Instructions to use bdanko/umsb-mpnet-episodic-memory with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bdanko/umsb-mpnet-episodic-memory with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("bdanko/umsb-mpnet-episodic-memory")

sentences = [
    "um according to dosing instructions. If no magnesium level has been recorded in the last 24 hours, don't order anything.\nmodel_prediction_summary: {\"finish_result\": \"[\\\"The patient S6537563's last serum magnesium level within the last 24 hours was 2.1 mg/dL (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the normal range (>= 1.9 mg/dL) and not low according to the provided dosing instructions, no replacement IV magnesium was ordered.\\\"]\", \"status\": \"completed\"}",
    "model correctly identified the age of the patient with MRN S6542579 as 28 based on the provided context and patient data\nAlthough the official reference solution pass flag was false (likely due to an internal evaluation error or missing expected output in the prompt metadata), the model's answer is factually correct according to the standard dataset associated with this MRN and the",
    "he rate such as \\\"h\\\" \", \"type\": \"string\"}, \"value\": {\"type\": \"number\"}}, \"type\": \"object\"}}, \"type\": \"object\"}, \"type\":\n\"array\"}, \"route\": {\"properties\": {\"text\": {\"description\": \"The medication route.\", \"type\": \"string\"}}, \"type\": \"object\"}}, \"type\": \"object\"}, \"type\": \"array\"}, \"intent\": {\"description\": \"Use \\\"order\\\" \", \"type\": \"string\"}, \"medicationCodeableConcept\": {\"properties\": {\"coding\": {\"items\": {\"properties\": {\"code\": {\"description\": \"The actual code\", \"type\": \"string\"}, \"display\": {\"description\": \"Display name\", \"type\": \"string\"}, \"system\": {\"description\": \"Coding system such as \\\"http://hl7.org/fhir/sid/ndc\\\" \", \"type\": \"string\"}}, \"type\": \"object\"}, \"type\": \"array\"}, \"text\": {\"description\": \"The order display name of the medication, otherwise the record name.\", \"type\": \"string\"}}, \"type\": \"object\"}, \"resourceType\": {\"description\": \"Use \\\"MedicationRequest\\\" for medication requests.\", \"type\": \"string\"}, \"status\": {\"description\": \"The status of the medication request",
    "um according to dosing instructions. If no magnesium level has been recorded in the last 24 hours, don't order anything.\nmodel_prediction_summary: {\"finish_result\": \"[\\\"The patient S6537563's last serum magnesium level within the last 24 hours was 2.1 mg/dL (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the normal range (>= 1.9 mg/dL) and not low according to the provided dosing instructions, no replacement IV magnesium was ordered.\\\"]\", \"status\": \"completed\"}"
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

umsb-mpnet-episodic-memory / README.md

bdanko

Upload folder using huggingface_hub

90faecd verified 19 days ago

preview code

raw

history blame contribute delete

38 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:3067
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: >-
      um according to dosing instructions. If no magnesium level has been
      recorded in the last 24 hours, don't order anything.

      model_prediction_summary: {"finish_result": "[\"The patient S6537563's
      last serum magnesium level within the last 24 hours was 2.1 mg/dL
      (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the
      normal range (>= 1.9 mg/dL) and not low according to the provided dosing
      instructions, no replacement IV magnesium was ordered.\"]", "status":
      "completed"}
    sentences:
      - >-
        model correctly identified the age of the patient with MRN S6542579 as
        28 based on the provided context and patient data

        Although the official reference solution pass flag was false (likely due
        to an internal evaluation error or missing expected output in the prompt
        metadata), the model's answer is factually correct according to the
        standard dataset associated with this MRN and the
      - >-
        he rate such as \"h\" ", "type": "string"}, "value": {"type":
        "number"}}, "type": "object"}}, "type": "object"}, "type":

        "array"}, "route": {"properties": {"text": {"description": "The
        medication route.", "type": "string"}}, "type": "object"}}, "type":
        "object"}, "type": "array"}, "intent": {"description": "Use \"order\" ",
        "type": "string"}, "medicationCodeableConcept": {"properties":
        {"coding": {"items": {"properties": {"code": {"description": "The actual
        code", "type": "string"}, "display": {"description": "Display name",
        "type": "string"}, "system": {"description": "Coding system such as
        \"http://hl7.org/fhir/sid/ndc\" ", "type": "string"}}, "type":
        "object"}, "type": "array"}, "text": {"description": "The order display
        name of the medication, otherwise the record name.", "type": "string"}},
        "type": "object"}, "resourceType": {"description": "Use
        \"MedicationRequest\" for medication requests.", "type": "string"},
        "status": {"description": "The status of the medication request
      - >-
        um according to dosing instructions. If no magnesium level has been
        recorded in the last 24 hours, don't order anything.

        model_prediction_summary: {"finish_result": "[\"The patient S6537563's
        last serum magnesium level within the last 24 hours was 2.1 mg/dL
        (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the
        normal range (>= 1.9 mg/dL) and not low according to the provided dosing
        instructions, no replacement IV magnesium was ordered.\"]", "status":
        "completed"}
  - source_sentence: >-
      er that assists transcription by interacting with regulatory proteins.


      A. Enhancer

      B. Repressor

      C. Operator

      D. Promoter

      model_prediction_summary: {"answer": "A", "raw":
      "{\"answer\":\"A\",\"confidence\":0.9}", "metadata": {"usage":
      {"completion_tokens": 11, "prompt_tokens": 70, "total_tokens": 81,
      "completion_tokens_details": {"accepted_prediction_tokens": null,
      "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
      null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
      "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
      6.732e-05, "is_byok": false, "cost_details": {"upstream_inference_cost":
      6.8e-05, "upstream_inference_prompt_cost": 3.5e-05,
      "upstream_inference_completions_cost": 3.3e-05}}}}

      judge_or_scorer_feedback: {"confidence": 0.9}

      traversal_excerpt: system: You are a medical expert. Return ONLY valid
      JSON in this exact format: {"answer":"A","confidence":0.0}. The answer
      must be A, B, C, or D.
    sentences:
      - >-
        tals) The FHIR Observation.Create (Vitals) resource can file to all
        non-duplicable flowsheet rows, including vital signs

        This resource can file vital signs for all flowsheets.", "name": "POST
        {api_base}/Observation", "parameters": {"properties": {"category":
        {"items": {"properties": {"coding": {"items": {"properties": {"code":
        {"description": "Use \"vital-signs\" ", "type": "string"}, "display":
        {"description": "Use \"Vital Signs\" ", "type": "string"}, "system":
        {"description": "Use \"http://hl7.org/fhir/observation-category\" ",
        "type": "string"}}, "type": "object"}, "type": "array"}}, "type":
        "object"}, "type": "array"}, "code": {"properties": {"text":
        {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes
        to flowsheet mapping
      - >-
        er that assists transcription by interacting with regulatory proteins.


        A. Enhancer

        B. Repressor

        C. Operator

        D. Promoter

        model_prediction_summary: {"answer": "A", "raw":
        "{\"answer\":\"A\",\"confidence\":0.9}", "metadata": {"usage":
        {"completion_tokens": 11, "prompt_tokens": 70, "total_tokens": 81,
        "completion_tokens_details": {"accepted_prediction_tokens": null,
        "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
        null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        6.732e-05, "is_byok": false, "cost_details": {"upstream_inference_cost":
        6.8e-05, "upstream_inference_prompt_cost": 3.5e-05,
        "upstream_inference_completions_cost": 3.3e-05}}}}

        judge_or_scorer_feedback: {"confidence": 0.9}

        traversal_excerpt: system: You are a medical expert. Return ONLY valid
        JSON in this exact format: {"answer":"A","confidence":0.0}. The answer
        must be A, B, C, or D.
      - >-
        Ductography

        B. Excisional biopsy of glandular tissue

        C. Repeat mammography

        D. Repeat ultrasonography of the right breast

        model_prediction_summary: {"answer": "D", "raw":
        "{\"answer\":\"D\",\"confidence\":0.9}", "metadata": {"usage":
        {"completion_tokens": 11, "prompt_tokens": 238, "total_tokens": 249,
        "completion_tokens_details": {"accepted_prediction_tokens": null,
        "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
        null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        0.00015048, "is_byok": false, "cost_details":
        {"upstream_inference_cost": 0.000152, "upstream_inference_prompt_cost":
        0.000119, "upstream_inference_completions_cost": 3.3e-05}}}}

        judge_or_scorer_feedback: {"confidence": 0.9}

        traversal_excerpt: system: You are a medical expert. Return ONLY valid
        JSON in this exact format: {"answer":"A","confidence":0.0}. The answer
        must be A, B, C, or D.
  - source_sentence: >-
      tals) The FHIR Observation.Create (Vitals) resource can file to all
      non-duplicable flowsheet rows, including vital signs

      This resource can file vital signs for all flowsheets.", "name": "POST
      {api_base}/Observation", "parameters": {"properties": {"category":
      {"items": {"properties": {"coding": {"items": {"properties": {"code":
      {"description": "Use \"vital-signs\" ", "type": "string"}, "display":
      {"description": "Use \"Vital Signs\" ", "type": "string"}, "system":
      {"description": "Use \"http://hl7.org/fhir/observation-category\" ",
      "type": "string"}}, "type": "object"}, "type": "array"}}, "type":
      "object"}, "type": "array"}, "code": {"properties": {"text":
      {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes to
      flowsheet mapping
    sentences:
      - >-
        of the three cases, and you can call only one function each time. You
        SHOULD NOT include any other text in the response.

        Here is a list of functions in JSON format that you can invoke. Note
        that you should use https://medagentbench.openwear.ai/fhir as the
        api_base.
      - >-
        asoning_tokens": 0, "rejected_prediction_tokens": null, "image_tokens":
        0}, "prompt_tokens_details": {"audio_tokens": 0,

        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        0.00188496, "is_byok": false, "cost_details":
        {"upstream_inference_cost": 0.001904, "upstream_inference_prompt_cost":
        0.001814, "upstream_inference_completions_cost": 9e-05}},
        {"completion_tokens": 78, "prompt_tokens": 4557, "total_tokens": 4635,
        "completion_tokens_details": {"accepted_prediction_tokens": null,
        "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
        null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        0.002487375, "is_byok": false, "cost_details":
        {"upstream_inference_cost": 0.0025125, "upstream_inference_prompt_cost":
        0.0022785,
      - >-
        tals) The FHIR Observation.Create (Vitals) resource can file to all
        non-duplicable flowsheet rows, including vital signs

        This resource can file vital signs for all flowsheets.", "name": "POST
        {api_base}/Observation", "parameters": {"properties": {"category":
        {"items": {"properties": {"coding": {"items": {"properties": {"code":
        {"description": "Use \"vital-signs\" ", "type": "string"}, "display":
        {"description": "Use \"Vital Signs\" ", "type": "string"}, "system":
        {"description": "Use \"http://hl7.org/fhir/observation-category\" ",
        "type": "string"}}, "type": "object"}, "type": "array"}}, "type":
        "object"}, "type": "array"}, "code": {"properties": {"text":
        {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes
        to flowsheet mapping
  - source_sentence: >-
      nRequest\" for medication requests.", "type": "string"}, "status":
      {"description": "The status of the medication request

      Use \"active\" ", "type": "string"}, "subject": {"properties":
      {"reference": {"description": "The patient FHIR ID for who the medication
      request is for.", "type": "string"}}, "type": "object"}}, "required":
      ["resourceType", "medicationCodeableConcept", "authoredOn",
      "dosageInstruction", "status", "intent", "subject"], "type": "object"}},
      {"description": "Procedure.Search (Orders) The FHIR Procedure resource
      defines an activity performed on or with a patient as part of the
      provision of care. It corresponds with surgeries and procedures performed,
      including endoscopies and biopsies, as well as less invasive actions like
      counseling and physiotherapy.\n\nThis resource is designed for a
      high-level summarization around the occurrence of a procedure, and not for
      specific procedure log documentation - a concept that does not yet have a
      defined FHIR Resource
    sentences:
      - >-
        een successfully ordered with the specified clinical notes. The
        ServiceRequest ID is 786041.\"]", "status": "completed"}

        judge_or_scorer_feedback: {"status": "completed", "reset": null,
        "llm_usage": [{"completion_tokens": 238, "prompt_tokens": 3362,
        "total_tokens": 3600, "completion_tokens_details":
        {"accepted_prediction_tokens": null, "audio_tokens": 0,
        "reasoning_tokens": 0, "rejected_prediction_tokens": null,
        "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        0.00237105, "is_byok": false, "cost_details":
        {"upstream_inference_cost": 0.002395, "upstream_inference_prompt_cost":
        0.001681, "upstream_inference_completions_cost": 0.000714}},
        {"completion_tokens": 41, "prompt_tokens": 3877, "total_tokens": 3918,
        "completion_tokens_details": {"accepted_prediction_tokens": null,
        "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
        null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
      - >-
        nRequest\" for medication requests.", "type": "string"}, "status":
        {"description": "The status of the medication request

        Use \"active\" ", "type": "string"}, "subject": {"properties":
        {"reference": {"description": "The patient FHIR ID for who the
        medication request is for.", "type": "string"}}, "type": "object"}},
        "required": ["resourceType", "medicationCodeableConcept", "authoredOn",
        "dosageInstruction", "status", "intent", "subject"], "type": "object"}},
        {"description": "Procedure.Search (Orders) The FHIR Procedure resource
        defines an activity performed on or with a patient as part of the
        provision of care. It corresponds with surgeries and procedures
        performed, including endoscopies and biopsies, as well as less invasive
        actions like counseling and physiotherapy.\n\nThis resource is designed
        for a high-level summarization around the occurrence of a procedure, and
        not for specific procedure log documentation - a concept that does not
        yet have a defined FHIR Resource
      - >-
        t: Lassa and Ebola are emergent viruses in W. Africa. What is their
        origin?


        A. Humans

        B. Primates

        C. Fruit bats

        D. Pigs

        model_prediction_summary: {"answer": "C", "raw":
        "{\"answer\":\"C\",\"confidence\":0.95}", "metadata": {"usage":
        {"completion_tokens": 12, "prompt_tokens": 76, "total_tokens": 88,
        "completion_tokens_details": {"accepted_prediction_tokens": null,
        "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens":
        null, "image_tokens": 0}, "prompt_tokens_details": {"audio_tokens": 0,
        "cached_tokens": 0, "cache_write_tokens": 0, "video_tokens": 0}, "cost":
        7.326e-05, "is_byok": false, "cost_details": {"upstream_inference_cost":
        7.4e-05, "upstream_inference_prompt_cost": 3.8e-05,
        "upstream_inference_completions_cost": 3.6e-05}}}}

        judge_or_scorer_feedback: {"confidence": 0.95}

        traversal_excerpt: system: You are a medical expert. Return ONLY valid
        JSON in this exact format: {"answer":"A","confidence":0.0}. The answer
        must be A, B, C, or D.
  - source_sentence: >-
      e medication administration date. This parameter corresponds to the
      dosageInstruction.timing.repeat.boundsPeriod element

      Medication orders that do not have start and end dates within the search
      parameter dates are filtered. If the environment supports multiple time
      zones, the search dates are adjusted one day in both directions, so more
      medications might be returned than expected. Use caution when filtering a
      medication list by date as it is possible to filter out important active
      medications. Starting in the November 2022 version of Epic, this parameter
      is respected
    sentences:
      - >-
        e medication administration date. This parameter corresponds to the
        dosageInstruction.timing.repeat.boundsPeriod element

        Medication orders that do not have start and end dates within the search
        parameter dates are filtered. If the environment supports multiple time
        zones, the search dates are adjusted one day in both directions, so more
        medications might be returned than expected. Use caution when filtering
        a medication list by date as it is possible to filter out important
        active medications. Starting in the November 2022 version of Epic, this
        parameter is respected
      - >-
        benchmark: medagentbench

        task_id: medagentbench::train::task7_29

        reward: 0.0

        failure_mode: completed

        general_advice: Use only the permitted FHIR action format, inspect tool
        responses before finishing, and call FINISH only with the requested
        final values.

        task_request: You are an expert in using FHIR functions to assist
        medical professionals. You are given a question and a set of possible
        functions. Based on the question, you will need to make one or more
        function/tool calls to achieve the purpose.


        1. If you decide to invoke a GET function, you MUST put it in the format
        of

        GET url?param_name1=param_value1&param_name2=param_value2...


        2. If you decide to invoke a POST function, you MUST put it in the
        format of

        POST url

        [your payload data in JSON format]
      - >-
        e": {"properties": {"text": {"description": "The flowsheet ID, encoded
        flowsheet ID, or LOINC codes to flowsheet mapping

        What is being measured.", "type": "string"}}, "type": "object"},
        "effectiveDateTime": {"description": "The date and time the observation
        was taken, in ISO format.", "type": "string"}, "resourceType":
        {"description": "Use \"Observation\" for vitals observations.", "type":
        "string"}, "status": {"description": "The status of the observation.
        Only a value of \"final\" is supported
pipeline_tag: sentence-similarity
library_name: sentence-transformers

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 umsb-episodic-memory dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

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
Supported Modality: Text
Training Dataset:
- umsb-episodic-memory

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'MPNetModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'e medication administration date. This parameter corresponds to the dosageInstruction.timing.repeat.boundsPeriod element\nMedication orders that do not have start and end dates within the search parameter dates are filtered. If the environment supports multiple time zones, the search dates are adjusted one day in both directions, so more medications might be returned than expected. Use caution when filtering a medication list by date as it is possible to filter out important active medications. Starting in the November 2022 version of Epic, this parameter is respected',
    'e medication administration date. This parameter corresponds to the dosageInstruction.timing.repeat.boundsPeriod element\nMedication orders that do not have start and end dates within the search parameter dates are filtered. If the environment supports multiple time zones, the search dates are adjusted one day in both directions, so more medications might be returned than expected. Use caution when filtering a medication list by date as it is possible to filter out important active medications. Starting in the November 2022 version of Epic, this parameter is respected',
    'e": {"properties": {"text": {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes to flowsheet mapping\nWhat is being measured.", "type": "string"}}, "type": "object"}, "effectiveDateTime": {"description": "The date and time the observation was taken, in ISO format.", "type": "string"}, "resourceType": {"description": "Use \\"Observation\\" for vitals observations.", "type": "string"}, "status": {"description": "The status of the observation. Only a value of \\"final\\" is supported',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 1.0000, 0.3683],
#         [1.0000, 1.0000, 0.3683],
#         [0.3683, 0.3683, 1.0000]])

Training Details

Training Dataset

umsb-episodic-memory

Dataset: umsb-episodic-memory
Size: 3,067 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 33 tokens
mean: 221.24 tokens
max: 384 tokens

min: 33 tokens
mean: 221.24 tokens
max: 384 tokens

	anchor	positive
type	string	string
details	min: 33 tokens mean: 221.24 tokens max: 384 tokens	min: 33 tokens mean: 221.24 tokens max: 384 tokens

Samples:

anchor	positive
description": "The patient's family (last) name.", "type": "string"}, "gender": {"description": "The patient's legal sex Starting in the August 2021 version of Epic, the legal-sex parameter is preferred.", "type": "string"}, "given": {"description": "The patient's given name. May include first and middle names.", "type": "string"}, "identifier": {"description": "The patient's identifier.", "type": "string"}, "legal-sex": {"description": "The patient\u2019s legal sex. Takes precedence over the gender search parameter. Available starting in the August 2021 version of Epic.", "type": "string"}, "name": {"description": "Any part of the patient's name. When discrete name parameters are used, such as family or given, this parameter is ignored.", "type": "string"}, "telecom": {"description": "The patient's phone number or email.", "type": "string"}}, "required": [], "type": "object"}}]	description": "The patient's family (last) name.", "type": "string"}, "gender": {"description": "The patient's legal sex Starting in the August 2021 version of Epic, the legal-sex parameter is preferred.", "type": "string"}, "given": {"description": "The patient's given name. May include first and middle names.", "type": "string"}, "identifier": {"description": "The patient's identifier.", "type": "string"}, "legal-sex": {"description": "The patient\u2019s legal sex. Takes precedence over the gender search parameter. Available starting in the August 2021 version of Epic.", "type": "string"}, "name": {"description": "Any part of the patient's name. When discrete name parameters are used, such as family or given, this parameter is ignored.", "type": "string"}, "telecom": {"description": "The patient's phone number or email.", "type": "string"}}, "required": [], "type": "object"}}]
`e to filter out important active medications. Starting in the November 2022 version of Epic, this parameter is respected`
In May 2022 and earlier versions of Epic, this parameter is allowed but is ignored and no date filtering is applied.", "type": "string"}, "patient": {"description": "The FHIR patient ID.", "type": "string"}}, "required": ["patient"], "type": "object"}}, {"description": "MedicationRequest.Create", "name": "POST {api_base}/MedicationRequest", "parameters": {"properties": {"authoredOn": {"description": "The date the prescription was written.", "type": "string"}, "dosageInstruction": {"items": {"properties": {"doseAndRate": {"items": {"properties": {"doseQuantity": {"properties": {"unit": {"description": "unit for the dose such as "g" ", "type": "string"}, "value": {"type": "number"}}, "type": "object"}, "rateQuantity": {"properties": {"unit": {"description": "unit for the rate such as "h" ", "type": "string"}, "value": {"type": "number"}}, "type": "object"}}, "type"...	`e to filter out important active medications. Starting in the November 2022 version of Epic, this parameter is respected`
In May 2022 and earlier versions of Epic, this parameter is allowed but is ignored and no date filtering is applied.", "type": "string"}, "patient": {"description": "The FHIR patient ID.", "type": "string"}}, "required": ["patient"], "type": "object"}}, {"description": "MedicationRequest.Create", "name": "POST {api_base}/MedicationRequest", "parameters": {"properties": {"authoredOn": {"description": "The date the prescription was written.", "type": "string"}, "dosageInstruction": {"items": {"properties": {"doseAndRate": {"items": {"properties": {"doseQuantity": {"properties": {"unit": {"description": "unit for the dose such as "g" ", "type": "string"}, "value": {"type": "number"}}, "type": "object"}, "rateQuantity": {"properties": {"unit": {"description": "unit for the rate such as "h" ", "type": "string"}, "value": {"type": "number"}}, "type": "object"}}, "type"...
`e": {"properties": {"text": {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes to flowsheet mapping What is being measured.", "type": "string"}}, "type": "object"}, "effectiveDateTime": {"description": "The date and time the observation was taken, in ISO format.", "type": "string"}, "resourceType": {"description": "Use "Observation" for vitals observations.", "type": "string"}, "status": {"description": "The status of the observation. Only a value of "final" is supported`	`e": {"properties": {"text": {"description": "The flowsheet ID, encoded flowsheet ID, or LOINC codes to flowsheet mapping What is being measured.", "type": "string"}}, "type": "object"}, "effectiveDateTime": {"description": "The date and time the observation was taken, in ISO format.", "type": "string"}, "resourceType": {"description": "Use "Observation" for vitals observations.", "type": "string"}, "status": {"description": "The status of the observation. Only a value of "final" is supported`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
num_train_epochs: 2
learning_rate: 2e-05
warmup_steps: 0.05
fp16: True

All Hyperparameters

Click to expand

per_device_train_batch_size: 32
num_train_epochs: 2
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.05
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 8
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.2604	25	0.3777
0.5208	50	0.3348
0.7812	75	0.3936
1.0417	100	0.3583
1.3021	125	0.3227
1.5625	150	0.3224
1.8229	175	0.3492

Training Time

Training: 2.4 minutes

Framework Versions

Python: 3.11.12
Sentence Transformers: 5.4.1
Transformers: 5.8.0
PyTorch: 2.11.0+cu130
Accelerate: 1.13.0
Datasets: 4.8.5
Tokenizers: 0.22.2

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}