elsayovita/bge-small-en-v1.5-esg

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

• 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}
}