poly-headline / README.md
dkcodes's picture
Add new SentenceTransformer model
02f54d6 verified
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:21473
  - loss:MultipleNegativesRankingLoss
base_model: google/embeddinggemma-300m
widget:
  - source_sentence: USGS reports all earthquakes below magnitude 8.0 this quarter
    sentences:
      - >-
        Megaquake by September 30? A "megaquake" is defined as an earthquake
        with a magnitude of 8.0 or greater. This market will resolve to “Yes” if
        1 or more earthquakes with a magnitude of 8.0 or higher occur anywhere
        on Earth between July 30 and September 30, 2025, 11:59 PM ET. Otherwise,
        this market will resolve to “No”. The resolution source for this market
        is the United States Geological Survey (USGS) Earthquake Hazards Program
        (https://earthquake.usgs.gov/earthquakes/browse/significant.php#sigdef).
        If an earthquake of substantial size has occurred within this market's
        timeframe but not yet appeared on the resolution source, this market may
        remain open until October 7, 2025, 11:59 PM ET, or until the earthquake
        in question otherwise appears on the resolution source. If such an
        earthquake has not appeared on the resolution source by that date,
        another credible resolution source will be used. After a qualifying
        earthquake is registered, this market will remain open for 24 hours to
        account for any revisions to its recorded magnitude. After 24 hours,
        this market will resolve according to the latest provided data.
      - >-
        Will "Elio" Opening Weekend Box Office be less than $20m? This market
        will resolve according to how much “Elio” (2025) will gross domestically
        on its opening weekend. The “Box Office”
        https://www.the-numbers.com/movie/Elio(2025)#tab=box-office will be used
        to resolve this market once the values for the 3-day opening weekend
        (June 20 - June 22) are final (i.e. not studio estimates). If the
        reported value falls exactly between two brackets, then this market will
        resolve to the higher range bracket. Please note, this market will
        resolve according to the The Numbers figures provided under Weekend Box
        Office Performance for the 3-day weekend (which typically includes
        Thursday's previews), regardless of whether domestic refers to only the
        USA, or to USA and Canada, etc. If there is no final data available by
        June 30, 2025, 11:59 PM ET, another credible resolution source will be
        chosen.
      - >-
        Researchers Explore Correlation Between Solar Activity and Seismic
        Events
  - source_sentence: VCT Americas Kickoff concludes with Team X
    sentences:
      - >-
        Will PNAS retract Dan Ariely’s 2012 paper on dishonesty by October 1,
        2021? This market will resolve to “Yes” if the Proceedings of the
        National Academy of Sciences issues a formal retraction for Dan Ariely’s
        2012 paper “Signing at the beginning makes ethics salient and decreases
        dishonest self-reports in comparison to signing at the end”,
        https://www.pnas.org/content/109/38/15197.short, on or before October 1,
        2021, 11:59:59 PM ET. This retraction may be initiated by either PNAS or
        the original authors of the article. Otherwise, this market will resolve
        to “No.” Note: corrections and partial retractions will also resolve to
        “No.” Only a full retraction of the article will count. The resolution
        source for this market will be official announcements from the
        Proceedings of the National Academy of Science, see here for a list of
        retractions https://www.pnas.org/retractions. In the event of ambiguity
        in terms of the market outcome, the market will be resolved in good
        faith at the sole discretion of the Markets Integrity Committee (MIC).
      - Emerging Valorant Rosters to Watch Ahead of 2025 VCT Events
      - >-
        Will 2GAME Esports win the VCT 2025 Americas Kickoff? VCT 2025: Americas
        Kickoff is scheduled to take place January 16 - February 8, 2025. Find
        more information about the tournament here:
        liquipedia.net/valorant/VCT/2025/Americas_League/Kickoff. This market
        will resolve to “Yes” if 2GAME Esports wins this tournament. Otherwise,
        this market will resolve to “No”. If this team is eliminated from the
        competition based on the official rules of the tournament, this market
        will resolve to “No”. If the winner of VCT 2025: Americas Kickoff is not
        determined by February 31, 2025, 11:59 PM ET, this market will resolve
        to “No”. The primary resolution source for this market is official
        information provided directly from the VCT (e.g.,
        valorantesports.com/en-US) and official footage of the tournament.
        However, other credible reporting may also be used.
  - source_sentence: >-
      Japan’s Central Election Management Council announces Constitutional
      Democratic Party leads in seats
    sentences:
      - >-
        MLB: Who will win Toronto Blue Jays v. Tampa Bay Rays, scheduled for
        August 2, 7:10 PM ET? In the upcoming MLB game scheduled for August 2,
        7:10 PM ET: If the Toronto Blue Jays win, this market will resolve to
        “Blue Jays”. If the Tampa Bay Rays win, this market will resolve to
        “Rays”. If the game is not completed by August 9 (11:59:59 PM ET), this
        market will resolve 50-50.
      - >-
        Will the Constitutional Democratic Party win the most seats in the 2024
        Japanese general election? Early general elections are scheduled to be
        held in Japan on 27 October 2024. This market will resolve to "Yes" if
        the Constitutional Democratic Party (立憲民主党, Rikken-minshutō) controls a
        greater number of seats in the House of Representatives of the National
        Diet of Japan than any other party after the results of the 2024
        Japanese general election are finalized. Otherwise, this market will
        resolve to "No". If the results of this election aren't known by
        December 31, 2024, 11:59 PM ET, this market will resolve to "No". In the
        case of a tie between this party and any other for the most seats
        controlled, this market will resolve in favor of the party whose listed
        name comes first in alphabetical order using the English translation
        version of party names. This market's resolution will be based solely on
        the number of seats won by the listed party, not any coalition or
        alliance of which it may be a part. The primary resolution source for
        this market will be official information from the Japanese government,
        specifically the Central Election Management Council. However, a
        consensus of credible media reports will also suffice to resolve this
        market.
      - >-
        Tokyo Hosts Annual Democracy Forum Highlighting Japan’s Political
        History
  - source_sentence: US Open official cancels Pegula versus Muchova semifinal match
    sentences:
      - >-
        US Open: Pegula vs. Muchova Jessica Pegula and Karolina Muchova are
        scheduled to play each other in a semifinal matchup in the US Open
        Women’s Singles Tournament on September 5, 2024, at 8:30 PM ET. This
        market will resolve to “Pegula” if Jessica Pegula wins her match against
        Karolina Muchova in the semifinals of the US Open Women’s Singles
        tournament. This market will resolve to “Muchova” if Karolina Muchova
        wins her match against Jessica Pegula in the semifinals of the US Open
        Women’s Singles tournament. If the match ends in a tie, is canceled, or
        delayed beyond September 12, 2024, this market will resolve to 50-50.
        The primary resolution source for this market will be official
        information from the US Open (ex: https://www.usopen.org/index.html)
        including live footage, however a consensus of credible reporting may
        also be used.
      - >-
        Megaquake in September? A "megaquake" is defined as an earthquake with a
        magnitude of 8.0 or greater. This market will resolve to “Yes” if 1 or
        more earthquakes with a magnitude of 8.0 or higher occur anywhere on
        earth between September 2 and September 30, 2024, 11:59 PM ET. Otherwise
        this market will resolve to “No”. The resolution source for this market
        is the United States Geological Survey (USGS) Earthquake hazards program
        (https://earthquake.usgs.gov/earthquakes/browse/significant.php#sigdef).
        If an earthquake of substantial size has occurred within this market's
        timeframe but not yet appeared on the resolution source, this market may
        remain open until October 7, 2024, 11:59 PM ET, or until the earthquake
        in question otherwise appears on the resolution source. If such an
        earthquake has not appeared on the resolution source by that date,
        another credible resolution source will be used.
      - Jessica Pegula Trains with New Coach Ahead of Upcoming Tennis Season
  - source_sentence: Binance adds $SMOLE to its spot crypto exchange
    sentences:
      - >-
        $SMOLE listed on Binance in March? This market will resolve to "Yes" if
        the crypto token smolecoin ($SMOLE) is listed for spot purchase on
        Binance by March 31, 2024, 11:59 PM ET. Otherwise, this market will
        resolve to "No". The primary resolution source for this market will be
        Binance, however a consensus of credible reporting will also be used.
      - >-
        Historical Overview: Binance’s Impact on Global Cryptocurrency Trading
        Since 2017
      - >-
        FDA approves PTC Therapeutics’ Vatiquinone for Friedreich’s ataxia? This
        market will resolve to "Yes" if the U.S. Food and Drug Administration
        (FDA) grants full or conditional approval for PTC Therapeutics’
        Vatiquinone as a treatment for Friedreich’s ataxia by August 31, 2025,
        11:59 PM ET. Otherwise, this market will resolve to "No." An approval is
        defined as: For new drugs: FDA issuance of an approval letter for a New
        Drug Application (NDA) or Biologics License Application (BLA) For
        already-marketed drugs seeking new indications: FDA approval of a
        supplemental NDA (sNDA) or supplemental BLA (sBLA) for the specific
        indication referenced For generic drugs: FDA approval of an Abbreviated
        New Drug Application (ANDA) For biosimilars: FDA approval of a 351(k)
        application The following constitute qualifying approvals: Standard
        approval (traditional approval based on clinical benefit), Accelerated
        approval (based on surrogate endpoints), Approval with Risk Evaluation
        and Mitigation Strategy (REMS), Approval with restricted distribution or
        indication limitations, except compassionate use/expanded access
        programs The following do not constitute qualifying approvals:
        Approvable letters that require additional actions before approval
        Tentative approvals pending patent or exclusivity expiration FDA
        requests for additional information or studies Extension of Prescription
        Drug User Fee Amendments dates Approval for compassionate use or
        expanded access programs only Approval only for export or for use
        outside the United States Emergency Use Authorization (EUA) without full
        approval Complete Response Letters (CRLs) indicating the application
        cannot be approved in its current form This market will immediately
        resolve to "No" if the FDA issues a Complete Response Letter (CRL) or
        explicitly declines to approve the application. If the drug sponsor
        withdraws the application before the end of the month, the market will
        resolve to "No" immediately. If the listed drug is approved before the
        end of the month, the market will resolve to "Yes," regardless of
        potential Advisory Committee votes against approval or later withdrawal
        of approval. Conditional approvals may include post-marketing
        requirements or commitments and still qualify. The primary resolution
        source will be official information from the FDA; however, a consensus
        of credible reporting will also be used.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on google/embeddinggemma-300m
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: base eval
          type: base_eval
        metrics:
          - type: cosine_accuracy
            value: 0.9233456254005432
            name: Cosine Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: test eval
          type: test_eval
        metrics:
          - type: cosine_accuracy
            value: 0.9998137354850769
            name: Cosine Accuracy

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m. 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: google/embeddinggemma-300m
  • Maximum Sequence Length: 2048 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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("dkcodes/poly-headline")
# Run inference
queries = [
    "Binance adds $SMOLE to its spot crypto exchange",
]
documents = [
    '$SMOLE listed on Binance in March? This market will resolve to "Yes" if the crypto token smolecoin ($SMOLE) is listed for spot purchase on Binance by March 31, 2024, 11:59 PM ET. Otherwise, this market will resolve to "No". The primary resolution source for this market will be Binance, however a consensus of credible reporting will also be used.',
    'Historical Overview: Binance’s Impact on Global Cryptocurrency Trading Since 2017',
    'FDA approves PTC Therapeutics’ Vatiquinone for Friedreich’s ataxia? This market will resolve to "Yes" if the U.S. Food and Drug Administration (FDA) grants full or conditional approval for PTC Therapeutics’ Vatiquinone as a treatment for Friedreich’s ataxia by August 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No." An approval is defined as: For new drugs: FDA issuance of an approval letter for a New Drug Application (NDA) or Biologics License Application (BLA) For already-marketed drugs seeking new indications: FDA approval of a supplemental NDA (sNDA) or supplemental BLA (sBLA) for the specific indication referenced For generic drugs: FDA approval of an Abbreviated New Drug Application (ANDA) For biosimilars: FDA approval of a 351(k) application The following constitute qualifying approvals: Standard approval (traditional approval based on clinical benefit), Accelerated approval (based on surrogate endpoints), Approval with Risk Evaluation and Mitigation Strategy (REMS), Approval with restricted distribution or indication limitations, except compassionate use/expanded access programs The following do not constitute qualifying approvals: Approvable letters that require additional actions before approval Tentative approvals pending patent or exclusivity expiration FDA requests for additional information or studies Extension of Prescription Drug User Fee Amendments dates Approval for compassionate use or expanded access programs only Approval only for export or for use outside the United States Emergency Use Authorization (EUA) without full approval Complete Response Letters (CRLs) indicating the application cannot be approved in its current form This market will immediately resolve to "No" if the FDA issues a Complete Response Letter (CRL) or explicitly declines to approve the application. If the drug sponsor withdraws the application before the end of the month, the market will resolve to "No" immediately. If the listed drug is approved before the end of the month, the market will resolve to "Yes," regardless of potential Advisory Committee votes against approval or later withdrawal of approval. Conditional approvals may include post-marketing requirements or commitments and still qualify. The primary resolution source will be official information from the FDA; however, a consensus of credible reporting will also be used.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[     0.8807,     -0.0750,      0.0007]])

Evaluation

Metrics

Triplet

Metric base_eval test_eval
cosine_accuracy 0.9233 0.9998

Training Details

Training Dataset

Unnamed Dataset

  • Size: 21,473 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 7 tokens
    • mean: 12.65 tokens
    • max: 24 tokens
    • min: 53 tokens
    • mean: 165.55 tokens
    • max: 573 tokens
    • min: 9 tokens
    • mean: 14.39 tokens
    • max: 26 tokens
  • Samples:
    anchor positive negative
    Katy Perry confirms relationship with Justin Trudeau publicly Katy Perry and Justin Trudeau confirmed relationship by August 31? This market will resolve to "Yes" if Katy Perry and Justin Trudeau are confirmed to be in a romantic relationship by August 31, 2025, 11:59 PM ET. Otherwise, this market will resolve to "No". Confirmation must come directly from Katy Perry or Justin Trudeau or their official representative(s), and may come through public statements, social media posts, etc. Katy Perry Announces New Album Release Date Amid Busy Year
    Jalen Milroe selected with first overall pick in NFL Draft Will Jalen Milroe be drafted in the First Round? This market will resolve to "Yes" if Jalen Milroe, the QB from Alabama, is selected in the first round of the 2025 NFL Draft scheduled for for April 24, 2025, in Green Bay, Wisconsin. Otherwise, this market will resolve to "No". The resolution source will be the official broadcast of the 2025 NFL Draft. Expectations Rise for Quarterbacks Entering the 2025 NFL Draft
    Robert F. Kennedy Jr. confirms endorsement of Donald Trump RFK Jr. endorses Trump before November? This market will resolve to "Yes" if Robert F. Kennedy Jr. announces that he will vote for Donald Trump or formally endorses Trump for President of the United States by October 31, 2024, 11:59 PM ET. Otherwise this market will resolve to "No". The resolution source for this market will be official information from Robert F. Kennedy Jr. or one of his representatives. Donald Trump Addresses His Campaign Strategies in Latest Rally
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 5,369 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 7 tokens
    • mean: 12.79 tokens
    • max: 27 tokens
    • min: 51 tokens
    • mean: 166.5 tokens
    • max: 491 tokens
    • min: 9 tokens
    • mean: 14.36 tokens
    • max: 25 tokens
  • Samples:
    anchor positive negative
    NOAA confirms average global temperature breaks record Will August 2021 average global temperature be the highest August temperature on record? This is a market on whether the average global land and ocean surface temperature for August 2021 will be the highest August temperature since global records began in 1880. The resolution source for this market will be the Global Climate Report for August 2021, published by NOAA's National Centers for Environmental Information (https://www.ncdc.noaa.gov/sotc/global/2021). This market will resolve to “Yes” if, for the month of August 2021 averaged as a whole, global land and ocean surface temperature anomaly, as measured by U.S. National Oceanic and Atmospheric Administration, will be greater than 0.98°C (1.76°F) above the 20th century average of 15.6°C (60.1°F), and “No” otherwise. Past data for the month of August can be found here https://www.ncdc.noaa.gov/cag/global/time-series/globe/land_ocean/1/8/1880-2021. This market will resolve when data is first available for the month of August 2021. In ... Scientists Discuss Long-Term Trends in Global Temperature Variability
    Mavericks overcome Celtics in overtime 23rd Will the Celtics or the Mavericks win their February 23rd matchup? This is a market on which team will win the February 23rd, 2021 matchup between the Boston Celtics and the Dallas Mavericks. In the event this game is delayed for whatever reason, the resolution of this market will be delayed until the game takes place. In the extraordinarily unlikely event the game is canceled altogether, the market will resolve to 50/50. In the event of overtime, this market will resolve to the eventual winner. Results of this market will be decided by official scores available on https://www.nba.com/. NBA Analysts Discuss Rising Trends in Team Strategies Across the League
    Lakers win Game 4 against Suns in playoff series Who will win Suns vs. Lakers: Game 4? This is a market on who will win in the First Round, Game 4, NBA Playoff matchup between the Phoenix Suns and the Los Angeles Lakers, scheduled to take place at 3:30 PM ET May 30, 2021. This market will resolve to “Suns” if the Phoenix Suns win, and “Lakers” if the Los Angeles Lakers win. If the match is postponed to a date on or before June 6, 2021, 3:30 PM ET, the same market conditions will apply. If the match is postponed to a date after June 6, 2021, 3:30 PM ET or cancelled altogether, the market will resolve 50-50. In the event of ambiguity in terms of the market outcome, the market will be resolved in good faith at the sole discretion of the Markets Integrity Committee (MIC). Phoenix Suns Team Chemistry Highlighted in Postseason Analysis
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 32
  • learning_rate: 2e-05
  • num_train_epochs: 5
  • warmup_ratio: 0.1
  • prompts: task: search result | query:

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 8
  • 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: 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: 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: 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}
  • parallelism_config: 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: None
  • hub_always_push: False
  • hub_revision: None
  • 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
  • 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
  • liger_kernel_config: None
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: task: search result | query:
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step base_eval_cosine_accuracy test_eval_cosine_accuracy
-1 -1 0.9233 0.9998

Framework Versions

  • Python: 3.12.12
  • Sentence Transformers: 5.1.2
  • Transformers: 4.57.0.dev0
  • PyTorch: 2.8.0+cu126
  • Accelerate: 1.11.0
  • Datasets: 4.0.0
  • Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

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

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}
}