metadata

language:
  - en
license: apache-2.0
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
widget:
  - source_sentence: >-
      The Health Services segment's revenues are primarily generated from the
      sale and managing of prescription drugs to eligible members in benefit
      plans maintained by clients.
    sentences:
      - >-
        What online platforms does The Home Depot operate for its product
        offerings?
      - >-
        How does the Company's Health Services segment generate most of its
        revenue?
      - What are the various diversity, equity, and inclusion councils at AMC?
  - source_sentence: Product gross margin decreased to 75.9% in 2023, compared to 2022.
    sentences:
      - What organizations do the cybersecurity leaders hold memberships in?
      - How much did product gross margin decrease from 2022 to 2023?
      - What items are included under Item 8 in the financial report?
  - source_sentence: >-
      Our apparel assortment includes items such as pants, shorts, tops, and
      jackets designed for a healthy lifestyle including athletic activities
      such as yoga, running, training, and most other activities.
    sentences:
      - What types of activities are lululemon's athletic apparels designed for?
      - >-
        How are the capital adequacy ratios of American Express and AENB
        determined under current federal banking regulations?
      - What was the company's worldwide effective income tax rate in 2023?
  - source_sentence: >-
      Rest of Asia Pacific net sales increased 1% or $240 million during 2023
      compared to 2022. The weakness in foreign currencies relative to the U.S.
      dollar had a significantly unfavorable year-over-year impact on Rest of
      Asia Pacific net sales. The net sales increase consisted of higher net
      sales of iPhone and Services, partially offset by lower net sales of Mac
      and iPad.
    sentences:
      - >-
        What primarily drove the increase in service fees and other revenue
        associated with Card Member cross-currency spending?
      - >-
        What was the balance of net cash used in financing activities for Costco
        for the 52 weeks ended August 28, 2022?
      - How did Rest of Asia Pacific net sales change in 2023 compared to 2022?
  - source_sentence: >-
      Cardiovascular/Metabolism/Other products sales were $3.7 billion, a
      decline of 5.5% as compared to the prior year.
    sentences:
      - >-
        What was the revenue decline percentage for
        Cardiovascular/Metabolism/Other products in 2023?
      - How is a membership's territory determined according to the description?
      - What informs the ESG disclosures mentioned in the text?
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: 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: 0.68
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8185714285714286
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8614285714285714
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9057142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.68
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27285714285714285
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17228571428571426
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09057142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.68
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8185714285714286
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8614285714285714
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9057142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7935961173570086
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7574988662131514
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.761336548534802
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6742857142857143
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.81
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8585714285714285
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9128571428571428
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6742857142857143
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1717142857142857
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09128571428571428
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6742857142857143
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.81
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8585714285714285
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9128571428571428
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7923231259157938
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7537448979591835
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7569742717128601
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6728571428571428
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8028571428571428
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.85
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9042857142857142
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6728571428571428
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2676190476190476
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09042857142857141
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6728571428571428
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8028571428571428
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.85
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9042857142857142
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7878292403814693
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7507125850340136
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7544072051783587
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6642857142857143
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8442857142857143
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8957142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6642857142857143
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16885714285714284
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08957142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6642857142857143
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8442857142857143
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8957142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7803597349541593
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7434574829931975
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.747244951206714
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6414285714285715
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7871428571428571
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8185714285714286
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8728571428571429
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6414285714285715
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2623809523809524
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1637142857142857
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08728571428571427
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6414285714285715
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7871428571428571
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8185714285714286
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8728571428571429
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7591433790735056
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7226213151927439
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7273040677676369
            name: Cosine Map@100

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the json dataset. 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 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json
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("JulioSanchezD/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Cardiovascular/Metabolism/Other products sales were $3.7 billion, a decline of 5.5% as compared to the prior year.',
    'What was the revenue decline percentage for Cardiovascular/Metabolism/Other products in 2023?',
    "How is a membership's territory determined according to the description?",
]
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

Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.68	0.6743	0.6729	0.6643	0.6414
cosine_accuracy@3	0.8186	0.81	0.8029	0.8	0.7871
cosine_accuracy@5	0.8614	0.8586	0.85	0.8443	0.8186
cosine_accuracy@10	0.9057	0.9129	0.9043	0.8957	0.8729
cosine_precision@1	0.68	0.6743	0.6729	0.6643	0.6414
cosine_precision@3	0.2729	0.27	0.2676	0.2667	0.2624
cosine_precision@5	0.1723	0.1717	0.17	0.1689	0.1637
cosine_precision@10	0.0906	0.0913	0.0904	0.0896	0.0873
cosine_recall@1	0.68	0.6743	0.6729	0.6643	0.6414
cosine_recall@3	0.8186	0.81	0.8029	0.8	0.7871
cosine_recall@5	0.8614	0.8586	0.85	0.8443	0.8186
cosine_recall@10	0.9057	0.9129	0.9043	0.8957	0.8729
cosine_ndcg@10	0.7936	0.7923	0.7878	0.7804	0.7591
cosine_mrr@10	0.7575	0.7537	0.7507	0.7435	0.7226
cosine_map@100	0.7613	0.757	0.7544	0.7472	0.7273

Training Details

Training Dataset

json

Dataset: json
Size: 6,300 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 11 tokens
mean: 45.6 tokens
max: 288 tokens

min: 9 tokens
mean: 20.54 tokens
max: 46 tokens

	positive	anchor
type	string	string
details	min: 11 tokens mean: 45.6 tokens max: 288 tokens	min: 9 tokens mean: 20.54 tokens max: 46 tokens

Samples:

positive	anchor
`Operating Expenses Our operating expenses consisted of the following:`	Year Ended December 31,
`Increases in yield, discount rate, capitalization rate or duration used in the valuation of level 3 investments would have resulted in a lower fair value measurement, while increases in recovery rate or multiples would have resulted in a higher fair value measurement as of both December 2023 and December 2022.`	`What was the impact on the fair value measurement of level 3 investments when the yield, discount rate, and capitalization rate were increased?`
`At December 31, 2023, Ford Credit’s liquidity sources, including cash, committed asset-backed facilities, and unsecured credit facilities, totaled $56.2 billion, up $5.2 billion from year-end 2022.`	`What sources contribute to Ford Credit’s liquidity as of December 31, 2023, and what was their total value?`

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: 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
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
0.8122	10	1.5473	-	-	-	-	-
0.9746	12	-	0.7821	0.7814	0.7723	0.7543	0.7229
1.6244	20	0.6848	-	-	-	-	-
1.9492	24	-	0.7906	0.7877	0.7824	0.7729	0.7519
2.4365	30	0.5164	-	-	-	-	-
2.9239	36	-	0.7921	0.7924	0.7887	0.7778	0.7587
3.2487	40	0.4455	-	-	-	-	-
3.8985	48	-	0.7936	0.7923	0.7878	0.7804	0.7591

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.9
Sentence Transformers: 3.4.1
Transformers: 4.41.2
PyTorch: 2.6.0+cu126
Accelerate: 1.4.0
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}
}