metadata

language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:882
  - loss:MatryoshkaLoss
  - loss:TripletLoss
base_model: BAAI/bge-base-en-v1.5
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
widget:
  - source_sentence: >-
      hide: footer


      Fields


      Fields in Argilla are define the content of a record that will be reviewed
      by a user.
    sentences:
      - >-
        The tourists tried to hide their footprints in the sand as they walked
        along the deserted beach.
      - >-
        Can the rg.Suggestion class be used to handle model predictions in
        Argilla?
      - >-
        Can users customize the fields in Argilla to fit their specific
        annotation needs?
  - source_sentence: >-
      === "Single condition"


      === "Multiple conditions"


      Filter by status


      You can filter records based on their status. The status can be pending,
      draft, submitted, or discarded.


      ```python

      import argilla_sdk as rg


      client = rg.Argilla(api_url="", api_key="")


      workspace = client.workspaces("my_workspace")


      dataset = client.datasets(name="my_dataset", workspace=workspace)


      status_filter = rg.Query(
          filter = rg.Filter(("status", "==", "submitted"))
      )
    sentences:
      - The submitted application was rejected due to incomplete documentation.
      - How can I apply filters to records by their status in Argilla?
      - >-
        Can Argilla's IntegerMetadataProperty support a range of integer values
        as metadata?
  - source_sentence: >-
      description: In this section, we will provide a step-by-step guide to show
      how to filter and query a dataset.


      Query, filter, and export records


      This guide provides an overview of how to query and filter a dataset in
      Argilla and export records.
    sentences:
      - >-
        The new restaurant in town offers a unique filter coffee that is a
        must-try for coffee enthusiasts.
      - >-
        Is it possible to design a user role with tailored access permissions
        within Argilla?
      - >-
        Can Argilla be employed to search and filter datasets based on
        particular requirements or keywords?
  - source_sentence: >-
      hide: footer


      Fields


      Fields in Argilla are define the content of a record that will be reviewed
      by a user.
    sentences:
      - >-
        Is it possible for annotators to tailor Argilla's fields to their unique
        annotation requirements?
      - >-
        The tourists tried to hide their footprints in the sand as they walked
        along the deserted beach.
      - >-
        Can this partnership with Prolific provide researchers with a broader
        range of annotators to draw from, enhancing the quality of their
        studies?
  - source_sentence: >-
      hide: footer


      rg.Argilla


      To interact with the Argilla server from python you can use the Argilla
      class. The Argilla client is used to create, get, update, and delete all
      Argilla resources, such as workspaces, users, datasets, and records.


      Usage Examples


      Connecting to an Argilla server


      To connect to an Argilla server, instantiate the Argilla class and pass
      the api_url of the server and the api_key to authenticate.


      ```python

      import argilla_sdk as rg
    sentences:
      - >-
        Can the Argilla class be employed to streamline dataset administration
        tasks in my Argilla server setup?
      - >-
        Is it possible to create new data entries in my dataset via Argilla's
        annotation tools?
      - The Argilla flowers were blooming beautifully in the garden.
pipeline_tag: sentence-similarity
model-index:
  - name: BGE base ArgillaSDK Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.1326530612244898
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.2857142857142857
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3877551020408163
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5204081632653061
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1326530612244898
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09523809523809525
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07755102040816327
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05204081632653061
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1326530612244898
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2857142857142857
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3877551020408163
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5204081632653061
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3086125494748455
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.24321752510528016
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.26038538311827203
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.10204081632653061
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.2755102040816326
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3877551020408163
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5102040816326531
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.10204081632653061
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09183673469387756
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07755102040816327
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05102040816326531
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.10204081632653061
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2755102040816326
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3877551020408163
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5102040816326531
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.29420081448590024
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.22640913508260446
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.24259809105769914
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.12244897959183673
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.2755102040816326
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3877551020408163
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.12244897959183673
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09183673469387753
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07755102040816327
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.049999999999999996
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.12244897959183673
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2755102040816326
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3877551020408163
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2931450934182018
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2290937803692905
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.24454883014070852
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.09183673469387756
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.25510204081632654
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3163265306122449
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.46938775510204084
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.09183673469387756
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.08503401360544219
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.06326530612244897
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.046938775510204075
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.09183673469387756
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.25510204081632654
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3163265306122449
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.46938775510204084
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2629197762336244
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.1992265954000647
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2164845577697655
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.08163265306122448
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.25510204081632654
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3163265306122449
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.47959183673469385
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08163265306122448
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.08503401360544219
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.06326530612244897
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04795918367346938
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08163265306122448
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.25510204081632654
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3163265306122449
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.47959183673469385
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2610977190273289
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.19399497894395853
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.20591442395637935
            name: Cosine Map@100

BGE base ArgillaSDK Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

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': True}) with Transformer model: BertModel 
  (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})
  (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("plaguss/bge-base-argilla-sdk-matryoshka")
# Run inference
sentences = [
    'hide: footer\n\nrg.Argilla\n\nTo interact with the Argilla server from python you can use the Argilla class. The Argilla client is used to create, get, update, and delete all Argilla resources, such as workspaces, users, datasets, and records.\n\nUsage Examples\n\nConnecting to an Argilla server\n\nTo connect to an Argilla server, instantiate the Argilla class and pass the api_url of the server and the api_key to authenticate.\n\n```python\nimport argilla_sdk as rg',
    'Can the Argilla class be employed to streamline dataset administration tasks in my Argilla server setup?',
    'The Argilla flowers were blooming beautifully in the garden.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1327
cosine_accuracy@3	0.2857
cosine_accuracy@5	0.3878
cosine_accuracy@10	0.5204
cosine_precision@1	0.1327
cosine_precision@3	0.0952
cosine_precision@5	0.0776
cosine_precision@10	0.052
cosine_recall@1	0.1327
cosine_recall@3	0.2857
cosine_recall@5	0.3878
cosine_recall@10	0.5204
cosine_ndcg@10	0.3086
cosine_mrr@10	0.2432
cosine_map@100	0.2604

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.102
cosine_accuracy@3	0.2755
cosine_accuracy@5	0.3878
cosine_accuracy@10	0.5102
cosine_precision@1	0.102
cosine_precision@3	0.0918
cosine_precision@5	0.0776
cosine_precision@10	0.051
cosine_recall@1	0.102
cosine_recall@3	0.2755
cosine_recall@5	0.3878
cosine_recall@10	0.5102
cosine_ndcg@10	0.2942
cosine_mrr@10	0.2264
cosine_map@100	0.2426

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1224
cosine_accuracy@3	0.2755
cosine_accuracy@5	0.3878
cosine_accuracy@10	0.5
cosine_precision@1	0.1224
cosine_precision@3	0.0918
cosine_precision@5	0.0776
cosine_precision@10	0.05
cosine_recall@1	0.1224
cosine_recall@3	0.2755
cosine_recall@5	0.3878
cosine_recall@10	0.5
cosine_ndcg@10	0.2931
cosine_mrr@10	0.2291
cosine_map@100	0.2445

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0918
cosine_accuracy@3	0.2551
cosine_accuracy@5	0.3163
cosine_accuracy@10	0.4694
cosine_precision@1	0.0918
cosine_precision@3	0.085
cosine_precision@5	0.0633
cosine_precision@10	0.0469
cosine_recall@1	0.0918
cosine_recall@3	0.2551
cosine_recall@5	0.3163
cosine_recall@10	0.4694
cosine_ndcg@10	0.2629
cosine_mrr@10	0.1992
cosine_map@100	0.2165

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0816
cosine_accuracy@3	0.2551
cosine_accuracy@5	0.3163
cosine_accuracy@10	0.4796
cosine_precision@1	0.0816
cosine_precision@3	0.085
cosine_precision@5	0.0633
cosine_precision@10	0.048
cosine_recall@1	0.0816
cosine_recall@3	0.2551
cosine_recall@5	0.3163
cosine_recall@10	0.4796
cosine_ndcg@10	0.2611
cosine_mrr@10	0.194
cosine_map@100	0.2059

Training Details

Training Dataset

Unnamed Dataset

Size: 882 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 90.85 tokens max: 198 tokens	min: 8 tokens mean: 25.44 tokens max: 91 tokens	min: 10 tokens mean: 22.33 tokens max: 61 tokens

Samples:

anchor	positive	negative
`` !!! note "Update the metadata" ThemetadataofRecordobject is a python dictionary. So to update the metadata of a record, you can iterate over the records and update the metadata by key or usingmetadata.update`. After that, you should update the records in the dataset.	`Can I use Argilla to annotate the metadata of Record objects and update them in the dataset?`	`The beautiful scenery of the Argilla valley in Italy is perfect for a relaxing summer vacation.`
`git checkout [branch-name] git rebase [default-branch] <br><br>If everything is right, we need to commit and push the changes to your fork. For that, run the following commands:<br><br>sh Add the changes to the staging area git add filename Commit the changes by writing a proper message git commit -m "commit-message" Push the changes to your fork`	`Can I commit Argilla's annotation changes and push them to a forked project repository after rebasing from the default branch?`	`The beautiful beach in Argilla, Spain, is a popular spot for surfers to catch a wave and enjoy the sunny weather.`
`Accessing Record Attributes The Record object has suggestions, responses, metadata, and vectors attributes that can be accessed directly whilst iterating over records in a dataset. python for record in dataset.records( with_suggestions=True, with_responses=True, with_metadata=True, with_vectors=True ): print(record.suggestions) print(record.responses) print(record.metadata) print(record.vectors)`	`Is it possible to retrieve the suggestions, responses, metadata, and vectors of a Record object at the same time when iterating over a dataset in Argilla?`	`The new hiking trail offered breathtaking suggestions for scenic views, responses to environmental concerns, and metadata about the surrounding ecosystem, but it lacked vectors for navigation.`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "TripletLoss",
    "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: epoch
per_device_eval_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 2e-05
lr_scheduler_type: cosine
warmup_ratio: 0.1
load_best_model_at_end: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 4
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 4
eval_accumulation_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: 3
max_steps: -1
lr_scheduler_type: cosine
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: 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: 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
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.1802	5	21.701	-	-	-	-	-
0.3604	10	21.7449	-	-	-	-	-
0.5405	15	21.7453	-	-	-	-	-
0.7207	20	21.7168	-	-	-	-	-
0.9009	25	21.6945	-	-	-	-	-
0.973	27	-	0.2165	0.2445	0.2426	0.2059	0.2604
1.0811	30	21.7248	-	-	-	-	-
1.2613	35	21.7322	-	-	-	-	-
1.4414	40	21.7367	-	-	-	-	-
1.6216	45	21.6821	-	-	-	-	-
1.8018	50	21.8392	-	-	-	-	-
1.9820	55	21.6441	0.2165	0.2445	0.2426	0.2059	0.2604
2.1622	60	21.8154	-	-	-	-	-
2.3423	65	21.7098	-	-	-	-	-
2.5225	70	21.6447	-	-	-	-	-
2.7027	75	21.6033	-	-	-	-	-
2.8829	80	21.8271	-	-	-	-	-
2.9189	81	-	0.2165	0.2445	0.2426	0.2059	0.2604

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.8
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2
Accelerate: 0.31.0
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",
}

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}
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification}, 
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}