metadata

base_model: BAAI/bge-small-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:11863
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      In the fiscal year 2022, the emissions were categorized into different
      scopes, with each scope representing a specific source of emissions
    sentences:
      - >-
        Question: What is NetLink proactive in identifying to be more efficient
        in? 
      - >-
        What standard is the Environment, Health, and Safety Management System
        (EHSMS) audited to by a third-party accredited certification body at the
        operational assets level of CLI?
      - >-
        What do the different scopes represent in terms of emissions in the
        fiscal year 2022?
  - source_sentence: >-
      NetLink is committed to protecting the security of all information and
      information systems, including both end-user data and corporate data. To
      this end, management ensures that the appropriate IT policies, personal
      data protection policy, risk mitigation strategies, cyber security
      programmes, systems, processes, and controls are in place to protect our
      IT systems and confidential data
    sentences:
      - '"What recognition did NetLink receive in FY22?"'
      - >-
        What measures does NetLink have in place to protect the security of all
        information and information systems, including end-user data and
        corporate data?
      - >-
        Question: What does Disclosure 102-10 discuss regarding the organization
        and its supply chain?
  - source_sentence: >-
      In the domain of economic performance, the focus is on the financial
      health and growth of the organization, ensuring sustainable profitability
      and value creation for stakeholders
    sentences:
      - >-
        What does NetLink prioritize by investing in its network to ensure
        reliability and quality of infrastructure?
      - >-
        What percentage of the total energy was accounted for by heat, steam,
        and chilled water in 2021 according to the given information?
      - >-
        What is the focus in the domain of economic performance, ensuring
        sustainable profitability and value creation for stakeholders?
  - source_sentence: >-
      Disclosure 102-41 discusses collective bargaining agreements and is found
      on page 98
    sentences:
      - What topic is discussed in Disclosure 102-41 on page 98 of the document?
      - >-
        What was the number of cases in 2021, following a decrease from 42 cases
        in 2020?
      - >-
        What type of data does GRI 101 provide in relation to connecting the
        nation?
  - source_sentence: >-
      Employee health and well-being has never been more topical than it was in
      the past year. We understand that people around the world, including our
      employees, have been increasingly exposed to factors affecting their
      physical and mental wellbeing. We are committed to creating an environment
      that supports our employees and ensures they feel valued and have a sense
      of belonging. We utilised
    sentences:
      - >-
        What aspect of the standard covers the evaluation of the management
        approach?
      - >-
        Question: What is the company's commitment towards its employees' health
        and well-being based on the provided context information?
      - >-
        What types of skills does NetLink focus on developing through their
        training and development opportunities for employees?
model-index:
  - name: BAAI BGE small en v1.5 ESG
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 384
          type: dim_384
        metrics:
          - type: cosine_accuracy@1
            value: 0.7661637022675546
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9170530220011801
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9370311051167496
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9542274298238219
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7661637022675546
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30568434066706
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18740622102334994
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09542274298238222
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.021282325062987634
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.025473695055588344
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.026028641808798603
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.026506317495106176
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.19177581579273692
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.843606136995247
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.023463069757038203
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.7621175082188316
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9118266880215797
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9353451909297816
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9527944027648992
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7621175082188316
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3039422293405265
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18706903818595635
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09527944027648994
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.02116993078385644
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.025328519111710558
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.025981810859160608
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.026466511187913874
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.19114210787645763
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8402866254821924
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.023374206451884923
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.7469442805361207
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.898423670235185
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9232066087836129
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9444491275394082
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7469442805361207
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2994745567450616
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1846413217567226
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09444491275394083
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.020748452237114468
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.02495621306208848
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.025644628021767035
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.02623469798720579
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.1883811701569402
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8264706590720244
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.02300099952981619
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.7106128298069628
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8668970749388856
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8978336002697462
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9243867487144904
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7106128298069628
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28896569164629515
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17956672005394925
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09243867487144905
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.01973924527241564
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.02408047430385794
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.02493982222971518
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.02567740968651363
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.1818069773338387
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7936283816963235
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.022106633007589808
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 32
          type: dim_32
        metrics:
          - type: cosine_accuracy@1
            value: 0.6166231138835033
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7788923543791622
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8194385905757396
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8608277838658013
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6166231138835033
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.259630784793054
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16388771811514793
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08608277838658013
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.017128419830097316
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.02163589873275451
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.022762183071548335
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.02391188288516115
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.16371507022328244
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7058398528705336
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.019714839230632157
            name: Cosine Map@100

BAAI BGE small en v1.5 ESG

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-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-small-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 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': 384, '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("elsayovita/bge-small-en-v1.5-esg")
# Run inference
sentences = [
    'Employee health and well-being has never been more topical than it was in the past year. We understand that people around the world, including our employees, have been increasingly exposed to factors affecting their physical and mental wellbeing. We are committed to creating an environment that supports our employees and ensures they feel valued and have a sense of belonging. We utilised',
    "Question: What is the company's commitment towards its employees' health and well-being based on the provided context information?",
    'What types of skills does NetLink focus on developing through their training and development opportunities for employees?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: dim_384
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7662
cosine_accuracy@3	0.9171
cosine_accuracy@5	0.937
cosine_accuracy@10	0.9542
cosine_precision@1	0.7662
cosine_precision@3	0.3057
cosine_precision@5	0.1874
cosine_precision@10	0.0954
cosine_recall@1	0.0213
cosine_recall@3	0.0255
cosine_recall@5	0.026
cosine_recall@10	0.0265
cosine_ndcg@10	0.1918
cosine_mrr@10	0.8436
cosine_map@100	0.0235

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7621
cosine_accuracy@3	0.9118
cosine_accuracy@5	0.9353
cosine_accuracy@10	0.9528
cosine_precision@1	0.7621
cosine_precision@3	0.3039
cosine_precision@5	0.1871
cosine_precision@10	0.0953
cosine_recall@1	0.0212
cosine_recall@3	0.0253
cosine_recall@5	0.026
cosine_recall@10	0.0265
cosine_ndcg@10	0.1911
cosine_mrr@10	0.8403
cosine_map@100	0.0234

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7469
cosine_accuracy@3	0.8984
cosine_accuracy@5	0.9232
cosine_accuracy@10	0.9444
cosine_precision@1	0.7469
cosine_precision@3	0.2995
cosine_precision@5	0.1846
cosine_precision@10	0.0944
cosine_recall@1	0.0207
cosine_recall@3	0.025
cosine_recall@5	0.0256
cosine_recall@10	0.0262
cosine_ndcg@10	0.1884
cosine_mrr@10	0.8265
cosine_map@100	0.023

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7106
cosine_accuracy@3	0.8669
cosine_accuracy@5	0.8978
cosine_accuracy@10	0.9244
cosine_precision@1	0.7106
cosine_precision@3	0.289
cosine_precision@5	0.1796
cosine_precision@10	0.0924
cosine_recall@1	0.0197
cosine_recall@3	0.0241
cosine_recall@5	0.0249
cosine_recall@10	0.0257
cosine_ndcg@10	0.1818
cosine_mrr@10	0.7936
cosine_map@100	0.0221

Information Retrieval

Dataset: dim_32
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6166
cosine_accuracy@3	0.7789
cosine_accuracy@5	0.8194
cosine_accuracy@10	0.8608
cosine_precision@1	0.6166
cosine_precision@3	0.2596
cosine_precision@5	0.1639
cosine_precision@10	0.0861
cosine_recall@1	0.0171
cosine_recall@3	0.0216
cosine_recall@5	0.0228
cosine_recall@10	0.0239
cosine_ndcg@10	0.1637
cosine_mrr@10	0.7058
cosine_map@100	0.0197

Training Details

Training Dataset

Unnamed Dataset

Size: 11,863 training samples
Columns: context and question
Approximate statistics based on the first 1000 samples:
context question
type string string
details
min: 13 tokens
mean: 40.74 tokens
max: 277 tokens

min: 11 tokens
mean: 24.4 tokens
max: 62 tokens

	context	question
type	string	string
details	min: 13 tokens mean: 40.74 tokens max: 277 tokens	min: 11 tokens mean: 24.4 tokens max: 62 tokens

Samples:

context	question
`The engagement with key stakeholders involves various topics and methods throughout the year`	`Question: What does the engagement with key stakeholders involve throughout the year?`
`For unitholders and analysts, the focus is on business and operations, the release of financial results, and the overall performance and announcements`	`Question: What is the focus for unitholders and analysts in terms of business and operations, financial results, performance, and announcements?`
`These are communicated through press releases and other required disclosures via SGXNet and NetLink's website`	`What platform is used to communicate press releases and required disclosures for NetLink?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        384,
        256,
        128,
        64,
        32
    ],
    "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
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: 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: 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
eval_on_start: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_32_cosine_map@100	dim_384_cosine_map@100	dim_64_cosine_map@100
0.4313	10	4.3426	-	-	-	-	-
0.8625	20	2.7083	-	-	-	-	-
1.0350	24	-	0.0229	0.0233	0.0195	0.0234	0.0220
1.2264	30	2.6835	-	-	-	-	-
1.6577	40	2.1702	-	-	-	-	-
1.9164	46	-	0.023	0.0234	0.0197	0.0235	0.0221

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.4.0+cu121
Accelerate: 0.32.1
Datasets: 2.21.0
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}
}