README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - asymmetric
  - inference-free
  - splade
  - generated_from_trainer
  - dataset_size:99000
  - loss:SpladeLoss
  - loss:SparseMultipleNegativesRankingLoss
  - loss:FlopsLoss
widget:
  - text: >-
      Rollin' (Limp Bizkit song) The music video was filmed atop the South Tower
      of the former World Trade Center in New York City. The introduction
      features Ben Stiller and Stephen Dorff mistaking Fred Durst for the valet
      and giving him the keys to their Bentley Azure. Also making a cameo is
      break dancer Mr. Wiggles. The rest of the video has several cuts to Durst
      and his bandmates hanging out of the Bentley as they drive about
      Manhattan. The song Ben Stiller is playing at the beginning is "My
      Generation" from the same album. The video also features scenes of Fred
      Durst with five girls dancing in a room. The video was filmed around the
      same time as the film Zoolander, which explains Stiller and Dorff's
      appearance. Fred Durst has a small cameo in that film.
  - text: >-
      Maze Runner: The Death Cure On April 22, 2017, the studio delayed the
      release date once again, to February 9, 2018, in order to allow more time
      for post-production; months later, on August 25, the studio moved the
      release forward two weeks.[17] The film will premiere on January 26, 2018
      in 3D, IMAX and IMAX 3D.[18][19]
  - text: who played the dj in the movie the warriors
  - text: >-
      Lionel Messi Born and raised in central Argentina, Messi was diagnosed
      with a growth hormone deficiency as a child. At age 13, he relocated to
      Spain to join Barcelona, who agreed to pay for his medical treatment.
      After a fast progression through Barcelona's youth academy, Messi made his
      competitive debut aged 17 in October 2004. Despite being injury-prone
      during his early career, he established himself as an integral player for
      the club within the next three years, finishing 2007 as a finalist for
      both the Ballon d'Or and FIFA World Player of the Year award, a feat he
      repeated the following year. His first uninterrupted campaign came in the
      2008–09 season, during which he helped Barcelona achieve the first
      treble in Spanish football. At 22 years old, Messi won the Ballon d'Or and
      FIFA World Player of the Year award by record voting margins.
  - text: >-
      Send In the Clowns "Send In the Clowns" is a song written by Stephen
      Sondheim for the 1973 musical A Little Night Music, an adaptation of
      Ingmar Bergman's film Smiles of a Summer Night. It is a ballad from Act
      Two, in which the character Desirée reflects on the ironies and
      disappointments of her life. Among other things, she looks back on an
      affair years earlier with the lawyer Fredrik, who was deeply in love with
      her but whose marriage proposals she had rejected. Meeting him after so
      long, she realizes she is in love with him and finally ready to marry him,
      but now it is he who rejects her: he is in an unconsummated marriage with
      a much younger woman. Desirée proposes marriage to rescue him from this
      situation, but he declines, citing his dedication to his bride. Reacting
      to his rejection, Desirée sings this song. The song is later reprised as a
      coda after Fredrik's young wife runs away with his son, and Fredrik is
      finally free to accept Desirée's offer.[1]
datasets:
  - sentence-transformers/natural-questions
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
  - query_active_dims
  - query_sparsity_ratio
  - corpus_active_dims
  - corpus_sparsity_ratio
co2_eq_emissions:
  emissions: 40.32092414763781
  energy_consumed: 0.10373222712421808
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.271
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: >-
      Inference-free SPLADE distilbert-base-uncased trained on Natural-Questions
      tuples
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.124
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.32
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.52
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.62
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5423437640649257
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.46220634920634923
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.46993244404328005
            name: Dot Map@100
          - type: query_active_dims
            value: 7.21999979019165
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999763449322122
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 55.45885467529297
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9981829875278392
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.46
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.52
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.36666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.24200000000000002
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04383405927588812
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07406949762623444
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.08852725075885176
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.11263403679653615
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.31346960788721207
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4925
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.13315774123427984
            name: Dot Map@100
          - type: query_active_dims
            value: 5.659999847412109
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9998145599945151
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 68.93396759033203
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9977414989977612
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.34
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.76
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.34
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.078
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.33
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.55
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.64
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5246562093175895
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.47938095238095235
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4679694682232657
            name: Dot Map@100
          - type: query_active_dims
            value: 10.319999694824219
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9996618832417657
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 48.96862030029297
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9983956287169815
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: dot_accuracy@1
            value: 0.37333333333333335
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5333333333333333
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6066666666666668
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7200000000000001
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.37333333333333335
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24444444444444444
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19333333333333336
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13333333333333333
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.23127801975862938
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.3813564992087448
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4495090835862839
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5375446789321787
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.46015652708990906
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4780291005291006
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.35701988450027516
            name: Dot Map@100
          - type: query_active_dims
            value: 7.733333110809326
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999746630852801
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 56.004758931296756
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9981651019287301
            name: Corpus Sparsity Ratio

Inference-free SPLADE distilbert-base-uncased trained on Natural-Questions tuples

This is a Asymmetric Inference-free SPLADE Sparse Encoder model trained on the natural-questions dataset using the sentence-transformers library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

• Model Type: Asymmetric Inference-free SPLADE Sparse Encoder
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 30522 dimensions
• Similarity Function: Dot Product
• Training Dataset:
  • natural-questions
• Language: en
• License: apache-2.0

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Sparse Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sparse Encoders on Hugging Face

Full Model Architecture

SparseEncoder(
  (0): Router(
    (query_0_IDF): IDF ({'frozen': False}, dim:30522, tokenizer: DistilBertTokenizerFast)
    (document_0_MLMTransformer): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False}) with MLMTransformer model: DistilBertForMaskedLM 
    (document_1_SpladePooling): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
  )
)

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 SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/inference-free-splade-distilbert-base-uncased-nq")
# Run inference
queries = [
    "is send in the clowns from a musical",
]
documents = [
    'Send In the Clowns "Send In the Clowns" is a song written by Stephen Sondheim for the 1973 musical A Little Night Music, an adaptation of Ingmar Bergman\'s film Smiles of a Summer Night. It is a ballad from Act Two, in which the character Desirée reflects on the ironies and disappointments of her life. Among other things, she looks back on an affair years earlier with the lawyer Fredrik, who was deeply in love with her but whose marriage proposals she had rejected. Meeting him after so long, she realizes she is in love with him and finally ready to marry him, but now it is he who rejects her: he is in an unconsummated marriage with a much younger woman. Desirée proposes marriage to rescue him from this situation, but he declines, citing his dedication to his bride. Reacting to his rejection, Desirée sings this song. The song is later reprised as a coda after Fredrik\'s young wife runs away with his son, and Fredrik is finally free to accept Desirée\'s offer.[1]',
    'The Suite Life on Deck The Suite Life on Deck is an American sitcom that aired on Disney Channel from September 26, 2008 to May 6, 2011. It is a sequel/spin-off of the Disney Channel Original Series The Suite Life of Zack & Cody. The series follows twin brothers Zack and Cody Martin and hotel heiress London Tipton in a new setting, the SS Tipton, where they attend classes at "Seven Seas High School" and meet Bailey Pickett while Mr. Moseby manages the ship. The ship travels around the world to nations such as Italy, France, Greece, India, Sweden and the United Kingdom where the characters experience different cultures, adventures, and situations.[1]',
    'Money in the Bank ladder match The first match was contested in 2005 at WrestleMania 21, after being invented (in kayfabe) by Chris Jericho.[1] At the time, it was exclusive to wrestlers of the Raw brand, and Edge won the inaugural match.[1] From then until 2010, the Money in the Bank ladder match, now open to all WWE brands, became a WrestleMania mainstay. 2010 saw a second and third Money in the Bank ladder match when the Money in the Bank pay-per-view debuted in July. Unlike the matches at WrestleMania, this new event featured two such ladder matches – one each for a contract for the WWE Championship and World Heavyweight Championship, respectively.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 30522] [3, 30522]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[8.9836, 0.0000, 0.0000]])

Evaluation

Metrics

Sparse Information Retrieval

• Datasets: NanoMSMARCO, NanoNFCorpus and NanoNQ
• Evaluated with SparseInformationRetrievalEvaluator

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ
dot_accuracy@1	0.32	0.46	0.34
dot_accuracy@3	0.52	0.5	0.58
dot_accuracy@5	0.62	0.52	0.68
dot_accuracy@10	0.8	0.6	0.76
dot_precision@1	0.32	0.46	0.34
dot_precision@3	0.1733	0.3667	0.1933
dot_precision@5	0.124	0.32	0.136
dot_precision@10	0.08	0.242	0.078
dot_recall@1	0.32	0.0438	0.33
dot_recall@3	0.52	0.0741	0.55
dot_recall@5	0.62	0.0885	0.64
dot_recall@10	0.8	0.1126	0.7
dot_ndcg@10	0.5423	0.3135	0.5247
dot_mrr@10	0.4622	0.4925	0.4794
dot_map@100	0.4699	0.1332	0.468
query_active_dims	7.22	5.66	10.32
query_sparsity_ratio	0.9998	0.9998	0.9997
corpus_active_dims	55.4589	68.934	48.9686
corpus_sparsity_ratio	0.9982	0.9977	0.9984

Sparse Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with SparseNanoBEIREvaluator with these parameters:

  {
      "dataset_names": [
          "msmarco",
          "nfcorpus",
          "nq"
      ]
  }
  

Metric	Value
dot_accuracy@1	0.3733
dot_accuracy@3	0.5333
dot_accuracy@5	0.6067
dot_accuracy@10	0.72
dot_precision@1	0.3733
dot_precision@3	0.2444
dot_precision@5	0.1933
dot_precision@10	0.1333
dot_recall@1	0.2313
dot_recall@3	0.3814
dot_recall@5	0.4495
dot_recall@10	0.5375
dot_ndcg@10	0.4602
dot_mrr@10	0.478
dot_map@100	0.357
query_active_dims	7.7333
query_sparsity_ratio	0.9997
corpus_active_dims	56.0048
corpus_sparsity_ratio	0.9982

Training Details

Training Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 99,000 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 11.71 tokens max: 26 tokens	min: 4 tokens mean: 131.81 tokens max: 450 tokens

• Samples:

  query	answer
  who played the father in papa don't preach	Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.
  where was the location of the battle of hastings	Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.
  how many puppies can a dog give birth to	Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]

• Loss: SpladeLoss with these parameters:

  {
      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
      "lambda_corpus": 0.003,
      "lambda_query": 0
  }
  

Evaluation Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 1,000 evaluation samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 11.69 tokens max: 23 tokens	min: 15 tokens mean: 134.01 tokens max: 512 tokens

• Samples:

  query	answer
  where is the tiber river located in italy	Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.
  what kind of car does jay gatsby drive	Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.
  who sings if i can dream about you	I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]

• Loss: SpladeLoss with these parameters:

  {
      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
      "lambda_corpus": 0.003,
      "lambda_query": 0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• batch_sampler: no_duplicates
• router_mapping: {'query': 'query', 'answer': 'document'}
• learning_rate_mapping: {'IDF\.weight': 0.001}

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• 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: 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: 1
• 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: 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
• 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
• router_mapping: {'query': 'query', 'answer': 'document'}
• learning_rate_mapping: {'IDF\.weight': 0.001}

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10
0.0323	200	0.2453	-	-	-	-	-
0.0646	400	0.0873	0.1016	0.5390	0.3208	0.5273	0.4624
0.0970	600	0.0705	-	-	-	-	-
0.1293	800	0.0605	0.0824	0.5449	0.3297	0.4931	0.4559
0.1616	1000	0.0606	-	-	-	-	-
0.1939	1200	0.0672	0.0826	0.5335	0.3240	0.5067	0.4547
0.2262	1400	0.0768	-	-	-	-	-
0.2586	1600	0.0836	0.0861	0.5213	0.3276	0.5354	0.4614
0.2909	1800	0.0783	-	-	-	-	-
0.3232	2000	0.0832	0.1030	0.5214	0.3142	0.4775	0.4377
0.3555	2200	0.0857	-	-	-	-	-
0.3878	2400	0.0851	0.0919	0.4909	0.3175	0.5332	0.4472
0.4202	2600	0.0848	-	-	-	-	-
0.4525	2800	0.0804	0.0950	0.5247	0.3179	0.5316	0.4581
0.4848	3000	0.0763	-	-	-	-	-
0.5171	3200	0.0781	0.0925	0.5350	0.3261	0.5254	0.4621
0.5495	3400	0.0816	-	-	-	-	-
0.5818	3600	0.0762	0.0893	0.5068	0.3171	0.5149	0.4462
0.6141	3800	0.0821	-	-	-	-	-
0.6464	4000	0.0733	0.0909	0.5523	0.3268	0.5435	0.4742
0.6787	4200	0.0772	-	-	-	-	-
0.7111	4400	0.0707	0.0868	0.5320	0.3104	0.5008	0.4477
0.7434	4600	0.0694	-	-	-	-	-
0.7757	4800	0.0733	0.0930	0.5369	0.3047	0.5012	0.4476
0.8080	5000	0.0693	-	-	-	-	-
0.8403	5200	0.0726	0.0863	0.5458	0.3095	0.5261	0.4605
0.8727	5400	0.0686	-	-	-	-	-
0.9050	5600	0.0634	0.0844	0.5479	0.3142	0.5361	0.4661
0.9373	5800	0.0656	-	-	-	-	-
0.9696	6000	0.0655	0.0828	0.5434	0.3134	0.5214	0.4594
-1	-1	-	-	0.5423	0.3135	0.5247	0.4602

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.104 kWh
• Carbon Emitted: 0.040 kg of CO2
• Hours Used: 0.271 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 4.2.0.dev0
• Transformers: 4.52.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.1
• Datasets: 2.21.0
• Tokenizers: 0.21.1

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",
}

SpladeLoss

@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}

SparseMultipleNegativesRankingLoss

@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}
}

FlopsLoss

@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
    }