Sailesh9999/bge-base-financial-matryoshka_3

BGE base Financial Matryoshka

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("Sailesh9999/bge-base-financial-matryoshka_3")
# Run inference
sentences = [
    'Chipotle retains an independent third-party compensation consultant each year to conduct a pay equity analysis of its U.S. and Canadian workforce, including factors of pay such as grade level, tenure in role, and external market conditions like geographic location, to ensure consistency and equitable treatment among employees.',
    'How does Chipotle ensure pay equity among its employees?',
    'How can one locate information on legal proceedings within the Consolidated Financial Statements?',
]
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	0.6871
cosine_accuracy@3	0.8214
cosine_accuracy@5	0.8586
cosine_accuracy@10	0.9
cosine_precision@1	0.6871
cosine_precision@3	0.2738
cosine_precision@5	0.1717
cosine_precision@10	0.09
cosine_recall@1	0.6871
cosine_recall@3	0.8214
cosine_recall@5	0.8586
cosine_recall@10	0.9
cosine_ndcg@10	0.7967
cosine_mrr@10	0.7634
cosine_map@10	0.7634

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6857
cosine_accuracy@3	0.82
cosine_accuracy@5	0.8557
cosine_accuracy@10	0.9014
cosine_precision@1	0.6857
cosine_precision@3	0.2733
cosine_precision@5	0.1711
cosine_precision@10	0.0901
cosine_recall@1	0.6857
cosine_recall@3	0.82
cosine_recall@5	0.8557
cosine_recall@10	0.9014
cosine_ndcg@10	0.7952
cosine_mrr@10	0.761
cosine_map@10	0.761

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6814
cosine_accuracy@3	0.8171
cosine_accuracy@5	0.8571
cosine_accuracy@10	0.8886
cosine_precision@1	0.6814
cosine_precision@3	0.2724
cosine_precision@5	0.1714
cosine_precision@10	0.0889
cosine_recall@1	0.6814
cosine_recall@3	0.8171
cosine_recall@5	0.8571
cosine_recall@10	0.8886
cosine_ndcg@10	0.7891
cosine_mrr@10	0.7567
cosine_map@10	0.7567

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6571
cosine_accuracy@3	0.8071
cosine_accuracy@5	0.8457
cosine_accuracy@10	0.8743
cosine_precision@1	0.6571
cosine_precision@3	0.269
cosine_precision@5	0.1691
cosine_precision@10	0.0874
cosine_recall@1	0.6571
cosine_recall@3	0.8071
cosine_recall@5	0.8457
cosine_recall@10	0.8743
cosine_ndcg@10	0.7724
cosine_mrr@10	0.7391
cosine_map@10	0.7391

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6157
cosine_accuracy@3	0.7686
cosine_accuracy@5	0.8171
cosine_accuracy@10	0.8557
cosine_precision@1	0.6157
cosine_precision@3	0.2562
cosine_precision@5	0.1634
cosine_precision@10	0.0856
cosine_recall@1	0.6157
cosine_recall@3	0.7686
cosine_recall@5	0.8171
cosine_recall@10	0.8557
cosine_ndcg@10	0.7405
cosine_mrr@10	0.7032
cosine_map@10	0.7032

Training Details

Training Dataset

Unnamed Dataset

• Size: 6,300 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 7 tokens mean: 46.55 tokens max: 439 tokens	min: 9 tokens mean: 20.43 tokens max: 46 tokens

• Samples:

  positive	anchor
  Americas	$
  Item 1 Business typically includes detailed information about the organization's operations, the nature of the business, and its strategic direction.	What is the title of the section that potentially discusses the operations or nature of a business in a document?
  Operating expenses as a percentage of total revenues decreased to 15.3% in 2023 compared to 15.9% in 2022.	What was the operating expenses as a percentage of total revenues in 2023?

• 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: 1e-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: 1e-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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@10	dim_256_cosine_map@10	dim_512_cosine_map@10	dim_64_cosine_map@10	dim_768_cosine_map@10
0.8122	10	1.7427	-	-	-	-	-
0.9746	12	-	0.7118	0.7377	0.7411	0.6774	0.7440
1.6244	20	0.9354	-	-	-	-	-
1.9492	24	-	0.7353	0.7544	0.7562	0.7008	0.7632
2.4365	30	0.674	-	-	-	-	-
2.9239	36	-	0.7382	0.7569	0.7612	0.7018	0.7625
3.2487	40	0.5862	-	-	-	-	-
3.8985	48	-	0.7391	0.7567	0.761	0.7032	0.7634

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.9.18
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.29.3
• 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}
}