README.md

metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:95159
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/multi-qa-mpnet-base-dot-v1
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
  - 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
widget:
  - source_sentence: medial deviation, first metatarsal misalignment
    sentences:
      - >-
        Deviation of the first toe away from the rest of the foot


        Hallux varus  

        Other namesSandal gap[1]  

        Radiography of the left foot of a young male showing progressive hallux
        varus  

        SpecialtyOrthopedic  
          
        Hallux varus is a deformity of the great toe joint where the hallux
        (great toe) is deviated medially (towards the midline of the body) away
        from the first metatarsal bone. The hallux usually moves in the
        transverse plane. Unlike hallux valgus, also known as hallux abducto
        valgus or bunion, hallux varus is uncommon in the West but it is common
        in cultures where the population remains unshod.


        ## Photos[edit]

          * 

        ## References[edit]

          1. ^ Weerakkody, Yuranga. "Sandal gap deformity - Radiology Reference Article - Radiopaedia.org". radiopaedia.org.

        ## External links[edit]


        Classification


        D

          * ICD-10: M20.3, Q66.3
          * ICD-9-CM: 735.1, 755.66
          * MeSH: D050488

          
          
          * v
          * t
          * e

        Acquired musculoskeletal deformities  
          
        Upper limb


        shoulder
      - >-
        Touraine (1955), who first described this condition (Touraine, 1941),
        discovered a total of 32 cases in 17 families examined. In 9 of the
        families, a parent and 1 or more children were affected. In 5 families
        with a total of 15 cases, only 2 or more sibs were affected. He quoted
        an instance of affected mother and 4 children. Mental retardation was
        frequently associated. In a series of 40 reported cases reviewed by
        Dociu et al. (1976), no lentigines were found other than those on the
        face.

          
        Inheritance \- Autosomal dominant Neuro \- Mental retardation Skin \-
        Facial lentigines ▲ Close
      - >-
        Trisomy 18, also called Edwards syndrome, is a chromosomal condition
        associated with abnormalities in many parts of the body. Individuals
        with trisomy 18 often have slow growth before birth (intrauterine growth
        retardation) and a low birth weight. Affected individuals may have heart
        defects and abnormalities of other organs that develop before birth.
        Other features of trisomy 18 include a small, abnormally shaped head; a
        small jaw and mouth; and clenched fists with overlapping fingers. Due to
        the presence of several life-threatening medical problems, many
        individuals with trisomy 18 die before birth or within their first
        month. Five to 10 percent of children with this condition live past
        their first year, and these children often have severe intellectual
        disability.


        ## Frequency
  - source_sentence: hyperreflexia, infantile onset
    sentences:
      - >-
        Furuncular myiasis in humans is caused by two species: the Cayor worm
        (larvae of the African tumbu fly Cordylobia anthropophaga) and the
        larvae of the human botfly (Dermatobia hominis).


        ## Epidemiology


        The prevalence is unknown but the cases reported in Europe occur
        following visits to affected regions (Latin America, Sub-Saharan Africa)
        or in association with animal importation.


        ## Clinical description


        In the case of Cordylobia anthropophaga, the females lay their eggs on
        damp fabric or on the ground. The larvae penetrate the skin following
        contact with the ground or with non-ironed contaminated fabric.
        Infection becomes evident within 10 to 15 days with the formation of a
        pseudo-furuncle or emergence of a maggot. Dermatobia hominis is found in
        Latin America. Infestation is usually localised to the scalp of infected
        individuals.
      - >-
        A rare ARX-related epileptic encephalopathy characterized by infantile
        onset of myoclonic epilepsy with generalized spasticity, severe global
        developmental delay, and moderate to profound intellectual disability.
        Obligate female carriers show subtle, generalized hyperreflexia. Late
        onset progressive spastic ataxia has also been reported.
      - >-
        Intestinal lymphangiectasia is a rare digestive disorder characterized
        by abnormally enlarged lymph vessels supplying the lining of the small
        intestine. Affected people may experience intermittent diarrhea, nausea,
        vomiting, swelling of the limbs and abdominal discomfort. Intestinal
        lymphangiectasia can be congenital (also called primary intestinal
        lymphangiectasia or Waldmann disease) in which case it affects children
        and young adults (mean age of onset, 11 years); it can also be
        associated with a variety of other conditions and affect older adults.
        Treatment generally involves control of symptoms with dietary and/or
        behavioral modifications and the use of certain medications.
  - source_sentence: mutations in CYLD gene, chromosome 16q12-q13
    sentences:
      - >-
        ##  Description


        Multiple familial trichoepithelioma (MFT) is an autosomal dominant
        disorder of skin appendage tumors characterized by the appearance of
        trichoepitheliomas.


        See also MFT1 (601606), which is caused by mutations in the CYLD gene
        (605018) on chromosome 16q12-q13.


        Mapping


        In 3 families with multiple familial trichoepithelioma, 2 African
        American and 1 Caucasian, Harada et al. (1996) found linkage of the
        disorder to a 4-cM region between IFNA (147660) and D9S126 on chromosome
        9p21; maximum combined lod = 3.31 at D9S171 at theta = 0.0.
      - >-
        This article has multiple issues. Please help improve it or discuss
        these issues on the talk page. (Learn how and when to remove these
        template messages)
      - >-
        Male congenital condition


        Buried penis on a circumcised 30 year old male not due to obesity


        Buried penis in a circumcised 40 year old male due to obesity


        Buried penis (also known as hidden penis or retractile penis) is a
        congenital or acquired condition, in which the penis is partially or
        completely hidden below the surface of the skin. It was first described
        by Edward Lawrence Keyes in 1919 as the apparent absence of the penis
        and as being buried beneath the skin of the abdomen, thigh, or
        scrotum.[1] Further research was done by Maurice Campbell in 1951 when
        he reported on the penis being buried beneath subcutaneous fat of the
        scrotum, perineum, hypogastrium, and thigh.[2]


        A buried penis can lead to obstruction of urinary stream, poor hygiene,
        soft tissue infection, phimosis, and inhibition of normal sexual
        function.
  - source_sentence: metastasis, lung pain, liver symptoms
    sentences:
      - >-
        Testicular seminomatous germ cell tumor is a rare testicular germ cell
        tumor (see this term), most commonly presenting with a painless mass in
        the scrotum, with a very high cure rate if caught in the early stages.


        ## Epidemiology


        Annual incidence in Europe is 1/62,000 people. It accounts for 40% of
        testicular cancer cases.


        ## Clinical description


        Seminoma usually presents in males between the ages of 30-40. A painless
        mass in the scrotum is indicative of disease. A long-standing hydrocele
        may be noted causing a feeling of heaviness in the testicle.
        Gynecomastia and back and flank pain are symptoms that are seen in some
        patients. Relapse after surgery can occur, usually (in 97% of cases) in
        the high iliac or retroperitoneal lymph nodes. Metastasis, although
        rare, can occur in some cases, affecting the lungs, liver, bones and
        central nervous system.


        ## Etiology
      - >-
        Proteus-like syndrome describes patients who do not meet the diagnostic
        criteria for Proteus syndrome (see this term) but who share a multitude
        of characteristic clinical features of the disease.


        ## Epidemiology


        The prevalence is unknown.


        ## Clinical description


        Proteus-like syndrome has the clinical features of Proteus syndrome but
        lacks some of the required criteria necessary for diagnosis. The main
        clinical features include skeletal overgrowth, hamartomous overgrowth of
        multiple tissues, cerebriform connective tissue nevi, vascular
        malformations and linear epidermal nevi.


        ## Etiology
      - >-
        "ESUS" redirects here. For other uses, see ESUS (disambiguation).


        Embolic stroke of undetermined source (ESUS) is a type of ischemic
        stroke with an unknown origin, defined as a non-lacunar brain infarct
        without proximal arterial stenosis or cardioembolic sources.[1] As such,
        it forms a subset of cryptogenic stroke, which is part of the
        TOAST-classification.[2] The following diagnostic criteria define an
        ESUS:[1]

          * Stroke detected by CT or MRI that is not lacunar
          * No major-risk cardioembolic source of embolism
          * Absence of extracranial or intracranial atherosclerosis causing 50% luminal stenosis in arteries supplying the area of ischaemia
          * No other specific cause of stroke identified (e.g., arteritis, dissection, migraine/vasospasm, drug misuse)

        ## Contents

          * 1 Causes
          * 2 Diagnosis
            * 2.1 Cryptogenic stroke vs ESUS
          * 3 Management
          * 4 Epidemiology
          * 5 References
          * 6 Further reading

        ## Causes[edit]
  - source_sentence: nerve cell dysfunction, riboflavin deficiency
    sentences:
      - >-
        Riboflavin transporter deficiency neuronopathy is a disorder that
        affects nerve cells (neurons). Affected individuals typically have
        hearing loss caused by nerve damage in the inner ear (sensorineural
        hearing loss) and signs of damage to other nerves.
      - >-
        A number sign (#) is used with this entry because autosomal recessive
        deafness-23 (DFNB23) is caused by homozygous mutation in the gene
        encoding protocadherin-15 (PCDH15; 605514) on chromosome 10q21.


        Mutation in the PCDH15 gene can also cause Usher syndrome type IF
        (602083).


        Clinical Features


        Ahmed et al. (2003) reported 3 families with isolated deafness. Two of
        the families had no history of nyctalopia, and the funduscopy and
        electroretinograms were normal in 2 older affected individuals from each
        family (age range, 13-44 years). Vestibular responses were intact in
        affected individuals.
      - >-
        A number sign (#) is used with this entry because hyperprolinemia type I
        (HYRPRO1) is caused by homozygous or compound heterozygous mutation in
        the proline dehydrogenase gene (PRODH; 606810) on chromosome 22q11.


        The PRODH gene falls within the region deleted in the 22q11 deletion
        syndrome, including DiGeorge syndrome (188400) and velocardiofacial
        syndrome (192430).


        Description


        Phang et al. (2001) noted that prospective studies of HPI probands
        identified through newborn screening as well as reports of several
        families have suggested that it is a metabolic disorder not clearly
        associated with clinical manifestations. Phang et al. (2001) concluded
        that HPI is a relatively benign condition in most individuals under most
        circumstances. However, other reports have suggested that some patients
        have a severe phenotype with neurologic manifestations, including
        epilepsy and mental retardation (Jacquet et al., 2003).


        ### Genetic Heterogeneity of Hyperprolinemia
pipeline_tag: sentence-similarity
model-index:
  - name: >-
      SentenceTransformer based on
      sentence-transformers/multi-qa-mpnet-base-dot-v1
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.1933234251743455
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5625928889905111
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7512289927975306
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8409740482451126
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1933234251743455
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.187530962996837
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15024579855950612
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08409740482451128
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1933234251743455
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5625928889905111
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7512289927975306
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8409740482451126
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5119882960837339
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.405861873730865
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4109594895459784
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.1949239739339202
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5672802103578369
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7570595632788385
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8415456728021036
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.1949239739339202
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.18909340345261233
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1514119126557677
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08415456728021035
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1949239739339202
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5672802103578369
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.7570595632788385
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8415456728021036
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5141471619143755
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.40838527858078216
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4135618156873651
            name: Dot Map@100

SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1

This is a sentence-transformers model finetuned from sentence-transformers/multi-qa-mpnet-base-dot-v1. 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/multi-qa-mpnet-base-dot-v1
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Dot Product

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': False}) with Transformer model: MPNetModel 
  (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})
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    'nerve cell dysfunction, riboflavin deficiency',
    'Riboflavin transporter deficiency neuronopathy is a disorder that affects nerve cells (neurons). Affected individuals typically have hearing loss caused by nerve damage in the inner ear (sensorineural hearing loss) and signs of damage to other nerves.',
    'A number sign (#) is used with this entry because hyperprolinemia type I (HYRPRO1) is caused by homozygous or compound heterozygous mutation in the proline dehydrogenase gene (PRODH; 606810) on chromosome 22q11.\n\nThe PRODH gene falls within the region deleted in the 22q11 deletion syndrome, including DiGeorge syndrome (188400) and velocardiofacial syndrome (192430).\n\nDescription\n\nPhang et al. (2001) noted that prospective studies of HPI probands identified through newborn screening as well as reports of several families have suggested that it is a metabolic disorder not clearly associated with clinical manifestations. Phang et al. (2001) concluded that HPI is a relatively benign condition in most individuals under most circumstances. However, other reports have suggested that some patients have a severe phenotype with neurologic manifestations, including epilepsy and mental retardation (Jacquet et al., 2003).\n\n### Genetic Heterogeneity of Hyperprolinemia',
]
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

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1933
cosine_accuracy@3	0.5626
cosine_accuracy@5	0.7512
cosine_accuracy@10	0.841
cosine_precision@1	0.1933
cosine_precision@3	0.1875
cosine_precision@5	0.1502
cosine_precision@10	0.0841
cosine_recall@1	0.1933
cosine_recall@3	0.5626
cosine_recall@5	0.7512
cosine_recall@10	0.841
cosine_ndcg@10	0.512
cosine_mrr@10	0.4059
cosine_map@100	0.411
dot_accuracy@1	0.1949
dot_accuracy@3	0.5673
dot_accuracy@5	0.7571
dot_accuracy@10	0.8415
dot_precision@1	0.1949
dot_precision@3	0.1891
dot_precision@5	0.1514
dot_precision@10	0.0842
dot_recall@1	0.1949
dot_recall@3	0.5673
dot_recall@5	0.7571
dot_recall@10	0.8415
dot_ndcg@10	0.5141
dot_mrr@10	0.4084
dot_map@100	0.4136

Training Details

Training Dataset

Unnamed Dataset

• Size: 95,159 training samples
• Columns: queries and chunks
• Approximate statistics based on the first 1000 samples:

  	queries	chunks
  type	string	string
  details	min: 5 tokens mean: 15.01 tokens max: 30 tokens	min: 5 tokens mean: 158.91 tokens max: 319 tokens

• Samples:

  queries	chunks
  hypotrichosis, wiry hair, onycholysis	Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.
  cleft lip, cleft palate, hair loss	Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.
  progressive patterned scalp, autosomal dominant inheritance	Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 1,
      "similarity_fct": "dot_score"
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 8,747 evaluation samples
• Columns: queries and chunks
• Approximate statistics based on the first 1000 samples:

  	queries	chunks
  type	string	string
  details	min: 6 tokens mean: 14.71 tokens max: 31 tokens	min: 4 tokens mean: 155.81 tokens max: 305 tokens

• Samples:

  queries	chunks
  white patches, corrugated tongue, immunocompromised, Epstein-Barr virus	Not to be confused with Hairy tongue. Hairy leukoplakia Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] SpecialtyGastroenterology Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition. Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis. ## Contents
  HIV-associated lesions, oral hairy leukoplakia, benign white lesions, tongue appearance	Not to be confused with Hairy tongue. Hairy leukoplakia Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] SpecialtyGastroenterology Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition. Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis. ## Contents
  hairy leukoplakia symptoms, non-scrapable lesions, HIV/AIDS, oral lesions	Not to be confused with Hairy tongue. Hairy leukoplakia Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] SpecialtyGastroenterology Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition. Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis. ## Contents

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 1,
      "similarity_fct": "dot_score"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 15
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• eval_on_start: 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: 32
• 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: 15
• 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: True
• 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: 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
• eval_on_start: True
• eval_use_gather_object: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	dot_map@100
0	0	-	1.4355	0.2271
0.1346	100	1.2599	-	-
0.2692	200	0.7627	-	-
0.4038	300	0.6061	-	-
0.5384	400	0.5632	-	-
0.6729	500	0.3965	0.4589	0.3852
0.8075	600	0.3104	-	-
0.9421	700	0.446	-	-
1.0767	800	0.4426	-	-
1.2113	900	0.4518	-	-
1.3459	1000	0.4145	0.3726	0.3964
1.4805	1100	0.4296	-	-
1.6151	1200	0.4144	-	-
1.7497	1300	0.1536	-	-
1.8843	1400	0.3425	-	-
2.0188	1500	0.3225	0.3433	0.3930
2.1534	1600	0.3529	-	-
2.2880	1700	0.3382	-	-
2.4226	1800	0.3092	-	-
2.5572	1900	0.339	-	-
2.6918	2000	0.1681	0.3633	0.4032
2.8264	2100	0.1753	-	-
2.9610	2200	0.2552	-	-
3.0956	2300	0.2549	-	-
3.2301	2400	0.2759	-	-
3.3647	2500	0.2513	0.3338	0.4066
3.4993	2600	0.258	-	-
3.6339	2700	0.2222	-	-
3.7685	2800	0.0541	-	-
3.9031	2900	0.2275	-	-
4.0377	3000	0.1919	0.3529	0.4026
4.1723	3100	0.215	-	-
4.3069	3200	0.2114	-	-
4.4415	3300	0.2153	-	-
4.5760	3400	0.2164	-	-
4.7106	3500	0.0773	0.3509	0.4090
4.8452	3600	0.1211	-	-
4.9798	3700	0.1553	-	-
5.1144	3800	0.1764	-	-
5.2490	3900	0.1953	-	-
5.3836	4000	0.1559	0.3474	0.4089
5.5182	4100	0.1686	-	-
5.6528	4200	0.1327	-	-
5.7873	4300	0.0514	-	-
5.9219	4400	0.1381	-	-
6.0565	4500	0.1445	0.3521	0.4056
6.1911	4600	0.1621	-	-
6.3257	4700	0.1365	-	-
6.4603	4800	0.1579	-	-
6.5949	4900	0.1547	-	-
6.7295	5000	0.0316	0.3895	0.4094
6.8641	5100	0.0958	-	-
6.9987	5200	0.1082	-	-
7.1332	5300	0.1379	-	-
7.2678	5400	0.1348	-	-
7.4024	5500	0.1322	0.3552	0.4100
7.5370	5600	0.1321	-	-
7.6716	5700	0.0763	-	-
7.8062	5800	0.0472	-	-
7.9408	5900	0.0989	-	-
8.0754	6000	0.1045	0.3631	0.3967
8.2100	6100	0.122	-	-
8.3445	6200	0.1057	-	-
8.4791	6300	0.1194	-	-
8.6137	6400	0.113	-	-
8.7483	6500	0.0126	0.3944	0.4116
8.8829	6600	0.089	-	-
9.0175	6700	0.0849	-	-
9.1521	6800	0.1052	-	-
9.2867	6900	0.111	-	-
9.4213	7000	0.1026	0.3665	0.4133
9.5559	7100	0.1165	-	-
9.6904	7200	0.0394	-	-
9.8250	7300	0.0443	-	-
9.9596	7400	0.0756	-	-
10.0942	7500	0.0806	0.3785	0.4090
10.2288	7600	0.103	-	-
10.3634	7700	0.0875	-	-
10.4980	7800	0.0959	-	-
10.6326	7900	0.0851	-	-
10.7672	8000	0.0073	0.3902	0.4136
10.9017	8100	0.079	-	-
11.0363	8200	0.0664	-	-
11.1709	8300	0.0766	-	-
11.3055	8400	0.084	-	-
11.4401	8500	0.0947	0.3733	0.4099
11.5747	8600	0.0906	-	-
11.7093	8700	0.0224	-	-
11.8439	8800	0.0424	-	-
11.9785	8900	0.0569	-	-
12.1131	9000	0.0697	0.3824	0.4071
12.2476	9100	0.095	-	-
12.3822	9200	0.0651	-	-
12.5168	9300	0.0756	-	-
12.6514	9400	0.065	-	-
12.7860	9500	0.0194	0.3876	0.4110
12.9206	9600	0.0595	-	-
13.0552	9700	0.0629	-	-
13.1898	9800	0.0808	-	-
13.3244	9900	0.0652	-	-
13.4590	10000	0.0802	0.3783	0.4091
13.5935	10100	0.0809	-	-
13.7281	10200	0.0111	-	-
13.8627	10300	0.0465	-	-
13.9973	10400	0.0504	-	-
14.1319	10500	0.068	0.3831	0.4071
14.2665	10600	0.0739	-	-
14.4011	10700	0.0734	-	-
14.5357	10800	0.0737	-	-
14.6703	10900	0.0379	-	-
14.8048	11000	0.0231	0.3841	0.4112
14.9394	11100	0.0493	-	-
15.0	11145	-	0.3902	0.4136

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.0.1
• Transformers: 4.43.3
• PyTorch: 2.3.1+cu121
• Accelerate: 0.30.1
• 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",
}

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}
}