---
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:649352
- loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-large-en-v1.5
widget:
- source_sentence: 'dataCollection.studyDesignSummary: Plan detailing how data will
be collected from patient cohorts.'
sentences:
- 'dataset.primary_site: The primary body site studied in this dataset.'
- 'dataset.research_design: A summary of the goals of the research or a general
description of the research''s relationship to a clinical application.'
- 'subject.taxon_id: NCBI identifier for classification of organisms.'
- source_sentence: 'discoveryAction.CohortSet: A title or description of the discoveryAction;
used to identify it in publications and databases.'
sentences:
- 'surgery_procedure_diagnosis_code.SurgeryTime: SurgeryTime'
- 'mass_spec_assay.chromatography_type: '
- 'study.full_name: The full name for the project.'
- source_sentence: 'ExperimentDesignTemplate.researcher: Identifies the entity responsible
for creating and sharing data in the ExperimentDesignTemplate.'
sentences:
- 'subject.ofloxacin_res_phenotype: '
- 'dataset.data_contributor: The name of the organization or individual that the
contributed dataset belongs to.'
- 'payer_plan_period.site_id: The care site ID.'
- source_sentence: 'experiment_data.PatientDatabaseEntry: Number of basepairs of genome
sequenced.'
sentences:
- 'exam.updt: Last update of AHS exam index record'
- 'study.study_setup: Category'
- 'subject.genome_length: Number of basepairs of genome sequenced.'
- source_sentence: 'StudyDesign.studyDescription: Free-text overview of data provided
for research purposes.'
sentences:
- 'sleep_test_file.bucket_path: '
- 'subject.age_at_index_gt89: Indicates whether the subject''s age at the time of
the study was greater than 89 years.'
- 'dataset.data_description: Brief description of the data being provided for this
experiment.'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# Base trained on appropriate relationships between similar biomedical variables
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) on the csv dataset. It maps sentences & paragraphs to a 1024-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-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- csv
- **Language:** en
- **License:** apache-2.0
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) 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): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'StudyDesign.studyDescription: Free-text overview of data provided for research purposes.',
'dataset.data_description: Brief description of the data being provided for this experiment.',
"subject.age_at_index_gt89: Indicates whether the subject's age at the time of the study was greater than 89 years.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
## Training Details
### Training Dataset
#### csv
* Dataset: csv
* Size: 649,352 training samples
* Columns: anchor and positive
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 14 tokens
- mean: 28.18 tokens
- max: 61 tokens
| - min: 6 tokens
- mean: 26.74 tokens
- max: 235 tokens
|
* Samples:
| anchor | positive |
|:-------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------|
| FluorophoreCouplingRatio.assay_protocol_doi: Description of a standardized flow cytometry assay procedure. | flow_cytometry_assay.protocol_doi: |
| FluorophoreCouplingRatio.cell_quality_check: Assay quality assurance measures. | flow_cytometry_assay.quality_control_measures: |
| FluorophoreCouplingRatio.AssaySpec: Represents a record of any updates made to the flow cytometry assay template. | flow_cytometry_assay.provenance: |
* Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Evaluation Dataset
#### csv
* Dataset: csv
* Size: 81,496 evaluation samples
* Columns: anchor and positive
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 12 tokens
- mean: 29.17 tokens
- max: 130 tokens
| - min: 7 tokens
- mean: 25.16 tokens
- max: 235 tokens
|
* Samples:
| anchor | positive |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------|
| treatment.cancerTreatmentTime: Comprehensive plan for healthcare services; including treatment and medication management. | treatment.treatment_span: |
| DiscoveryPlan.StudyObjective: Main disease type description provides a concise summary of the primary disease being investigated in this dataset. | dataset.disease_type: The primary type of disease studied in this dataset; if applicable. |
| DiscoveryPlan.StudyObjective: Main disease type description provides a concise summary of the primary disease being investigated in this dataset. | dataset.disease_type: The primary type of disease studied in this dataset; if applicable. |
* Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `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`: 16
- `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`: 5e-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}
- `tp_size`: 0
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional