Avinashc/bge-base-financial-matryoshka

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the json dataset. 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
• Training Dataset:
  • json
• 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("Avinashc/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Management assessed the effectiveness of the company’s internal control over financial reporting as of December 31, 2023. In making this assessment, we used the criteria set forth by the Committee of Sponsoring Organizations of the Treadway Commission (COSO) in Internal Control—Integrated Framework (2013).',
    'What criteria did Caterpillar Inc. use to assess the effectiveness of its internal control over financial reporting as of December 31, 2023?',
    'What are the primary components of U.S. sales volumes for Ford?',
]
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	0.6514
cosine_accuracy@3	0.79
cosine_accuracy@5	0.8229
cosine_accuracy@10	0.8786
cosine_precision@1	0.6514
cosine_precision@3	0.2633
cosine_precision@5	0.1646
cosine_precision@10	0.0879
cosine_recall@1	0.6514
cosine_recall@3	0.79
cosine_recall@5	0.8229
cosine_recall@10	0.8786
cosine_ndcg@10	0.7658
cosine_mrr@10	0.7298
cosine_map@100	0.7338

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6471
cosine_accuracy@3	0.7829
cosine_accuracy@5	0.8229
cosine_accuracy@10	0.8686
cosine_precision@1	0.6471
cosine_precision@3	0.261
cosine_precision@5	0.1646
cosine_precision@10	0.0869
cosine_recall@1	0.6471
cosine_recall@3	0.7829
cosine_recall@5	0.8229
cosine_recall@10	0.8686
cosine_ndcg@10	0.7589
cosine_mrr@10	0.7236
cosine_map@100	0.7284

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6257
cosine_accuracy@3	0.7614
cosine_accuracy@5	0.8214
cosine_accuracy@10	0.87
cosine_precision@1	0.6257
cosine_precision@3	0.2538
cosine_precision@5	0.1643
cosine_precision@10	0.087
cosine_recall@1	0.6257
cosine_recall@3	0.7614
cosine_recall@5	0.8214
cosine_recall@10	0.87
cosine_ndcg@10	0.747
cosine_mrr@10	0.7077
cosine_map@100	0.7119

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.62
cosine_accuracy@3	0.7371
cosine_accuracy@5	0.7829
cosine_accuracy@10	0.8486
cosine_precision@1	0.62
cosine_precision@3	0.2457
cosine_precision@5	0.1566
cosine_precision@10	0.0849
cosine_recall@1	0.62
cosine_recall@3	0.7371
cosine_recall@5	0.7829
cosine_recall@10	0.8486
cosine_ndcg@10	0.7301
cosine_mrr@10	0.6927
cosine_map@100	0.6974

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5729
cosine_accuracy@3	0.7014
cosine_accuracy@5	0.73
cosine_accuracy@10	0.7829
cosine_precision@1	0.5729
cosine_precision@3	0.2338
cosine_precision@5	0.146
cosine_precision@10	0.0783
cosine_recall@1	0.5729
cosine_recall@3	0.7014
cosine_recall@5	0.73
cosine_recall@10	0.7829
cosine_ndcg@10	0.6772
cosine_mrr@10	0.6436
cosine_map@100	0.6506

Training Details

Training Dataset

json

• Dataset: json
• 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: 44.33 tokens max: 289 tokens	min: 9 tokens mean: 20.43 tokens max: 46 tokens

• Samples:

  positive	anchor
  The Company defines fair value as the price received to transfer an asset or paid to transfer a liability in an orderly transaction between market participants at the measurement date. In accordance with ASC 820, Fair Value Measurements and Disclosures, the Company uses the fair value hierarchy which prioritizes the inputs used to measure fair value. The hierarchy gives the highest priority to unadjusted quoted prices in active markets for identical assets or liabilities (Level 1), observable inputs other than quoted prices (Level 2), and unobservable inputs (Level 3).	What is the role of Level 1, Level 2, and Level 3 inputs in the fair value hierarchy according to ASC 820?
  In the event of conversion of the Notes, if shares are delivered to the Company under the Capped Call Transactions, they will offset the dilutive effect of the shares that the Company would issue under the Notes.	What happens to the dilutive effect of shares issued under the Notes if shares are delivered to the Company under the Capped Call Transactions during the conversion?
  Marketing expenses increased $48.8 million to $759.2 million in the year ended December 31, 2023 compared to the year ended December 31, 2022.	How much did the marketing expenses increase in the year ended December 31, 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: 2e-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: 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: 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	dim_768_cosine_map@100	dim_512_cosine_map@100	dim_256_cosine_map@100	dim_128_cosine_map@100	dim_64_cosine_map@100
0.64	1	0.7114	0.7030	0.6891	0.6658	0.6075
1.92	3	0.7323	0.7288	0.7106	0.6916	0.6464
2.56	4	0.7338	0.7284	0.7119	0.6974	0.6506

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.2.0
• Transformers: 4.41.2
• PyTorch: 2.2.0a0+6a974be
• Accelerate: 0.27.0
• 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}
}