metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4012
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: >-
      We employed genetic, cytological, and genomic approaches to better
      understand the role of PR-Set7 and H4K20 methylation in regulating DNA
      replication and genome stability in Drosophila cells. Thus, coordinating
      the status of H4K20 methylation is pivotal for the proper selection of DNA
      replication origins in higher eukaryotes. The methylation state of lysine
      20 on histone H4 (H4K20) has been linked to chromatin compaction,
      transcription, DNA repair and DNA replication. Histone turnover is often
      associated with various histone modifications such as H3K56 acetylation
      (H3K56Ac), H3K36 methylation (H3K36me), and H4K20 methylation (H4K20me).
      We review the signaling pathways and functions associated with a single
      residue, H4K20, as a model chromatin and clinically important mark that
      regulates biological processes ranging from the DNA damage response and
      DNA replication to gene expression and silencing. <CopyrightInformation>©
      2016 by The American Society for Biochemistry and Molecular Biology,
      Inc.</C In particular, the methylation states of H3K4, H3K36 and H4K20
      have been associated with establishing active, repressed or poised origins
      depending on the timing and extent of methylation. 5BrC and 5ClC may cause
      aberrant methylation of cytosine during DNA replication and mimic the
      endogenous methylation signal associated with gene silencing.
    sentences:
      - Is H4K20 methylation associated with DNA replication?
      - What is the function of the protein Cuf1?
      - Which syndromes are associated with heterochromia iridum?
  - source_sentence: >-
      The Abbreviated Injury Scale (AIS) is an objective anatomically-based
      injury severity scoring system that classifies each injury by body region
      on a 6 point scale. AIS is the system used to determine the Injury
      Severity Score (ISS) of the multiply injured trauma patient.


      AIS CLASSIFICATIONS

      The AIS classifies individual injuries by body region as follows:

      AIS 1 – Minor

      AIS 2 – Moderate

      AIS 3 – Serious

      AIS 4 – Severe

      AIS 5 – Critical

      AIS 6 – Maximal (currently untreatable)
    sentences:
      - What is the role of the Hof1-Cyk3 interaction in yeast?
      - Which drugs are included in the MAID chemotherapy regimen for sarcoma?
      - What is Abbreviated Injury Scale (AIS) used to determine?
  - source_sentence: >-
      Multicluster Pcdh diversity is required for mouse olfactory neural circuit
      assembly. The vertebrate clustered protocadherin (Pcdh) cell surface
      proteins are encoded by three closely linked gene clusters (Pcdhα, Pcdhβ,
      and Pcdhγ). Although deletion of individual Pcdh clusters had subtle
      phenotypic consequences, the loss of all three clusters (tricluster
      deletion) led to a severe axonal arborization defect and loss of
      self-avoidance.
    sentences:
      - Does thyroid hormone affect cardiac remodeling?
      - >-
        What are the effects of the deletion of all three Pcdh clusters
        (tricluster deletion) in mice?
      - >-
        Which R/bioconductor package has been developed to aid in epigenomic
        analysis?
  - source_sentence: >-
      Huntington disease (HD; OMIM 143100), a progressive neurodegenerative
      disorder, is caused by an expanded trinucleotide CAG (polyQ) motif in the
      HTT gene. Mutations of the huntingtin protein (HTT) gene underlie both
      adult-onset and juvenile forms of Huntington's disease (HD).
    sentences:
      - What is resistin?
      - Does thyroid hormone signaling affect microRNAs expression in the heart?
      - What gene is mutated in Huntington's disease?
  - source_sentence: >-
      Nusinersen is a modified antisense oligonucleotide that binds to a
      specific sequence in the intron, downstream of exon 7 on the pre-messenger
      ribonucleic acid (pre-mRNA) of the SMN2 gene. This modulates the splicing
      of the SMN2 mRNA transcript to include exon 7, thereby increasing the
      production of full-length SMN protein. It is approved for treatment of 
      spinal muscular atrophy.
    sentences:
      - Describe mechanism of action of Nusinersen.
      - What is Mobilome-seq?
      - What percentage of currently available drugs are metabolized by CYP3A4?
pipeline_tag: sentence-similarity
library_name: sentence-transformers
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
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: sentence transformers/all mpnet base v2
          type: sentence-transformers/all-mpnet-base-v2
        metrics:
          - type: cosine_accuracy@1
            value: 0.8472418670438473
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9335219236209336
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9490806223479491
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9603960396039604
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8472418670438473
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.31117397454031115
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1898161244695898
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09603960396039603
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8472418670438473
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9335219236209336
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9490806223479491
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9603960396039604
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9092929874201823
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8923284165151212
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8935812728750705
            name: Cosine Map@100

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the json dataset. 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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json

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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): 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("anoyinonion/all-mpnet-base-v2-bioasq-1epoc-batch32-100")
# Run inference
sentences = [
    'Nusinersen is a modified antisense oligonucleotide that binds to a specific sequence in the intron, downstream of exon 7 on the pre-messenger ribonucleic acid (pre-mRNA) of the SMN2 gene. This modulates the splicing of the SMN2 mRNA transcript to include exon 7, thereby increasing the production of full-length SMN protein. It is approved for treatment of  spinal muscular atrophy.',
    'Describe mechanism of action of Nusinersen.',
    'What percentage of currently available drugs are metabolized by CYP3A4?',
]
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: sentence-transformers/all-mpnet-base-v2
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8472
cosine_accuracy@3	0.9335
cosine_accuracy@5	0.9491
cosine_accuracy@10	0.9604
cosine_precision@1	0.8472
cosine_precision@3	0.3112
cosine_precision@5	0.1898
cosine_precision@10	0.096
cosine_recall@1	0.8472
cosine_recall@3	0.9335
cosine_recall@5	0.9491
cosine_recall@10	0.9604
cosine_ndcg@10	0.9093
cosine_mrr@10	0.8923
cosine_map@100	0.8936

Training Details

Training Dataset

json

Dataset: json
Size: 4,012 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 3 tokens
mean: 63.14 tokens
max: 384 tokens

min: 5 tokens
mean: 16.13 tokens
max: 49 tokens

	positive	anchor
type	string	string
details	min: 3 tokens mean: 63.14 tokens max: 384 tokens	min: 5 tokens mean: 16.13 tokens max: 49 tokens

Samples:

positive	anchor
`Aberrant patterns of H3K4, H3K9, and H3K27 histone lysine methylation were shown to result in histone code alterations, which induce changes in gene expression, and affect the proliferation rate of cells in medulloblastoma.`	`What is the implication of histone lysine methylation in medulloblastoma?`
`STAG1/STAG2 proteins are tumour suppressor proteins that suppress cell proliferation and are essential for differentiation.`	`What is the role of STAG1/STAG2 proteins in differentiation?`
`The association between cell phone use and incident glioblastoma remains unclear. Some studies have reported that cell phone use was associated with incident glioblastoma, and with reduced survival of patients diagnosed with glioblastoma. However, other studies have repeatedly replicated to find an association between cell phone use and glioblastoma.`	`What is the association between cell phone use and glioblastoma?`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: 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: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
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	sentence-transformers/all-mpnet-base-v2_cosine_ndcg@10
0.7937	100	0.1152	0.9093

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
Transformers: 4.47.1
PyTorch: 2.1.2+cu121
Accelerate: 1.2.1
Datasets: 2.19.1
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

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

MultipleNegativesRankingLoss

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