 in price, taking its yield to 1.23 percent from 1.16 percent late on Monday.	The benchmark 10-year note US10YT=RR lost 11/32 in price, taking its yield to 3.21 percent from 3.17 percent late on Monday.	2.0
  I use Elinchrom Skyports, but if money is not an issue then go for PocketWizards.	Or just go with the ultra-cheap YongNuo RF-602, which give you a lot of bang for the buck.	1.2000000476837158

• Loss: AnglELoss with these parameters:

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

glue/stsb_1

• Dataset: glue/stsb_1 at bcdcba7
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 5 tokens mean: 16.46 tokens max: 44 tokens	min: 6 tokens mean: 16.47 tokens max: 44 tokens	min: 0.0 mean: 2.35 max: 5.0

• Samples:

  sentence1	sentence2	label
  The room used for defecation is almost always referred to by euphemism.	I'm English, and would probably use 'toilet' most of the time, and always in the context of a private home.	1.600000023841858
  The two-year note US2YT=RR fell 5/32 in price, taking its yield to 1.23 percent from 1.16 percent late on Monday.	The benchmark 10-year note US10YT=RR lost 11/32 in price, taking its yield to 3.21 percent from 3.17 percent late on Monday.	2.0
  I use Elinchrom Skyports, but if money is not an issue then go for PocketWizards.	Or just go with the ultra-cheap YongNuo RF-602, which give you a lot of bang for the buck.	1.2000000476837158

• Loss: CoSENTLoss with these parameters:

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

glue/stsb_2

• Dataset: glue/stsb_2 at bcdcba7
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 5 tokens mean: 16.46 tokens max: 44 tokens	min: 6 tokens mean: 16.47 tokens max: 44 tokens	min: 0.0 mean: 2.35 max: 5.0

• Samples:

  sentence1	sentence2	label
  The room used for defecation is almost always referred to by euphemism.	I'm English, and would probably use 'toilet' most of the time, and always in the context of a private home.	1.600000023841858
  The two-year note US2YT=RR fell 5/32 in price, taking its yield to 1.23 percent from 1.16 percent late on Monday.	The benchmark 10-year note US10YT=RR lost 11/32 in price, taking its yield to 3.21 percent from 3.17 percent late on Monday.	2.0
  I use Elinchrom Skyports, but if money is not an issue then go for PocketWizards.	Or just go with the ultra-cheap YongNuo RF-602, which give you a lot of bang for the buck.	1.2000000476837158

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

sick/relatedness_0

• Dataset: sick/relatedness_0
• Size: 495 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 495 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.69 tokens max: 32 tokens	min: 6 tokens mean: 12.15 tokens max: 30 tokens	min: 1.0 mean: 3.59 max: 5.0

• Samples:

  sentence1	sentence2	label
  The young boys are playing outdoors and the man is smiling nearby	There is no boy playing outdoors and there is no man smiling	3.5999999046325684
  A person in a black jacket is doing tricks on a motorbike	A skilled person is riding a bicycle on one wheel	3.4000000953674316
  Four children are doing backbends in the gym	Four girls are doing backbends and playing outdoors	3.799999952316284

• Loss: AnglELoss with these parameters:

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

sick/relatedness_1

• Dataset: sick/relatedness_1
• Size: 495 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 495 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.69 tokens max: 32 tokens	min: 6 tokens mean: 12.15 tokens max: 30 tokens	min: 1.0 mean: 3.59 max: 5.0

• Samples:

  sentence1	sentence2	label
  The young boys are playing outdoors and the man is smiling nearby	There is no boy playing outdoors and there is no man smiling	3.5999999046325684
  A person in a black jacket is doing tricks on a motorbike	A skilled person is riding a bicycle on one wheel	3.4000000953674316
  Four children are doing backbends in the gym	Four girls are doing backbends and playing outdoors	3.799999952316284

• Loss: CoSENTLoss with these parameters:

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

sick/relatedness_2

• Dataset: sick/relatedness_2
• Size: 495 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 495 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 12.69 tokens max: 32 tokens	min: 6 tokens mean: 12.15 tokens max: 30 tokens	min: 1.0 mean: 3.59 max: 5.0

• Samples:

  sentence1	sentence2	label
  The young boys are playing outdoors and the man is smiling nearby	There is no boy playing outdoors and there is no man smiling	3.5999999046325684
  A person in a black jacket is doing tricks on a motorbike	A skilled person is riding a bicycle on one wheel	3.4000000953674316
  Four children are doing backbends in the gym	Four girls are doing backbends and playing outdoors	3.799999952316284

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

sts-companion_0

• Dataset: sts-companion_0 at fd8beff
• Size: 5,289 evaluation samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.24 max: 5.0	min: 5 tokens mean: 19.56 tokens max: 81 tokens	min: 5 tokens mean: 17.21 tokens max: 72 tokens

• Samples:

  label	sentence1	sentence2
  3.8	After all, it is by no means certain that the proposed definition of equitable price is better than any other, because the various definitions that are currently in use in the Member States are all perfectly satisfactory.	In fact, it is not absolutely certain that the definition of price that is proposed is better than another, because the different currently in the Member States all fully.
  2.0	rslw: no, why would i hate them?	why do you hate america so much?
  3.0	Families of #Newtown Victims Look for Answers on #Gun Violence #NRA	Families of Newtown School Massacre Victims Organize Against Gun Violence

• Loss: AnglELoss with these parameters:

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

sts-companion_1

• Dataset: sts-companion_1 at fd8beff
• Size: 5,289 evaluation samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.24 max: 5.0	min: 5 tokens mean: 19.56 tokens max: 81 tokens	min: 5 tokens mean: 17.21 tokens max: 72 tokens

• Samples:

  label	sentence1	sentence2
  3.8	After all, it is by no means certain that the proposed definition of equitable price is better than any other, because the various definitions that are currently in use in the Member States are all perfectly satisfactory.	In fact, it is not absolutely certain that the definition of price that is proposed is better than another, because the different currently in the Member States all fully.
  2.0	rslw: no, why would i hate them?	why do you hate america so much?
  3.0	Families of #Newtown Victims Look for Answers on #Gun Violence #NRA	Families of Newtown School Massacre Victims Organize Against Gun Violence

• Loss: CoSENTLoss with these parameters:

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

sts-companion_2

• Dataset: sts-companion_2 at fd8beff
• Size: 5,289 evaluation samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	float	string	string
  details	min: 0.0 mean: 3.24 max: 5.0	min: 5 tokens mean: 19.56 tokens max: 81 tokens	min: 5 tokens mean: 17.21 tokens max: 72 tokens

• Samples:

  label	sentence1	sentence2
  3.8	After all, it is by no means certain that the proposed definition of equitable price is better than any other, because the various definitions that are currently in use in the Member States are all perfectly satisfactory.	In fact, it is not absolutely certain that the definition of price that is proposed is better than another, because the different currently in the Member States all fully.
  2.0	rslw: no, why would i hate them?	why do you hate america so much?
  3.0	Families of #Newtown Victims Look for Answers on #Gun Violence #NRA	Families of Newtown School Massacre Victims Organize Against Gun Violence

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 24
• learning_rate: 3.5e-05
• weight_decay: 1e-06
• num_train_epochs: 2
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 24
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 3.5e-05
• weight_decay: 1e-06
• 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: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0025	500	6.0463
0.0050	1000	2.5823
0.0074	1500	1.1895
0.0099	2000	0.9445
0.0124	2500	0.8209
0.0149	3000	0.7738
0.0174	3500	0.7587
0.0198	4000	0.7189
0.0223	4500	0.7077
0.0248	5000	0.6986
0.0273	5500	0.6977
0.0297	6000	0.6969
0.0322	6500	0.6646
0.0347	7000	0.6125
0.0372	7500	0.6107
0.0397	8000	0.6454
0.0421	8500	0.6437
0.0446	9000	0.6001
0.0471	9500	0.613
0.0496	10000	0.5964
0.0521	10500	0.6019
0.0545	11000	0.5807
0.0570	11500	0.5661
0.0595	12000	0.5615
0.0620	12500	0.5679
0.0645	13000	0.5783
0.0669	13500	0.5627
0.0694	14000	0.5501
0.0719	14500	0.538
0.0744	15000	0.5828
0.0769	15500	0.5524
0.0793	16000	0.5327
0.0818	16500	0.5356
0.0843	17000	0.4979
0.0868	17500	0.5223
0.0892	18000	0.4955
0.0917	18500	0.5079
0.0942	19000	0.506
0.0967	19500	0.4926
0.0992	20000	0.4845
0.1016	20500	0.5078
0.1041	21000	0.4937
0.1066	21500	0.4937
0.1091	22000	0.4971
0.1116	22500	0.4699
0.1140	23000	0.5022
0.1165	23500	0.5162
0.1190	24000	0.5221
0.1215	24500	0.5147
0.1240	25000	0.4719
0.1264	25500	0.489
0.1289	26000	0.5117
0.1314	26500	0.4643
0.1339	27000	0.469
0.1364	27500	0.5095
0.1388	28000	0.441
0.1413	28500	0.4765
0.1438	29000	0.4943
0.1463	29500	0.4797
0.1487	30000	0.4709
0.1512	30500	0.4429
0.1537	31000	0.429
0.1562	31500	0.4445
0.1587	32000	0.4982
0.1611	32500	0.4501
0.1636	33000	0.4812
0.1661	33500	0.4483
0.1686	34000	0.4613
0.1711	34500	0.4646
0.1735	35000	0.4737
0.1760	35500	0.4648
0.1785	36000	0.4004
0.1810	36500	0.4346
0.1835	37000	0.4536
0.1859	37500	0.4469
0.1884	38000	0.4381
0.1909	38500	0.4451
0.1934	39000	0.4202
0.1958	39500	0.4437
0.1983	40000	0.4188
0.2008	40500	0.4016
0.2033	41000	0.4258
0.2058	41500	0.4072
0.2082	42000	0.4248
0.2107	42500	0.4414
0.2132	43000	0.4317
0.2157	43500	0.445
0.2182	44000	0.4106
0.2206	44500	0.4343
0.2231	45000	0.4025
0.2256	45500	0.4235
0.2281	46000	0.4583
0.2306	46500	0.4001
0.2330	47000	0.4188
0.2355	47500	0.4073
0.2380	48000	0.4407
0.2405	48500	0.4214
0.2430	49000	0.4181
0.2454	49500	0.4153
0.2479	50000	0.4171
0.2504	50500	0.4174
0.2529	51000	0.3984
0.2553	51500	0.4045
0.2578	52000	0.403
0.2603	52500	0.4109
0.2628	53000	0.4445
0.2653	53500	0.4114
0.2677	54000	0.3777
0.2702	54500	0.3682
0.2727	55000	0.3973
0.2752	55500	0.3998
0.2777	56000	0.3988
0.2801	56500	0.3965
0.2826	57000	0.434
0.2851	57500	0.3958
0.2876	58000	0.417
0.2901	58500	0.3767
0.2925	59000	0.3901
0.2950	59500	0.398
0.2975	60000	0.3788
0.3000	60500	0.4102
0.3025	61000	0.3718
0.3049	61500	0.394
0.3074	62000	0.3836
0.3099	62500	0.4169
0.3124	63000	0.4074
0.3148	63500	0.4379
0.3173	64000	0.3747
0.3198	64500	0.4141
0.3223	65000	0.3865
0.3248	65500	0.395
0.3272	66000	0.3571
0.3297	66500	0.3847
0.3322	67000	0.3778
0.3347	67500	0.4095
0.3372	68000	0.4036
0.3396	68500	0.3824
0.3421	69000	0.3811
0.3446	69500	0.368
0.3471	70000	0.4028
0.3496	70500	0.3978
0.3520	71000	0.3765
0.3545	71500	0.3735
0.3570	72000	0.3625
0.3595	72500	0.3696
0.3619	73000	0.3999
0.3644	73500	0.353
0.3669	74000	0.3902
0.3694	74500	0.3925
0.3719	75000	0.3382
0.3743	75500	0.3531
0.3768	76000	0.3618
0.3793	76500	0.3372
0.3818	77000	0.382
0.3843	77500	0.3866
0.3867	78000	0.3513
0.3892	78500	0.3727
0.3917	79000	0.3603
0.3942	79500	0.397
0.3967	80000	0.351
0.3991	80500	0.3675
0.4016	81000	0.3861
0.4041	81500	0.3423
0.4066	82000	0.3618
0.4091	82500	0.3784
0.4115	83000	0.3688
0.4140	83500	0.3343
0.4165	84000	0.3831
0.4190	84500	0.4134
0.4214	85000	0.3548
0.4239	85500	0.3422
0.4264	86000	0.3471
0.4289	86500	0.3506
0.4314	87000	0.3338
0.4338	87500	0.3283
0.4363	88000	0.3696
0.4388	88500	0.3476
0.4413	89000	0.3662
0.4438	89500	0.3607
0.4462	90000	0.3553
0.4487	90500	0.3637
0.4512	91000	0.388
0.4537	91500	0.348
0.4562	92000	0.3678
0.4586	92500	0.3961
0.4611	93000	0.3309
0.4636	93500	0.3639
0.4661	94000	0.3393
0.4686	94500	0.3861
0.4710	95000	0.3484
0.4735	95500	0.3511
0.4760	96000	0.3445
0.4785	96500	0.3486
0.4809	97000	0.3262
0.4834	97500	0.3342
0.4859	98000	0.3845
0.4884	98500	0.3481
0.4909	99000	0.3275
0.4933	99500	0.3567
0.4958	100000	0.3656
0.4983	100500	0.3299
0.5008	101000	0.3396
0.5033	101500	0.3497
0.5057	102000	0.3484
0.5082	102500	0.3684
0.5107	103000	0.318
0.5132	103500	0.2966
0.5157	104000	0.3452
0.5181	104500	0.3365
0.5206	105000	0.3352
0.5231	105500	0.3854
0.5256	106000	0.3712
0.5280	106500	0.334
0.5305	107000	0.3381
0.5330	107500	0.3289
0.5355	108000	0.3332
0.5380	108500	0.3441
0.5404	109000	0.3701
0.5429	109500	0.3268
0.5454	110000	0.3072
0.5479	110500	0.3348
0.5504	111000	0.3501
0.5528	111500	0.3179
0.5553	112000	0.3276
0.5578	112500	0.3958
0.5603	113000	0.3317
0.5628	113500	0.3564
0.5652	114000	0.3042
0.5677	114500	0.3482
0.5702	115000	0.3383
0.5727	115500	0.3557
0.5752	116000	0.3195
0.5776	116500	0.3265
0.5801	117000	0.3174
0.5826	117500	0.3392
0.5851	118000	0.3279
0.5875	118500	0.3254
0.5900	119000	0.3501
0.5925	119500	0.336
0.5950	120000	0.3899
0.5975	120500	0.3614
0.5999	121000	0.3473
0.6024	121500	0.3275
0.6049	122000	0.3213
0.6074	122500	0.303
0.6099	123000	0.3258
0.6123	123500	0.3175
0.6148	124000	0.3418
0.6173	124500	0.3422
0.6198	125000	0.3212
0.6223	125500	0.3171
0.6247	126000	0.3428
0.6272	126500	0.3327
0.6297	127000	0.3126
0.6322	127500	0.3194
0.6346	128000	0.3341
0.6371	128500	0.3246
0.6396	129000	0.3154
0.6421	129500	0.3224
0.6446	130000	0.3422
0.6470	130500	0.2983
0.6495	131000	0.3257
0.6520	131500	0.301
0.6545	132000	0.3276
0.6570	132500	0.34
0.6594	133000	0.3348
0.6619	133500	0.3298
0.6644	134000	0.323
0.6669	134500	0.3099
0.6694	135000	0.3454
0.6718	135500	0.3088
0.6743	136000	0.3501
0.6768	136500	0.3238
0.6793	137000	0.3017
0.6818	137500	0.3071
0.6842	138000	0.3165
0.6867	138500	0.2963
0.6892	139000	0.3186
0.6917	139500	0.3292
0.6941	140000	0.3108
0.6966	140500	0.3156
0.6991	141000	0.3188
0.7016	141500	0.2935
0.7041	142000	0.319
0.7065	142500	0.3123
0.7090	143000	0.302
0.7115	143500	0.3254
0.7140	144000	0.3018
0.7165	144500	0.3272
0.7189	145000	0.3258
0.7214	145500	0.3557
0.7239	146000	0.2816
0.7264	146500	0.3372
0.7289	147000	0.3406
0.7313	147500	0.3564
0.7338	148000	0.3341
0.7363	148500	0.3068
0.7388	149000	0.3565
0.7413	149500	0.3161
0.7437	150000	0.3187
0.7462	150500	0.3356
0.7487	151000	0.3103
0.7512	151500	0.3316
0.7536	152000	0.2906
0.7561	152500	0.3262
0.7586	153000	0.3039
0.7611	153500	0.301
0.7636	154000	0.3108
0.7660	154500	0.2937
0.7685	155000	0.2802
0.7710	155500	0.2926
0.7735	156000	0.3112
0.7760	156500	0.309
0.7784	157000	0.3059
0.7809	157500	0.313
0.7834	158000	0.3024
0.7859	158500	0.3122
0.7884	159000	0.2937
0.7908	159500	0.3102
0.7933	160000	0.3206
0.7958	160500	0.2895
0.7983	161000	0.3207
0.8007	161500	0.3099
0.8032	162000	0.2979
0.8057	162500	0.3607
0.8082	163000	0.3325
0.8107	163500	0.3117
0.8131	164000	0.3027
0.8156	164500	0.3347
0.8181	165000	0.3034
0.8206	165500	0.2918
0.8231	166000	0.315
0.8255	166500	0.2943
0.8280	167000	0.3407
0.8305	167500	0.312
0.8330	168000	0.2758
0.8355	168500	0.3487
0.8379	169000	0.3216
0.8404	169500	0.3087
0.8429	170000	0.2963
0.8454	170500	0.2879
0.8479	171000	0.3588
0.8503	171500	0.3507
0.8528	172000	0.3208
0.8553	172500	0.3181
0.8578	173000	0.2946
0.8602	173500	0.2846
0.8627	174000	0.3069
0.8652	174500	0.3134
0.8677	175000	0.3164
0.8702	175500	0.3191
0.8726	176000	0.2892
0.8751	176500	0.3081
0.8776	177000	0.2622
0.8801	177500	0.298
0.8826	178000	0.337
0.8850	178500	0.2701
0.8875	179000	0.2966
0.8900	179500	0.2894
0.8925	180000	0.3133
0.8950	180500	0.3172
0.8974	181000	0.2937
0.8999	181500	0.2804
0.9024	182000	0.3296
0.9049	182500	0.2831
0.9074	183000	0.2719
0.9098	183500	0.3014
0.9123	184000	0.2939
0.9148	184500	0.2835
0.9173	185000	0.3625
0.9197	185500	0.3056
0.9222	186000	0.3241
0.9247	186500	0.2916
0.9272	187000	0.2913
0.9297	187500	0.2813
0.9321	188000	0.2967
0.9346	188500	0.3152
0.9371	189000	0.2752
0.9396	189500	0.2855
0.9421	190000	0.3114
0.9445	190500	0.3117
0.9470	191000	0.305
0.9495	191500	0.316
0.9520	192000	0.2817
0.9545	192500	0.2777
0.9569	193000	0.2823
0.9594	193500	0.3473
0.9619	194000	0.3045
0.9644	194500	0.2951
0.9668	195000	0.3043
0.9693	195500	0.2739
0.9718	196000	0.2671
0.9743	196500	0.2876
0.9768	197000	0.267
0.9792	197500	0.3052
0.9817	198000	0.2789
0.9842	198500	0.2794
0.9867	199000	0.2907
0.9892	199500	0.2758
0.9916	200000	0.3191
0.9941	200500	0.2741
0.9966	201000	0.269
0.9991	201500	0.2939
1.0016	202000	0.2716
1.0040	202500	0.3019
1.0065	203000	0.3044
1.0090	203500	0.2788
1.0115	204000	0.2759
1.0140	204500	0.2746
1.0164	205000	0.2908
1.0189	205500	0.27
1.0214	206000	0.2686
1.0239	206500	0.2816
1.0263	207000	0.2916
1.0288	207500	0.2948
1.0313	208000	0.2814
1.0338	208500	0.2454
1.0363	209000	0.2638
1.0387	209500	0.2887
1.0412	210000	0.3043
1.0437	210500	0.2737
1.0462	211000	0.2693
1.0487	211500	0.2825
1.0511	212000	0.284
1.0536	212500	0.2693
1.0561	213000	0.2721
1.0586	213500	0.2677
1.0611	214000	0.267
1.0635	214500	0.2752
1.0660	215000	0.3046
1.0685	215500	0.2788
1.0710	216000	0.2612
1.0735	216500	0.2984
1.0759	217000	0.2838
1.0784	217500	0.2752
1.0809	218000	0.2592
1.0834	218500	0.2728
1.0858	219000	0.2643
1.0883	219500	0.2636
1.0908	220000	0.2581
1.0933	220500	0.2652
1.0958	221000	0.2637
1.0982	221500	0.2734
1.1007	222000	0.2703
1.1032	222500	0.2537
1.1057	223000	0.2765
1.1082	223500	0.2744
1.1106	224000	0.2525
1.1131	224500	0.2798
1.1156	225000	0.2749
1.1181	225500	0.2886
1.1206	226000	0.2889
1.1230	226500	0.2756
1.1255	227000	0.2694
1.1280	227500	0.2712
1.1305	228000	0.2701
1.1329	228500	0.2433
1.1354	229000	0.3027
1.1379	229500	0.2572
1.1404	230000	0.2682
1.1429	230500	0.2794
1.1453	231000	0.2521
1.1478	231500	0.271
1.1503	232000	0.2418
1.1528	232500	0.2426
1.1553	233000	0.2404
1.1577	233500	0.2991
1.1602	234000	0.2571
1.1627	234500	0.2737
1.1652	235000	0.2513
1.1677	235500	0.2901
1.1701	236000	0.2489
1.1726	236500	0.2548
1.1751	237000	0.2895
1.1776	237500	0.2195
1.1801	238000	0.2362
1.1825	238500	0.2522
1.1850	239000	0.2532
1.1875	239500	0.2468
1.1900	240000	0.2506
1.1924	240500	0.2422
1.1949	241000	0.2325
1.1974	241500	0.2487
1.1999	242000	0.2315
1.2024	242500	0.2195
1.2048	243000	0.234
1.2073	243500	0.2313
1.2098	244000	0.253
1.2123	244500	0.2621
1.2148	245000	0.2433
1.2172	245500	0.2455
1.2197	246000	0.2485
1.2222	246500	0.2192
1.2247	247000	0.2423
1.2272	247500	0.2565
1.2296	248000	0.227
1.2321	248500	0.2255
1.2346	249000	0.2428
1.2371	249500	0.2506
1.2396	250000	0.2525
1.2420	250500	0.2195
1.2445	251000	0.2585
1.2470	251500	0.23
1.2495	252000	0.2146
1.2519	252500	0.2564
1.2544	253000	0.2335
1.2569	253500	0.2149
1.2594	254000	0.2751
1.2619	254500	0.2714
1.2643	255000	0.2386
1.2668	255500	0.2123
1.2693	256000	0.1983
1.2718	256500	0.2266
1.2743	257000	0.2416
1.2767	257500	0.2202
1.2792	258000	0.2175
1.2817	258500	0.2696
1.2842	259000	0.2454
1.2867	259500	0.2413
1.2891	260000	0.2117
1.2916	260500	0.2249
1.2941	261000	0.2516
1.2966	261500	0.226
1.2990	262000	0.2175
1.3015	262500	0.2212
1.3040	263000	0.2286
1.3065	263500	0.2197
1.3090	264000	0.2446
1.3114	264500	0.2474
1.3139	265000	0.25
1.3164	265500	0.2342
1.3189	266000	0.2382
1.3214	266500	0.2228
1.3238	267000	0.2408
1.3263	267500	0.2122
1.3288	268000	0.2069
1.3313	268500	0.2278
1.3338	269000	0.23
1.3362	269500	0.2458
1.3387	270000	0.2375
1.3412	270500	0.2324
1.3437	271000	0.1933
1.3462	271500	0.2282
1.3486	272000	0.2308
1.3511	272500	0.2405
1.3536	273000	0.2097
1.3561	273500	0.2146
1.3585	274000	0.2025
1.3610	274500	0.2444
1.3635	275000	0.2063
1.3660	275500	0.2165
1.3685	276000	0.2347
1.3709	276500	0.2188
1.3734	277000	0.2005
1.3759	277500	0.2168
1.3784	278000	0.1846
1.3809	278500	0.2299
1.3833	279000	0.2108
1.3858	279500	0.2209
1.3883	280000	0.1987
1.3908	280500	0.2218
1.3933	281000	0.2078
1.3957	281500	0.2268
1.3982	282000	0.2208
1.4007	282500	0.2114
1.4032	283000	0.2111
1.4057	283500	0.2091
1.4081	284000	0.2301
1.4106	284500	0.231
1.4131	285000	0.1773
1.4156	285500	0.2026
1.4180	286000	0.2642
1.4205	286500	0.2203
1.4230	287000	0.1972
1.4255	287500	0.2095
1.4280	288000	0.1908
1.4304	288500	0.1959
1.4329	289000	0.1783
1.4354	289500	0.215
1.4379	290000	0.2032
1.4404	290500	0.195
1.4428	291000	0.2339
1.4453	291500	0.2118
1.4478	292000	0.2089
1.4503	292500	0.2201
1.4528	293000	0.1976
1.4552	293500	0.2068
1.4577	294000	0.2256
1.4602	294500	0.2233
1.4627	295000	0.2022
1.4651	295500	0.1961
1.4676	296000	0.2252
1.4701	296500	0.2185
1.4726	297000	0.1927
1.4751	297500	0.1983
1.4775	298000	0.1956
1.4800	298500	0.1851
1.4825	299000	0.2053
1.4850	299500	0.2106
1.4875	300000	0.2221
1.4899	300500	0.1912
1.4924	301000	0.2068
1.4949	301500	0.1929
1.4974	302000	0.21
1.4999	302500	0.2102
1.5023	303000	0.1769
1.5048	303500	0.2144
1.5073	304000	0.2213
1.5098	304500	0.1909
1.5123	305000	0.1661
1.5147	305500	0.1867
1.5172	306000	0.1859
1.5197	306500	0.1901
1.5222	307000	0.2428
1.5246	307500	0.1973
1.5271	308000	0.2198
1.5296	308500	0.1884
1.5321	309000	0.182
1.5346	309500	0.1879
1.5370	310000	0.1844
1.5395	310500	0.2378
1.5420	311000	0.18
1.5445	311500	0.1745
1.5470	312000	0.1723
1.5494	312500	0.2071
1.5519	313000	0.1799
1.5544	313500	0.175
1.5569	314000	0.2341
1.5594	314500	0.1852
1.5618	315000	0.202
1.5643	315500	0.1827
1.5668	316000	0.2029
1.5693	316500	0.1777
1.5718	317000	0.2193
1.5742	317500	0.1966
1.5767	318000	0.1811
1.5792	318500	0.1716
1.5817	319000	0.2036
1.5841	319500	0.1719
1.5866	320000	0.1992
1.5891	320500	0.1983
1.5916	321000	0.2162
1.5941	321500	0.2094
1.5965	322000	0.2195
1.5990	322500	0.1907
1.6015	323000	0.2261
1.6040	323500	0.1834
1.6065	324000	0.1719
1.6089	324500	0.1719
1.6114	325000	0.1938
1.6139	325500	0.1957
1.6164	326000	0.1951
1.6189	326500	0.1836
1.6213	327000	0.1802
1.6238	327500	0.1797
1.6263	328000	0.1898
1.6288	328500	0.2018
1.6312	329000	0.1729
1.6337	329500	0.2015
1.6362	330000	0.1822
1.6387	330500	0.1749
1.6412	331000	0.1829
1.6436	331500	0.2003
1.6461	332000	0.1714
1.6486	332500	0.1718
1.6511	333000	0.1697
1.6536	333500	0.1836
1.6560	334000	0.1953
1.6585	334500	0.1859
1.6610	335000	0.1862
1.6635	335500	0.1733
1.6660	336000	0.1961
1.6684	336500	0.1735
1.6709	337000	0.1917
1.6734	337500	0.2077
1.6759	338000	0.171
1.6784	338500	0.1741
1.6808	339000	0.1719
1.6833	339500	0.1672
1.6858	340000	0.173
1.6883	340500	0.1684
1.6907	341000	0.1848
1.6932	341500	0.19
1.6957	342000	0.1764
1.6982	342500	0.1631
1.7007	343000	0.1709
1.7031	343500	0.1941
1.7056	344000	0.1738
1.7081	344500	0.1678
1.7106	345000	0.1685
1.7131	345500	0.1794
1.7155	346000	0.1709
1.7180	346500	0.1807
1.7205	347000	0.2089
1.7230	347500	0.1677
1.7255	348000	0.1571
1.7279	348500	0.2283
1.7304	349000	0.183
1.7329	349500	0.2039
1.7354	350000	0.1896
1.7378	350500	0.1921
1.7403	351000	0.1983
1.7428	351500	0.1738
1.7453	352000	0.1871
1.7478	352500	0.1936
1.7502	353000	0.1726
1.7527	353500	0.1822
1.7552	354000	0.1687
1.7577	354500	0.1733
1.7602	355000	0.1721
1.7626	355500	0.1838
1.7651	356000	0.1503
1.7676	356500	0.166
1.7701	357000	0.1544
1.7726	357500	0.165
1.7750	358000	0.1785
1.7775	358500	0.1729
1.7800	359000	0.1735
1.7825	359500	0.1582
1.7850	360000	0.1932
1.7874	360500	0.1554
1.7899	361000	0.1804
1.7924	361500	0.1833
1.7949	362000	0.1557
1.7973	362500	0.1733
1.7998	363000	0.1937
1.8023	363500	0.1543
1.8048	364000	0.2162
1.8073	364500	0.1977
1.8097	365000	0.1783
1.8122	365500	0.1758
1.8147	366000	0.2004
1.8172	366500	0.1752
1.8197	367000	0.1815
1.8221	367500	0.1643
1.8246	368000	0.1749
1.8271	368500	0.1772
1.8296	369000	0.1959
1.8321	369500	0.1621
1.8345	370000	0.2145
1.8370	370500	0.1797
1.8395	371000	0.174
1.8420	371500	0.187
1.8445	372000	0.1556
1.8469	372500	0.2023
1.8494	373000	0.1968
1.8519	373500	0.2218
1.8544	374000	0.1656
1.8568	374500	0.1893
1.8593	375000	0.1589
1.8618	375500	0.1722
1.8643	376000	0.1609
1.8668	376500	0.1949
1.8692	377000	0.1801
1.8717	377500	0.1618
1.8742	378000	0.1683
1.8767	378500	0.1532
1.8792	379000	0.1563
1.8816	379500	0.1942
1.8841	380000	0.1634
1.8866	380500	0.1547
1.8891	381000	0.1615
1.8916	381500	0.1938
1.8940	382000	0.1685
1.8965	382500	0.1862
1.8990	383000	0.1514
1.9015	383500	0.1666
1.9039	384000	0.1861
1.9064	384500	0.1447
1.9089	385000	0.1844
1.9114	385500	0.1504
1.9139	386000	0.1772
1.9163	386500	0.2152
1.9188	387000	0.1768
1.9213	387500	0.208
1.9238	388000	0.1718
1.9263	388500	0.1614
1.9287	389000	0.1635
1.9312	389500	0.1671
1.9337	390000	0.1981
1.9362	390500	0.1622
1.9387	391000	0.1519
1.9411	391500	0.1795
1.9436	392000	0.1912
1.9461	392500	0.1726
1.9486	393000	0.1878
1.9511	393500	0.1642
1.9535	394000	0.1626
1.9560	394500	0.1614
1.9585	395000	0.2133
1.9610	395500	0.1761
1.9634	396000	0.1756
1.9659	396500	0.1823
1.9684	397000	0.1555
1.9709	397500	0.1556
1.9734	398000	0.1652
1.9758	398500	0.1525
1.9783	399000	0.1869
1.9808	399500	0.1486
1.9833	400000	0.1702
1.9858	400500	0.1525
1.9882	401000	0.167
1.9907	401500	0.1929
1.9932	402000	0.1478
1.9957	402500	0.182
1.9982	403000	0.1598

Framework Versions

• Python: 3.11.4
• Sentence Transformers: 3.3.1
• Transformers: 4.48.0.dev0
• PyTorch: 2.4.0+cu121
• Accelerate: 1.0.1
• Datasets: 2.20.0
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

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

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

AnglELoss

@misc{li2023angleoptimized,
    title={AnglE-optimized Text Embeddings},
    author={Xianming Li and Jing Li},
    year={2023},
    eprint={2309.12871},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}