Nishanth7803/bge-base-finetuned-financial

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. Dataset - philschmid/finanical-rag-embedding-dataset

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("Nishanth7803/bge-base-finetuned-financial")
# Run inference
sentences = [
    'Personal Systems net revenue was $35,684 million for the fiscal year 2023.',
    'What was the total net revenue for the Personal Systems segment in the fiscal year 2023?',
    'What are the revised maximum leverage ratios under the Senior Credit Facilities for the periods specified and in connection with certain material acquisitions?',
]
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	0.7071
cosine_accuracy@3	0.8286
cosine_accuracy@5	0.8657
cosine_accuracy@10	0.9043
cosine_precision@1	0.7071
cosine_precision@3	0.2762
cosine_precision@5	0.1731
cosine_precision@10	0.0904
cosine_recall@1	0.7071
cosine_recall@3	0.8286
cosine_recall@5	0.8657
cosine_recall@10	0.9043
cosine_ndcg@10	0.809
cosine_mrr@10	0.7781
cosine_map@100	0.7818

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7
cosine_accuracy@3	0.8357
cosine_accuracy@5	0.8671
cosine_accuracy@10	0.9114
cosine_precision@1	0.7
cosine_precision@3	0.2786
cosine_precision@5	0.1734
cosine_precision@10	0.0911
cosine_recall@1	0.7
cosine_recall@3	0.8357
cosine_recall@5	0.8671
cosine_recall@10	0.9114
cosine_ndcg@10	0.8093
cosine_mrr@10	0.7763
cosine_map@100	0.7797

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7029
cosine_accuracy@3	0.8357
cosine_accuracy@5	0.8629
cosine_accuracy@10	0.9014
cosine_precision@1	0.7029
cosine_precision@3	0.2786
cosine_precision@5	0.1726
cosine_precision@10	0.0901
cosine_recall@1	0.7029
cosine_recall@3	0.8357
cosine_recall@5	0.8629
cosine_recall@10	0.9014
cosine_ndcg@10	0.8069
cosine_mrr@10	0.7762
cosine_map@100	0.7801

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.69
cosine_accuracy@3	0.8171
cosine_accuracy@5	0.8457
cosine_accuracy@10	0.8971
cosine_precision@1	0.69
cosine_precision@3	0.2724
cosine_precision@5	0.1691
cosine_precision@10	0.0897
cosine_recall@1	0.69
cosine_recall@3	0.8171
cosine_recall@5	0.8457
cosine_recall@10	0.8971
cosine_ndcg@10	0.7941
cosine_mrr@10	0.7612
cosine_map@100	0.765

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6429
cosine_accuracy@3	0.7786
cosine_accuracy@5	0.82
cosine_accuracy@10	0.86
cosine_precision@1	0.6429
cosine_precision@3	0.2595
cosine_precision@5	0.164
cosine_precision@10	0.086
cosine_recall@1	0.6429
cosine_recall@3	0.7786
cosine_recall@5	0.82
cosine_recall@10	0.86
cosine_ndcg@10	0.7522
cosine_mrr@10	0.7176
cosine_map@100	0.7227

Training Details

Training Dataset

philschmid/finanical-rag-embedding-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: 8 tokens mean: 46.23 tokens max: 289 tokens	min: 7 tokens mean: 20.38 tokens max: 41 tokens

• Samples:

  positive	anchor
  In addition, most group health plans and issuers of group or individual health insurance coverage are required to disclose personalized pricing information to their participants, beneficiaries, and enrollees through an online consumer tool, by phone, or in paper form, upon request. Cost estimates must be provided in real-time based on cost-sharing information that is accurate at the time of the request.	What are the requirements for health insurers and group health plans in providing cost estimates to consumers?
  Gross profit energy generation and storage segment	$
  In addition, eBay authenticates eligible luxury and collectible items in five categories through “Authenticity Guarantee”, an independent authentication service available in the United States, the United Kingdom, Germany, Australia and Canada.	What does eBay's Authenticity Guarantee service offer?

• 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
• fp16: 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: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• 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@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.8122	10	1.5914	-	-	-	-	-
0.9746	12	-	0.7520	0.7713	0.7706	0.6969	0.7753
1.6244	20	0.6901	-	-	-	-	-
1.9492	24	-	0.7616	0.7821	0.7799	0.7173	0.7795
2.4365	30	0.4967	-	-	-	-	-
2.9239	36	-	0.7643	0.7815	0.7801	0.7219	0.7817
3.2487	40	0.3894	-	-	-	-	-
3.8985	48	-	0.765	0.7801	0.7797	0.7227	0.7818

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.3.0+cu121
• Accelerate: 0.31.0
• Datasets: 2.19.2
• 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}
}