last-checkpoint/README.md

metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:156483
  - loss:AdaptiveLayerLoss
  - loss:CoSENTLoss
  - loss:GISTEmbedLoss
  - loss:OnlineContrastiveLoss
  - loss:MultipleNegativesSymmetricRankingLoss
base_model: microsoft/deberta-v3-small
datasets:
  - sentence-transformers/all-nli
  - sentence-transformers/stsb
  - tals/vitaminc
  - nyu-mll/glue
  - allenai/scitail
  - sentence-transformers/xsum
  - sentence-transformers/sentence-compression
  - allenai/sciq
  - allenai/qasc
  - allenai/openbookqa
  - sentence-transformers/msmarco-msmarco-distilbert-base-v3
  - sentence-transformers/natural-questions
  - sentence-transformers/trivia-qa
  - sentence-transformers/quora-duplicates
  - sentence-transformers/gooaq
widget:
  - source_sentence: Centrosome-independent mitotic spindle formation in  vertebrates.
    sentences:
      - Birds pair up with the same bird in mating season.
      - We use voltage to keep track of electric potential energy.
      - A mitotic spindle forms from the centrosomes.
  - source_sentence: >-
      Three women in festive dresses are dancing in a large city street while a
      large crowd is behind them holding up a banner.
    sentences:
      - Three women dance in front of a large crowd
      - A person is taking a little girl with a toy from an Airman.
      - A man is sitting.
  - source_sentence: A young child is washing his hands with soap in the kitchen.
    sentences:
      - A surfer catches a wave.
      - Male in brown leather jacket and black slacks, looking down at his phone
      - The child uses soap to wash his hands.
  - source_sentence: A group of children enjoy their time on the beach.
    sentences:
      - People watch another person do a trick.
      - Children are at the beach.
      - A person is kicking.
  - source_sentence: Are juiveniles capable of reproduction?
    sentences:
      - >-
        In at least some species, juveniles are capable of reproduction before
        reaching the adult size and shape.
      - >-
        The Alpine Rhine begins in the most western part of the Swiss canton of
        Graubünden, and later forms the border between Switzerland to the West
        and Liechtenstein and later Austria to the East.
      - >-
        Private school numbers have been in decline since the mid-1970s as a
        result of many private schools opting to become state-integrated
        schools, mostly due of financial difficulties stemming from changes in
        student numbers and/or the economy.
pipeline_tag: sentence-similarity

SentenceTransformer based on microsoft/deberta-v3-small

This is a sentence-transformers model finetuned from microsoft/deberta-v3-small on the nli-pairs, sts-label, vitaminc-pairs, qnli-contrastive, scitail-pairs-qa, scitail-pairs-pos, xsum-pairs, compression-pairs, sciq_pairs, qasc_pairs, openbookqa_pairs, msmarco_pairs, nq_pairs, trivia_pairs, quora_pairs and gooaq_pairs datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: microsoft/deberta-v3-small
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity
• Training Datasets:
  • nli-pairs
  • sts-label
  • vitaminc-pairs
  • qnli-contrastive
  • scitail-pairs-qa
  • scitail-pairs-pos
  • xsum-pairs
  • compression-pairs
  • sciq_pairs
  • qasc_pairs
  • openbookqa_pairs
  • msmarco_pairs
  • nq_pairs
  • trivia_pairs
  • quora_pairs
  • gooaq_pairs
• Language: en

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("bobox/DeBERTaV3-TR-AllSoft-LT-n")
# Run inference
sentences = [
    'Are juiveniles capable of reproduction?',
    'In at least some species, juveniles are capable of reproduction before reaching the adult size and shape.',
    'Private school numbers have been in decline since the mid-1970s as a result of many private schools opting to become state-integrated schools, mostly due of financial difficulties stemming from changes in student numbers and/or the economy.',
]
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

nli-pairs

• Dataset: nli-pairs at d482672
• Size: 12,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 16.62 tokens max: 62 tokens	min: 4 tokens mean: 9.46 tokens max: 29 tokens

• Samples:

  sentence1	sentence2
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.
  Children smiling and waving at camera	There are children present
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

sts-label

• Dataset: sts-label at ab7a5ac
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 6 tokens mean: 9.81 tokens max: 27 tokens	min: 5 tokens mean: 9.74 tokens max: 25 tokens	min: 0.0 mean: 0.54 max: 1.0

• Samples:

  sentence1	sentence2	score
  A plane is taking off.	An air plane is taking off.	1.0
  A man is playing a large flute.	A man is playing a flute.	0.76
  A man is spreading shreded cheese on a pizza.	A man is spreading shredded cheese on an uncooked pizza.	0.76

• Loss: CoSENTLoss with these parameters:

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

vitaminc-pairs

• Dataset: vitaminc-pairs at be6febb
• Size: 15,594 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	int	string	string
  details	1: 100.00%	min: 7 tokens mean: 16.49 tokens max: 62 tokens	min: 7 tokens mean: 37.48 tokens max: 124 tokens

• Samples:

  label	sentence1	sentence2
  1	August Burns Red is a Christian band .	August Burns Red is a Christian band .
  1	The 2018 UEFA Super Cup will be played at the A . Le Coq Arena after 14 August , 2018 .	It will be played at the A . Le Coq Arena in Tallinn , Estonia , on 15 August 2018 , and it will be the first European club final held in Estonia.
  1	Father of the Bride album was preceded by two double singles .	It will be released on May 3 , 2019 by Columbia Records , and was preceded by two double singles : '' Harmony Hall '' '' / '' 2021 '' '' and '' Sunflower '' '' / `` '' Big Blue '' '' . ''

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

qnli-contrastive

• Dataset: qnli-contrastive at bcdcba7
• Size: 8,000 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: 13.98 tokens max: 40 tokens	min: 8 tokens mean: 35.16 tokens max: 201 tokens	0: 100.00%

• Samples:

  sentence1	sentence2	label
  Who was awarded first prize in the all-Arab oud contest in Egypt in 2003?	Israeli Arab musicians have achieved fame beyond Israel's borders: Elias and Murkus frequently play to audiences in Europe and America, and oud player Darwish Darwish (Prof. Elias's student) was awarded first prize in the all-Arab oud contest in Egypt in 2003.	0
  What are the three principles every plan should consider?	According to Vitruvius, a good building should satisfy the three principles of firmitas, utilitas, venustas, commonly known by the original translation – firmness, commodity and delight.	0
  More importantly than their language aspect how do the Seto and Võro dialects set themselves apart from each other?	These are sometimes considered either variants of a South Estonian language, or separate languages altogether.	0

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "OnlineContrastiveLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

scitail-pairs-qa

• Dataset: scitail-pairs-qa at 0cc4353
• Size: 14,987 training samples
• Columns: sentence2 and sentence1
• Approximate statistics based on the first 1000 samples:

  	sentence2	sentence1
  type	string	string
  details	min: 7 tokens mean: 16.03 tokens max: 41 tokens	min: 6 tokens mean: 14.98 tokens max: 31 tokens

• Samples:

  sentence2	sentence1
  We call the major artery carrying recently oxygenated blood away from the heart the aorta.	What do we call the major artery carrying recently oxygenated blood away from the heart?
  The understory of the rainforest commonly has ferns and other ground plants.	What part of the rainforest commonly has ferns and other ground plants?
  Dimensional analysis is used to carry out metric unit conversions.	What is used to carry out metric unit conversions?

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

scitail-pairs-pos

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

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 23.28 tokens max: 62 tokens	min: 7 tokens mean: 15.71 tokens max: 37 tokens

• Samples:

  sentence1	sentence2
  Composition Of Blood Blood consists of red and white cells, blood platelets and watery plasma (serum).	Blood is made up of red blood cells, white blood cells, platelets, and plasma.
  The diversity among organisms has arisen through mutations , which are changes in the structure of DNA molecules.	Mutations are changes to an organism’s dna and are an important driver of diversity in populations.
  As America's most abundant energy source, coal is currently used to generate nearly 60 percent of our electricity.	Coal is the source of most electricity.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

xsum-pairs

• Dataset: xsum-pairs at 788ddaf
• Size: 2,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 2 tokens mean: 352.07 tokens max: 512 tokens	min: 6 tokens mean: 27.26 tokens max: 70 tokens

• Samples:

  sentence1	sentence2
  Kate and Pete Shippey campaigned for all grounds to have them because their eldest son struggled to watch matches at Sunderland's Stadium of Light. The club was the first to open a room, with a view of the pitch, last year. Mr Shippey said it was "tremendous" Middlesbrough Football Club had also now followed suit. "I'm hoping over the coming years that many fans, kids with the challenges, and their parents and carers, will come and enjoy the game, open a door that previously was shut to them," he said. The space at Middlesbrough has no view of the pitch but will live stream matches on a big screen. There are therapeutic lights, autism-appropriate toys and a quiet feed of crowd noise. The Shippeys have been involved in similar "sensory sanctuaries" at Watford, Airdrie and Rangers football clubs. Mrs Shippey said a football match was a "very unpredictable environment". "The over-stimulation, the speakers are noisy, people around you are noisy, they might be shouting out to a friend before the match starts and then obviously, when the game kicks off, the roar of the crowds, people shouting at players," she said. Her son "can't handle it, it's just far too much", she said. Middlesbrough FC's room opens on Sunday for its match against Manchester United.	A couple with three autistic sons have persuaded a fifth football club to open a sensory room for fans with the condition.
  The animated programmes ask youngsters to choose between two options at several points in their plots. The firm says the nature of its online streaming platform has allowed it to experiment with "branching narrative" tech in a way that would not be possible for traditional broadcasters. But it acknowledges that such shows are more costly to make than normal. "It was actually a little bit more than twice as much animation as a typical episode," explained Doug Langdale, executive producer of the Puss in Book series, which was made in conjunction with Dreamworks Studios. "It was about 50 minutes [of footage] where it would normally be 22. Especially with computer animation, that's tremendously more expensive. "It's not easy or cheap. But it's the next thing, and we've got to try it." The programmes can be watched and controlled via smart TVs, games consoles and iOS devices - but cannot be downloaded and viewed offline. In addition to the special episode of Puss in Book - subtitled Trapped in an Epic Tale - Netflix is making an interactive episode of the stop-motion series Buddy Thunderstruck available. The former has two possible endings and the latter, four, but in both cases there are several ways that viewers can steer the stories to their conclusions. It has taken two years to bring the shows to screen, with part of the challenge being trying to ensure their plots remain logical and compelling whatever choices are made. A third child's show, based on the superhero Stretch Armstrong, is planned for 2018. But at present Netflix has no plans for adult-themed choice-based shows, nor has it committed itself to making further examples for children. "The main priority right now is starting to learn how our members are going to engage with this [and] learning how we can tell these stories," Carla Fisher, Netflix's director of product innovation, told the BBC. "Then we will go from there." Netflix is far from being the first to develop interactive programming. Beyond the many video games that have adopted the format, there have been: However, one media analyst said scripted entertainment risked being made "gimmicky" by being forced into an interactive format. "When it comes to linear entertainment there is an attraction to being presented with a fixed story, and having that crafted narrative presented to you by the director and writers," explained Tom Harrington of Enders Analysis. "I doubt Netflix is going to be filled with these kind of interactive shows in 10 years. "But it does know the value of great press, and it will get lots of publicity out of this."	Netflix is launching two interactive children's TV shows that let audiences determine the on-screen action.
  Media playback is unsupported on your device 26 January 2015 Last updated at 15:05 GMT The number of paramedics leaving the profession in London has almost trebled in the last three years, and Jason Killens of London Ambulance Service says he cannot employ paramedics quickly enough from the UK's universities. There will be another recruitment drive in Australia in September. Sarah Harris meets the recruits marking their national day in their new home.	It is the first day of work for some of the 175 paramedics recruited in Australia to join the London Ambulance Service.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

compression-pairs

• Dataset: compression-pairs at 605bc91
• Size: 8,000 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 10 tokens mean: 31.89 tokens max: 125 tokens	min: 5 tokens mean: 10.21 tokens max: 28 tokens

• Samples:

  sentence1	sentence2
  The USHL completed an expansion draft on Monday as 10 players who were on the rosters of USHL teams during the 2009-10 season were selected by the League's two newest entries, the Muskegon Lumberjacks and Dubuque Fighting Saints.	USHL completes expansion draft
  Major League Baseball Commissioner Bud Selig will be speaking at St. Norbert College next month.	Bud Selig to speak at St. Norbert College
  It's fresh cherry time in Michigan and the best time to enjoy this delicious and nutritious fruit.	It's cherry time

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "MultipleNegativesSymmetricRankingLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

sciq_pairs

• Dataset: sciq_pairs at 2c94ad3
• Size: 11,679 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 7 tokens mean: 17.26 tokens max: 60 tokens	min: 2 tokens mean: 84.37 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  What type of organism is commonly used in preparation of foods such as cheese and yogurt?	Mesophiles grow best in moderate temperature, typically between 25°C and 40°C (77°F and 104°F). Mesophiles are often found living in or on the bodies of humans or other animals. The optimal growth temperature of many pathogenic mesophiles is 37°C (98°F), the normal human body temperature. Mesophilic organisms have important uses in food preparation, including cheese, yogurt, beer and wine.
  What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?	Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to southwest or the reverse in the Northern Hemisphere. The winds blow northwest to southeast or the reverse in the southern hemisphere.
  Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always what?	Summary Changes of state are examples of phase changes, or phase transitions. All phase changes are accompanied by changes in the energy of a system. Changes from a more-ordered state to a less-ordered state (such as a liquid to a gas) areendothermic. Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always exothermic. The conversion of a solid to a liquid is called fusion (or melting). The energy required to melt 1 mol of a substance is its enthalpy of fusion (ΔHfus). The energy change required to vaporize 1 mol of a substance is the enthalpy of vaporization (ΔHvap). The direct conversion of a solid to a gas is sublimation. The amount of energy needed to sublime 1 mol of a substance is its enthalpy of sublimation (ΔHsub) and is the sum of the enthalpies of fusion and vaporization. Plots of the temperature of a substance versus heat added or versus heating time at a constant rate of heating are calledheating curves. Heating curves relate temperature changes to phase transitions. A superheated liquid, a liquid at a temperature and pressure at which it should be a gas, is not stable. A cooling curve is not exactly the reverse of the heating curve because many liquids do not freeze at the expected temperature. Instead, they form a supercooled liquid, a metastable liquid phase that exists below the normal melting point. Supercooled liquids usually crystallize on standing, or adding a seed crystal of the same or another substance can induce crystallization.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

qasc_pairs

• Dataset: qasc_pairs at a34ba20
• Size: 8,134 training samples
• Columns: id, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	id	sentence1	sentence2
  type	string	string	string
  details	min: 17 tokens mean: 21.35 tokens max: 27 tokens	min: 5 tokens mean: 11.47 tokens max: 25 tokens	min: 14 tokens mean: 35.55 tokens max: 66 tokens

• Samples:

  id	sentence1	sentence2
  3E7TUJ2EGCLQNOV1WEAJ2NN9ROPD9K	What type of water formation is formed by clouds?	beads of water are formed by water vapor condensing. Clouds are made of water vapor.. Beads of water can be formed by clouds.
  3LS2AMNW5FPNJK3C3PZLZCPX562OQO	Where do beads of water come from?	beads of water are formed by water vapor condensing. Condensation is the change of water vapor to a liquid.. Vapor turning into a liquid leaves behind beads of water
  3TMFV4NEP8DPIPCI8H9VUFHJG8V8W3	What forms beads of water?	beads of water are formed by water vapor condensing. An example of water vapor is steam.. Steam forms beads of water.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

openbookqa_pairs

• Dataset: openbookqa_pairs at 388097e
• Size: 2,740 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 3 tokens mean: 13.83 tokens max: 78 tokens	min: 4 tokens mean: 11.37 tokens max: 30 tokens

• Samples:

  sentence1	sentence2
  The sun is responsible for	the sun is the source of energy for physical cycles on Earth
  When food is reduced in the stomach	digestion is when stomach acid breaks down food
  Stars are	a star is made of gases

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

msmarco_pairs

• Dataset: msmarco_pairs at 28ff31e
• Size: 12,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 4 tokens mean: 8.61 tokens max: 27 tokens	min: 18 tokens mean: 75.09 tokens max: 206 tokens

• Samples:

  sentence1	sentence2
  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.
  what is the mechanism of action of fibrinolytic or thrombolytic drugs?	Baillière's Clinical Haematology. 6 Mechanism of action of the thrombolytic agents. 6 Mechanism of action of the thrombolytic agents JEFFREY I. WEITZ Fibrin formed during the haemostatic, inflammatory or tissue repair process serves a temporary role, and must be degraded to restore normal tissue function and structure.
  what is normal plat count	78 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).The average platelet count is 237,000 per mcL in men and 266,000 per mcL in women.8 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

nq_pairs

• Dataset: nq_pairs at f9e894e
• Size: 12,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 10 tokens mean: 11.77 tokens max: 21 tokens	min: 16 tokens mean: 131.57 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  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 Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.
  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: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

trivia_pairs

• Dataset: trivia_pairs at a7c36e3
• Size: 12,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 15.16 tokens max: 48 tokens	min: 19 tokens mean: 456.87 tokens max: 512 tokens

• Samples:

  sentence1	sentence2
  Which American-born Sinclair won the Nobel Prize for Literature in 1930?	The Nobel Prize in Literature 1930 The Nobel Prize in Literature 1930 Sinclair Lewis The Nobel Prize in Literature 1930 Sinclair Lewis Prize share: 1/1 The Nobel Prize in Literature 1930 was awarded to Sinclair Lewis "for his vigorous and graphic art of description and his ability to create, with wit and humour, new types of characters". Photos: Copyright © The Nobel Foundation Share this: To cite this page MLA style: "The Nobel Prize in Literature 1930". Nobelprize.org. Nobel Media AB 2014. Web. 18 Jan 2017. http://www.nobelprize.org/nobel_prizes/literature/laureates/1930/
  Where in England was Dame Judi Dench born?	Judi Dench - IMDb IMDb Actress
  In which decade did Billboard magazine first publish and American hit chart?	The US Billboard song chart The US Billboard song chart Search this site with Google Song chart US Billboard The Billboard magazine has published various music charts starting (with sheet music) in 1894, the first "Music Hit Parade" was published in 1936 , the first "Music Popularity Chart" was calculated in 1940 . These charts became less irregular until the weekly "Hot 100" was started in 1958 . The current chart combines sales, airplay and downloads. A music collector that calls himself Bullfrog has been consolidating the complete chart from 1894 to the present day. he has published this information in a comprehenive spreadsheet (which can be obtained at bullfrogspond.com/ ). The Bullfrog data assigns each song a unique identifier, something like "1968_076" (which just happens to be the Bee Gees song "I've Gotta Get A Message To You"). This "Whitburn Number" is provided to match with the books of Joel Whitburn and consists of the year and a ranking within the year. A song that first entered the charts in December and has a long run is listed the following year. This numbering scheme means that songs which are still in the charts cannot be assigned a final id, because their ranking might change. So the definitive listing for a year cannot be final until about April. In our listing we only use songs with finalised IDs, this means that every year we have to wait until last year's entries are finalised before using them. (Source bullfrogspond.com/ , the original version used here was 20090808 with extra data from: the 2009 data from 20091219 the 2010 data from 20110305 the 2011 data from 20120929 the 2012 data from 20130330 the 2013 data from 20150328 The 20150328 data was the last one produced before the Billboard company forced the data to be withdrawn. As far as we know there are no more recent data sets available. This pattern of obtaining the data for a particular year in the middle of the following one comes from the way that the Bullfrog project generates the identifier for a song (what they call the "Prefix" in the spreadsheet). Recent entries are identified with keys like "2015-008" while older ones have keys like "2013_177". In the second case the underscore is significant, it indicates that this was the 177th biggest song released in 2013. Now, of course, during the year no one knows where a particular song will rank, so the underscore names can't be assigned until every song from a particular year has dropped out of the charts, so recent records are temporarily assigned a name with a dash. In about May of the following year the rankings are calculated and the final identifiers are assigned. That is why we at the Turret can only grab this data retrospectively. Attributes The original spreadsheet has a number of attributes, we have limited our attention to just a few of them: 134 9 The songs with the most entries on the chart were White Christmas (with 33 versions and a total of 110 weeks) and Stardust (with 19 and a total of 106 weeks). position The peak position that songs reached in the charts should show an smooth curve from number one down to the lowest position. This chart has more songs in the lower peak positions than one would expect. Before 1991 the profile of peak positions was exactly as you would expect, that year Billboard introduced the concept of "Recurrent" tracks, that is they removed any track from the chart which had spent more than twenty weeks in the chart and had fallen to the lower positions. weeks The effect of the "Recurrent" process, by which tracks are removed if they have spent at least twenty weeks in the chart and have fallen to the lower reaches, can clearly be seen in the strange spike in this attribute. This "adjustment" was intended to promote newer songs and ensure the chart does not become "stale". In fact since it was introduced in 1991 the length of long chart runs has increased, this might reflect the more conscious efforts of record companies to "game" the charts by controlling release times and promotions, or it coul

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

quora_pairs

• Dataset: quora_pairs at 451a485
• Size: 8,000 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 6 tokens mean: 13.53 tokens max: 42 tokens	min: 6 tokens mean: 13.68 tokens max: 43 tokens

• Samples:

  sentence1	sentence2
  Astrology: I am a Capricorn Sun Cap moon and cap rising...what does that say about me?	I'm a triple Capricorn (Sun, Moon and ascendant in Capricorn) What does this say about me?
  How can I be a good geologist?	What should I do to be a great geologist?
  How do I read and find my YouTube comments?	How can I see all my Youtube comments?

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

gooaq_pairs

• Dataset: gooaq_pairs at b089f72
• Size: 12,500 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 8 tokens mean: 11.6 tokens max: 21 tokens	min: 13 tokens mean: 57.74 tokens max: 127 tokens

• Samples:

  sentence1	sentence2
  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: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

Evaluation Datasets

nli-pairs

• Dataset: nli-pairs at d482672
• Size: 1,500 evaluation samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 5 tokens mean: 17.64 tokens max: 63 tokens	min: 4 tokens mean: 9.67 tokens max: 29 tokens

• Samples:

  anchor	positive
  Two women are embracing while holding to go packages.	Two woman are holding packages.
  Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.	Two kids in numbered jerseys wash their hands.
  A man selling donuts to a customer during a world exhibition event held in the city of Angeles	A man selling donuts to a customer.

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

scitail-pairs-pos

• Dataset: scitail-pairs-pos at 0cc4353
• Size: 1,304 evaluation 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: 22.52 tokens max: 67 tokens	min: 8 tokens mean: 15.34 tokens max: 36 tokens	0: ~47.50% 1: ~52.50%

• Samples:

  sentence1	sentence2	label
  An introduction to atoms and elements, compounds, atomic structure and bonding, the molecule and chemical reactions.	Replace another in a molecule happens to atoms during a substitution reaction.	0
  Wavelength The distance between two consecutive points on a sinusoidal wave that are in phase;	Wavelength is the distance between two corresponding points of adjacent waves called.	1
  humans normally have 23 pairs of chromosomes.	Humans typically have 23 pairs pairs of chromosomes.	1

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "GISTEmbedLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

qnli-contrastive

• Dataset: qnli-contrastive 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	int
  details	min: 6 tokens mean: 14.13 tokens max: 36 tokens	min: 4 tokens mean: 36.58 tokens max: 225 tokens	0: 100.00%

• Samples:

  sentence1	sentence2	label
  What came into force after the new constitution was herald?	As of that day, the new constitution heralding the Second Republic came into force.	0
  What is the first major city in the stream of the Rhine?	The most important tributaries in this area are the Ill below of Strasbourg, the Neckar in Mannheim and the Main across from Mainz.	0
  What is the minimum required if you want to teach in Canada?	In most provinces a second Bachelor's Degree such as a Bachelor of Education is required to become a qualified teacher.	0

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "OnlineContrastiveLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 1,
      "prior_layers_weight": 0.5,
      "kl_div_weight": 1.25,
      "kl_temperature": 0.5
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 28
• per_device_eval_batch_size: 24
• learning_rate: 2e-05
• weight_decay: 7.5e-07
• num_train_epochs: 5
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_kwargs: {'num_cycles': 5}
• warmup_ratio: 0.2
• save_safetensors: False
• fp16: True
• push_to_hub: True
• hub_model_id: bobox/DeBERTaV3-TR-AllSoft-LT-n
• hub_strategy: checkpoint
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 28
• per_device_eval_batch_size: 24
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 2e-05
• weight_decay: 7.5e-07
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 5
• max_steps: -1
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_kwargs: {'num_cycles': 5}
• warmup_ratio: 0.2
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: True
• resume_from_checkpoint: None
• hub_model_id: bobox/DeBERTaV3-TR-AllSoft-LT-n
• hub_strategy: checkpoint
• hub_private_repo: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	qnli-contrastive loss	nli-pairs loss	scitail-pairs-pos loss
0.0250	140	17.3783	-	-	-
0.0500	280	10.3883	-	-	-
0.0750	420	6.239	-	-	-
0.1001	560	5.6986	-	-	-
0.1251	700	5.4609	5.3307	5.2213	3.9345
0.1501	840	5.2036	-	-	-
0.1751	980	4.9986	-	-	-
0.2001	1120	4.4918	-	-	-
0.2251	1260	4.2202	-	-	-
0.2501	1400	4.0922	4.3783	4.1164	2.4736
0.2751	1540	3.3935	-	-	-
0.3002	1680	3.5528	-	-	-
0.3252	1820	3.6013	-	-	-
0.3502	1960	3.275	-	-	-
0.3752	2100	3.2832	3.4020	3.1333	1.8786
0.4002	2240	3.0276	-	-	-
0.4252	2380	2.8936	-	-	-
0.4502	2520	2.7427	-	-	-
0.4753	2660	3.0206	-	-	-
0.5003	2800	2.575	2.8864	2.6768	1.5112
0.5253	2940	2.5411	-	-	-
0.5503	3080	2.5173	-	-	-
0.5753	3220	2.5333	-	-	-
0.6003	3360	2.6302	-	-	-
0.6253	3500	2.5134	2.4320	2.3164	1.3295
0.6503	3640	2.4442	-	-	-
0.6754	3780	2.2516	-	-	-
0.7004	3920	2.3152	-	-	-
0.7254	4060	2.0466	-	-	-
0.7504	4200	2.2551	2.4112	2.0880	1.1470
0.7754	4340	2.1891	-	-	-
0.8004	4480	2.0993	-	-	-
0.8254	4620	1.7904	-	-	-
0.8505	4760	2.0401	-	-	-
0.8755	4900	1.8895	1.9137	1.8439	0.9787
0.9005	5040	2.0058	-	-	-
0.9255	5180	2.0126	-	-	-
0.9505	5320	2.067	-	-	-
0.9755	5460	2.1337	-	-	-
1.0005	5600	1.8408	1.8655	1.7102	0.9210
1.0255	5740	1.7539	-	-	-
1.0506	5880	1.9194	-	-	-
1.0756	6020	1.7071	-	-	-
1.1006	6160	1.7053	-	-	-
1.1256	6300	1.8023	1.5953	1.5203	0.7954
1.1506	6440	1.7448	-	-	-
1.1756	6580	1.7874	-	-	-
1.2006	6720	1.7441	-	-	-
1.2257	6860	1.4535	-	-	-
1.2507	7000	1.7103	1.7566	1.4382	0.7307
1.2757	7140	1.4028	-	-	-
1.3007	7280	1.5999	-	-	-
1.3257	7420	1.7167	-	-	-
1.3507	7560	1.4903	-	-	-
1.3757	7700	1.5666	1.5942	1.3535	0.6812
1.4008	7840	1.4289	-	-	-
1.4258	7980	1.4531	-	-	-
1.4508	8120	1.2831	-	-	-
1.4758	8260	1.5913	-	-	-
1.5008	8400	1.2771	1.6052	1.2932	0.6548
1.5258	8540	1.2718	-	-	-
1.5508	8680	1.374	-	-	-
1.5758	8820	1.4011	-	-	-
1.6009	8960	1.571	-	-	-
1.6259	9100	1.54	1.5300	1.2734	0.6386
1.6509	9240	1.3765	-	-	-
1.6759	9380	1.3131	-	-	-
1.7009	9520	1.3459	-	-	-
1.7259	9660	1.1947	-	-	-
1.7509	9800	1.4422	1.5141	1.2626	0.6337
1.7760	9940	1.3539	-	-	-
1.8010	10080	1.3033	-	-	-
1.8260	10220	1.1106	-	-	-
1.8510	10360	1.3733	-	-	-
1.8760	10500	1.2665	1.4497	1.2357	0.6096
1.9010	10640	1.351	-	-	-
1.9260	10780	1.3464	-	-	-
1.9510	10920	1.1087	-	-	-
1.9761	11060	1.1635	-	-	-
2.0011	11200	1.1354	1.4097	1.1946	0.6180
2.0261	11340	1.1174	-	-	-
2.0511	11480	1.3446	-	-	-
2.0761	11620	1.1409	-	-	-
2.1011	11760	1.1902	-	-	-
2.1261	11900	1.2951	1.2629	1.1403	0.5851
2.1512	12040	1.2077	-	-	-
2.1762	12180	1.2858	-	-	-
2.2012	12320	1.267	-	-	-
2.2262	12460	1.0026	-	-	-
2.2512	12600	1.2523	1.3819	1.1073	0.5534
2.2762	12740	1.0009	-	-	-
2.3012	12880	1.1822	-	-	-
2.3262	13020	1.3998	-	-	-
2.3513	13160	1.0833	-	-	-
2.3763	13300	1.1998	1.2879	1.0725	0.5350
2.4013	13440	1.0898	-	-	-
2.4263	13580	1.1658	-	-	-
2.4513	13720	1.0127	-	-	-
2.4763	13860	1.2826	-	-	-
2.5013	14000	1.0243	1.3113	1.0619	0.5269
2.5264	14140	1.0344	-	-	-
2.5514	14280	1.1904	-	-	-
2.5764	14420	1.2133	-	-	-
2.6014	14560	1.3826	-	-	-
2.6264	14700	1.3857	1.3533	1.0945	0.5431
2.6514	14840	1.2257	-	-	-
2.6764	14980	1.2372	-	-	-
2.7014	15120	1.1853	-	-	-
2.7265	15260	1.0465	-	-	-
2.7515	15400	1.3469	1.5210	1.0670	0.5464
2.7765	15540	1.1843	-	-	-
2.8015	15680	1.113	-	-	-
2.8265	15820	0.8078	-	-	-
2.8515	15960	1.0437	-	-	-
2.8765	16100	0.9093	1.1596	0.9908	0.4938
2.9016	16240	1.044	-	-	-
2.9266	16380	1.0227	-	-	-
2.9516	16520	0.8159	-	-	-
2.9766	16660	0.8426	-	-	-
3.0016	16800	0.7955	1.1895	0.9681	0.4912
3.0266	16940	0.856	-	-	-
3.0516	17080	1.0754	-	-	-
3.0766	17220	0.9151	-	-	-
3.1017	17360	1.0051	-	-	-
3.1267	17500	1.0075	1.0658	0.9583	0.4853
3.1517	17640	0.9909	-	-	-
3.1767	17780	1.029	-	-	-
3.2017	17920	1.0292	-	-	-
3.2267	18060	0.8334	-	-	-
3.2517	18200	1.0119	1.1172	0.9485	0.4674
3.2768	18340	0.8582	-	-	-
3.3018	18480	1.0397	-	-	-
3.3268	18620	1.1988	-	-	-
3.3518	18760	0.9432	-	-	-
3.3768	18900	1.0573	1.0815	0.9437	0.4679
3.4018	19040	0.9829	-	-	-
3.4268	19180	1.0573	-	-	-
3.4518	19320	0.9449	-	-	-
3.4769	19460	1.2005	-	-	-
3.5019	19600	0.9171	1.2315	0.9503	0.4799
3.5269	19740	0.9425	-	-	-
3.5519	19880	1.1213	-	-	-
3.5769	20020	1.1128	-	-	-
3.6019	20160	1.331	-	-	-
3.6269	20300	1.0495	1.1413	0.9468	0.4434
3.6520	20440	0.9698	-	-	-
3.6770	20580	0.9148	-	-	-
3.7020	20720	0.9042	-	-	-
3.7270	20860	0.8232	-	-	-
3.7520	21000	1.0163	1.2883	0.9020	0.4574
3.7770	21140	0.9735	-	-	-
3.8020	21280	0.8371	-	-	-
3.8271	21420	0.6344	-	-	-
3.8521	21560	0.87	-	-	-
3.8771	21700	0.7404	1.0644	0.8661	0.4353
3.9021	21840	0.8486	-	-	-
3.9271	21980	0.8895	-	-	-
3.9521	22120	0.7476	-	-	-
3.9771	22260	0.6761	-	-	-

Framework Versions

• Python: 3.10.13
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2
• Accelerate: 0.30.1
• Datasets: 2.19.2
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

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

AdaptiveLayerLoss

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings}, 
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    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},
}

GISTEmbedLoss

@misc{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning}, 
    author={Aivin V. Solatorio},
    year={2024},
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}