metadata

base_model: BAAI/bge-base-en-v1.5
datasets: []
language:
  - en
library_name: sentence-transformers
license: apache-2.0
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1500
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      The depreciation and amortization expense for the year 2021 was recorded
      at $3,103.
    sentences:
      - >-
        In what sequence do the signature pages appear relative to the financial
        documents in this report?
      - What was the depreciation and amortization expense in 2021?
      - >-
        What was the net impact on other comprehensive income (loss), net of
        tax, for the fiscal year ended March 31, 2023?
  - source_sentence: 'Actual Asset Returns: U.S. Plans: (21.20)%, Non-U.S. Plans: (25.40)%.'
    sentences:
      - >-
        What were the total other current liabilities for the fiscal year ending
        in 2023 compared to 2022?
      - >-
        What was the percentage of proprietary brand product sales as part of
        the front store revenues in 2023?
      - >-
        By how much did actual asset returns vary between U.S. and Non-U.S.
        pension plans in 2023?
  - source_sentence: >-
      Intellectual property rights are important to Nike's brand, success, and
      competitive position. The company strategically pursues protections of
      these rights and vigorously protects them against third-party theft and
      infringement.
    sentences:
      - >-
        What types of legal issues are generally categorized under Commitments
        and Contingencies in a Form 10-K?
      - >-
        What role does intellectual property play in Nike's competitive
        position?
      - How is the revenue from sales of Online-Hosted Service Games recognized?
  - source_sentence: >-
      Item 3, titled 'Legal Proceedings' in a 10-K filing, directs to Note 16
      where specific information is further detailed in Item 8 of Part II.
    sentences:
      - How does Garmin manage the costs of manufacturing its products?
      - What is indicated by Item 3, 'Legal Proceedings', in a 10-K filing?
      - >-
        How much did UnitedHealthcare's cash provided by operating activities
        amount to in 2023?
  - source_sentence: >-
      During 2023, FedEx ranked 18th in FORTUNE magazine's 'World's Most Admired
      Companies' list and maintained its position as the highest-ranked delivery
      company on the list.
    sentences:
      - >-
        What was the total depreciation and amortization expense for the company
        in 2023?
      - >-
        What was the valuation allowance against deferred tax assets at the end
        of 2023, and what changes may affect its realization?
      - What recognition did FedEx receive from FORTUNE magazine in 2023?
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.7766666666666666
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.86
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.89
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9333333333333333
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7766666666666666
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2866666666666667
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17799999999999996
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09333333333333332
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7766666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.86
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.89
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9333333333333333
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8519532537710081
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8263650793650793
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8285686593594938
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.7566666666666667
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.87
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8933333333333333
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9333333333333333
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7566666666666667
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17866666666666664
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09333333333333332
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7566666666666667
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.87
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8933333333333333
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9333333333333333
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8462349355848354
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8183306878306877
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8207466430359656
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.76
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.86
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.89
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9266666666666666
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.76
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2866666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17799999999999996
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09266666666666666
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.76
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.86
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.89
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9266666666666666
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8433224215661056
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8166931216931217
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8190592083326618
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.7066666666666667
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.84
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8633333333333333
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.91
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7066666666666667
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27999999999999997
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17266666666666666
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09099999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7066666666666667
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.84
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8633333333333333
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.91
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8099084142081584
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7776230158730157
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7810311049771785
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6833333333333333
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7933333333333333
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8366666666666667
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.88
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6833333333333333
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26444444444444437
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1673333333333333
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.088
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6833333333333333
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7933333333333333
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8366666666666667
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.88
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7796467165928374
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7475780423280424
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.751941519893099
            name: Cosine Map@100

BGE base 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("adarshheg/bge-base-financial-matryoshka")
# Run inference
sentences = [
    "During 2023, FedEx ranked 18th in FORTUNE magazine's 'World's Most Admired Companies' list and maintained its position as the highest-ranked delivery company on the list.",
    'What recognition did FedEx receive from FORTUNE magazine in 2023?',
    'What was the valuation allowance against deferred tax assets at the end of 2023, and what changes may affect its realization?',
]
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	0.7767
cosine_accuracy@3	0.86
cosine_accuracy@5	0.89
cosine_accuracy@10	0.9333
cosine_precision@1	0.7767
cosine_precision@3	0.2867
cosine_precision@5	0.178
cosine_precision@10	0.0933
cosine_recall@1	0.7767
cosine_recall@3	0.86
cosine_recall@5	0.89
cosine_recall@10	0.9333
cosine_ndcg@10	0.852
cosine_mrr@10	0.8264
cosine_map@100	0.8286

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7567
cosine_accuracy@3	0.87
cosine_accuracy@5	0.8933
cosine_accuracy@10	0.9333
cosine_precision@1	0.7567
cosine_precision@3	0.29
cosine_precision@5	0.1787
cosine_precision@10	0.0933
cosine_recall@1	0.7567
cosine_recall@3	0.87
cosine_recall@5	0.8933
cosine_recall@10	0.9333
cosine_ndcg@10	0.8462
cosine_mrr@10	0.8183
cosine_map@100	0.8207

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.76
cosine_accuracy@3	0.86
cosine_accuracy@5	0.89
cosine_accuracy@10	0.9267
cosine_precision@1	0.76
cosine_precision@3	0.2867
cosine_precision@5	0.178
cosine_precision@10	0.0927
cosine_recall@1	0.76
cosine_recall@3	0.86
cosine_recall@5	0.89
cosine_recall@10	0.9267
cosine_ndcg@10	0.8433
cosine_mrr@10	0.8167
cosine_map@100	0.8191

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7067
cosine_accuracy@3	0.84
cosine_accuracy@5	0.8633
cosine_accuracy@10	0.91
cosine_precision@1	0.7067
cosine_precision@3	0.28
cosine_precision@5	0.1727
cosine_precision@10	0.091
cosine_recall@1	0.7067
cosine_recall@3	0.84
cosine_recall@5	0.8633
cosine_recall@10	0.91
cosine_ndcg@10	0.8099
cosine_mrr@10	0.7776
cosine_map@100	0.781

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6833
cosine_accuracy@3	0.7933
cosine_accuracy@5	0.8367
cosine_accuracy@10	0.88
cosine_precision@1	0.6833
cosine_precision@3	0.2644
cosine_precision@5	0.1673
cosine_precision@10	0.088
cosine_recall@1	0.6833
cosine_recall@3	0.7933
cosine_recall@5	0.8367
cosine_recall@10	0.88
cosine_ndcg@10	0.7796
cosine_mrr@10	0.7476
cosine_map@100	0.7519

Training Details

Training Dataset

Unnamed Dataset

Size: 1,500 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 6 tokens
mean: 46.0 tokens
max: 239 tokens

min: 9 tokens
mean: 20.82 tokens
max: 42 tokens

	positive	anchor
type	string	string
details	min: 6 tokens mean: 46.0 tokens max: 239 tokens	min: 9 tokens mean: 20.82 tokens max: 42 tokens

Samples:

positive	anchor
`In the U.S., Visa Inc.'s total nominal payments volume increased by 17% from $4,725 billion in 2021 to $5,548 billion in 2022.`	`What is the total percentage increase in Visa Inc.'s nominal payments volume in the U.S. from 2021 to 2022?`
`The section titled 'Financial Wtatement and Supplementary Data' is labeled with the number 39 in the document.`	`What is the numerical label associated with the section on Financial Statements and Supplementary Data in the document?`
`The consolidated financial statements and accompanying notes are incorporated by reference herein.`	`Are the consolidated financial statements and accompanying notes incorporated by reference in the Annual Report on Form 10-K?`

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: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 2
lr_scheduler_type: cosine
warmup_ratio: 0.1
tf32: False
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: 2
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: False
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	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
0.6809	2	0.7796	0.8153	0.8165	0.7375	0.8186
1.3617	4	0.781	0.8191	0.8207	0.7519	0.8286

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.33.0
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}
}