metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - csr
  - generated_from_trainer
  - dataset_size:3011496
  - loss:CSRLoss
  - loss:SparseMultipleNegativesRankingLoss
base_model: mixedbread-ai/mxbai-embed-large-v1
widget:
  - source_sentence: how much is a car title transfer in minnesota?
    sentences:
      - >-
        This complex is a larger molecule than the original crystal violet stain
        and iodine and is insoluble in water. ... Conversely, the the outer
        membrane of Gram negative bacteria is degraded and the thinner
        peptidoglycan layer of Gram negative cells is unable to retain the
        crystal violet-iodine complex and the color is lost.
      - >-
        Get insurance on the car and provide proof. Bring this information
        (including the title) to the Minnesota DVS office, as well as $10 for
        the filing fee and $7.25 for the titling fee. There is also a $10
        transfer tax, as well as a 6.5% sales tax on the purchase price.
      - >-
        One of the risks of DNP is that it accelerates the metabolism to a
        dangerously fast level. Our metabolic system operates at the rate it
        does for a reason – it is safe. Speeding up the metabolism may help burn
        off fat, but it can also trigger a number of potentially dangerous side
        effects, such as: fever.
  - source_sentence: what is the difference between 18 and 20 inch tires?
    sentences:
      - >-
        The only real difference is a 20" rim would be more likely to be
        damaged, as you pointed out. Beyond looks, there is zero benefit for the
        20" rim. Also, just the availability of tires will likely be much more
        limited for the larger rim. ... Tire selection is better for 18" wheels
        than 20" wheels.
      - >-
        ['Open your Outlook app on your mobile device and click on the Settings
        gear icon.', 'Under Settings, click on the Signature option.', 'Enter
        either a generic signature that could be used for all email accounts
        tied to your Outlook app, or a specific signature, Per Account
        Signature, for each email account.']
      - >-
        The average normal body temperature is around 98.6 degrees Fahrenheit,
        or 37 degrees Celsius. If your body temperature drops to just a few
        degrees lower than this, your blood vessels in your hands, feet, arms,
        and legs start to get narrower.
  - source_sentence: whom the bell tolls meaning?
    sentences:
      - >-
        Answer: Humans are depicted in Hindu art often in sensuous and erotic
        postures.
      - >-
        The phrase "For whom the bell tolls" refers to the church bells that are
        rung when a person dies. Hence, the author is suggesting that we should
        not be curious as to for whom the church bell is tolling for. It is for
        all of us.
      - '[''Automatically.'', ''When connected to car Bluetooth and,'', ''Manually.'']'
  - source_sentence: how long before chlamydia symptoms appear?
    sentences:
      - >-
        Most people who have chlamydia don't notice any symptoms. If you do get
        symptoms, these usually appear between 1 and 3 weeks after having
        unprotected sex with an infected person. For some people they don't
        develop until many months later. Sometimes the symptoms can disappear
        after a few days.
      - >-
        ['Open the My Verizon app . ... ', 'Tap the Menu icon. ... ', 'Tap
        Manage device for the appropriate mobile number. ... ', 'Tap Transfer
        content between phones. ... ', 'Tap Start Transfer.']
      - >-
        Psychiatrist vs Psychologist A psychiatrist is classed as a medical
        doctor, they include a physical examination of symptoms in their
        assessment and are able to prescribe medicine: a psychologist is also a
        doctor by virtue of their PHD level qualification, but is not medically
        trained and cannot prescribe.
  - source_sentence: are you human korean novela?
    sentences:
      - >-
        Many cysts heal on their own, which means that conservative treatments
        like rest and anti-inflammatory painkillers can often be enough to get
        rid of them. However, in some cases, routine drainage of the sac may be
        necessary to reduce symptoms.
      - >-
        A relative of European pear varieties like Bartlett and Anjou, the Asian
        pear is great used in recipes or simply eaten out of hand. It retains a
        crispness that works well in slaws and salads, and it holds its shape
        better than European pears when baked and cooked.
      - >-
        Are You Human? (Korean: 너도 인간이니; RR: Neodo Inganini; lit. Are You Human
        Too?) is a 2018 South Korean television series starring Seo Kang-jun and
        Gong Seung-yeon. It aired on KBS2's Mondays and Tuesdays at 22:00 (KST)
        time slot, from June 4 to August 7, 2018.
datasets:
  - sentence-transformers/gooaq
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
  - row_non_zero_mean_query
  - row_sparsity_mean_query
  - row_non_zero_mean_corpus
  - row_sparsity_mean_corpus
co2_eq_emissions:
  emissions: 352.04549733882556
  energy_consumed: 0.9056951014886098
  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: 2.117
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: Sparse CSR model trained on Natural Questions
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 128
          type: NanoMSMARCO_128
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.21333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.36
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.64
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6055413265295657
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5249365079365079
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5299802344587291
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 128
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.96875
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 128
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.96875
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 128
          type: NanoNFCorpus_128
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.52
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.32
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.27999999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.24600000000000002
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.0215204036359272
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.04799314214281322
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.06373415154707394
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.0979246816076223
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.28193067797046806
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4415793650793651
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.11047621170887942
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 128
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.96875
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 128
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.96875
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 128
          type: NanoNQ_128
        metrics:
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.37
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.54
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.62
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.73
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.54915705928894
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5041904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.49271607077427093
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 128
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.96875
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 128
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.96875
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 128
          type: NanoBEIR_mean_128
        metrics:
          - type: dot_accuracy@1
            value: 0.3666666666666667
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7733333333333334
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3666666666666667
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24444444444444446
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.18800000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.138
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2505068012119757
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.40933104738093773
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.47457805051569135
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5626415605358741
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.47887635459632455
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.49023544973544975
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3777241723139599
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 128
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.96875
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 128
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.96875
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 256
          type: NanoMSMARCO_256
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.21333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.44
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.64
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6593706160726032
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5844126984126984
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.587731189263798
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 256
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9375
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 256
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9375
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 256
          type: NanoNFCorpus_256
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.48
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3399999999999999
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.316
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.274
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.039388755003198654
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07303098045854087
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09531734035764254
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.13417588936034655
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3210896460550523
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.43734920634920627
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.14778423566638732
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 256
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9375
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 256
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9375
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 256
          type: NanoNQ_256
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.68
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.23333333333333336
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15200000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.086
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.63
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.77
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6014886386931141
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5650238095238095
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5493009547376917
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 256
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9375
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 256
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9375
            name: Row Sparsity Mean Corpus
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 256
          type: NanoBEIR_mean_256
        metrics:
          - type: dot_accuracy@1
            value: 0.39999999999999997
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6000000000000001
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6866666666666665
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8133333333333334
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.39999999999999997
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2622222222222222
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.20533333333333337
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.15
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2997962516677329
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.44767699348618023
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5051057801192141
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6013919631201156
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5273163002735899
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5289285714285713
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.428272126555959
            name: Dot Map@100
          - type: row_non_zero_mean_query
            value: 256
            name: Row Non Zero Mean Query
          - type: row_sparsity_mean_query
            value: 0.9375
            name: Row Sparsity Mean Query
          - type: row_non_zero_mean_corpus
            value: 256
            name: Row Non Zero Mean Corpus
          - type: row_sparsity_mean_corpus
            value: 0.9375
            name: Row Sparsity Mean Corpus

Sparse CSR model trained on Natural Questions

This is a CSR Sparse Encoder model finetuned from mixedbread-ai/mxbai-embed-large-v1 on the gooaq dataset using the sentence-transformers library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: CSR Sparse Encoder
Base model: mixedbread-ai/mxbai-embed-large-v1
Maximum Sequence Length: 512 tokens
Output Dimensionality: 4096 dimensions
Similarity Function: Dot Product
Training Dataset:
- gooaq
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): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30})
)

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/csr-mxbai-embed-large-v1-gooaq-1e-5-512bs")
# Run inference
sentences = [
    'are you human korean novela?',
    "Are You Human? (Korean: 너도 인간이니; RR: Neodo Inganini; lit. Are You Human Too?) is a 2018 South Korean television series starring Seo Kang-jun and Gong Seung-yeon. It aired on KBS2's Mondays and Tuesdays at 22:00 (KST) time slot, from June 4 to August 7, 2018.",
    'A relative of European pear varieties like Bartlett and Anjou, the Asian pear is great used in recipes or simply eaten out of hand. It retains a crispness that works well in slaws and salads, and it holds its shape better than European pears when baked and cooked.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 4096)

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

Evaluation

Metrics

Sparse Information Retrieval

Datasets: NanoMSMARCO_128, NanoNFCorpus_128 and NanoNQ_128
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "max_active_dims": 128
}
```

Metric	NanoMSMARCO_128	NanoNFCorpus_128	NanoNQ_128
dot_accuracy@1	0.36	0.36	0.38
dot_accuracy@3	0.64	0.46	0.58
dot_accuracy@5	0.74	0.52	0.66
dot_accuracy@10	0.86	0.68	0.78
dot_precision@1	0.36	0.36	0.38
dot_precision@3	0.2133	0.32	0.2
dot_precision@5	0.148	0.28	0.136
dot_precision@10	0.086	0.246	0.082
dot_recall@1	0.36	0.0215	0.37
dot_recall@3	0.64	0.048	0.54
dot_recall@5	0.74	0.0637	0.62
dot_recall@10	0.86	0.0979	0.73
dot_ndcg@10	0.6055	0.2819	0.5492
dot_mrr@10	0.5249	0.4416	0.5042
dot_map@100	0.53	0.1105	0.4927
row_non_zero_mean_query	128.0	128.0	128.0
row_sparsity_mean_query	0.9688	0.9688	0.9688
row_non_zero_mean_corpus	128.0	128.0	128.0
row_sparsity_mean_corpus	0.9688	0.9688	0.9688

Sparse Nano BEIR

Dataset: NanoBEIR_mean_128

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "max_active_dims": 128
}

Metric	Value
dot_accuracy@1	0.3667
dot_accuracy@3	0.56
dot_accuracy@5	0.64
dot_accuracy@10	0.7733
dot_precision@1	0.3667
dot_precision@3	0.2444
dot_precision@5	0.188
dot_precision@10	0.138
dot_recall@1	0.2505
dot_recall@3	0.4093
dot_recall@5	0.4746
dot_recall@10	0.5626
dot_ndcg@10	0.4789
dot_mrr@10	0.4902
dot_map@100	0.3777
row_non_zero_mean_query	128.0
row_sparsity_mean_query	0.9688
row_non_zero_mean_corpus	128.0
row_sparsity_mean_corpus	0.9688

Sparse Information Retrieval

Datasets: NanoMSMARCO_256, NanoNFCorpus_256 and NanoNQ_256
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "max_active_dims": 256
}
```

Metric	NanoMSMARCO_256	NanoNFCorpus_256	NanoNQ_256
dot_accuracy@1	0.44	0.32	0.44
dot_accuracy@3	0.64	0.48	0.68
dot_accuracy@5	0.74	0.6	0.72
dot_accuracy@10	0.9	0.72	0.82
dot_precision@1	0.44	0.32	0.44
dot_precision@3	0.2133	0.34	0.2333
dot_precision@5	0.148	0.316	0.152
dot_precision@10	0.09	0.274	0.086
dot_recall@1	0.44	0.0394	0.42
dot_recall@3	0.64	0.073	0.63
dot_recall@5	0.74	0.0953	0.68
dot_recall@10	0.9	0.1342	0.77
dot_ndcg@10	0.6594	0.3211	0.6015
dot_mrr@10	0.5844	0.4373	0.565
dot_map@100	0.5877	0.1478	0.5493
row_non_zero_mean_query	256.0	256.0	256.0
row_sparsity_mean_query	0.9375	0.9375	0.9375
row_non_zero_mean_corpus	256.0	256.0	256.0
row_sparsity_mean_corpus	0.9375	0.9375	0.9375

Sparse Nano BEIR

Dataset: NanoBEIR_mean_256

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "max_active_dims": 256
}

Metric	Value
dot_accuracy@1	0.4
dot_accuracy@3	0.6
dot_accuracy@5	0.6867
dot_accuracy@10	0.8133
dot_precision@1	0.4
dot_precision@3	0.2622
dot_precision@5	0.2053
dot_precision@10	0.15
dot_recall@1	0.2998
dot_recall@3	0.4477
dot_recall@5	0.5051
dot_recall@10	0.6014
dot_ndcg@10	0.5273
dot_mrr@10	0.5289
dot_map@100	0.4283
row_non_zero_mean_query	256.0
row_sparsity_mean_query	0.9375
row_non_zero_mean_corpus	256.0
row_sparsity_mean_corpus	0.9375

Training Details

Training Dataset

gooaq

Dataset: gooaq at b089f72
Size: 3,011,496 training samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.87 tokens
max: 23 tokens

min: 14 tokens
mean: 60.09 tokens
max: 201 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.87 tokens max: 23 tokens	min: 14 tokens mean: 60.09 tokens max: 201 tokens

Samples:

question	answer
`what is the difference between clay and mud mask?`	`The main difference between the two is that mud is a skin-healing agent, while clay is a cosmetic, drying agent. Clay masks are most useful for someone who has oily skin and is prone to breakouts of acne and blemishes.`
`myki how much on card?`	`A full fare myki card costs $6 and a concession, seniors or child myki costs $3. For more information about how to use your myki, visit ptv.vic.gov.au or call 1800 800 007.`
`how to find out if someone blocked your phone number on iphone?`	`If you get a notification like "Message Not Delivered" or you get no notification at all, that's a sign of a potential block. Next, you could try calling the person. If the call goes right to voicemail or rings once (or a half ring) then goes to voicemail, that's further evidence you may have been blocked.`

Loss: CSRLoss with these parameters:

{
    "beta": 0.1,
    "gamma": 1.0,
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}

Evaluation Dataset

gooaq

Dataset: gooaq at b089f72
Size: 1,000 evaluation samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.88 tokens
max: 22 tokens

min: 14 tokens
mean: 61.03 tokens
max: 127 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.88 tokens max: 22 tokens	min: 14 tokens mean: 61.03 tokens max: 127 tokens

Samples:

question	answer
`how do i program my directv remote with my tv?`	`['Press MENU on your remote.', 'Select Settings & Help > Settings > Remote Control > Program Remote.', 'Choose the device (TV, audio, DVD) you wish to program. ... ', 'Follow the on-screen prompts to complete programming.']`
`are rodrigues fruit bats nocturnal?`	`Before its numbers were threatened by habitat destruction, storms, and hunting, some of those groups could number 500 or more members. Sunrise, sunset. Rodrigues fruit bats are most active at dawn, at dusk, and at night.`
`why does your heart rate increase during exercise bbc bitesize?`	`During exercise there is an increase in physical activity and muscle cells respire more than they do when the body is at rest. The heart rate increases during exercise. The rate and depth of breathing increases - this makes sure that more oxygen is absorbed into the blood, and more carbon dioxide is removed from it.`

Loss: CSRLoss with these parameters:

{
    "beta": 0.1,
    "gamma": 1.0,
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
learning_rate: 1e-05
num_train_epochs: 1
warmup_ratio: 0.1
bf16: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
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: 1e-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: True
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: 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: 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
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_128_dot_ndcg@10	NanoNFCorpus_128_dot_ndcg@10	NanoNQ_128_dot_ndcg@10	NanoBEIR_mean_128_dot_ndcg@10	NanoMSMARCO_256_dot_ndcg@10	NanoNFCorpus_256_dot_ndcg@10	NanoNQ_256_dot_ndcg@10	NanoBEIR_mean_256_dot_ndcg@10
-1	-1	-	-	0.6421	0.2724	0.5528	0.4891	0.6425	0.2985	0.6194	0.5201
0.0170	100	0.5414	-	-	-	-	-	-	-	-	-
0.0340	200	0.5387	-	-	-	-	-	-	-	-	-
0.0510	300	0.5183	-	-	-	-	-	-	-	-	-
0.0680	400	0.5215	-	-	-	-	-	-	-	-	-
0.0850	500	0.5011	-	-	-	-	-	-	-	-	-
0.1020	600	0.5	-	-	-	-	-	-	-	-	-
0.1190	700	0.4885	-	-	-	-	-	-	-	-	-
0.1360	800	0.4777	0.3915	0.6173	0.2782	0.5465	0.4807	0.6406	0.3038	0.6318	0.5254
0.1530	900	0.4793	-	-	-	-	-	-	-	-	-
0.1700	1000	0.472	-	-	-	-	-	-	-	-	-
0.1870	1100	0.4679	-	-	-	-	-	-	-	-	-
0.2040	1200	0.4666	-	-	-	-	-	-	-	-	-
0.2210	1300	0.4569	-	-	-	-	-	-	-	-	-
0.2380	1400	0.4642	-	-	-	-	-	-	-	-	-
0.2550	1500	0.4611	-	-	-	-	-	-	-	-	-
0.272	1600	0.4537	0.3851	0.6314	0.266	0.5664	0.4879	0.6451	0.3238	0.6363	0.5351
0.2890	1700	0.4554	-	-	-	-	-	-	-	-	-
0.3060	1800	0.4475	-	-	-	-	-	-	-	-	-
0.3230	1900	0.4512	-	-	-	-	-	-	-	-	-
0.3400	2000	0.4522	-	-	-	-	-	-	-	-	-
0.3570	2100	0.4475	-	-	-	-	-	-	-	-	-
0.3740	2200	0.4499	-	-	-	-	-	-	-	-	-
0.3910	2300	0.4467	-	-	-	-	-	-	-	-	-
0.4080	2400	0.4467	0.3940	0.6264	0.2643	0.5719	0.4875	0.6092	0.3350	0.6363	0.5268
0.4250	2500	0.4477	-	-	-	-	-	-	-	-	-
0.4420	2600	0.4466	-	-	-	-	-	-	-	-	-
0.4590	2700	0.4436	-	-	-	-	-	-	-	-	-
0.4760	2800	0.4434	-	-	-	-	-	-	-	-	-
0.4930	2900	0.4437	-	-	-	-	-	-	-	-	-
0.5100	3000	0.4381	-	-	-	-	-	-	-	-	-
0.5270	3100	0.4426	-	-	-	-	-	-	-	-	-
0.5440	3200	0.4461	0.3850	0.5866	0.2857	0.5567	0.4763	0.6232	0.3313	0.6220	0.5255
0.5610	3300	0.4453	-	-	-	-	-	-	-	-	-
0.5780	3400	0.4361	-	-	-	-	-	-	-	-	-
0.5950	3500	0.436	-	-	-	-	-	-	-	-	-
0.6120	3600	0.4444	-	-	-	-	-	-	-	-	-
0.6290	3700	0.4405	-	-	-	-	-	-	-	-	-
0.6460	3800	0.4346	-	-	-	-	-	-	-	-	-
0.6630	3900	0.4345	-	-	-	-	-	-	-	-	-
0.6800	4000	0.4399	0.3857	0.5963	0.2898	0.5537	0.4800	0.6479	0.3129	0.6058	0.5222
0.6970	4100	0.434	-	-	-	-	-	-	-	-	-
0.7140	4200	0.4353	-	-	-	-	-	-	-	-	-
0.7310	4300	0.4277	-	-	-	-	-	-	-	-	-
0.7480	4400	0.4361	-	-	-	-	-	-	-	-	-
0.7650	4500	0.445	-	-	-	-	-	-	-	-	-
0.7820	4600	0.4331	-	-	-	-	-	-	-	-	-
0.7990	4700	0.4329	-	-	-	-	-	-	-	-	-
0.8160	4800	0.4336	0.3827	0.5929	0.2894	0.5617	0.4813	0.6444	0.3241	0.6120	0.5268
0.8330	4900	0.4319	-	-	-	-	-	-	-	-	-
0.8501	5000	0.4342	-	-	-	-	-	-	-	-	-
0.8671	5100	0.439	-	-	-	-	-	-	-	-	-
0.8841	5200	0.434	-	-	-	-	-	-	-	-	-
0.9011	5300	0.4396	-	-	-	-	-	-	-	-	-
0.9181	5400	0.4355	-	-	-	-	-	-	-	-	-
0.9351	5500	0.4326	-	-	-	-	-	-	-	-	-
0.9521	5600	0.4304	0.3810	0.6055	0.2819	0.5492	0.4789	0.6594	0.3211	0.6015	0.5273
0.9691	5700	0.4316	-	-	-	-	-	-	-	-	-
0.9861	5800	0.427	-	-	-	-	-	-	-	-	-

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.906 kWh
Carbon Emitted: 0.352 kg of CO2
Hours Used: 2.117 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: 4.49.0
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",
}

CSRLoss

@misc{wen2025matryoshkarevisitingsparsecoding,
      title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
      author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
      year={2025},
      eprint={2503.01776},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2503.01776},
}

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}
}