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: >-
      What was the total amount of current assets reported by The Hershey
      Company for the year 2023?
    sentences:
      - >-
        The total AUS for all categories, including alternative investments,
        equity, fixed income, and liquidity products, summed up to $2,812
        billion in 2023.
      - >-
        The Hershey Company reported a total of current assets amounting to
        $2,912,103 for the year 2023.
      - >-
        Information on legal proceedings is included in Note 15 to the
        Consolidated Financial Statements.
  - source_sentence: What is listed under Item 8 in the document?
    sentences:
      - >-
        Chubb Limited further advanced their goal of greater product, customer,
        and geographical diversification with incremental purchases that led to
        a controlling majority interest in Huatai Insurance Group Co. Ltd,
        owning about 76.5 percent as of July 1, 2023.
      - Item 8 includes Financial Statements and Supplementary Data.
      - >-
        Further, state attorneys general may bring civil actions seeking either
        injunction or an unspecified amount in damages in response to violations
        of the HIPAA privacy and security regulations.
  - source_sentence: >-
      What were the main factors contributing to the change in net sales for
      fiscal 2022?
    sentences:
      - >-
        The decrease in consolidated net sales in fiscal 2022 compared to fiscal
        2021 was primarily attributable to the translation impact of a stronger
        U.S. dollar, a decline in sales from new software releases and video
        game accessories, partially offset by an increase in sales of new gaming
        hardware and toys and collectibles.
      - >-
        We receive payment from the delivery partner subsequent to the transfer
        of food and the payment terms are short-term in nature.
      - >-
        Net cash used in investing activities was $30.0 million in the year
        ended December 31, 2022, and increased to $73.3 million in the year
        ended December 31, 2023.
  - source_sentence: What informs the ESG disclosures mentioned in the text?
    sentences:
      - >-
        Common Equity Tier 1 (CET1) Capital refers to the total of common stock
        and related surplus minus treasury stock, retained earnings, AOCI, and
        qualifying minority interests after factoring in the necessary
        regulatory adjustments and deductions.
      - >-
        Constant currency revenue percentage change is calculated by determining
        the change in current period revenues over prior period revenues where
        current period foreign currency revenues are translated using prior year
        exchange outstanding rates and hedging effects are excluded from
        revenues of both periods.
      - >-
        Our ESG disclosures are also informed by relevant topics identified
        through third-party ESG reporting organizations, frameworks and
        standards, such as the TCFD.
  - source_sentence: How many new aircraft did Delta Air Lines take delivery of in 2023?
    sentences:
      - In 2023, Delta took delivery of 43 aircraft.
      - >-
        The listing of our common stock on the NYSE could potentially create a
        conflict between the exchange’s regulatory responsibilities to
        vigorously oversee the listing and trading of securities, on the one
        hand, and our commercial and economic interest, on the other hand.
      - >-
        The Company's enterprise DEI Strategy is aligned to the DEI Vision and
        Mission and rests on four core pillars: •Build a workforce of
        individuals with diverse backgrounds, cultures, abilities and
        perspectives  •Foster a culture of inclusion where every individual
        belongs •Transform talent and business processes to achieve equitable
        opportunities for all •Drive innovation and growth with our business to
        serve diverse markets around the world.
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: 0.7
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8328571428571429
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8614285714285714
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9171428571428571
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2776190476190476
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17228571428571426
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09171428571428569
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8328571428571429
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8614285714285714
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9171428571428571
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8082439242024833
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7734971655328796
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7770743874539329
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6914285714285714
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8328571428571429
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8685714285714285
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9185714285714286
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6914285714285714
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2776190476190476
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1737142857142857
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09185714285714283
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6914285714285714
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8328571428571429
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8685714285714285
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9185714285714286
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8056533729911755
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7695113378684802
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7731633620598676
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6928571428571428
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8328571428571429
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.87
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.91
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6928571428571428
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2776190476190476
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.174
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09099999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6928571428571428
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8328571428571429
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.87
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.91
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8031697277454632
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7687063492063488
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.772758974076829
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.67
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8028571428571428
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8628571428571429
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9057142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.67
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2676190476190476
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17257142857142854
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09057142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.67
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8028571428571428
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8628571428571429
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9057142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7882417708737697
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7505816326530609
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7545140112362249
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6557142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7871428571428571
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8171428571428572
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8742857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6557142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2623809523809524
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16342857142857142
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08742857142857141
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6557142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7871428571428571
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8171428571428572
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8742857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7637005971170125
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7285300453514736
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7336775414052045
            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("ChristianBernhard/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'How many new aircraft did Delta Air Lines take delivery of in 2023?',
    'In 2023, Delta took delivery of 43 aircraft.',
    'The listing of our common stock on the NYSE could potentially create a conflict between the exchange’s regulatory responsibilities to vigorously oversee the listing and trading of securities, on the one hand, and our commercial and economic interest, on the other hand.',
]
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	0.7	0.6914	0.6929	0.67	0.6557
cosine_accuracy@3	0.8329	0.8329	0.8329	0.8029	0.7871
cosine_accuracy@5	0.8614	0.8686	0.87	0.8629	0.8171
cosine_accuracy@10	0.9171	0.9186	0.91	0.9057	0.8743
cosine_precision@1	0.7	0.6914	0.6929	0.67	0.6557
cosine_precision@3	0.2776	0.2776	0.2776	0.2676	0.2624
cosine_precision@5	0.1723	0.1737	0.174	0.1726	0.1634
cosine_precision@10	0.0917	0.0919	0.091	0.0906	0.0874
cosine_recall@1	0.7	0.6914	0.6929	0.67	0.6557
cosine_recall@3	0.8329	0.8329	0.8329	0.8029	0.7871
cosine_recall@5	0.8614	0.8686	0.87	0.8629	0.8171
cosine_recall@10	0.9171	0.9186	0.91	0.9057	0.8743
cosine_ndcg@10	0.8082	0.8057	0.8032	0.7882	0.7637
cosine_mrr@10	0.7735	0.7695	0.7687	0.7506	0.7285
cosine_map@100	0.7771	0.7732	0.7728	0.7545	0.7337

Training Details

Training Dataset

json

Dataset: json
Size: 6,300 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 9 tokens
mean: 20.82 tokens
max: 41 tokens

min: 9 tokens
mean: 47.65 tokens
max: 371 tokens

	anchor	positive
type	string	string
details	min: 9 tokens mean: 20.82 tokens max: 41 tokens	min: 9 tokens mean: 47.65 tokens max: 371 tokens

Samples:

anchor	positive
`What challenges did the company face in its supply chain during fiscal 2021?`	`During fiscal 2021, we experienced significant disruptions in our supply chain which impacted our ability to ship products from overseas on a timely basis.`
`Is the information on Legal proceedings in the report straightforward or referenced to another section?`	`The information on Legal proceedings called for by Item 3 is incorporated by reference to Note 19 of the Notes to Consolidated Financial Statements in Item 8 of the report.`
`What factors particularly influence sales comparisons and comparable sales growth according to the annual report?`	`Sales comparisons can also be particularly influenced by certain factors that are beyond our control: fluctuations in currency exchange rates (with respect to our international operations); inflation or deflation and changes in the cost of gasoline and associated competitive conditions.`

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	1.5819	-	-	-	-	-
0.9746	12	-	0.7909	0.7912	0.7907	0.7723	0.7444
1.6244	20	0.6676	-	-	-	-	-
1.9492	24	-	0.7991	0.7994	0.7983	0.7849	0.7571
2.4365	30	0.4321	-	-	-	-	-
2.9239	36	-	0.8089	0.8048	0.8016	0.7879	0.7637
3.2487	40	0.3958	-	-	-	-	-
3.8985	48	-	0.8082	0.8057	0.8032	0.7882	0.7637

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 1.2.0
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}
}