metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
  - dataset_size:164
base_model: Snowflake/snowflake-arctic-embed-l
widget:
  - source_sentence: >-
      What steps must be taken before an app can receive communication from Flow
      actions?
    sentences:
      - >-
        Before your app can receive communication from Flow actions, you need to
        create one or more standardized API endpoints on your web server. Review
        the information for each endpoint to understand its requirements, the
        format of the payload, and the expected response. You'll also learn how
        to avoid processing duplicate requests, identify an action by its ID,
        and verify requests for security purposes.
      - >-
        Apps must be properly configured to respond to trigger lifecycle
        callbacks. When a merchant attempts to enable a workflow that uses the
        trigger, Shopify Flow sends a lifecycle callback to the app's web
        server. If it doesn't promptly receive a response or receives a response
        with an HTTP status code that isn't 2xx, then the merchant can't enable
        the workflow and make use of the trigger.


        Note: Legacy trigger discovery webhook extensions created using the
        Partner Dashboard are deprecated and must migrate to the CLI before they
        can be edited.


        How trigger lifecycle callbacks work


        Trigger lifecycle callbacks contain identifying information about the
        trigger and the store using it and indicate whether the trigger is being
        used. You can use this information to track the stores that are
        currently using your triggers and then send trigger requests to only
        those stores.


        Properties
      - >-
        Enter a title and description for the action. In the Action Preview
        area, you can see how the title and action display to merchants when
        they're choosing actions in Shopify Flow.


        Enter the URL for the action execution endpoint that you created.
        Shopify Flow sends the action's JSON payload to this endpoint when it's
        about to execute your action.


        Step 2: Customize a Flow action configuration file


        In this section you'll use the default action template and update it to
        be a functional extension example. Once you have generated a Flow
        extension using Shopify CLI, follow the instructions below:


        Change the description to Place a bid on an auction.


        Update the extensions.runtime_url to an endpoint where you can receive
        the runtime request.


        On the second settings.fields field, update the following values:


        type to number_decimal


        key to amount


        name to Bid Amount


        Add a description property and set it to The amount of the bid
  - source_sentence: >-
      What type and key are assigned to the second settings.fields field in the
      configuration?
    sentences:
      - >-
        [[settings.fields]] type = "customer_reference"


        [[settings.fields]] type = "single_line_text_field" key = "your field
        key" ```


        Trigger extension properties


        Extension properties are listed in the [[extensions]] section and enable
        you to define the interface between Flow and your event.


        Property name Description Rules name Required Name of your extension.
        Will be the merchant-facing name of your task in the editor. This should
        be something that is human readable. type Required The type of your
        extension. This should always be set to “flow_trigger” for Flow
        triggers. - Value must be flow_trigger . handle Required A unique
        identifier for your extension. This property cannot be changed once
        you’ve run the dev or deploy command. - Cannot exceed 30 characters. -
        Must be unique across your app's extensions. - Must only contain
        alphanumeric characters and hyphens. description Optional A description
        of your extension. This description will be shown in the Flow editor
        navigation panel.
      - >-
        Change the description to Place a bid on an auction.


        Update the extensions.runtime_url to an endpoint where you can receive
        the runtime request.


        On the second settings.fields field, update the following values:


        type to number_decimal


        key to amount


        name to Bid Amount


        Add a description property and set it to The amount of the bid


        ```bash [[extensions]] name = "Place Auction Bid" type = "flow_action"
        handle = "place-bid" description = "Place a bid on an auction"
        runtime_url = "https://your-server-domain/path/to/action/handler"


        [settings]


        [[settings.fields]] type = "customer_reference" required = true


        [[settings.fields]] type = "number_decimal" key = "amount" name = "Bid
        Amount" description = "The amount of the bid" required = true ```


        Step 3: Configure your web server


        To build a Shopify Flow action, you need to add a service to your web
        server to listen for the JSON payload that Shopify Flow sends when the
        action runs.


        Optionally, you can also add the following:
      - >-
        To give merchants a more seamless action configuration experience, and
        to allow them to manage resources that are external to Shopify Flow, you
        can embed a page from your app in the Shopify Flow editor.


        In your Shopify Flow action configuration, merchants see a preview with
        an image and text that's fetched from your custom configuration page
        preview URL. Merchants can click the button to access the custom
        configuration page.


        Your custom configuration page is then displayed in a frame in the
        Shopify admin.


        In this tutorial, you'll learn how to render a custom configuration page
        in Shopify Flow, customize the page frame, and access data relevant to
        your action in the custom configuration page context.


        Requirements


        You've created a Partner account.


        You've created an app.


        Resources


        To implement this feature, you'll use the following:


        Shopify App Bridge


        App Bridge components


        App Bridge actions specific to the custom configuration page


        Implementing a custom configuration page
  - source_sentence: >-
      What is the purpose of updating the description in the flow extension to
      "Trigger for auction bids"?
    sentences:
      - >-
        The following procedure requires you to have generated a flow extension
        using Shopify CLI. In this section you'll use the default trigger
        template and update it to be a functional extension example.


        Change description to Trigger for auction bids.


        On the second [[settings.fields]] field, update:


        type to number_decimal


        key to Amount


        ```bash [[extensions]] name = "Auction Bid Placed" type = "flow_trigger"
        handle = "auction-bid-placed" description = "Trigger for auction bids."


        [settings]


        [[settings.fields]] type = "customer_reference"


        [[settings.fields]] type = "number_decimal" key = "Amount" ```


        Step 3: Enable the draft version of your trigger


        Running app dev allows changes made to local files to update the draft
        version of your Flow task extensions. The draft version is only
        available in your development store.
      - >-
        Custom step descriptions added within the workflow.


        Adding additional locales


        Add new .json files prefixed with the locale, for example es.json.


        Add default to one of the locales to make it the fallback if a
        merchant's locale isn't in the locales you have provided. Example:
        en.default.json.


        Step descriptions


        You can provide translated custom step descriptions by adding a
        translation key wrapped by curly braces in the step description field.
        For example, {expressShippingCondition}. Ensure there's no other
        characters before or after {yourKey}. After adding this to your
        workflow, you can update the translation files to include the step
        description.


        The following is an example:
      - >-
        Supported field types


        When you create a trigger, you add the fields that your trigger sends to
        Shopify Flow in the [settings] section of the TOML file. These fields
        define what your event plans to send to Shopify Flow. Merchants can then
        use that data in their conditions and actions.


        You can add two types of fields: custom fields or predefined reference
        fields.


        Reference field types


        A reference field lets you send the identifier of a Shopify resource to
        Shopify Flow. This allows merchants to build workflows that use any data
        related to that resource.


        For example, your trigger sends a customer ID to Shopify Flow. The
        merchant can create a condition that checks customer / amountSpent and
        customer / tags. In their action, the merchant can include the template
        variables for customers, such as {{customer.email}}.


        To specify that a trigger will include a reference field, you only need
        to specify the type and an optional description property. For example:


        ```bash ...


        [settings]
  - source_sentence: >-
      How can you add custom configuration page URLs to your Shopify Flow action
      configuration?
    sentences:
      - >-
        Custom step descriptions added within the workflow.


        Adding additional locales


        Add new .json files prefixed with the locale, for example es.json.


        Add default to one of the locales to make it the fallback if a
        merchant's locale isn't in the locales you have provided. Example:
        en.default.json.


        Step descriptions


        You can provide translated custom step descriptions by adding a
        translation key wrapped by curly braces in the step description field.
        For example, {expressShippingCondition}. Ensure there's no other
        characters before or after {yourKey}. After adding this to your
        workflow, you can update the translation files to include the step
        description.


        The following is an example:
      - >-
        Navigate to your app directory.


        Run the following command to start using draft versions of your
        extension(s):


        ```bash


        !/bin/bash


        shopify app dev ```


        Follow the prompts.


        Step 4: Test your trigger


        After the app dev command has started, you can test the draft version of
        your trigger in Shopify Flow.


        In your development store, create a workflow that uses the trigger that
        you created for your app.


        Using the Admin GraphQL API, send a flowTriggerReceive mutation with the
        following arguments:


        The handle of the trigger


        The payload of the trigger containing the fields defined in the
        extension TOML


        The size of the payload (keys included) must be under 50 KB. If the size
        of the properties body exceeds the limit, then Shopify responds to the
        GraphQL request with a validation error reading Properties size exceeds
        the limit of 50000 bytes. As a result, workflows with the specified
        trigger won't start from this request.


        The following is an example of a flowTriggerReceive mutation:
      - >-
        const titleBar = TitleBar.create(app, { title: '', buttons: { primary:
        primaryBtn, secondary: [secondaryBtn], }, })


        // update buttons after initialization const newPrimary =
        Button.create(app, { label: 'New button', })
        newPrimary.subscribe(Button.Action.CLICK, () => { console.log('new
        primary button clicked') })


        titleBar.set({ buttons: { primary: newPrimary, secondary:
        [secondaryBtn], }, })


        jsx import { TitleBar } from '@shopify/app-bridge-react'


        function Page() { const buttons = { primaryAction: { content: 'Button
        1', onAction: () => { console.log('button 1 clicked') }, },
        secondaryActions: [ { content: 'Button 2', onAction: () => {
        console.log('button 2 clicked') }, }, ], }


        return } ```


        Next steps


        Add custom configuration page preview URL and custom validation
        endpoints to your app.


        Add your custom configuration page preview URL, custom configuration
        page URL, and custom validation URL to your Shopify Flow action
        configuration.
  - source_sentence: >-
      How can you access step and property information on the custom
      configuration page?
    sentences:
      - >-
        Property Data type Description Example flow_trigger_definition_id String
        The unique identifier for your Shopify Flow trigger. Add row to
        spreadsheet has_enabled_flow Boolean Whether the store has an enabled
        workflow that uses your trigger. Valid values: true : There is at least
        one workflow that is enabled and that uses your trigger. false : There
        are no enabled workflows that use your trigger. true shop_id Number The
        unique identifier for the Shopify store. 690933842 shopify_domain String
        The myshopify domain of the Shopify store. johnsapparel.myshopify.com
        timestamp ISO 8601 date and timestamp The time when the notification was
        created. Notifications with newer timestamps should take precedence. If
        you already have a timestamp in your datastore and you receive a newer
        timestamp, then overwrite this payload's information in your datastore.
        Conversely, if you receive a timestamp that is older than the
        information in your datastore, then ignore this payload.
        2019-01-25T16:44:10.999Z
      - >-
        Implementing a custom configuration page


        To build a custom configuration page, you'll use Shopify App Bridge to
        render a page from your app page in Shopify Flow.


        From the context of the custom configuration page, you can then access
        step and property information that you can use to display the
        appropriate information.


        You can also add additional buttons to the App Bridge title bar, or
        trigger a redirect to the previous page.


        Use Shopify App Bridge to render your app page


        Note: The specifics of the Custom Configuration Page integration varies
        between Shopify App Bridge versions. Make sure you implement the
        integration specific to your Shopify App Bridge version.


        To render your custom configuration page, you need to integrate Shopify
        App Bridge on the route that you want to render. To learn about setting
        up Shopify App Bridge, refer to one of the following pages:


        Getting started with Shopify App Bridge


        Getting started with App Bridge React


        Access action information
      - >-
        To give merchants a more seamless action configuration experience, and
        to allow them to manage resources that are external to Shopify Flow, you
        can embed a page from your app in the Shopify Flow editor.


        In your Shopify Flow action configuration, merchants see a preview with
        an image and text that's fetched from your custom configuration page
        preview URL. Merchants can click the button to access the custom
        configuration page.


        Your custom configuration page is then displayed in a frame in the
        Shopify admin.


        In this tutorial, you'll learn how to render a custom configuration page
        in Shopify Flow, customize the page frame, and access data relevant to
        your action in the custom configuration page context.


        Requirements


        You've created a Partner account.


        You've created an app.


        Resources


        To implement this feature, you'll use the following:


        Shopify App Bridge


        App Bridge components


        App Bridge actions specific to the custom configuration page


        Implementing a custom configuration page
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 Snowflake/snowflake-arctic-embed-l
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.5416666666666666
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 1
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5416666666666666
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.20000000000000004
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5416666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 1
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8144765845238192
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.75
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.75
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-l

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. 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: Snowflake/snowflake-arctic-embed-l
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

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: 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:

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("thomfoolery/AIE5-MidTerm-finetuned-embeddings")
# Run inference
sentences = [
    'How can you access step and property information on the custom configuration page?',
    "Implementing a custom configuration page\n\nTo build a custom configuration page, you'll use Shopify App Bridge to render a page from your app page in Shopify Flow.\n\nFrom the context of the custom configuration page, you can then access step and property information that you can use to display the appropriate information.\n\nYou can also add additional buttons to the App Bridge title bar, or trigger a redirect to the previous page.\n\nUse Shopify App Bridge to render your app page\n\nNote: The specifics of the Custom Configuration Page integration varies between Shopify App Bridge versions. Make sure you implement the integration specific to your Shopify App Bridge version.\n\nTo render your custom configuration page, you need to integrate Shopify App Bridge on the route that you want to render. To learn about setting up Shopify App Bridge, refer to one of the following pages:\n\nGetting started with Shopify App Bridge\n\nGetting started with App Bridge React\n\nAccess action information",
    "To give merchants a more seamless action configuration experience, and to allow them to manage resources that are external to Shopify Flow, you can embed a page from your app in the Shopify Flow editor.\n\nIn your Shopify Flow action configuration, merchants see a preview with an image and text that's fetched from your custom configuration page preview URL. Merchants can click the button to access the custom configuration page.\n\nYour custom configuration page is then displayed in a frame in the Shopify admin.\n\nIn this tutorial, you'll learn how to render a custom configuration page in Shopify Flow, customize the page frame, and access data relevant to your action in the custom configuration page context.\n\nRequirements\n\nYou've created a Partner account.\n\nYou've created an app.\n\nResources\n\nTo implement this feature, you'll use the following:\n\nShopify App Bridge\n\nApp Bridge components\n\nApp Bridge actions specific to the custom configuration page\n\nImplementing a custom configuration page",
]
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]

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5417
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.5417
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.5417
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.8145
cosine_mrr@10	0.75
cosine_map@100	0.75

Training Details

Training Dataset

Unnamed Dataset

Size: 164 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 164 samples:
sentence_0 sentence_1
type string string
details
min: 13 tokens
mean: 19.51 tokens
max: 32 tokens

min: 77 tokens
mean: 198.13 tokens
max: 309 tokens

	sentence_0	sentence_1
type	string	string
details	min: 13 tokens mean: 19.51 tokens max: 32 tokens	min: 77 tokens mean: 198.13 tokens max: 309 tokens

Samples:

sentence_0	sentence_1
`What is the purpose of templates in Shopify Flow?`	How templates work A template in Shopify Flow is an example workflow that can be copied into a merchant's shop. Templates help merchants automate a specific use case with minimal or no additional configuration. Flow's template library offers hundreds of templates with features to filter, browse, and search. You can create a template for Shopify Flow that showcases your custom triggers and actions and help merchants do more. Next steps Follow our step by step guide on creating a Flow template. Learn more about how localize your template, the approval process, and more in the reference resource
`How can merchants utilize the template library in Shopify Flow?`	How templates work A template in Shopify Flow is an example workflow that can be copied into a merchant's shop. Templates help merchants automate a specific use case with minimal or no additional configuration. Flow's template library offers hundreds of templates with features to filter, browse, and search. You can create a template for Shopify Flow that showcases your custom triggers and actions and help merchants do more. Next steps Follow our step by step guide on creating a Flow template. Learn more about how localize your template, the approval process, and more in the reference resource
`What is required for the test web server to successfully send information to Shopify Flow?`	Requirements Make sure that you have the following: A test web server that you can use to send information to Shopify Flow. You can use an existing web server. This web server needs to be able to send POST requests to Shopify's GraphQL Admin API. A test app that works with the test web server and can send HTTP requests. A development store that has Shopify Flow and the test app installed. Your application has access to the read_customers scope. The trigger you will build using this tutorial will be using a customer reference which requires that scope. Step 1: Create a Flow trigger extension To give your Flow action a meaningful name, use the following guidelines: Use an object acted on + past tense verb format. For example, Auction bid placed. Use sentence case. Don't use punctuation. Separate words using spaces. Using Shopify CLI The following steps show how to create a trigger that sends bid information to Shopify Flow when a bid is placed on an auction.

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
num_train_epochs: 10
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
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
num_train_epochs: 10
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: False
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: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_ndcg@10
1.0	17	0.8353
2.0	34	0.8299
2.9412	50	0.8507
3.0	51	0.8507
4.0	68	0.8353
5.0	85	0.8452
5.8824	100	0.8606
6.0	102	0.8606
7.0	119	0.8299
8.0	136	0.8145
8.8235	150	0.8145
9.0	153	0.8145
10.0	170	0.8145

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.2
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",
}

MatryoshkaLoss

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

MultipleNegativesRankingLoss

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