README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - asymmetric
  - inference-free
  - 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: 0.8090849715672191
  energy_consumed: 0.0020815045242041953
  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: 0.019
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: Dual IDF 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: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.48
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.64
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.15999999999999998
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.11599999999999999
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.064
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.22
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.48
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.58
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.64
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.42806448797401003
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3595238095238096
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.36991983251424254
            name: Dot Map@100
          - type: query_active_dims
            value: 7.360000133514404
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9997588624554906
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 48.652191162109375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9984059959648087
            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: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.56
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.30666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.21
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04630877020110327
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.0756046838259871
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.08754950684817618
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.10356284427632172
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2778867231758672
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5051904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.12857109041882986
            name: Dot Map@100
          - type: query_active_dims
            value: 5.739999771118164
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9998119389367958
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 162.21571350097656
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9946852855808604
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.2
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.32
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.44
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.2
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.10666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.08800000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.06000000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.19
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.31
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.42
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.57
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.362900761644351
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.30826984126984125
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3052999960864357
            name: Dot Map@100
          - type: query_active_dims
            value: 10.420000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999658606903994
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 70.97537231445312
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9976746159388489
            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: 0.2933333333333334
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.44
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5266666666666667
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.2933333333333334
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1911111111111111
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15466666666666667
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11133333333333334
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.15210292340036777
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.28853489460866233
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3625165022827254
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.43785428142544053
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.35628399093140944
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.390994708994709
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.267930306339836
            name: Dot Map@100
          - type: query_active_dims
            value: 7.839999993642171
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9997431360987601
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 83.01258549629136
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9972802376811385
            name: Corpus Sparsity Ratio

Dual IDF trained on Natural-Questions tuples

This is a Asymmetric Inference-free 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 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: BertTokenizerFast)
    (document_0_IDF): IDF ({'frozen': False}, dim:30522, tokenizer: BertTokenizerFast)
  )
)

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/dual-inference-free-1e-3-lr")
# Run inference
sentences = [
    'is send in the clowns from a musical',
    '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]',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 30522)

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

Evaluation

Metrics

Sparse Information Retrieval

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

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ
dot_accuracy@1	0.22	0.46	0.2
dot_accuracy@3	0.48	0.52	0.32
dot_accuracy@5	0.58	0.56	0.44
dot_accuracy@10	0.64	0.62	0.6
dot_precision@1	0.22	0.46	0.2
dot_precision@3	0.16	0.3067	0.1067
dot_precision@5	0.116	0.26	0.088
dot_precision@10	0.064	0.21	0.06
dot_recall@1	0.22	0.0463	0.19
dot_recall@3	0.48	0.0756	0.31
dot_recall@5	0.58	0.0875	0.42
dot_recall@10	0.64	0.1036	0.57
dot_ndcg@10	0.4281	0.2779	0.3629
dot_mrr@10	0.3595	0.5052	0.3083
dot_map@100	0.3699	0.1286	0.3053
query_active_dims	7.36	5.74	10.42
query_sparsity_ratio	0.9998	0.9998	0.9997
corpus_active_dims	48.6522	162.2157	70.9754
corpus_sparsity_ratio	0.9984	0.9947	0.9977

Sparse Nano BEIR

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

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

Metric	Value
dot_accuracy@1	0.2933
dot_accuracy@3	0.44
dot_accuracy@5	0.5267
dot_accuracy@10	0.62
dot_precision@1	0.2933
dot_precision@3	0.1911
dot_precision@5	0.1547
dot_precision@10	0.1113
dot_recall@1	0.1521
dot_recall@3	0.2885
dot_recall@5	0.3625
dot_recall@10	0.4379
dot_ndcg@10	0.3563
dot_mrr@10	0.391
dot_map@100	0.2679
query_active_dims	7.84
query_sparsity_ratio	0.9997
corpus_active_dims	83.0126
corpus_sparsity_ratio	0.9973

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,
      "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,
      "lambda_query": 0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 0.001
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• batch_sampler: no_duplicates
• router_mapping: {'query': 'query', 'answer': 'document'}

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• 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: 0.001
• 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: {}

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
0.0129	20	1.4602	-	-	-	-	-
0.0259	40	1.475	-	-	-	-	-
0.0388	60	1.4423	-	-	-	-	-
0.0517	80	1.3811	-	-	-	-	-
0.0646	100	1.3892	-	-	-	-	-
0.0776	120	1.3915	-	-	-	-	-
0.0905	140	1.3578	-	-	-	-	-
0.1034	160	1.3228	-	-	-	-	-
0.1164	180	1.4135	-	-	-	-	-
0.1293	200	1.3201	1.4134	0.3888	0.2746	0.3329	0.3321
0.1422	220	1.3075	-	-	-	-	-
0.1551	240	1.2517	-	-	-	-	-
0.1681	260	1.3211	-	-	-	-	-
0.1810	280	1.2643	-	-	-	-	-
0.1939	300	1.2157	-	-	-	-	-
0.2069	320	1.2574	-	-	-	-	-
0.2198	340	1.2402	-	-	-	-	-
0.2327	360	1.2648	-	-	-	-	-
0.2456	380	1.2618	-	-	-	-	-
0.2586	400	1.1786	1.2860	0.4112	0.2775	0.3467	0.3451
0.2715	420	1.1676	-	-	-	-	-
0.2844	440	1.2259	-	-	-	-	-
0.2973	460	1.196	-	-	-	-	-
0.3103	480	1.1637	-	-	-	-	-
0.3232	500	1.1513	-	-	-	-	-
0.3361	520	1.1434	-	-	-	-	-
0.3491	540	1.1363	-	-	-	-	-
0.3620	560	1.2238	-	-	-	-	-
0.3749	580	1.1308	-	-	-	-	-
0.3878	600	1.1721	1.1986	0.4374	0.2821	0.3757	0.3651
0.4008	620	1.132	-	-	-	-	-
0.4137	640	1.0576	-	-	-	-	-
0.4266	660	1.084	-	-	-	-	-
0.4396	680	1.1129	-	-	-	-	-
0.4525	700	1.1029	-	-	-	-	-
0.4654	720	1.0382	-	-	-	-	-
0.4783	740	1.0705	-	-	-	-	-
0.4913	760	1.0797	-	-	-	-	-
0.5042	780	1.0042	-	-	-	-	-
0.5171	800	1.0494	1.1380	0.4382	0.2773	0.3736	0.3631
0.5301	820	1.0712	-	-	-	-	-
0.5430	840	1.0126	-	-	-	-	-
0.5559	860	1.0747	-	-	-	-	-
0.5688	880	1.0293	-	-	-	-	-
0.5818	900	1.0129	-	-	-	-	-
0.5947	920	1.0257	-	-	-	-	-
0.6076	940	0.9716	-	-	-	-	-
0.6206	960	1.0351	-	-	-	-	-
0.6335	980	0.9991	-	-	-	-	-
0.6464	1000	0.9438	1.0958	0.4272	0.2760	0.3559	0.3530
0.6593	1020	0.996	-	-	-	-	-
0.6723	1040	0.9851	-	-	-	-	-
0.6852	1060	1.0347	-	-	-	-	-
0.6981	1080	1.0152	-	-	-	-	-
0.7111	1100	0.9757	-	-	-	-	-
0.7240	1120	0.9727	-	-	-	-	-
0.7369	1140	1.007	-	-	-	-	-
0.7498	1160	1.0072	-	-	-	-	-
0.7628	1180	1.0113	-	-	-	-	-
0.7757	1200	1.0297	1.0682	0.4204	0.2734	0.3568	0.3502
0.7886	1220	0.9995	-	-	-	-	-
0.8016	1240	0.9866	-	-	-	-	-
0.8145	1260	0.9517	-	-	-	-	-
0.8274	1280	1.005	-	-	-	-	-
0.8403	1300	0.9981	-	-	-	-	-
0.8533	1320	0.9861	-	-	-	-	-
0.8662	1340	0.9802	-	-	-	-	-
0.8791	1360	0.9841	-	-	-	-	-
0.8920	1380	0.9591	-	-	-	-	-
0.9050	1400	0.9788	1.0540	0.4295	0.2731	0.3629	0.3552
0.9179	1420	0.9513	-	-	-	-	-
0.9308	1440	0.93	-	-	-	-	-
0.9438	1460	1.0113	-	-	-	-	-
0.9567	1480	0.9854	-	-	-	-	-
0.9696	1500	0.9736	-	-	-	-	-
0.9825	1520	0.9361	-	-	-	-	-
0.9955	1540	1.0048	-	-	-	-	-
-1	-1	-	-	0.4281	0.2779	0.3629	0.3563

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.002 kWh
• Carbon Emitted: 0.001 kg of CO2
• Hours Used: 0.019 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: 4.52.3
• 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}
    }