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_ndcg@100
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:9000
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      個人向け資産事業の商品、能力、専門性を維持していくこともできるでしょう」
      シティのプライベート・バンクは、世界で最も富裕な個人、家族、法律事務所向けに資産の
      保護と責任ある蓄積を支援しています。シティ・プライベートバンクの顧客ビジネスの合計 は約 5,500 億ドルに上ります。1 万 3,000
      を超える超富裕層のお客様にサービスを提供して おり、その中には�
    sentences:
      - >-
        How does the Citi Private Bank assist its clients and what is the total
        customer business of Citi Private Bank?
      - What are the effects of opening new card accounts for balance transfer?
      - What are some resources to learn about personal finance and credit?
  - source_sentence: >-
      今後とも一層のお引立てを賜ります よう、お願い申し上げます。 ◆管理会社 ◆代行協会員 シティグループ・ファースト・ シティグループ証券株式会社
      インベストメント・マネジメント・リミテッド 
       目 次 頁 Ⅰ．運用の経過等 １ Ⅱ．直近10期の運用実績 ５ Ⅲ．ファンドの経理状況 ６ Ⅳ．お知らせ 36 （注１）米ドルの円換算額は、便宜上、2016年４月28日現在
    sentences:
      - What are the specifications of Citi® Savings Account?
      - What are the fees for Citi Miles AheadSM Savings Account?
      - >-
        What are some regulations that might affect my use of your accounts and
        products?
  - source_sentence: >-
      antage® Miles earned from the Miles Boost do not count toward elite-status
      Exclusions qualification or AAdvantage Million MilerSM status. and Citi
      Miles Ahead Savings account owners will not earn a Miles Boost for:
      Restrictions • Purchases made using a different Eligible Card than the one
      associated with your Citi Miles Ahead Savings account; • Purchases
      appearing on an Eligible Card after the Eligible Card or Citi Miles Ahead
      Savings account closes; • Purchases appearing on an Eligible Card billing
      statement if the AMB in your Citi Miles Ahead Savings account was less
      than 10,000 for the calendar month preceding the Eligible Card billing
      statement date. For example, if your Eligible Card billing statement is
      dated July 10, and the AMB in your Citi Miles Ahead Savings account for
      the month of June was nine thousand ($9,000) dollars, you will not earn a
      Miles Boost for purchases appearing on that July 10 billing statement. •
      AAdvantage® Miles
    sentences:
      - What impact will China's tech advancement have on global market?
      - >-
        What are the bonus miles requirements for Citi Miles Ahead Savings
        account?
      - >-
        What features are being phased out at Citibank ATMs between June 1 and
        June 23, 2023?
  - source_sentence: ' collateral movements as agreed Reinvestment of Cash money market funds by the parties. Citi has controls in Citi offers opportunities to reduce • Offers client-friendly dashboard for place to help prevent unauthorized service expenses through the one-stop access to balances and an movements of collateral. Earnings Credit Rate (ECR) Program interface for research and trading. or cash investment capabilities Tri-Party ACA Solutions through Citi Margin Manager. Where subject to an ACA, the pledgor Under a tri-party ACA with Citi, may be allowed to reinvest cash secured parties can choose to 1) allow Earning Credit Rate (ECR) Program collateral given secured party’s the pledgor to withdraw or replace With the ECR Program, Citi assists approval. collateral at their discretion or 2) clients with collateral accounts to require the pledgor to obtain approval earn credits on U.S. dollar deposits to • Displays portfolio information online for asset release. help offset services expenses. Citi’s and identifies eligible investments ECR'
    sentences:
      - >-
        In what situations is Citibank not liable to consumers under the
        agreement?
      - >-
        What services does Citi provide in relation to collateral margin
        management?
      - What are the changes in equity and reserves?
  - source_sentence: |2-
       be sure you had enough cash on hand to pay the fare. Channels, TTS Of course, all of that changed in the blink of an eye with the advent of ride sharing. Now getting from point A to point B is as easy as opening an app on your smart phone. Not only is it simple to book the ride, but once your account is set up, payment is absolutely seamless. No longer do you have to search your wallet for cash. The app knows who you are and the entire transaction happens in the background, without further input on the part of the rider or the driver. Payment is embedded in the experience as part of the natural flow, so you don’t have to think about it. 
       2 Treasury and Trade Solutions The invisible bank 3 This is just one example of the changes happening in today’s hyper-connected world. Artificial intelligence (AI), cloud is poised to deliver the “invisible bank,” where treasury and banking functions meld together. The continuous evolution of banking computing
    sentences:
      - How is Mexico's credit rating affecting its economy?
      - How is a credit card introductory APR beneficial?
      - What is the advent of ride sharing?
model-index:
  - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.049
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.115
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.15
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.205
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.049
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.03833333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.03
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0205
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.049
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.115
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.15
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.205
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.11801851461489118
            name: Cosine Ndcg@10
          - type: cosine_ndcg@100
            value: 0.17325672881676993
            name: Cosine Ndcg@100
          - type: cosine_mrr@10
            value: 0.09126269841269843
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.1008423759256844
            name: Cosine Map@100

SentenceTransformer based on BAAI/bge-base-en-v1.5

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("MugheesAwan11/bge-base-citi-dataset-9k-1k-e1")
# Run inference
sentences = [
    ' be sure you had enough cash on hand to pay the fare. Channels, TTS Of course, all of that changed in the blink of an eye with the advent of ride sharing. Now getting from point A to point B is as easy as opening an app on your smart phone. Not only is it simple to book the ride, but once your account is set up, payment is absolutely seamless. No longer do you have to search your wallet for cash. The app knows who you are and the entire transaction happens in the background, without further input on the part of the rider or the driver. Payment is embedded in the experience as part of the natural flow, so you don’t have to think about it. \n 2 Treasury and Trade Solutions The invisible bank 3 This is just one example of the changes happening in today’s hyper-connected world. Artificial intelligence (AI), cloud is poised to deliver the “invisible bank,” where treasury and banking functions meld together. The continuous evolution of banking computing',
    'What is the advent of ride sharing?',
    'How is a credit card introductory APR beneficial?',
]
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	0.049
cosine_accuracy@3	0.115
cosine_accuracy@5	0.15
cosine_accuracy@10	0.205
cosine_precision@1	0.049
cosine_precision@3	0.0383
cosine_precision@5	0.03
cosine_precision@10	0.0205
cosine_recall@1	0.049
cosine_recall@3	0.115
cosine_recall@5	0.15
cosine_recall@10	0.205
cosine_ndcg@10	0.118
cosine_ndcg@100	0.1733
cosine_mrr@10	0.0913
cosine_map@100	0.1008

Training Details

Training Dataset

Unnamed Dataset

Size: 9,000 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 116 tokens
mean: 207.16 tokens
max: 288 tokens

min: 4 tokens
mean: 15.73 tokens
max: 37 tokens

	positive	anchor
type	string	string
details	min: 116 tokens mean: 207.16 tokens max: 288 tokens	min: 4 tokens mean: 15.73 tokens max: 37 tokens

Samples:

positive	anchor
ation. US 10-year Treasury yields have risen more than 30 basis points since the Sep 20 FOMC meeting, but just 5 basis points for 2-year notes, steepening the yield curve. Most importantly, the recent rise in rates was a “break out” for yields above post-COVID expansion highs (Figure 4). Figure 4: 10-year US Nominal Treasury yield and 10-year Inflation Indexed US Treasury Source: Haver Analytics as of September 28, 2023. Gray areas are recessions. Past performance is no guarantee of future results. Real results may vary. Citi Global Wealth Investments	CIO Strategy Bulletin
`extension How to Save Money Using the Citi Shop Extension`	Citi.com Save money online shopping Save shopping online How to save money shopping online How to Save Money Shopping Online
common control of Citigroup. Outside the U.S., investment products and services are provided by other Citigroup affiliates. Investment Management services (including portfolio management) are available through CGMI, CGA, Citibank, N.A. and other affiliated advisory businesses. These Citigroup affiliates, including CGA, will be compensated for the respective investment management, advisory, administrative, distribution and placement services they may provide. International Personal Bank U.S. (“IPB U.S.”) is a business of Citigroup which provides its clients access to a broad array of products and services available through Citigroup, its bank and non-bank affiliates worldwide (collectively, “Citi”). Through IPB U.S. prospects and clients have access to the Citigold® Private Client International, Citigold® International, International Personal, Citi Global Executive Preferred, and Citi Global Executive Account Packages. Investment products and services are made available through Citi Personal Investments International (“CPII”), a business	`What are the typical assumpitons given in the report?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768
    ],
    "matryoshka_weights": [
        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
learning_rate: 2e-05
num_train_epochs: 1
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: 1
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: 1
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_768_cosine_map@100
0.0355	10	2.0527	-
0.0709	20	2.3092	-
0.1064	30	1.8688	-
0.1418	40	1.8818	-
0.1773	50	1.75	-
0.2128	60	1.8462	-
0.2482	70	1.7534	-
0.2837	80	1.7534	-
0.3191	90	1.7454	-
0.3546	100	1.7037	-
0.3901	110	1.6765	-
0.4255	120	1.5392	-
0.4610	130	1.722	-
0.4965	140	1.5609	-
0.5319	150	1.6001	-
0.5674	160	1.5694	-
0.6028	170	1.7528	-
0.6383	180	1.5393	-
0.6738	190	1.6765	-
0.7092	200	1.4197	-
0.7447	210	1.5231	-
0.7801	220	1.7733	-
0.8156	230	1.5464	-
0.8511	240	1.5321	-
0.8865	250	1.5727	-
0.9220	260	1.5909	-
0.9574	270	1.6485	-
0.9929	280	1.6605	-
1.0	282	-	0.1008

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.32.1
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}
}