metadata

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:100231
  - loss:DebiasedMultipleNegativesRankingLoss
base_model: answerdotai/ModernBERT-base
widget:
  - source_sentence: who led the army that defeated the aztecs
    sentences:
      - >-
        Spanish conquest of the Aztec Empire The Spanish conquest of the Aztec
        Empire, or the Spanish-Aztec War (1519-21)[3] was one of the most
        significant and complex events in world history. There are multiple
        sixteenth-century narratives of the events by Spanish conquerors, their
        indigenous allies, and the defeated Aztecs. It was not solely a contest
        between a small contingent of Spaniards defeating the Aztec Empire, but
        rather the creation of a coalition of Spanish invaders with tributaries
        to the Aztecs, and most especially the Aztecs' indigenous enemies and
        rivals. They combined forces to defeat the Mexica of Tenochtitlan over a
        two-year period. For the Spanish, the expedition to Mexico was part of a
        project of Spanish colonization of the New World after twenty-five years
        of permanent Spanish settlement and further exploration in the
        Caribbean. The Spanish made landfall in Mexico in 1517. A Spanish
        settler in Cuba, Hernán Cortés, led an expedition (entrada) to Mexico,
        landing in February 1519, following an earlier expedition led by Juan de
        Grijalva to Yucatán in 1517. Two years later Cortés and his retinue set
        sail, thus beginning the expedition of exploration and conquest.[4] The
        Spanish campaign against the Aztec Empire had its final victory on
        August 13, 1521, when a coalition army of Spanish forces and native
        Tlaxcalan warriors led by Cortés and Xicotencatl the Younger captured
        the emperor Cuauhtemoc and Tenochtitlan, the capital of the Aztec
        Empire. The fall of Tenochtitlan marks the beginning of Spanish rule in
        central Mexico, and they established their capital of Mexico City on the
        ruins of Tenochtitlan.
      - >-
        The Girl with All the Gifts Justineau awakens in the Rosalind Franklin.
        Melanie leads her to a group of intelligent hungries, to whom Justineau,
        wearing an environmental protection suit, starts teaching the alphabet.
      - >-
        Wendy Makkena In 1992 she had a supporting role in the movie Sister Act
        as the shy but talented singing nun Sister Mary Robert, a role she
        reprised in Sister Act 2: Back in the Habit the following year. She
        appeared in various other television roles until 1997, when she starred
        in Air Bud, followed by the independent film Finding North. She
        continued appearing on television shows such as The Job, Oliver Beene,
        and Listen Up![citation needed]
  - source_sentence: who went to the most nba finals in a row
    sentences:
      - >-
        List of NBA franchise post-season streaks The San Antonio Spurs hold the
        longest active consecutive playoff appearances with 21 appearances,
        starting in the 1998 NBA Playoffs (also the longest active playoff
        streak in any major North American sports league as of 2017). The Spurs
        have won five NBA championships during the streak. The Philadelphia
        76ers (formerly known as Syracuse Nationals) hold the all-time record
        for consecutive playoff appearances with 22 straight appearances between
        1950 and 1971. The 76ers won two NBA championships during their streak.
        The Boston Celtics hold the longest consecutive NBA Finals appearance
        streak with ten appearances between 1957 and 1966. During the streak,
        the Celtics won eight consecutive NBA championshipsâ€”also an NBA
        record.
      - >-
        Dear Dumb Diary Dear Dumb Diary is a series of children's novels by Jim
        Benton. Each book is written in the first person view of a middle school
        girl named Jamie Kelly. The series is published by Scholastic in English
        and Random House in Korean. Film rights to the series have been optioned
        by the Gotham Group.[2]
      - >-
        Voting rights in the United States Eligibility to vote in the United
        States is established both through the federal constitution and by state
        law. Several constitutional amendments (the 15th, 19th, and 26th
        specifically) require that voting rights cannot be abridged on account
        of race, color, previous condition of servitude, sex, or age for those
        above 18; the constitution as originally written did not establish any
        such rights during 1787â€“1870. In the absence of a specific federal law
        or constitutional provision, each state is given considerable discretion
        to establish qualifications for suffrage and candidacy within its own
        respective jurisdiction; in addition, states and lower level
        jurisdictions establish election systems, such as at-large or single
        member district elections for county councils or school boards.
  - source_sentence: who did the vocals on mcdonald's jingle i'm loving it
    sentences:
      - >-
        I'm Lovin' It (song) "I'm Lovin' It" is a song recorded by American
        singer-songwriter Justin Timberlake. It was written by Pusha T and
        produced by The Neptunes.
      - >-
        Vallabhbhai Patel As the first Home Minister and Deputy Prime Minister
        of India, Patel organised relief efforts for refugees fleeing from
        Punjab and Delhi and worked to restore peace across the nation. He led
        the task of forging a united India, successfully integrating into the
        newly independent nation those British colonial provinces that had been
        "allocated" to India. Besides those provinces that had been under direct
        British rule, approximately 565 self-governing princely states had been
        released from British suzerainty by the Indian Independence Act of 1947.
        Employing frank diplomacy with the expressed option to deploy military
        force, Patel persuaded almost every princely state to accede to India.
        His commitment to national integration in the newly independent country
        was total and uncompromising, earning him the sobriquet "Iron Man of
        India".[3] He is also affectionately remembered as the "Patron saint of
        India's civil servants" for having established the modern all-India
        services system. He is also called the Unifier of India.[4]
      - >-
        National debt of the United States As of July 31, 2018, debt held by the
        public was $15.6 trillion and intragovernmental holdings were $5.7
        trillion, for a total or "National Debt" of $21.3 trillion.[5] Debt held
        by the public was approximately 77% of GDP in 2017, ranked 43rd highest
        out of 207 countries.[6] The Congressional Budget Office forecast in
        April 2018 that the ratio will rise to nearly 100% by 2028, perhaps
        higher if current policies are extended beyond their scheduled
        expiration date.[7] As of December 2017, $6.3 trillion or approximately
        45% of the debt held by the public was owned by foreign investors, the
        largest being China (about $1.18 trillion) then Japan (about $1.06
        trillion).[8]
  - source_sentence: who is the actress of harley quinn in suicide squad
    sentences:
      - >-
        Tariffs in United States history Tariffs were the main source of revenue
        for the federal government from 1789 to 1914. During this period, there
        was vigorous debate between the various political parties over the
        setting of tariff rates. In general Democrats favored a tariff that
        would pay the cost of government, but no higher. Whigs and Republicans
        favored higher tariffs to protect and encourage American industry and
        industrial workers. Since the early 20th century, however, U.S. tariffs
        have been very low and have been much less a matter of partisan debate.
      - >-
        The Rolling Stones The Rolling Stones are an English rock band formed in
        London, England in 1962. The first stable line-up consisted of Brian
        Jones (guitar, harmonica), Mick Jagger (lead vocals), Keith Richards
        (guitar, backing vocals), Bill Wyman (bass), Charlie Watts (drums), and
        Ian Stewart (piano). Stewart was removed from the official line-up in
        1963 but continued as a touring member until his death in 1985. Jones
        left the band less than a month prior to his death in 1969, having
        already been replaced by Mick Taylor, who remained until 1974. After
        Taylor left the band, Ronnie Wood took his place in 1975 and has been on
        guitar in tandem with Richards ever since. Following Wyman's departure
        in 1993, Darryl Jones joined as their touring bassist. Touring
        keyboardists for the band have been Nicky Hopkins (1967–1982), Ian
        McLagan (1978–1981), Billy Preston (through the mid-1970s) and Chuck
        Leavell (1982–present). The band was first led by Brian Jones, but after
        developing into the band's songwriters, Jagger and Richards assumed
        leadership while Jones dealt with legal and personal troubles.
      - >-
        Margot Robbie After moving to the United States, Robbie starred in the
        short-lived ABC drama series Pan Am (2011–2012). In 2013, she made her
        big screen debut in Richard Curtis's romantic comedy-drama film About
        Time and co-starred in Martin Scorsese's biographical black comedy The
        Wolf of Wall Street. In 2015, Robbie co-starred in the romantic
        comedy-drama film Focus, appeared in the romantic World War II drama
        film Suite Française and starred in the science fiction film Z for
        Zachariah. That same year, she played herself in The Big Short. In 2016,
        she portrayed Jane Porter in the action-adventure film The Legend of
        Tarzan and Harley Quinn in the superhero film Suicide Squad. She
        appeared on Time magazine's "The Most Influential People of 2017"
        list.[4]
  - source_sentence: what is meaning of am and pm in time
    sentences:
      - >-
        America's Got Talent America's Got Talent (often abbreviated as AGT) is
        a televised American talent show competition, broadcast on the NBC
        television network. It is part of the global Got Talent franchise
        created by Simon Cowell, and is produced by Fremantle North America and
        SYCOtv, with distribution done by Fremantle. Since its premiere in June
        2006, each season is run during the network's summer schedule, with the
        show having featured various hosts - it is currently hosted by Tyra
        Banks, since 2017.[2] It is the first global edition of the franchise,
        after plans for a British edition in 2005 were suspended, following a
        dispute between Paul O'Grady, the planned host, and the British
        broadcaster ITV; production of this edition later resumed in 2007.[3]
      - >-
        Times Square Times Square is a major commercial intersection, tourist
        destination, entertainment center and neighborhood in the Midtown
        Manhattan section of New York City at the junction of Broadway and
        Seventh Avenue. It stretches from West 42nd to West 47th Streets.[1]
        Brightly adorned with billboards and advertisements, Times Square is
        sometimes referred to as "The Crossroads of the World",[2] "The Center
        of the Universe",[3] "the heart of The Great White Way",[4][5][6] and
        the "heart of the world".[7] One of the world's busiest pedestrian
        areas,[8] it is also the hub of the Broadway Theater District[9] and a
        major center of the world's entertainment industry.[10] Times Square is
        one of the world's most visited tourist attractions, drawing an
        estimated 50 million visitors annually.[11] Approximately 330,000 people
        pass through Times Square daily,[12] many of them tourists,[13] while
        over 460,000 pedestrians walk through Times Square on its busiest
        days.[7]
      - >-
        12-hour clock The 12-hour clock is a time convention in which the 24
        hours of the day are divided into two periods:[1] a.m. (from the Latin,
        ante meridiem, meaning before midday) and p.m. (post meridiem, meaning
        past midday).[2] Each period consists of 12 hours numbered: 12 (acting
        as zero),[3] 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11. The 24 hour/day
        cycle starts at 12 midnight (often indicated as 12 a.m.), runs through
        12 noon (often indicated as 12 p.m.), and continues to the midnight at
        the end of the day. The 12-hour clock was developed over time from the
        mid-second millennium BC to the 16th century AD.
datasets:
  - sentence-transformers/natural-questions
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on answerdotai/ModernBERT-base
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: cosine_accuracy@1
            value: 0.14
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.24
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.4
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.14
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.07999999999999999
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.06
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04000000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.14
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.24
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.25076046577886124
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.20557936507936506
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.21939187046366332
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: cosine_accuracy@1
            value: 0.14
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.28
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.36
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.14
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.064
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.038
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.14
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.16
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.19
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.15720914647954295
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2121904761904762
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12322210117624575
            name: Cosine Map@100
      - task:
          type: nano-beir
          name: Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: cosine_accuracy@1
            value: 0.14
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.38
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.14
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.08666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.062
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.03900000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.10500000000000001
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.19
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.22999999999999998
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.29500000000000004
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2039848061292021
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.20888492063492065
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.17130698581995454
            name: Cosine Map@100

SentenceTransformer based on answerdotai/ModernBERT-base

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-base on the natural-questions dataset. 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.

This is a test model to experiment with the proposed DebiasedMultipleNegativesRankingLoss from Pull Request #3148 in the Sentence Transformers repository, using commit 370bf473e60b57f7d01a6e084b5acaabdac38a2c.

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 Dataset:
- natural-questions
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': 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("tomaarsen/ModernBERT-base-nq-debiased-mnrl")
# Run inference
sentences = [
    'what is meaning of am and pm in time',
    '12-hour clock The 12-hour clock is a time convention in which the 24 hours of the day are divided into two periods:[1] a.m. (from the Latin, ante meridiem, meaning before midday) and p.m. (post meridiem, meaning past midday).[2] Each period consists of 12 hours numbered: 12 (acting as zero),[3] 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11. The 24 hour/day cycle starts at 12 midnight (often indicated as 12 a.m.), runs through 12 noon (often indicated as 12 p.m.), and continues to the midnight at the end of the day. The 12-hour clock was developed over time from the mid-second millennium BC to the 16th century AD.',
    "America's Got Talent America's Got Talent (often abbreviated as AGT) is a televised American talent show competition, broadcast on the NBC television network. It is part of the global Got Talent franchise created by Simon Cowell, and is produced by Fremantle North America and SYCOtv, with distribution done by Fremantle. Since its premiere in June 2006, each season is run during the network's summer schedule, with the show having featured various hosts - it is currently hosted by Tyra Banks, since 2017.[2] It is the first global edition of the franchise, after plans for a British edition in 2005 were suspended, following a dispute between Paul O'Grady, the planned host, and the British broadcaster ITV; production of this edition later resumed in 2007.[3]",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Datasets: NanoMSMARCO and NanoHotpotQA
Evaluated with InformationRetrievalEvaluator

Metric	NanoMSMARCO	NanoHotpotQA
cosine_accuracy@1	0.14	0.14
cosine_accuracy@3	0.24	0.28
cosine_accuracy@5	0.3	0.3
cosine_accuracy@10	0.4	0.36
cosine_precision@1	0.14	0.14
cosine_precision@3	0.08	0.0933
cosine_precision@5	0.06	0.064
cosine_precision@10	0.04	0.038
cosine_recall@1	0.14	0.07
cosine_recall@3	0.24	0.14
cosine_recall@5	0.3	0.16
cosine_recall@10	0.4	0.19
cosine_ndcg@10	0.2508	0.1572
cosine_mrr@10	0.2056	0.2122
cosine_map@100	0.2194	0.1232

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with NanoBEIREvaluator

Metric	Value
cosine_accuracy@1	0.14
cosine_accuracy@3	0.26
cosine_accuracy@5	0.3
cosine_accuracy@10	0.38
cosine_precision@1	0.14
cosine_precision@3	0.0867
cosine_precision@5	0.062
cosine_precision@10	0.039
cosine_recall@1	0.105
cosine_recall@3	0.19
cosine_recall@5	0.23
cosine_recall@10	0.295
cosine_ndcg@10	0.204
cosine_mrr@10	0.2089
cosine_map@100	0.1713

Training Details

Training Dataset

natural-questions

Dataset: 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: 12.46 tokens
max: 25 tokens

min: 16 tokens
mean: 139.02 tokens
max: 537 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 12.46 tokens max: 25 tokens	min: 16 tokens mean: 139.02 tokens max: 537 tokens

Samples:

query	answer
`who is required to report according to the hmda`	`Home Mortgage Disclosure Act US financial institutions must report HMDA data to their regulator if they meet certain criteria, such as having assets above a specific threshold. The criteria is different for depository and non-depository institutions and are available on the FFIEC website.[4] In 2012, there were 7,400 institutions that reported a total of 18.7 million HMDA records.[5]`
`what is the definition of endoplasmic reticulum in biology`	Endoplasmic reticulum The endoplasmic reticulum (ER) is a type of organelle in eukaryotic cells that forms an interconnected network of flattened, membrane-enclosed sacs or tube-like structures known as cisternae. The membranes of the ER are continuous with the outer nuclear membrane. The endoplasmic reticulum occurs in most types of eukaryotic cells, but is absent from red blood cells and spermatozoa. There are two types of endoplasmic reticulum: rough and smooth. The outer (cytosolic) face of the rough endoplasmic reticulum is studded with ribosomes that are the sites of protein synthesis. The rough endoplasmic reticulum is especially prominent in cells such as hepatocytes. The smooth endoplasmic reticulum lacks ribosomes and functions in lipid manufacture and metabolism, the production of steroid hormones, and detoxification.[1] The smooth ER is especially abundant in mammalian liver and gonad cells. The lacy membranes of the endoplasmic reticulum were first seen in 1945 using elect...
`what does the ski mean in polish names`	`Polish name Since the High Middle Ages, Polish-sounding surnames ending with the masculine -ski suffix, including -cki and -dzki, and the corresponding feminine suffix -ska/-cka/-dzka were associated with the nobility (Polish szlachta), which alone, in the early years, had such suffix distinctions.[1] They are widely popular today.`

Loss: DebiasedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 1.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

natural-questions

Dataset: natural-questions at f9e894e
Size: 100,231 evaluation samples
Columns: query and answer
Approximate statistics based on the first 1000 samples:
query answer
type string string
details
min: 10 tokens
mean: 12.46 tokens
max: 22 tokens

min: 12 tokens
mean: 138.0 tokens
max: 649 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 12.46 tokens max: 22 tokens	min: 12 tokens mean: 138.0 tokens max: 649 tokens

Samples:

query	answer
`difference between russian blue and british blue cat`	Russian Blue The coat is known as a "double coat", with the undercoat being soft, downy and equal in length to the guard hairs, which are an even blue with silver tips. However, the tail may have a few very dull, almost unnoticeable stripes. The coat is described as thick, plush and soft to the touch. The feeling is softer than the softest silk. The silver tips give the coat a shimmering appearance. Its eyes are almost always a dark and vivid green. Any white patches of fur or yellow eyes in adulthood are seen as flaws in show cats.[3] Russian Blues should not be confused with British Blues (which are not a distinct breed, but rather a British Shorthair with a blue coat as the British Shorthair breed itself comes in a wide variety of colors and patterns), nor the Chartreux or Korat which are two other naturally occurring breeds of blue cats, although they have similar traits.
`who played the little girl on mrs doubtfire`	`Mara Wilson Mara Elizabeth Wilson[2] (born July 24, 1987) is an American writer and former child actress. She is known for playing Natalie Hillard in Mrs. Doubtfire (1993), Susan Walker in Miracle on 34th Street (1994), Matilda Wormwood in Matilda (1996) and Lily Stone in Thomas and the Magic Railroad (2000). Since retiring from film acting, Wilson has focused on writing.`
`what year did the movie the sound of music come out`	The Sound of Music (film) The film was released on March 2, 1965 in the United States, initially as a limited roadshow theatrical release. Although critical response to the film was widely mixed, the film was a major commercial success, becoming the number one box office movie after four weeks, and the highest-grossing film of 1965. By November 1966, The Sound of Music had become the highest-grossing film of all-time—surpassing Gone with the Wind—and held that distinction for five years. The film was just as popular throughout the world, breaking previous box-office records in twenty-nine countries. Following an initial theatrical release that lasted four and a half years, and two successful re-releases, the film sold 283 million admissions worldwide and earned a total worldwide gross of $286,000,000.

Loss: DebiasedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 1.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 8e-05
num_train_epochs: 1
warmup_ratio: 0.05
seed: 12
bf16: True
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: 128
per_device_eval_batch_size: 128
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: 8e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.05
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: 12
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_cosine_ndcg@10	NanoHotpotQA_cosine_ndcg@10	NanoBEIR_mean_cosine_ndcg@10
0	0	-	-	0.0785	0.1489	0.1137
0.0129	10	4.8033	-	-	-	-
0.0258	20	4.5295	-	-	-	-
0.0387	30	4.2124	-	-	-	-
0.0515	40	4.0863	-	-	-	-
0.0644	50	4.0048	3.9563	0.1444	0.1660	0.1552
0.0773	60	3.9686	-	-	-	-
0.0902	70	3.9192	-	-	-	-
0.1031	80	3.9276	-	-	-	-
0.1160	90	3.9104	-	-	-	-
0.1289	100	3.8971	3.8877	0.2041	0.1293	0.1667
0.1418	110	3.8987	-	-	-	-
0.1546	120	3.8861	-	-	-	-
0.1675	130	3.8987	-	-	-	-
0.1804	140	3.8811	-	-	-	-
0.1933	150	3.8697	3.8478	0.1918	0.1084	0.1501
0.2062	160	3.8621	-	-	-	-
0.2191	170	3.8628	-	-	-	-
0.2320	180	3.8733	-	-	-	-
0.2448	190	3.8551	-	-	-	-
0.2577	200	3.862	3.8324	0.1940	0.0977	0.1458
0.2706	210	3.8545	-	-	-	-
0.2835	220	3.8495	-	-	-	-
0.2964	230	3.8459	-	-	-	-
0.3093	240	3.8438	-	-	-	-
0.3222	250	3.8425	3.8238	0.1933	0.1498	0.1716
0.3351	260	3.843	-	-	-	-
0.3479	270	3.8486	-	-	-	-
0.3608	280	3.8409	-	-	-	-
0.3737	290	3.8345	-	-	-	-
0.3866	300	3.8446	3.8154	0.1937	0.1532	0.1735
0.3995	310	3.8281	-	-	-	-
0.4124	320	3.8316	-	-	-	-
0.4253	330	3.8325	-	-	-	-
0.4381	340	3.8298	-	-	-	-
0.4510	350	3.8379	3.8104	0.1690	0.1559	0.1624
0.4639	360	3.821	-	-	-	-
0.4768	370	3.8297	-	-	-	-
0.4897	380	3.8206	-	-	-	-
0.5026	390	3.8222	-	-	-	-
0.5155	400	3.8243	3.8031	0.2141	0.1544	0.1843
0.5284	410	3.8328	-	-	-	-
0.5412	420	3.8211	-	-	-	-
0.5541	430	3.82	-	-	-	-
0.5670	440	3.8167	-	-	-	-
0.5799	450	3.8062	3.7988	0.2281	0.1392	0.1837
0.5928	460	3.8166	-	-	-	-
0.6057	470	3.8164	-	-	-	-
0.6186	480	3.8207	-	-	-	-
0.6314	490	3.815	-	-	-	-
0.6443	500	3.813	3.7943	0.2381	0.1260	0.1821
0.6572	510	3.8144	-	-	-	-
0.6701	520	3.8172	-	-	-	-
0.6830	530	3.8175	-	-	-	-
0.6959	540	3.8126	-	-	-	-
0.7088	550	3.8077	3.7913	0.2501	0.1395	0.1948
0.7216	560	3.8022	-	-	-	-
0.7345	570	3.8131	-	-	-	-
0.7474	580	3.8067	-	-	-	-
0.7603	590	3.8175	-	-	-	-
0.7732	600	3.8084	3.7870	0.2751	0.1480	0.2116
0.7861	610	3.8029	-	-	-	-
0.7990	620	3.8125	-	-	-	-
0.8119	630	3.817	-	-	-	-
0.8247	640	3.8038	-	-	-	-
0.8376	650	3.8054	3.7877	0.2274	0.1449	0.1861
0.8505	660	3.8041	-	-	-	-
0.8634	670	3.8012	-	-	-	-
0.8763	680	3.8117	-	-	-	-
0.8892	690	3.8098	-	-	-	-
0.9021	700	3.8008	3.7848	0.2466	0.1551	0.2008
0.9149	710	3.8038	-	-	-	-
0.9278	720	3.7949	-	-	-	-
0.9407	730	3.8044	-	-	-	-
0.9536	740	3.7982	-	-	-	-
0.9665	750	3.804	3.7832	0.2585	0.1587	0.2086
0.9794	760	3.8038	-	-	-	-
0.9923	770	3.8046	-	-	-	-
1.0	776	-	-	0.2508	0.1572	0.2040

Framework Versions

Python: 3.11.10
Sentence Transformers: 3.4.0.dev0
Transformers: 4.48.0.dev0
PyTorch: 2.6.0.dev20241112+cu121
Accelerate: 1.2.0
Datasets: 3.2.0
Tokenizers: 0.21.0

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",
}

DebiasedMultipleNegativesRankingLoss

@inproceedings{chuang2020debiased,
    title={Debiased Contrastive Learning},
    author={Ching-Yao Chuang and Joshua Robinson and Lin Yen-Chen and Antonio Torralba and Stefanie Jegelka},
    booktitle={Advances in Neural Information Processing Systems},
    year={2020},
    url={https://arxiv.org/pdf/2007.00224}
}