benjamintli/modernbert-msmarco-cocondenser-negatives

SentenceTransformer based on answerdotai/ModernBERT-base

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-base. 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: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

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, 'architecture': 'OptimizedModule'})
  (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("modernbert-msmarco-cocondenser-negatives")
# Run inference
queries = [
    "can bleeding hemorrhoids cause anemia",
]
documents = [
    'While hemorrhoids can bleed, the amount of actual blood loss is typically slight, so anemia is very uncommon with bleeding hemorrhoids. If you are on blood thinners, such as Aspirin and warfarin, the bleeding might be more impressive, but again anemia would be unexpected.',
    "Dr. Mark Rasak Dr. Rasak. Stressor: Gastritis , menstruation , hemorrhoids etc can cause blood loss and chronic anemia . This is a stressor on the heart. The heart senses the blood loss with not only volume loss but blood carries oxygen too. So the heart try's to circulate the blood it does have as quickly as possible .This can ...Read more.",
    'The presentation of bleeding depends on the amount and location of hemorrhage. A person with an upper GI hemorrhage may also present with complications of anemia, including chest pain, syncope, fatigue and shortness of breath.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.8144, 0.6382, 0.5735]])

Evaluation

Metrics

Information Retrieval

• Dataset: eval
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8795
cosine_accuracy@3	0.9473
cosine_accuracy@5	0.9605
cosine_accuracy@10	0.9723
cosine_precision@1	0.8795
cosine_precision@3	0.3158
cosine_precision@5	0.1921
cosine_precision@10	0.0972
cosine_recall@1	0.8795
cosine_recall@3	0.9473
cosine_recall@5	0.9605
cosine_recall@10	0.9723
cosine_ndcg@10	0.9297
cosine_mrr@10	0.9156
cosine_map@100	0.9166

Training Details

Training Dataset

Unnamed Dataset

• Size: 316,420 training samples
• Columns: query, positive, negative_0, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, negative_7, negative_8, and negative_9
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative_0	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9
  type	string	string	string	string	string	string	string	string	string	string	string	string
  details	min: 4 tokens mean: 9.13 tokens max: 29 tokens	min: 16 tokens mean: 79.88 tokens max: 237 tokens	min: 20 tokens mean: 77.1 tokens max: 214 tokens	min: 16 tokens mean: 76.39 tokens max: 187 tokens	min: 20 tokens mean: 79.0 tokens max: 212 tokens	min: 16 tokens mean: 79.47 tokens max: 237 tokens	min: 21 tokens mean: 77.86 tokens max: 221 tokens	min: 24 tokens mean: 80.84 tokens max: 237 tokens	min: 18 tokens mean: 77.73 tokens max: 305 tokens	min: 14 tokens mean: 79.84 tokens max: 259 tokens	min: 22 tokens mean: 81.75 tokens max: 250 tokens	min: 22 tokens mean: 78.52 tokens max: 239 tokens

• Samples:

  query	positive	negative_0	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9
  is trypanosoma found outside the plasma?	Trypanosoma is found outside the blood cell, in the plasma and Plasmodium is found inside the blood cell.n mammals the mature red blood cells have no nuclei and therefore have no DNA (intact DNA that is) in them. However, the red blood cells of other animals do contain nuclei an … d DNA.	Trypanosoma is a zooflagellate protozoan parasite that is found in the blood of vertebrates. They are sometimes known as endoparasites, blood parasites, or extra cellular parasites.	Genus Leishmania are always intracellular, principally in cells of the reticuloendothelial system. b. Genus Trypanosoma contains members that may be found both in the circulating blood and intracellularly in cardiac muscle. African-blood; American-cardiac muscle.2.In all probability, the hemoflagellates were originally parasites of insects.. Trypomastigote and epimastigote (amastigote stage) forms may be found in human tissue & blood-the amastigote is a tissue stage; trypomastigote is blood stage; the epimastigote is the developmental stage in the bug. 5.	• This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids. Transmission: • Trypanosoma are transmitted primarily by the Glossina spp., tsetse fly, Stomoxys, tabanid and reduviid bugs, and by venereal contact.	Trypanosomes are also found in the Americas in the form of Trypanosoma cruzi, which causes American human trypanosomiasis, or Chagas' disease. This disease is found in humans in two forms: as an amastigote in the cells, and as a trymastigote in the blood. The vectors for Trypanosoma cruzi include members of the order Hemiptera, such as assassin flies, which ingest the amastigote or trymastigote and carry them to animals or humans.	Trypanosomiasis This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.	• This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.Transmission: • Trypanosoma are transmitted primarily by the Glossina spp., tsetse fly, Stomoxys, tabanid and reduviid bugs, and by venereal contact.ublished by kedar karki. Trypanosomiasis This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.	Trypanosoma: A genus of flagellate protozoans found in the blood and lymph of vertebrates and invertebrates, both hosts being required to complete the life cycle.	Published by kedar karki. Trypanosomiasis This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.	Trypanosomiasis This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.iseases caused by protozoa. Dr.Kedar Karki M.V.St.Preventive Veterinary Medicine Philippines. Trypanosomiasis. • This is a protozoan disease of animals and humans caused by parasites of the genus Trypanosoma, which are found in blood plasma, various body tissues and fluids.	Figure 1. Trypanosoma cruzi trypomastigote in blood smear. Morphology: T. cruzi is a single-celled organism that exists in three distinct forms, namely, the infectious trypomastigote found in the bloodstream, the intracellular amastigote found in tissues, and the reproductive epimastigote found in the reduviid insect.
  who played elizabeth swann	Here's What Young Elizabeth Swann From Pirates Of The Caribbean Looks Like Now. Pirates of the Caribbean: The Curse of the Black Pearl turns 13 this summer, which means it's been well over a decade since we first started shipping Elizabeth Swann (Keira Knightley) and Will Turner (Orlando Bloom).	Clifford has to be free-range — he's that big a a big red dog. But E.E. still shows no care or remorse for what he does. To nail the message home, Emily Elizabeth is played by Grey DeLisle, known for playing roles of characters that are just that.	Ten-year-old Elizabeth Swann and her father, then Captain Weatherby Swann, were en route from England to Port Royal in the Caribbean when their ship came upon a wrecked vessel—the victim of a pirate attack. The only survivor was a young boy, Will Turner.	Stephanie Weir appeared as the energetic 7-year-old Dot Goddard on MAD Tv (FOX) Aries Spears impersonated Bill Cosby on MADtv. (FOX) Alex Borstein portrayed as Miss Swan a rude elderly asian woman. (Randy Holmes/FOX.) Mo Collins was forever clueless as Lorraine Swanson on MADtv. (FOX)	The first season of The Crown premieres on Netflix on Nov. 4. Elizabeth is played by Claire Foy, who you may know as Anne Boleyn from the miniseries Wolf Hall. Queen Elizabeth's husband of 69 years, Prince Philip, is played by Matt Smith.	By Susanna Lazarus. Series three of Mr Selfridge sees two glamorous additions as real-life sisters Kara and Hannah Tointon join the cast as Rosalie and Violette, daughters of department store owner Harry Gordon Selfridge (played by Jeremy Piven).'ve walked up and down the aisle about 1,500 times.. Although, the actress – who played Dawn Swann for four years in EastEnders – is relieved one of her characters finally reached the altar. A couple of times I've almost made it down the aisle but never quite. I was always the bride but never the bride..	Remembering the best 'MADtv' sketches, from Stuart to Miss Swan. 1 Michael McDonald starred as Stuart on MADtv. 2 Stephanie Weir appeared as the energetic 7-year-old Dot Goddard on MAD Tv. 3 Aries Spears impersonated Bill Cosby on MADtv. 4 Alex Borstein portrayed as Miss Swan a rude elderly asian woman.	In the movie Freedom Writers, Hilary Swank's character lives with her husband Scott, played by actor Patrick Dempsey (Grey's Anatomy). In the film, as Erin Gruwell becomes more devoted to her teaching, her husband Scott starts to feel neglected.	Character Focus: MadTV's Miss Swan. Anyone who is a fan of MadTV or has even heard of the show has probably heard of the character Miss Bunny Swan: an Asian character that was played by Alex Borstein, a white actress. Miss Swan (pictured at right) was the embodiment of almost every stereotype of Asian-American women.	1 Hilary Swank won the Best Actress Oscar for her role as headstrong Maggie Fitzgerald, a working-class waitress who aspired to be a professional women's boxer-and then suffered a terminal illness, in Million Dollar Baby (2004).	elizabeth swann Elizabeth Turner she is beauty she is grace she will punch you in the face potc potc edit potc gif gif pirates of the caribbean pirate king theseabeours i havent made anything in sooo long so its not that great dead man's chest curse of the black pearl Keira Knightley dailypotc.
  causes of jelly like stool	GI eval: Pregnancy does not cause thing like jelly in the stool. If this is recurring problem for you consider seeing a gastroenterologist. They can test for intestinal worms and other digestive disorders that may cause string like jelly stools. ...Read more.	5 I have a clear jelly like substance in my stool. It will appear for a few days, then go away for 6 months or so, with cramping. Intermittent mucus: Mucus discharge occurs in up to 50% of patients with irritable bowel syndrome, with or without pain.	1 I have a clear jelly like substance in my stool. Dr. Charles Cattano Dr. Cattano. 4 doctors agreed: Intermittent mucus: Mucus discharge occurs in up to 50% of patients with irritable bowel syndrome, with or without pain.	Key points. 1 Most changes in stool are due to a change in diet. 2 Runny green or mustard-coloured stool is common in breast-fed babies. 3 Pale stool accompanied by yellowish skin and eyes or dark urine may indicate hepatitis. 4 Seek medical attention right away. 5 Red and jelly-like stool is considered an emergency.	However, being knowledgeable about your digestive process can help you identify health issues. Some common causes of a change in stool shape are: Diverticulosis causes pothole-like craters in the lining of the colon, as well as a narrowing of the diameter of the colon due to the wall thickening. The result is narrow, pellet-like stools that often fall apart in the bowl and can be difficult to expel.	Anxiety, however, is often the cause of jelly legs, especially severe anxiety. Take our free 7 minute anxiety test to score your anxiety severity and learn more about how to control your anxiety. Start the anxiety test here. When your legs feel like jelly, standing can feel unusual. It may be accompanied by dizziness or balance issues that are either related to the weakness in your legs, or the direct result of anxiety causing other symptoms and conditions.	We're sorry, an error occurred. 1 Mucus, a thick, jelly-like substance, is quite common in the body, including in the stool. If large amounts of mucus are found in your stool, you may have an underlying health condition.	What causes a baby or toddler to have bright blood in the stool (poop, poo) 1 An infant who is having bouts of screaming and drawing up the legs, maybe with vomiting as well, who then passes what looks like red currant jelly in the bowel motion may have intussusception and you need to see your doctor urgently - read more.	Some common causes of a change in stool shape are: 1 Diverticulosis causes pothole-like craters in the lining of the colon, as well as a narrowing of the diameter of the colon due to the wall thickening. 2 The result is narrow, pellet-like stools that often fall apart in the bowl and can be difficult to expel.	Anxiety, however, is often the cause of jelly legs, and is often a symptom experienced in combination with many other symptoms. To see how your anxiety compares to other people, and get recommendations for next steps, take my 7 minute anxiety test. When your legs feel like jelly, standing can feel unusual.	Weak legs can be a frightening feeling, and there are several health conditions that can cause your legs to become weak, such as low blood pressure. Anxiety, however, is often the cause of jelly legs, and is often a symptom experienced in combination with many other symptoms. To see how your anxiety compares to other people, and get recommendations for next steps, take my 7 minute anxiety test. When your legs feel like jelly, standing can feel unusual. It may be accompanied by dizziness or balance issues that are either related to the weakness in your legs, or the direct result of anxiety causing other symptoms and conditions.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64,
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 16,654 evaluation samples
• Columns: query, positive, negative_0, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, negative_7, negative_8, and negative_9
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative_0	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9
  type	string	string	string	string	string	string	string	string	string	string	string	string
  details	min: 4 tokens mean: 9.22 tokens max: 28 tokens	min: 19 tokens mean: 80.8 tokens max: 236 tokens	min: 14 tokens mean: 76.02 tokens max: 315 tokens	min: 22 tokens mean: 78.8 tokens max: 210 tokens	min: 20 tokens mean: 77.66 tokens max: 237 tokens	min: 21 tokens mean: 79.6 tokens max: 227 tokens	min: 17 tokens mean: 78.66 tokens max: 221 tokens	min: 20 tokens mean: 79.16 tokens max: 278 tokens	min: 17 tokens mean: 79.3 tokens max: 210 tokens	min: 22 tokens mean: 78.71 tokens max: 231 tokens	min: 21 tokens mean: 77.02 tokens max: 214 tokens	min: 19 tokens mean: 80.09 tokens max: 235 tokens

• Samples:

  query	positive	negative_0	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9
  what does rims acronym stand for in insurance	Looking for the definition of RIMS? Find out what is the full meaning of RIMS on Abbreviations.com! 'R&D Information Management System' is one option -- get in to view more @ The Web's largest and most authoritative acronyms and abbreviations resource.	(rɪm) n., v. rimmed, rim•ming. n. 1. the outer, often circular edge or border of something. 2. the outer circle of a wheel, attached to the hub by spokes. 3. a circular strip of metal forming the connection between an automobile wheel and tire. 4. a drive wheel or flywheel, as on a spinning mule.	The rim is the outer edge of a wheel, holding the tire. It makes up the outer circular design of the wheel on which the inside edge of the tire is mounted on vehicles such as automobiles. For example, on a bicycle wheel the rim is a large hoop attached to the outer ends of the spokes of the wheel that holds the tire and tube. The term rim is also used non-technically to refer to the entire wheel, or even to a tire. In the 1st millennium BC, an iron rim was introduced around the wooden wheels o	Risk and Insurance Acronyms A. AAA-American Academy of Actuaries; American Arbitration Association. AACI-American Association of Crops Insurers. AADC-American Association of Dental Consultants. AAI-Accredited Adviser in Insurance; Alliance of American Insurers. AAIM-American Academy of Insurance Medicine	Rim (wheel) The rim is the outer edge of a wheel, holding the tire. It makes up the outer circular design of the wheel on which the inside edge of the tire is mounted on vehicles such as automobiles. For example, on a bicycle wheel the rim is a large hoop attached to the outer ends of the spokes of the wheel that holds the tire and tube.	Definition of rim. 1a : brinkb : the outer often curved or circular edge or border of something. 2a : the outer part of a wheel joined to the hub usually by spokesb : a removable outer metal band on an automobile wheel to which the tire is attached.	A rim is an external flange that is machined, cast, molded, stamped or pressed around the bottom of a firearms cartridge. Thus, rimmed cartridges are sometimes called flanged cartridges.Almost all cartridges feature an extractor or headspacing rim, in spite of the fact that some cartridges are known as rimless cartridges.here are various types of firearms rims in use in modern ammunition. These types are rimmed, rimless, semi-rimmed, rebated rim, and belted. These categories describe the size of the rim in relation to the base of the case.	Definition of rim. 1 1a : brinkb : the outer often curved or circular edge or border of something. 2 2a : the outer part of a wheel joined to the hub usually by spokesb : a removable outer metal band on an automobile wheel to which the tire is attached. 3 3 : frame 4c( 1)	Reaction Injection Molding. RIM is a process where reactive liquid components-usually Thermoset polyurethane-are mixed inside a closed mold cavity under pressure. This process is widely used in the automotive industry to produce internal and external parts. Reinforced Reaction Injection Molding (R-RIM) is a close-molding process.	The insurance industry’s vocabulary is riddled with acronyms, abbreviations and 'catchy' names. A. roadmap is essential to effectively move about the insurance world. For example: Comp - free tickets to a Dolphins football game or a line of business in insurance, short for. workers’ compensation. BEEP - a high-pitched sound of a horn or Bureau Entry and Edit Package developed by ACCCT. Although entitled ‘Acronyms and Abbreviations’, this section also includes 'catchy' names. The acronyms and abbreviations in this section are not defined; however, their definitions can be found in the glossary	rim. n. 1. a. The upper or outer edge of an object, especially when curved or circular. See Synonyms at border. b. The upper edge of a steep slope; a cliff or brink: the rim of a canyon.2. a. The circular outer part of a wheel, furthest from the axle.he had made friends with the spring down in the hollow-- that wonderful deep, clear icy-cold spring; it was set about with smooth red sandstones and rimmed in by great palm-like clumps of water fern; and beyond it was a log bridge over the brook. Anne Of Green Gables by Montgomery, Lucy Maud View in context.
  actress who played loretta lynn	Now, three and a half years after the group’s epic Last Waltz farewell, Helm has won a whole new following playing the father of country queen Loretta Lynn in her movie bio, Coal Miner’s Daughter. Sissy Spacek, the brilliant actress in the title role, flatteringly found Levon “strong enough to be sensitive.” Loretta herself decided he didn’t need coaching, because “he looked so much like Daddy, I figured he just knew.” But don’t expect Helm, 39, to don a pair of Foster Grants, leave his modest home in Springdale, Ark. and head for Hollywood.	Loretta Swit played nurse Margaret Hotlips Houlihan on MASH. She was nominated for four Golden Globes for her role and won two Emmys. The 75-year-old actress starred in several made-for-TV movies after MASH ended, including the romantic comedy, 14 Going on 30 and The Best Christmas Pageant Ever..	Coal Miner's Daughter starring Sissy Spacek & Tommy Lee Jones is a terrific movie full of Loretta Lynn's music, but sung by Sissy! A very interesting story of Loretta's personal life & rise to country music stardom.	Actress Betty Lynn, who played Thelma Lou on 'The Andy Griffith Show', will celebrate her 90th birthday with friends and fans in Mount Airy, N.C. Andy Griffith and Don Knotts in a classic scene about an exploding goat. . A publicity photo from 1960 with Don Knotts and Andy Griffith.	Loretta Lynn (née Webb, April 14, 1932) is a an American country music singer-songwriter with multiple gold albums over a career of almost 60 years.	Sissy Spacek sings all the songs herself and does a great job as Loretta Lynn. If you like biographical movies, you need to see The Coal Miner's Daughter.. NOTE: That was my Amazon review from the year 2000 of this great film from the year I was born.	PG|2 hr 5 min. Plot Summary. Raised in rural Kentucky poverty and married at the age of 13, Loretta Lynn (Sissy Spacek) begins writing and singing her own country songs in her early 20s.	Lynn was born and raised in Butcher Hollow, Van Lear, Kentucky, a mining community near Paintsville. Her mother was of Scots-Irish and Cherokee ancestry. Loretta was the second of eight children. She was named after the film star Loretta Young. Ted Webb never got to see his daughter become famous, as he died in 1959 of coalworker's pneumoconiosis (commonly known as black lung or black lung disease) before Loretta's first single, I'm A Honky Tonk Girl, was released.	Actress Betty Lynn, who played Thelma Lou on 'The Andy Griffith Show', will celebrate her 90th birthday with friends and fans in Mount Airy, N.C. Mark Washburn The Charlotte Observer. Andy Griffith and Don Knotts in a classic scene about an exploding goat.	Loretta Lynn (nee Née; webb Born april, 14) 1932 is a multiple gold Album american country music-singer songwriter whose work spans nearly 60. years	From Wikipedia, the free encyclopedia. Oliver Vanetta Lynn, Jr. (August 27, 1926 – August 22, 1996), better known as Doolittle Lynn (also Doo and Mooney) was an American talent manager and country music figure, best known as the husband of country music legend Loretta Lynn.
  what is the coldest month in nebraska?	Graph of average and extreme temperature ranges by day for Omaha, NE. Temperature The warmest month in Offutt Air Force Base, Omaha, Nebraska is July with an average high temperature of 87.5°F. The hottest day on record was July 21 1974 when the temperature hit 109.0°F. During January the overnight temperature drops to an average of 14.5°F with the lowest temperature of -23.8°F being recorded on January 4 2010.	Average temperatures are fairly uniform across Nebraska, with hot summers and generally cold winters. Average annual precipitation decreases east to west from about 31.5 inches (800 mm) in the southeast corner of the state to about 13.8 inches (350 mm) in the Panhandle.	Omaha Weather, When to Go and Climate Information. (Omaha, Nebraska - NE, USA) Omaha is home to a moderate climate, which is best described as being continental and humid. Summers are warm, while winters are cold and frosty. The summer months, from June to September, feature typically hot, sunny weather. Temperatures are around 30°C / 86°F during July and August, with many fine days, although the weather can be changeable in Omaha at any time.	Over the course of the year, the temperature in Omaha typically varies from 16°F to 87°F and is rarely below -2°F or above 96°F. The hot season lasts for 119 days, from May 24 to September 20, with an average daily high temperature above 76°F. The hottest day of the year is July 20, with an average high of 87°F and low of 68°F. The cold season lasts for 94 days, from November 26 to February 28, with an average daily high temperature below 44°F. The coldest day of the year is January 13, with an average low of 16°F and high of 34°F.	Summers are warm, while winters are cold and frosty. The summer months, from June to September, feature typically hot, sunny weather. Temperatures are around 30°C / 86°F during July and August, with many fine days, although the weather can be changeable in Omaha at any time. Worth noting, tornados and heavy thunderstorms are known to occur during the summer months.	The best time to visit Kearney, Nebraska is in the spring and summer. Spring temperatures are cool with averages in the low 50's and highs in the mid 60's. Nights are cold with lows in the low 40's. Summer temperatures are mild with averages in the low 70's and highs in the low 80's.	CLIMATE OVERVIEW. Omaha, Nebraska, gets 31 inches of rain per year. The US average is 39. Snowfall is 30 inches. The average US city gets 26 inches of snow per year. The number of days with any measurable precipitation is 57. On average, there are 214 sunny days per year in Omaha, Nebraska. The July high is around 86 degrees. The January low is 14. Sperling's comfort index for Omaha is a 38 out of 100, where a higher score indicates a more comfortable year-around climate. The US average for the comfort index is 54.	I live in Nebraska and it's snowing in May. I want to move somewhere that has consistent 60's-80's without crappy weather. No sleeting in the spring, wretchedly cold winters and insanely hot summers.	On average, there are 216 sunny days per year in Gretna, Nebraska. The July high is around 86 degrees. The January low is 14. Sperling's comfort index for Gretna is a 35 out of 100, where a higher score indicates a more comfortable year-around climate. The US average for the comfort index is 54.	Offutt AFB, Nebraska, gets 32 inches of rain per year. The US average is 39. Snowfall is 25 inches. The average US city gets 26 inches of snow per year. The number of days with any measurable precipitation is 56. On average, there are 216 sunny days per year in Offutt AFB, Nebraska. The July high is around 86 degrees. The January low is 14. Sperling's comfort index for Offutt AFB is a 34 out of 100, where a higher score indicates a more comfortable year-around climate. The US average for the comfort index is 54.	The numbers here tell you how hot and cold the weather usually is in Omaha, Nebraska during each month of the year. The average high and low temperatures are listed below monthly and annually for the city, in both degrees Fahrenheit and Celsius. Maximums and minimums are only part of the temperature picture.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64,
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 1024
• num_train_epochs: 1
• learning_rate: 2e-05
• warmup_steps: 0.1
• bf16: True
• eval_strategy: epoch
• per_device_eval_batch_size: 1024
• push_to_hub: True
• hub_model_id: modernbert-msmarco-cocondenser-negatives
• load_best_model_at_end: True
• dataloader_num_workers: 4
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• per_device_train_batch_size: 1024
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: trackio
• eval_strategy: epoch
• per_device_eval_batch_size: 1024
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: True
• hub_private_repo: None
• hub_model_id: modernbert-msmarco-cocondenser-negatives
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: True
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: False
• dataloader_num_workers: 4
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	eval_cosine_ndcg@10
0.1613	50	6.0298	-	-
0.3226	100	2.1972	-	-
0.4839	150	1.7358	-	-
0.6452	200	1.5594	-	-
0.8065	250	1.4726	-	-
0.9677	300	1.4325	-	-
1.0	310	-	1.448	0.9297

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.3.0
• Transformers: 5.3.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.7.0
• Tokenizers: 0.22.2

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",
}

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}
}