metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:183
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
widget:
  - source_sentence: >-
      14 William O. Douglas, quoted in Charles Hurd, Film Booking Issue Ordered
      Reopened,” New York Times, May 4, 1948, 1. 15 Movie Crisis Laid to Video
      Inroads And Dwindling of Foreign Market, New York Times, February 27,
      1949, F1. For details on the lawsuit and its effects, see Arthur De Vany
      and Henry McMillan, Was the Antitrust Action that Broke Up the Movie
      Studios Good for the Movies? Evidence from the Stock Market. American Law
      and Economics Review 6, no. 1 (2004): 135-53; and J.C. Strick, The
      Economics of the Motion Picture Industry: A Survey, Philosophy of the
      Social Sciences 8, no. 4 (December 1978): 406-17. 16 The Hollywood feature
      films for which Eisler provided music are Hangmen Also Die (1942), None
      But the Lonely Heart (1944), Jealousy (1945), The Spanish Main (1945); A
      Scandal in Paris (1946), Deadline at Dawn (1946), Woman on the Beach
      (1947), and So Well Remembered (1947). Most of these are
      middle-of-the-road genre pieces, but the first NOTES 267
    sentences:
      - >-
        What is the opinion of Ernest Irving, a pioneer of British film music,
        on the overall quality of American film music?
      - >-
        What is the title of the 2007 film directed by David Fincher, produced
        by Michael Medavoy, and featuring a storyline based on a real-life
        serial killer, as mentioned in the provided context information?
      - >-
        What was the primary reason behind the lawsuit that led to the breakup
        of the movie studios, as suggested by the article in the New York Times
        on February 27, 1949?
  - source_sentence: >-
      But Gorbman (who like Flinn and Kalinak approached film music from a
      formal background not in musicology but in literary criticism) was
      certainly not the first scholar engaged in so-called film studies44 to
      address the role that extra-diegetic music played in classical-style
      films. Two years before Gorbman's book was published, the trio of
      Bordwell, Staiger, and Thompson brought out their monumental The Classical
      Hollywood Cinema: Film Style and Production to 1960. As noted above, and
      apropos of its title, the book focuses on filmic narrative style and the
      technical devices that made this style possible. In its early pages,
      however, it also contains insightful comments on classical cinema's use of
      music. The book's first music-related passage lays a foundation for
      Gorbman's point about how a score might lend unity to a film by recycling
      distinctive themes that within the THE GOLDEN AGE OF FILM MUSIC, 1933-49
      143
    sentences:
      - >-
        What is the possible reason, as suggested by David Thomson, for why
        David Lean's filmmaking style may have declined after the movie "Summer
        Madness" (US, 1955)?
      - >-
        What shift in the portrayal of hard body male characters in film, as
        exemplified by the actors who played these roles in the 1980s and 1990s,
        suggests that societal expectations and norms may be changing?
      - >-
        What is the significance of the authors' formal background in literary
        criticism rather than musicology, as mentioned in the context of
        Gorbman's approach to film music?
  - source_sentence: >-
      (1931); Georg Wilhelm Pabst's Kameradschaft (1931); Fritz Lang's M (1931)
      and Das Testament der Dr. Mabuse (1932); and Carl Theodor Dreyer's Vampyr
      (1932). These films’ subtle mix of actual silence with accompanying music
      and more or less realistic sound effects has drawn and doubtless will
      continue to draw serious analytical attention from film scholars.45 And
      even in their own time they drew due attention aplenty from critics of
      avant-garde persuasion.46 The mere fact that these films differed from the
      sonic norm attracted the notice, if not always the praise, of movie
      reviewers for the popular press. Writing from London, a special
      correspondent for the New York Times observed that Hitchcock's Blackmail
      goes some way to showing how the cinematograph and the microphone can be
      mated without their union being forced upon the attention of a punctilious
      world as VITAPHONE AND MOVIETONE, 1926-8 101
    sentences:
      - >-
        What was the primary limitation that led to the failure of Edison's
        first Kinetophone, which was an early attempt at sound film featuring
        musical accompaniment?
      - >-
        What was the specific sonic approach employed by the mentioned films of
        Georg Wilhelm Pabst, Fritz Lang, and Carl Theodor Dreyer that drew
        serious analytical attention from film scholars?
      - >-
        What limitation in Martin Scorsese's background, as mentioned in the
        text, restricted his choice of subjects at this stage in his career?
  - source_sentence: "39\tdivided into small, three-dimensional cubes known as volumetric pixels, or voxels. When viewers are watching certain images, the voxel demonstrates how these images in the movie are mapped into brain activity. Clips of the movie are reconstructed through brain imaging and computer stimulation by associating visual patterns in the movie with the corresponding brain activity. However, these reconstructions are blurry and are hard to make because researchers say, blood flow signals measured using fMRI change much more slowly than the neural signals that encode dynamic information in movies. Psychology and neuroscience professor, Jack Gallant explains in an interview that primary visual cortex responds to the local features of the movie such as edges, colors, motion, and texture but this part of the brain cannot understand the objects in the movie. In addition, movies that show people are reconstructed with better accuracy than abstract images. Using Neuroimaging For Entertainment Success Can brain scans predict movie success in the box office? Two marketing researchers from the Rotterdam School of Management devised an experiment by using EEG on participants. EEG demonstrated that individual choice and box office success correlate with different types of brain activity. From article, How Neuroimaging Can Save The Entertainment Industry Millions of Dollars, it states, individual choice is predicted best by high frontocentral beta activity, the choice of the general population is predicted by frontal gamma activity. Perhaps, with quickly advanced technology, predicting movie genre and plots that can hit the box office could be successful. Neurocinema in Hollywood One strategy that helps filmmakers, producers, and distributors to achieve global market success is by using fMRI and EEG to make a better storyline, characters, sound effects, and other"
    sentences:
      - >-
        What significant change in the portrayal of Rocky's character is evident
        in the 2015 movie Creed, as compared to the original 1976 film Rocky?
      - >-
        What factors led to the selection of the films "Spider-man" (2002),
        "Cars" (2006), and "Avatar" (2009) for the research project examining
        the relationship between film and society in the early 2000s?
      - >-
        What is the main reason why researchers find it challenging to
        reconstruct abstract images from movie clips using brain imaging and
        computer stimulation?
  - source_sentence: "11\tdocumentary film so unpleasant when most had sat through horror pictures that were appreciably more violent and bloody.  The answer that McCauley came up with was that the fictional nature of horror films affords viewers a sense of control by placing psychological distance between them and the violent acts they have witnessed. Most people who view horror movies understand that the filmed events are unreal, which furnishes them with psychological distance from the horror portrayed in the film. In fact, there is evidence that young viewers who perceive greater realism in horror films are more negatively affected by their exposure to horror films than viewers who perceive the film as unreal (Hoekstra, Harris, & Helmick, 1999). Four Viewing Motivations for Graphic Horror   According to Dr. Deirdre Johnston (1995) study Adolescents’ Motivations for Viewing Graphic Horror of Human Communication Research there are four different main reasons for viewing graphic horror. From the study of a small sample of 220 American adolescents who like watching horror movies, Dr. Johnston reported that: The four viewing motivations are found to be related to viewers’ cognitive and affective responses to horror films, as well as viewers’ tendency to identify with either the killers or victims in these films.\" Dr. Johnson notes that:  1) gore watchers typically had low empathy, high sensation seeking, and (among  males only) a strong identification with the killer, 2) thrill watchers typically had  both high empathy and sensation seeking, identified themselves more with the  victims, and liked the suspense of the film, 3) independent watchers typically had  a  high empathy for the victim along with a high positive effect for overcoming  fear, and 4) problem watchers typically had high empathy for the victim but were"
    sentences:
      - >-
        What was the name of the series published by Oliver Ditson from 1918-25
        that contained ensemble music for motion picture plays?
      - >-
        What shift in the cultural, political, and social contexts of the 1980s
        and 1990s may have led to the deconstruction of the hard body characters
        portrayed by actors such as Stallone and Schwarzenegger in more recent
        movies?
      - >-
        What is the primary reason why viewers who perceive greater realism in
        horror films are more negatively affected by their exposure to horror
        films than viewers who perceive the film as unreal?
datasets:
  - YxBxRyXJx/QAsimple_for_BGE_241019
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: BGE base Movie Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.8205128205128205
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9743589743589743
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8205128205128205
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.32478632478632485
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.20000000000000004
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8205128205128205
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9743589743589743
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9207838928594967
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8940170940170941
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8940170940170938
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.8461538461538461
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9230769230769231
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8461538461538461
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30769230769230776
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.20000000000000004
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8461538461538461
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9230769230769231
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9233350110390831
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8982905982905982
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8982905982905982
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.8461538461538461
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9230769230769231
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9487179487179487
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8461538461538461
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30769230769230776
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18974358974358976
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8461538461538461
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9230769230769231
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9487179487179487
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9234104189545929
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.898962148962149
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.898962148962149
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.7692307692307693
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8974358974358975
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9487179487179487
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9487179487179487
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7692307692307693
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29914529914529925
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18974358974358976
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09487179487179488
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7692307692307693
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8974358974358975
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9487179487179487
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9487179487179487
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8688480033444261
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8418803418803418
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8443986568986569
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.5641025641025641
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8717948717948718
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9230769230769231
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9487179487179487
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5641025641025641
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2905982905982907
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18461538461538465
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09487179487179488
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5641025641025641
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8717948717948718
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9230769230769231
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9487179487179487
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.768187565996018
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.708119658119658
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7088711597999523
            name: Cosine Map@100

BGE base Movie Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the q_asimple_for_bge_241019 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.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- q_asimple_for_bge_241019
Language: en
License: apache-2.0

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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

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("YxBxRyXJx/bge-base-movie-matryoshka")
# Run inference
sentences = [
    '11\tdocumentary film so unpleasant when most had sat through horror pictures that were appreciably more violent and bloody.  The answer that McCauley came up with was that the fictional nature of horror films affords viewers a sense of control by placing psychological distance between them and the violent acts they have witnessed. Most people who view horror movies understand that the filmed events are unreal, which furnishes them with psychological distance from the horror portrayed in the film. In fact, there is evidence that young viewers who perceive greater realism in horror films are more negatively affected by their exposure to horror films than viewers who perceive the film as unreal (Hoekstra, Harris, & Helmick, 1999). Four Viewing Motivations for Graphic Horror   According to Dr. Deirdre Johnston (1995) study Adolescents’ Motivations for Viewing Graphic Horror of Human Communication Research there are four different main reasons for viewing graphic horror. From the study of a small sample of 220 American adolescents who like watching horror movies, Dr. Johnston reported that: The four viewing motivations are found to be related to viewers’ cognitive and affective responses to horror films, as well as viewers’ tendency to identify with either the killers or victims in these films." Dr. Johnson notes that:  1) gore watchers typically had low empathy, high sensation seeking, and (among  males only) a strong identification with the killer, 2) thrill watchers typically had  both high empathy and sensation seeking, identified themselves more with the  victims, and liked the suspense of the film, 3) independent watchers typically had  a  high empathy for the victim along with a high positive effect for overcoming  fear, and 4) problem watchers typically had high empathy for the victim but were',
    'What is the primary reason why viewers who perceive greater realism in horror films are more negatively affected by their exposure to horror films than viewers who perceive the film as unreal?',
    'What shift in the cultural, political, and social contexts of the 1980s and 1990s may have led to the deconstruction of the hard body characters portrayed by actors such as Stallone and Schwarzenegger in more recent movies?',
]
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: dim_768, dim_512, dim_256, dim_128 and dim_64
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.8205	0.8462	0.8462	0.7692	0.5641
cosine_accuracy@3	0.9744	0.9231	0.9231	0.8974	0.8718
cosine_accuracy@5	1.0	1.0	0.9487	0.9487	0.9231
cosine_accuracy@10	1.0	1.0	1.0	0.9487	0.9487
cosine_precision@1	0.8205	0.8462	0.8462	0.7692	0.5641
cosine_precision@3	0.3248	0.3077	0.3077	0.2991	0.2906
cosine_precision@5	0.2	0.2	0.1897	0.1897	0.1846
cosine_precision@10	0.1	0.1	0.1	0.0949	0.0949
cosine_recall@1	0.8205	0.8462	0.8462	0.7692	0.5641
cosine_recall@3	0.9744	0.9231	0.9231	0.8974	0.8718
cosine_recall@5	1.0	1.0	0.9487	0.9487	0.9231
cosine_recall@10	1.0	1.0	1.0	0.9487	0.9487
cosine_ndcg@10	0.9208	0.9233	0.9234	0.8688	0.7682
cosine_mrr@10	0.894	0.8983	0.899	0.8419	0.7081
cosine_map@100	0.894	0.8983	0.899	0.8444	0.7089

Training Details

Training Dataset

q_asimple_for_bge_241019

Dataset: q_asimple_for_bge_241019 at 66635cd
Size: 183 training samples
Columns: positive and anchor
Approximate statistics based on the first 183 samples:
positive anchor
type string string
details
min: 191 tokens
mean: 356.1 tokens
max: 512 tokens

min: 16 tokens
mean: 36.04 tokens
max: 66 tokens

	positive	anchor
type	string	string
details	min: 191 tokens mean: 356.1 tokens max: 512 tokens	min: 16 tokens mean: 36.04 tokens max: 66 tokens

Samples:

positive	anchor
1 Introduction Why do we watch horror films? What makes horror films so exciting to watch? Why do our bodies sweat and muscles tense when we are scared? How do filmmakers, producers, sound engineers, and cinematographers specifically design a horror film? Can horror movies cause negative, lasting effects on the audience? These are some of the questions that are answered by exploring the aesthetics of horror films and the psychology behind horror movies. Chapter 1, The Allure of Horror Film, illustrates why we are drawn to scary films by studying different psychological theories and factors. Ideas include: catharsis, subconscious mind, curiosity, thrill, escape from reality, relevance, unrealism, and imagination. Also, this chapter demonstrates why people would rather watch fiction films than documentaries and the motivations for viewing graphic horror. Chapter 2, Mise-en-scène in Horror Movies, includes purposeful arrangement of scenery and stage properties of horror movie. Also...	`What is the name of the emerging field of scientists and filmmakers that uses fMRI and EEG to read people's brain activity while watching movie scenes?`
3 Chapter 1: The Allure of Horror Film Overview Although watching horror films can make us feel anxious and uneasy, we still continue to watch other horror films one after another. It is ironic how we hate the feeling of being scared, but we still enjoy the thrill. So why do we pay money to watch something to be scared? Eight Theories on why we watch Horror Films From research by philosophers, psychoanalysts, and psychologists there are theories that can explain why we are drawn to watching horror films. The first theory, psychoanalyst, Sigmund Freud portrays that horror comes from the “uncanny” emergence of images and thoughts of the primitive id. The purpose of horror films is to highlight unconscious fears, desire, urges, and primeval archetypes that are buried deep in our collective subconscious images of mothers and shadows play important roles because they are common to us all. For example, in Alfred Hitchcock's Psycho, a mother plays the role of evil in the main character...	`What process, introduced by the Greek Philosopher Aristotle, involves the release of negative emotions through the observation of violent or scary events, resulting in a purging of aggressive emotions?`
5 principle unknowable (Jancovich, 2002, p. 35). This meaning, the audience already knows that the plot and the characters are already disgusting, but the surprises in the horror narrative through the discovery of curiosity should give satisfaction. Marvin Zuckerman (1979) proposed that people who scored high in sensation seeking scale often reported a greater interest in exciting things like rollercoasters, bungee jumping and horror films. He argued more individuals who are attracted to horror movies desire the sensation of experience. However, researchers did not find the correlation to thrill-seeking activities and enjoyment of watching horror films always significant. The Gender Socialization theory (1986) by Zillman, Weaver, Mundorf and Aust exposed 36 male and 36 female undergraduates to a horror movie with the same age, opposite-gender companion of low or high initial appeal who expressed mastery, affective indifference, or distress. They reported that young men enjoyed the fi...	`What is the proposed theory by Marvin Zuckerman (1979) regarding the relationship between sensation seeking and interest in exciting activities, including horror films?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 5
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-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: 5
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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: True
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_fused
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: False
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	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	1	0.8987	0.8983	0.8835	0.8419	0.7773
2.0	2	0.9218	0.9141	0.9075	0.8721	0.8124
1.0	1	0.9218	0.9141	0.9075	0.8721	0.8124
2.0	2	0.9356	0.9302	0.9118	0.8750	0.8057
3.0	4	0.9302	0.9233	0.9234	0.8783	0.7759
4.0	5	0.9208	0.9233	0.9234	0.8688	0.7682

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
Transformers: 4.46.3
PyTorch: 2.5.1+cu121
Accelerate: 1.1.1
Datasets: 3.1.0
Tokenizers: 0.20.3

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

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