sidbrahim's picture
Upload folder using huggingface_hub
4481ba7 verified
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1584
  - loss:CoSENTLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: >-
      1988: born on November 27 in Paris | 2006: returns to Paris | 2008: begins
      her career | 2009: plays Éléonore in L'Orpheline with an additional arm |
      2013: selected to play in a short film | 2019: notable career start with
      'Portrait of a Young Girl in Flames' | 2019: wins the Lumière Award for
      Best Actress | 2019: film receives the screenplay prize at the Cannes Film
      Festival | 2019: plays Marianne in 'Portrait of a Young Girl in Flames' |
      2020: plays the role of an autistic young girl in 'Jumbo' | 2020: presents
      her second short film, Shakira | 2021: first long film officially selected
      for the Cannes Film Festival | 2022: continues her American ascent by
      participating in 'Tár' | 2023: supports the movement against the pension
      reform project
    sentences:
      - >-
        1946: Born in New York City | 1968: Had a role in the drama That Nice
        Boy (aka The Square Root) | 1969: Changed stage name from Mike Stallone
        to Sylvester E. Stallone | 1970: First starring role in The Party at
        Kitty and Stud's | 1971: Starred in the erotic off-Broadway stage play
        Score | 1972: Failed to get a job as an extra in The Godfather | 1973:
        Achieved first proper starring role in No Place to Hide | 1974: First
        film role: The Lords of Flatbush | 1976: Gained worldwide fame with the
        role in Rocky | 1977: Nominated for ten Oscars at the 49th Academy
        Awards | 1978: Debut in Paradise Alley | 1979: Wrote, directed, and
        starred in Rocky II | 1981: Starred in Escape to Victory | 1982: Played
        John Rambo in First Blood
      - >-
        1966: Born in Paris, France | 1995: Debut in La Haine, received two
        César Award nominations | 1996: Met Monica Bellucci on set of The
        Apartment | 1999: Married Monica Bellucci in Monaco | 2004: Daughter
        Deva born | 2007: Critical acclaim for performance in Eastern Promises |
        2008: Won César Award for Best Actor for role as Jacques Mesrine | 2010:
        Daughter Léonie born | 2010: Nominated for Screen Actors Guild Award for
        Outstanding Performance by a Cast in a Motion Picture for Black Swan |
        2013: Announced separation from Monica Bellucci | 2016: Won Canadian
        Screen Award for Best Supporting Actor for role in It's Only the End of
        the World | 2018: Married Tina Kunakey in Bidart, France | 2019:
        Daughter Amazonie born | 2019: Nominated for César Award for Best Actor
        for role in The Specials
      - >-
        1967: Born in Shirebrook, Derbyshire, England on 26 July | 1978:
        Attended local grammar school | 1990: Competed for England in the 1990
        Commonwealth Games | 1998: Casted in Lock, Stock and Two Smoking Barrels
        | 2000: Casted in Snatch | 2010: Casted in The Expendables | 2011: First
        career milestone - The Mechanic | 2012: Awards - Box office success |
        2013: Advocated for stunt performers at Academy Awards (2013) | 2013:
        Cameo - Fast & Furious 6 | 2013: Casted in Fast & Furious franchise |
        2014: Inducted into International Sports Hall of Fame (2014) | 2016:
        Engaged to Rosie Huntington-Whiteley (2016) | 2017: Son born (2017)
  - source_sentence: >-
      1983: Born on 11 August in Melbourne, Victoria | 2004: Became a part of
      Home and Away | 2007: Left Home and Away | 2009: Played James T. Kirk's
      father in Star Trek | 2010: Married Elsa Pataky | 2011: Starred as Thor in
      the Marvel Cinematic Universe | 2012: Daughter India Rose born | 2012:
      Played the character Kale Garrity in A Perfect Getaway | 2012: Reprised
      the role of Thor in The Avengers | 2013: Reprised Thor in Thor: The Dark
      World (2013) | 2013: Starred in Rush | 2014: Donated fees to the
      Australian Children Foundation | 2014: Twin sons born | 2015: Co-starred
      in Vacation
    sentences:
      - >-
        1979: Born in Emmett, Idaho | 1996: Participated in International
        Modeling and Talent Association competition | 1997: Appeared on The
        Price Is Right | 1997: Graduated from Centennial High School in Boise,
        Idaho | 2008: Became known for role as Jesse Pinkman in Breaking Bad |
        2009: Starred in The Last House on the Left | 2010: Nominated for
        Primetime Emmy Award for Outstanding Supporting Actor in a Drama Series
        | 2012: Engaged to Lauren Parsekian in Paris | 2013: Declared October 1
        as Aaron Paul Sturtevant Day | 2013: Got Breaking Bad tattoos with Bryan
        Cranston | 2013: Helped organize a contest to raise $1.6 million for
        anti-bullying organization | 2013: Married Lauren Parsekian in Malibu |
        2018: Daughter Story Annabelle born | 2022: Dropped birth surname to
        'Paul'
      - >-
        1929: born on November 12 in Philadelphia | 1947: educated at Ravenhill
        Academy | 1951: appears in 14 Hours | 1953: stars in Mogambo | 1955:
        wins the Academy Award for Best Actress | 1956: becomes a Grand-Cross of
        the Order of Saint Charles of Monaco | 1956: civil marriage | 1956:
        religious marriage | 1956: ends her acting career | 1956: famous and
        admired wedding dress | 1960: godmother of AS Monaco | 1962: Dame
        Grand-Cross of the Order of Beneficence (Greece) | 1963: founds the
        World Association of Friends of Children | 1964: founds the Princess
        Grace Foundation of Monaco
      - >-
        1989: born on July 23 in Fulham, London | 2002: appears in Harry Potter
        and the Chamber of Secrets | 2003: offers a strand of hair and an
        autograph for the British Charity | 2004: plays in Harry Potter and the
        Prisoner of Azkaban | 2005: plays in Harry Potter and the Goblet of Fire
        | 2007: leaves hand and footprints in front of Grauman's Chinese Theatre
        | 2007: Television film My Son Jack | 2007: Writes in the magazine
        Rubbish | 2008: Nominated for a Drama Desk Award | 2008: Main role in
        Equus | 2009: plays in Harry Potter and the Deathly Hallows | 2011: Emma
        Watson describes him as a cute, generous, and energetic boy | 2011: Main
        role of J Pierrepont Finch on Broadway | 2012: First major project after
        Harry Potter
  - source_sentence: >-
      1929: born on November 12 in Philadelphia | 1947: educated at Ravenhill
      Academy | 1951: appears in 14 Hours | 1953: stars in Mogambo | 1955: wins
      the Academy Award for Best Actress | 1956: becomes a Grand-Cross of the
      Order of Saint Charles of Monaco | 1956: civil marriage | 1956: religious
      marriage | 1956: ends her acting career | 1956: famous and admired wedding
      dress | 1960: godmother of AS Monaco | 1962: Dame Grand-Cross of the Order
      of Beneficence (Greece) | 1963: founds the World Association of Friends of
      Children | 1964: founds the Princess Grace Foundation of Monaco
    sentences:
      - >-
        1979: born on March 9 in Guatemala | 2005: completed studies at the
        Juilliard School | 2006: small role in The Hitman's Bodyguard | 2008:
        small role in Che | 2013: confirmed with Llewyn Davis in Inside Llewyn
        Davis | 2015: participated in Star Wars, episode VII : The Force Awakens
        | 2017: married Elvira Lind | 2022: jury member of the 19th Marrakech
        International Film Festival
      - >-
        1983: Born on August 11 in Melbourne (Victoria) | 2003: Begins in Summer
        Bay | 2010: Portrays Sam Phelan in Ca$h | 2011: Portrays Thor | 2012:
        Portrays the male lead in the fantasy blockbuster Snow White and the
        Hunter | 2012: Portrays Curt Vaughan in The Cabin in the Woods | 2012:
        Reteams with Joss Whedon for Avengers | 2013: In 2013, he first portrays
        the Formula 1 pilot James Hunt in the sports drama Rush | 2015: Portrays
        the hacker Nicholas Hathaway in the techno-thriller Hacker | 2015:
        Reteams with Joss Whedon for Avengers: Age of Ultron | 2017:
        Simultaneously films Avengers: Infinity War and Avengers: Endgame |
        2018: Attempts to leave the Thor costume by directing the war film Horse
        Soldiers | 2019: Shares the screen with the science fiction blockbuster
        MIB | 2019: Actor announces in the Australian edition of the Daily
        Telegraph that he is putting his career on hold
      - >-
        1970: Born on 7 March in Westminster, London | 1988: Graduated from
        Trinity Hall, Cambridge with upper second-class honours | 1994: Stage
        debut in 'Design for Living' | 1999: International breakthrough in 'The
        Mummy' | 2001: Began dating Darren Aronofsky | 2004: Appeared in the
        comedy Envy | 2005: Starred in The Constant Gardener | 2005: Won
        Laurence Olivier Award for Best Actress for 'A Streetcar Named Desire' |
        2006: Received BAFTA Britannia Award for British Artist of the Year |
        2006: Starred in The Fountain | 2009: Played Hypatia of Alexandria in
        Agora | 2010: Starred in The Whistleblower | 2011: Became a naturalised
        American citizen | 2011: Played Blanche DuBois in A Streetcar Named
        Desire
  - source_sentence: >-
      1981: Born on 9 February in Westminster, London | 1999: Debut in Journey's
      End | 2005: Graduated from Royal Academy of Dramatic Art | 2006: First
      film role in Unrelated | 2007: Started boarding at Windlesham House School
      | 2007: Won Laurence Olivier Award for Best Newcomer in a Play | 2011:
      First career milestone: Midnight in Paris, War Horse | 2011: Nominated for
      BAFTA Rising Star Award | 2011: Portrayed Loki in Thor | 2011: Voiceover:
      The Ancient Egyptian Book of the Dead | 2012: Television: The Hollow Crown
      | 2013: Film: Thor: The Dark World | 2013: Traveled to Guinea to raise
      awareness about hunger and malnutrition | 2014: Film: Muppets Most Wanted
    sentences:
      - >-
        1979: Born on June 21 in Virginia, Minnesota | 2000: Discovered by Rae
        Dawn Chong | 2000: Role in the short film Cursed Part 3 | 2000: Waiter
        at the Shrimp Bubba Gump Company restaurant in Maui | 2006: Everwood
        cancelled | 2008: Major role in Wanted: Choose Your Own Adventure |
        2012: Son Jack born, August 25 | 2014: Ranked second in People's Sexiest
        Men Alive list | 2014: Star in two films in the top 3 of the biggest box
        office successes in North America in 2014 | 2014: Cover of Entertainment
        Weekly | 2014: Premature son born, December 5 | 2014: Guardians of the
        Galaxy tops box office on opening weekend | 2014: Voiced Emmet
        Brickowoski in The Lego Movie | 2014: Awarded CinemaCon Award for Best
        Breakthrough Performance
      - >-
        1978: born on November 17 in London (Ontario) | 2001: graduated from
        York University | 2001: first role on screen in My Name Is Tanino |
        2001: first Genie Award nomination for her role in The Road to You |
        2002: first Hollywood film, Hot Tease | 2004: became famous with leading
        roles in Lolita and Never Forget | 2004: romantic role in Never Forget |
        2004: role of Regina George in Mean Girls | 2005: marriage with Ryan
        Gosling (2005-2011) | 2006: hosts the Academy Award for Technical
        Achievement | 2006: appears on the cover of Vanity Fair with Scarlett
        Johansson and Keira Knightley (2006) | 2006: performs in the stage
        production of The Vagina Monologues | 2006: participates in the Day
        Without Immigrants protest | 2006: turns down roles in The Devil Wears
        Prada, Casino Royale, Mission: Impossible III, and A Nightmare on Elm
        Street
      - >-
        1980: Born in London, Ontario, Canada | 1993: Joined The All New Mickey
        Mouse Club | 1995: Returned to Canada | 1996: Appeared in Goosebumps |
        1998: Filmed Young Hercules in New Zealand | 2000: Film breakthrough in
        Remember the Titans | 2000: Published solo album 'Angel With Tatooed
        Wings' | 2001: Lead role in The Believer | 2002: Co-star in Murder by
        Numbers | 2002: Co-star in The Slaughter Rule | 2003: Starred in The
        United States of Leland | 2004: Achieved mainstream popularity for The
        Notebook | 2004: Signed with Terrence Malick for Che (2004) | 2004:
        Starred in The Notebook
  - source_sentence: >-
      1983: Born on August 11 in Melbourne (Victoria) | 2003: Begins in Summer
      Bay | 2010: Portrays Sam Phelan in Ca$h | 2011: Portrays Thor | 2012:
      Portrays the male lead in the fantasy blockbuster Snow White and the
      Hunter | 2012: Portrays Curt Vaughan in The Cabin in the Woods | 2012:
      Reteams with Joss Whedon for Avengers | 2013: In 2013, he first portrays
      the Formula 1 pilot James Hunt in the sports drama Rush | 2015: Portrays
      the hacker Nicholas Hathaway in the techno-thriller Hacker | 2015: Reteams
      with Joss Whedon for Avengers: Age of Ultron | 2017: Simultaneously films
      Avengers: Infinity War and Avengers: Endgame | 2018: Attempts to leave the
      Thor costume by directing the war film Horse Soldiers | 2019: Shares the
      screen with the science fiction blockbuster MIB | 2019: Actor announces in
      the Australian edition of the Daily Telegraph that he is putting his
      career on hold
    sentences:
      - >-
        1962: Born on 6 August in Ipoh, Perak, Malaysia | 1983: Won Miss
        Malaysia World beauty contest | 1985: First lead role in Yes, Madam |
        1987: Married Dickson Poon | 1988: Married Dickson Poon from 1988 to
        1992 | 1997: Starred in Tomorrow Never Dies | 1998: Dated Alan Heldman
        from 1998 to 2000 | 2000: Starred in Crouching Tiger, Hidden Dragon |
        2004: Began dating Jean Todt | 2005: Starred in Memoirs of a Geisha |
        2008: Became an ambassador for FIA's Make Roads Safe campaign | 2011:
        Chosen by Guerlain as skincare ambassador in 2011 | 2013: Changed to the
        role of executive producer for Pad Yatra: A Green Odyssey | 2013:
        Supports Malaysian prime minister Najib Razak and Barisan Nasional
      - >-
        1948: Born on December 21, 1948, in Washington, D.C. | 1972: Earned a BA
        in drama from Morehouse College | 1980: Made his professional theater
        debut in Mother Courage and Her Children at The Public Theater in New
        York City | 1980: Married LaTanya Richardson | 1982: Daughter Zoe born |
        1990: Appeared in Jungle Fever as a crack cocaine addict | 1993: Starred
        in Jurassic Park | 1994: Debut in Pulp Fiction | 1994: Received Golden
        Globe nomination for Pulp Fiction | 1995: Received BAFTA Award for Best
        Supporting Role | 1996: First bald role in The Great White Hype | 1998:
        Hosted the MTV Movie Awards (1998) | 2000: Received star on the
        Hollywood Walk of Fame | 2006: Won the German Bambi Award for
        International Film
      - >-
        1979: born on August 27 in Emmett (Idaho) | 1996: graduates from
        Centennial High School in Boise | 2000: selected as a candidate for
        Juste Prix in 2000 | 2007: joins the Big Love series | 2008: plays Jesse
        Pinkman in Breaking Bad | 2010: wins the Emmy Award for Best Supporting
        Actor | 2013: marries Lauren Parsekian in Malibu | 2018: daughter Story
        Annabelle is born
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: validation
          type: validation
        metrics:
          - type: pearson_cosine
            value: 0.8520244193617519
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7196384923568855
            name: Spearman Cosine

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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: sentence-transformers/all-mpnet-base-v2
  • Maximum Sequence Length: 384 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    '1983: Born on August 11 in Melbourne (Victoria) | 2003: Begins in Summer Bay | 2010: Portrays Sam Phelan in Ca$h | 2011: Portrays Thor | 2012: Portrays the male lead in the fantasy blockbuster Snow White and the Hunter | 2012: Portrays Curt Vaughan in The Cabin in the Woods | 2012: Reteams with Joss Whedon for Avengers | 2013: In 2013, he first portrays the Formula 1 pilot James Hunt in the sports drama Rush | 2015: Portrays the hacker Nicholas Hathaway in the techno-thriller Hacker | 2015: Reteams with Joss Whedon for Avengers: Age of Ultron | 2017: Simultaneously films Avengers: Infinity War and Avengers: Endgame | 2018: Attempts to leave the Thor costume by directing the war film Horse Soldiers | 2019: Shares the screen with the science fiction blockbuster MIB | 2019: Actor announces in the Australian edition of the Daily Telegraph that he is putting his career on hold',
    '1948: Born on December 21, 1948, in Washington, D.C. | 1972: Earned a BA in drama from Morehouse College | 1980: Made his professional theater debut in Mother Courage and Her Children at The Public Theater in New York City | 1980: Married LaTanya Richardson | 1982: Daughter Zoe born | 1990: Appeared in Jungle Fever as a crack cocaine addict | 1993: Starred in Jurassic Park | 1994: Debut in Pulp Fiction | 1994: Received Golden Globe nomination for Pulp Fiction | 1995: Received BAFTA Award for Best Supporting Role | 1996: First bald role in The Great White Hype | 1998: Hosted the MTV Movie Awards (1998) | 2000: Received star on the Hollywood Walk of Fame | 2006: Won the German Bambi Award for International Film',
    "1962: Born on 6 August in Ipoh, Perak, Malaysia | 1983: Won Miss Malaysia World beauty contest | 1985: First lead role in Yes, Madam | 1987: Married Dickson Poon | 1988: Married Dickson Poon from 1988 to 1992 | 1997: Starred in Tomorrow Never Dies | 1998: Dated Alan Heldman from 1998 to 2000 | 2000: Starred in Crouching Tiger, Hidden Dragon | 2004: Began dating Jean Todt | 2005: Starred in Memoirs of a Geisha | 2008: Became an ambassador for FIA's Make Roads Safe campaign | 2011: Chosen by Guerlain as skincare ambassador in 2011 | 2013: Changed to the role of executive producer for Pad Yatra: A Green Odyssey | 2013: Supports Malaysian prime minister Najib Razak and Barisan Nasional",
]
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

Semantic Similarity

Metric Value
pearson_cosine 0.852
spearman_cosine 0.7196

Training Details

Training Dataset

Unnamed Dataset

  • Size: 1,584 training samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 score
    type string string int
    details
    • min: 34 tokens
    • mean: 145.44 tokens
    • max: 230 tokens
    • min: 34 tokens
    • mean: 148.79 tokens
    • max: 230 tokens
    • 0: ~75.30%
    • 1: ~24.70%
  • Samples:
    sentence1 sentence2 score
    1952: Born on April 10 in Lansing, Michigan 1974: Promoted to shodan in aikido 1975: First marriage with Miyako Fujitani
    1978: Born on February 7 in Cedar Rapids (Iowa) 1996: Attends the University of Iowa to study biochemistry 2000: Appears in the romantic comedy Coming Soon
    1967: Born on July 16 in Irvine, California 1990: Member of the comedy group The Groundlings 1990: University of Southern California, degree in sports information
  • Loss: CoSENTLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "pairwise_cos_sim"
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 192 evaluation samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 192 samples:
    sentence1 sentence2 score
    type string string int
    details
    • min: 38 tokens
    • mean: 150.14 tokens
    • max: 251 tokens
    • min: 38 tokens
    • mean: 155.21 tokens
    • max: 251 tokens
    • 0: ~75.00%
    • 1: ~25.00%
  • Samples:
    sentence1 sentence2 score
    1970: Born on 7 March in Westminster, London 1988: Graduated from Trinity Hall, Cambridge with upper second-class honours 1994: Stage debut in 'Design for Living'
    1970: born on March 7, 1970 in the Westminster district of London 1983: attended North London Collegiate School 1986: attended Benenden School
    1948: Born on December 21, 1948, in Washington, D.C. 1972: Earned a BA in drama from Morehouse College 1980: Made his professional theater debut in Mother Courage and Her Children at The Public Theater in New York City
  • Loss: CoSENTLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "pairwise_cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: epoch
  • per_device_eval_batch_size: 16
  • learning_rate: 3e-05
  • warmup_ratio: 0.1
  • fp16: True
  • load_best_model_at_end: True
  • ddp_find_unused_parameters: False

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: epoch
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 16
  • 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: 3e-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: 3
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.1
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: False
  • fp16: True
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: 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
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: False
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • dispatch_batches: None
  • split_batches: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss Validation Loss validation_spearman_cosine
0.1263 25 1.3871 - -
0.2525 50 0.9039 - -
0.3788 75 0.766 - -
0.5051 100 0.9601 - -
0.6313 125 0.2709 - -
0.7576 150 0.1721 - -
0.8838 175 0.3169 - -
1.0 198 - 1.2392 0.7227
1.0101 200 0.1533 - -
1.1364 225 0.0193 - -
1.2626 250 0.0494 - -
1.3889 275 0.0029 - -
1.5152 300 0.0173 - -
1.6414 325 0.0201 - -
1.7677 350 0.0031 - -
1.8939 375 0.2825 - -
2.0 396 - 1.0842 0.7196

Framework Versions

  • Python: 3.10.16
  • Sentence Transformers: 3.3.1
  • Transformers: 4.48.0
  • PyTorch: 2.4.0
  • Accelerate: 1.2.1
  • 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",
}

CoSENTLoss

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