metadata

language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4247
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
datasets: []
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
widget:
  - source_sentence: >-
      The Opa1 protein localizes to the mitochondria.Opa1 is found normally in
      the mitochondrial intermembrane space.
    sentences:
      - Which is the cellular localization of the protein Opa1?
      - Which are the genes responsible for Dyskeratosis Congenita?
      - List blood marker for Non-Hodgkin lymphoma.
  - source_sentence: >-
      CorrSite identifies potential allosteric ligand-binding sites based on
      motion correlation analyses between cavities.We find that CARDS captures
      allosteric communication between the two cAMP-Binding Domains
      (CBDs)Overall, it is demonstrated that the communication pathways could be
      multiple and intrinsically disposed, and the MC path generation approach
      provides an effective tool for the prediction of key residues that mediate
      the allosteric communication in an ensemble of pathways and functionally
      plausible residuesWe utilized a data set of 24 known allosteric sites from
      23 monomer proteins to calculate the correlations between potential
      ligand-binding sites and corresponding orthosteric sites using a Gaussian
      network model (GNM)Here, we introduce the Correlation of All Rotameric and
      Dynamical States (CARDS) framework for quantifying correlations between
      both the structure and disorder of different regions of a proteinWe
      present a novel method, "MutInf", to identify statistically significant
      correlated motions from equilibrium molecular dynamics simulationsCorrSite
      identifies potential allosteric ligand-binding sites based on motion
      correlation analyses between cavities.Here, a Monte Carlo (MC) path
      generation approach is proposed and implemented to define likely
      allosteric pathways through generating an ensemble of maximum probability
      paths.Here, a Monte Carlo (MC) path generation approach is proposed and
      implemented to define likely allosteric pathways through generating an
      ensemble of maximum probability paths. Overall, it is demonstrated that
      the communication pathways could be multiple and intrinsically disposed,
      and the MC path generation approach provides an effective tool for the
      prediction of key residues that mediate the allosteric communication in an
      ensemble of pathways and functionally plausible residues We utilized a
      data set of 24 known allosteric sites from 23 monomer proteins to
      calculate the correlations between potential ligand-binding sites and
      corresponding orthosteric sites using a Gaussian network model (GNM)A
      Monte Carlo (MC) path generation approach is proposed and implemented to
      define likely allosteric pathways through generating an ensemble of
      maximum probability paths. A novel method, "MutInf", to identify
      statistically significant correlated motions from equilibrium molecular
      dynamics simulations. CorrSite identifies potential alloster-binding sites
      based on motion correlation analyses between cavities. The Correlation of
      All Rotameric and Dynamical States (CARDS) framework for quantifying
      correlations between both the structure and disorder of different regions
      of a proteinComputational tools for predicting allosteric pathways in
      proteins include MCPath, MutInf, pySCA, CorrSite, and CARDS.
    sentences:
      - Computational tools for predicting allosteric pathways in proteins
      - What is PANTHER-PSEP?
      - What illness is transmitted by the Lone Star Tick, Amblyomma americanum?
  - source_sentence: >-
      Dopaminergic drugs should be given in patients with BMS. 

      Catuama reduces the symptoms of BMS and may be a novel therapeutic
      strategy for the treatment of this disease.

      Capsaicin, alpha-lipoic acid (ALA), and clonazepam were those that showed
      more reduction in symptoms of BMS.

      Treatment with placebos produced a response that was 72% as large as the
      response to active drugs
    sentences:
      - What is the cyberknife used for?
      - Which compounds exist that are thyroid hormone analogs?
      - Which are the drugs utilized for the burning mouth syndrome?
  - source_sentence: Tinea is a superficial fungal infections of the skin.
    sentences:
      - Which molecule is targeted by a monoclonal antibody Mepolizumab?
      - What disease is tinea ?
      - Which algorithm is used for detection of long repeat expansions?
  - source_sentence: >-
      Basset is an open source package which applies CNNs to learn the
      functional activity of DNA sequences from genomics data. Basset was
      trained on a compendium of accessible genomic sites mapped in 164 cell
      types by DNase-seq, and demonstrated greater predictive accuracy than
      previous methods. Basset predictions for the change in accessibility
      between variant alleles were far greater for Genome-wide association study
      (GWAS) SNPs that are likely to be causal relative to nearby SNPs in
      linkage disequilibrium with them. With Basset, a researcher can perform a
      single sequencing assay in their cell type of interest and simultaneously
      learn that cell's chromatin accessibility code and annotate every mutation
      in the genome with its influence on present accessibility and latent
      potential for accessibility. Thus, Basset offers a powerful computational
      approach to annotate and interpret the noncoding genome.
    sentences:
      - Givosiran is used for treatment of which disease?
      - Describe the applicability of Basset in the context of deep learning
      - What is the causative agent of the "Panama disease" affecting bananas?
pipeline_tag: sentence-similarity
model-index:
  - name: BGE base BioASQ Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.8432203389830508
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9427966101694916
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.961864406779661
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9788135593220338
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8432203389830508
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3142655367231638
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19237288135593222
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0978813559322034
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8432203389830508
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9427966101694916
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.961864406779661
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9788135593220338
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9167805960832026
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8963327280064567
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8971987609787653
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.8538135593220338
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9427966101694916
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.961864406779661
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9745762711864406
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8538135593220338
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3142655367231638
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19237288135593222
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09745762711864407
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8538135593220338
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9427966101694916
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.961864406779661
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9745762711864406
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9198462326957965
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9016772598870054
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9026755533837086
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.8453389830508474
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9385593220338984
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9555084745762712
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9745762711864406
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8453389830508474
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3128531073446327
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19110169491525425
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09745762711864407
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8453389830508474
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9385593220338984
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9555084745762712
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9745762711864406
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.914207272128957
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8944528517621736
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8952712251263324
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.8220338983050848
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9279661016949152
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9449152542372882
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9703389830508474
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8220338983050848
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3093220338983051
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18898305084745767
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09703389830508474
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8220338983050848
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9279661016949152
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9449152542372882
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9703389830508474
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.901534580728345
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8789800242130752
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8801051507894794
            name: Cosine Map@100

BGE base BioASQ Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("pavanmantha/bge-base-en-bioembed768")
# Run inference
sentences = [
    "Basset is an open source package which applies CNNs to learn the functional activity of DNA sequences from genomics data. Basset was trained on a compendium of accessible genomic sites mapped in 164 cell types by DNase-seq, and demonstrated greater predictive accuracy than previous methods. Basset predictions for the change in accessibility between variant alleles were far greater for Genome-wide association study (GWAS) SNPs that are likely to be causal relative to nearby SNPs in linkage disequilibrium with them. With Basset, a researcher can perform a single sequencing assay in their cell type of interest and simultaneously learn that cell's chromatin accessibility code and annotate every mutation in the genome with its influence on present accessibility and latent potential for accessibility. Thus, Basset offers a powerful computational approach to annotate and interpret the noncoding genome.",
    'Describe the applicability of Basset in the context of deep learning',
    'What is the causative agent of the "Panama disease" affecting bananas?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8432
cosine_accuracy@3	0.9428
cosine_accuracy@5	0.9619
cosine_accuracy@10	0.9788
cosine_precision@1	0.8432
cosine_precision@3	0.3143
cosine_precision@5	0.1924
cosine_precision@10	0.0979
cosine_recall@1	0.8432
cosine_recall@3	0.9428
cosine_recall@5	0.9619
cosine_recall@10	0.9788
cosine_ndcg@10	0.9168
cosine_mrr@10	0.8963
cosine_map@100	0.8972

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8538
cosine_accuracy@3	0.9428
cosine_accuracy@5	0.9619
cosine_accuracy@10	0.9746
cosine_precision@1	0.8538
cosine_precision@3	0.3143
cosine_precision@5	0.1924
cosine_precision@10	0.0975
cosine_recall@1	0.8538
cosine_recall@3	0.9428
cosine_recall@5	0.9619
cosine_recall@10	0.9746
cosine_ndcg@10	0.9198
cosine_mrr@10	0.9017
cosine_map@100	0.9027

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8453
cosine_accuracy@3	0.9386
cosine_accuracy@5	0.9555
cosine_accuracy@10	0.9746
cosine_precision@1	0.8453
cosine_precision@3	0.3129
cosine_precision@5	0.1911
cosine_precision@10	0.0975
cosine_recall@1	0.8453
cosine_recall@3	0.9386
cosine_recall@5	0.9555
cosine_recall@10	0.9746
cosine_ndcg@10	0.9142
cosine_mrr@10	0.8945
cosine_map@100	0.8953

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.822
cosine_accuracy@3	0.928
cosine_accuracy@5	0.9449
cosine_accuracy@10	0.9703
cosine_precision@1	0.822
cosine_precision@3	0.3093
cosine_precision@5	0.189
cosine_precision@10	0.097
cosine_recall@1	0.822
cosine_recall@3	0.928
cosine_recall@5	0.9449
cosine_recall@10	0.9703
cosine_ndcg@10	0.9015
cosine_mrr@10	0.879
cosine_map@100	0.8801

Training Details

Training Dataset

Unnamed Dataset

Size: 4,247 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 3 tokens
mean: 102.44 tokens
max: 512 tokens

min: 5 tokens
mean: 15.78 tokens
max: 44 tokens

	positive	anchor
type	string	string
details	min: 3 tokens mean: 102.44 tokens max: 512 tokens	min: 5 tokens mean: 15.78 tokens max: 44 tokens

Samples:

positive	anchor
`Restless legs syndrome (RLS), also known as Willis-Ekbom disease (WED), is a common movement disorder characterized by an uncontrollable urge to move because of uncomfortable, sometimes painful sensations in the legs with a diurnal variation and a release with movement.`	`Willis-Ekbom disease is also known as?`
`Report the outcomes of laser in situ keratomileusis (LASIK) for high myopia correction after long-term follow-up['Report the outcomes of laser in situ keratomileusis (LASIK) for high myopia correction after long-term follow-up.']Laser in situ keratomileusis is also known as LASIKLaser in situ keratomileusis (LASIK)`	`What is another name for keratomileusis?`
CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them.CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them. CellMaps can easily be integrated in any web page by using an available JavaScript API. Computations and analyses are remotely executed in high-end servers, and all the functionalities are available through RESTful web services. CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them. Computations and analyses are remotely executed in high-end servers, and all the functionalities are available through RESTful web services. CellMaps can easily be integrated in any web page by using an available JavaScript API. CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them. Computations and analyses are remotely executed in high-end servers, and all the functionalities are available through RESTful web services. CellMaps can easily be integrated in any web page by using an available JavaScript API.CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them. CellMaps is an HTML5 open-source web tool that allows displaying, editing, exploring and analyzing biological networks as well as integrating metadata into them. CellMaps can easily be integrated in any web page by using an available JavaScript API. Computations and analyses are remotely executed in high-end servers, and all the functionalities are available through RESTful web services.	`What is CellMaps?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 10
lr_scheduler_type: cosine
warmup_ratio: 0.1
fp16: True
tf32: False
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_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: 10
max_steps: -1
lr_scheduler_type: cosine
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: False
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_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_768_cosine_map@100
0.9624	8	-	0.8560	0.8821	0.8904	0.8876
1.2030	10	1.2833	-	-	-	-
1.9248	16	-	0.8655	0.8808	0.8909	0.8889
2.4060	20	0.4785	-	-	-	-
2.8872	24	-	0.8720	0.8875	0.8893	0.8921
3.6090	30	0.2417	-	-	-	-
3.9699	33	-	0.8751	0.8924	0.8955	0.8960
4.8120	40	0.1607	-	-	-	-
4.9323	41	-	0.8799	0.8932	0.8964	0.8952
5.8947	49	-	0.8785	0.8944	0.9009	0.8982
6.0150	50	0.1152	-	-	-	-
6.9774	58	-	0.8803	0.8947	0.9018	0.8975
7.2180	60	0.0924	-	-	-	-
7.9398	66	-	0.8802	0.8956	0.9016	0.8973
8.4211	70	0.0832	-	-	-	-
8.9023	74	-	0.8801	0.8956	0.9027	0.8972
9.6241	80	0.074	0.8801	0.8953	0.9027	0.8972

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2
Accelerate: 0.31.0
Datasets: 2.19.2
Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}