metadata

language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
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: Net cash used in financing activities in 2023 was $2,430 million.
    sentences:
      - >-
        What criteria does Airbnb, Inc. use to assess if an available-for-sale
        security should be recorded as impaired on their financial statements?
      - >-
        What was the total amount of net cash used in financing activities in
        2023?
      - >-
        How much did Visa authorize for its share repurchase program in October
        2023?
  - source_sentence: >-
      Microsoft® and Windows® are either registered trademarks or trademarks of
      Microsoft Corporation in the United States and/or other countries.
    sentences:
      - >-
        Where does Eli Lilly and Company manufacture and distribute its
        products?
      - >-
        What is the significance of Microsoft® and Windows® in relation to
        Microsoft Corporation?
      - >-
        What percentage of total net revenue did the Americas region contribute
        in 2023?
  - source_sentence: >-
      We make available free of charge on the Investor Relations section of our
      corporate website all of the reports we file with or furnish to the SEC as
      soon as reasonably practicable, after the reports are filed or furnished.
    sentences:
      - Is there a cost to access reports filed by Intuit Inc. with the SEC?
      - >-
        What amount of cash, cash equivalents, and restricted cash did the
        company have at the end of the period?
      - >-
        Where in IBM’s 2023 Form 10-K can the Financial Statement Schedule be
        found?
  - source_sentence: >-
      The U.S. Automobile Information and Disclosure Act also requires
      manufacturers of motor vehicles to disclose certain information regarding
      the manufacturer’s suggested retail price, optional equipment and pricing.
    sentences:
      - What does the Adjusted Effective Tax Rate measure exclude?
      - >-
        What was the fair value of the total consideration transferred for the
        acquisition discussed, and how was it composed?
      - >-
        Which act requires U.S. automobile manufacturers to disclose certain
        pricing and equipment information?
  - source_sentence: >-
      Under the Insurance Act, Chubb's Bermuda domiciled subsidiaries are
      prohibited from declaring or paying any dividends of more than 25 percent
      of total statutory capital and surplus, as shown in its previous financial
      year statutory balance sheet, unless at least seven days before payment of
      the dividends, it files with the BMA an affidavit signed by at least two
      directors of the relevant Bermuda domiciled subsidiary (one of whom must
      be a director resident in Bermuda) and by the relevant Bermuda domiciled
      subsidiary’s principal representative, that it will continue to meet its
      required solvency margins. Furthermore, Bermuda domiciled subsidiaries may
      only declare and pay a dividend from retained earnings and a dividend or
      distribution from contributed surplus if it has no reasonable grounds for
      believing that it is, or would after the payment be, unable to pay its
      liabilities as they become due, or if the realizable value of its assets
      would be less than the aggregate of its liabilities. In addition, Chubb's
      Bermuda domiciled subsidiaries must obtain the BMA's prior approval before
      reducing total statutory capital, as shown in its previous financial
      year's financial statements, by 15 percent or more.
    sentences:
      - >-
        What are the restrictions and requirements for Bermuda domiciled
        subsidiaries regarding the distribution of dividends under the Insurance
        Act?
      - What section deals with financial statements and supplementary data?
      - What measures has the company implemented to ensure workplace safety?
pipeline_tag: sentence-similarity
model-index:
  - name: BGE small Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.7042857142857143
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8457142857142858
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.88
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9242857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7042857142857143
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28190476190476194
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.176
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09242857142857142
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7042857142857143
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8457142857142858
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.88
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9242857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8153543862763872
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7803667800453513
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7829122109320609
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.7057142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8471428571428572
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8685714285714285
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9242857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7057142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28238095238095234
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17371428571428568
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09242857142857142
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7057142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8471428571428572
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8685714285714285
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9242857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.815124112835889
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7802040816326532
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7828080021041772
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 384
          type: dim_384
        metrics:
          - type: cosine_accuracy@1
            value: 0.7071428571428572
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8385714285714285
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8757142857142857
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9228571428571428
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7071428571428572
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27952380952380956
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17514285714285713
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09228571428571428
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7071428571428572
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8385714285714285
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8757142857142857
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9228571428571428
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.815223056195625
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7808248299319727
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7833488292208493
            name: Cosine Map@100

BGE small Financial 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("haophancs/bge-base-financial-matryoshka")
# Run inference
sentences = [
    "Under the Insurance Act, Chubb's Bermuda domiciled subsidiaries are prohibited from declaring or paying any dividends of more than 25 percent of total statutory capital and surplus, as shown in its previous financial year statutory balance sheet, unless at least seven days before payment of the dividends, it files with the BMA an affidavit signed by at least two directors of the relevant Bermuda domiciled subsidiary (one of whom must be a director resident in Bermuda) and by the relevant Bermuda domiciled subsidiary’s principal representative, that it will continue to meet its required solvency margins. Furthermore, Bermuda domiciled subsidiaries may only declare and pay a dividend from retained earnings and a dividend or distribution from contributed surplus if it has no reasonable grounds for believing that it is, or would after the payment be, unable to pay its liabilities as they become due, or if the realizable value of its assets would be less than the aggregate of its liabilities. In addition, Chubb's Bermuda domiciled subsidiaries must obtain the BMA's prior approval before reducing total statutory capital, as shown in its previous financial year's financial statements, by 15 percent or more.",
    'What are the restrictions and requirements for Bermuda domiciled subsidiaries regarding the distribution of dividends under the Insurance Act?',
    'What section deals with financial statements and supplementary data?',
]
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	0.7043
cosine_accuracy@3	0.8457
cosine_accuracy@5	0.88
cosine_accuracy@10	0.9243
cosine_precision@1	0.7043
cosine_precision@3	0.2819
cosine_precision@5	0.176
cosine_precision@10	0.0924
cosine_recall@1	0.7043
cosine_recall@3	0.8457
cosine_recall@5	0.88
cosine_recall@10	0.9243
cosine_ndcg@10	0.8154
cosine_mrr@10	0.7804
cosine_map@100	0.7829

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7057
cosine_accuracy@3	0.8471
cosine_accuracy@5	0.8686
cosine_accuracy@10	0.9243
cosine_precision@1	0.7057
cosine_precision@3	0.2824
cosine_precision@5	0.1737
cosine_precision@10	0.0924
cosine_recall@1	0.7057
cosine_recall@3	0.8471
cosine_recall@5	0.8686
cosine_recall@10	0.9243
cosine_ndcg@10	0.8151
cosine_mrr@10	0.7802
cosine_map@100	0.7828

Information Retrieval

Dataset: dim_384
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7071
cosine_accuracy@3	0.8386
cosine_accuracy@5	0.8757
cosine_accuracy@10	0.9229
cosine_precision@1	0.7071
cosine_precision@3	0.2795
cosine_precision@5	0.1751
cosine_precision@10	0.0923
cosine_recall@1	0.7071
cosine_recall@3	0.8386
cosine_recall@5	0.8757
cosine_recall@10	0.9229
cosine_ndcg@10	0.8152
cosine_mrr@10	0.7808
cosine_map@100	0.7833

Training Details

Training Dataset

Unnamed Dataset

Size: 6,300 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 8 tokens
mean: 45.4 tokens
max: 252 tokens

min: 9 tokens
mean: 20.43 tokens
max: 45 tokens

	positive	anchor
type	string	string
details	min: 8 tokens mean: 45.4 tokens max: 252 tokens	min: 9 tokens mean: 20.43 tokens max: 45 tokens

Samples:

positive	anchor
`In 2023, $2.2 billion or 5% was primarily related to patient co-pay assistance, cash discounts for prompt payment, distributor fees, and sales return provisions.`	`What was the amount of sales return provisions in 2023 as part of gross-to-net deductions?`
`Cash and cash equivalents were $21.9 billion at the end of 2023 as compared to $14.1 billion at the end of 2022, showing a $7.8 billion increase.`	`How much did cash and cash equivalents increase by the end of 2023 compared to the end of 2022?`
`The net increase in cash and cash equivalents for UnitedHealthcare in 2023 compared to 2022 was $72 million.`	`What was the net increase in cash and cash equivalents for UnitedHealthcare in 2023 compared to 2022?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        384
    ],
    "matryoshka_weights": [
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
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: 4
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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_fused
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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_384_cosine_map@100	dim_512_cosine_map@100	dim_768_cosine_map@100
0.8122	10	0.8256	-	-	-
0.9746	12	-	0.7719	0.7679	0.7652
1.6244	20	0.2984	-	-	-
1.9492	24	-	0.7784	0.7810	0.7791
2.4365	30	0.201	-	-	-
2.9239	36	-	0.7835	0.7832	0.7828
3.2487	40	0.1705	-	-	-
3.8985	48	-	0.7833	0.7828	0.7829

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.2
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.2.0+cu121
Accelerate: 0.31.0
Datasets: 2.19.1
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}
}

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}
}