BGE Small Financial Matryoshka

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: BAAI/bge-small-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• 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': 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)

Evaluation

Metrics

Information Retrieval

• Dataset: dim_384
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 384 3}

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 256 3}

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 128 3}

Training Details

Training Dataset

json

• Dataset: json
• Size: 5,000 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 10 tokens mean: 20.32 tokens max: 40 tokens	min: 4 tokens mean: 45.48 tokens max: 252 tokens

• Samples:

  anchor	positive
  What was the impact on the fair value measurement of level 3 investments when the yield, discount rate, and capitalization rate were increased?	Increases in yield, discount rate, capitalization rate or duration used in the valuation of level 3 investments would have resulted in a lower fair value measurement, while increases in recovery rate or multiples would have resulted in a higher fair value measurement as of both December 2023 and December 2022.
  What factors led to the increase in Intelligent Edge earnings from operations as a percentage of net revenue?	Intelligent Edge earnings from operations as a percentage of net revenue increased 12.4 percentage points primarily due to decreases in cost of products and services as a percentage of net revenue and operating expenses as a percentage of net revenue.
  What drove the increase in the Family of Apps income from operations in 2023?	Family of Apps FoA income from operations in 2023 increased $20.21 billion, or 47%, compared to 2022. The increase was mostly driven by higher advertising revenue and a decrease in marketing and sales expenses.

• Loss: MatryoshkaLoss with these parameters:
  json

  1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 384, 5 256, 6 128 7 ], 8 "matryoshka_weights": [ 9 1, 10 1, 11 1 12 ], 13 "n_dims_per_step": -1 14}

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• gradient_accumulation_steps: 8
• learning_rate: 2e-05
• num_train_epochs: 4
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• load_best_model_at_end: True
• dataloader_pin_memory: False
• gradient_checkpointing: True
• batch_sampler: no_duplicates

All Hyperparameters

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.9.22
• Sentence Transformers: 4.1.0
• Transformers: 4.52.1
• PyTorch: 2.6.0
• Accelerate: 1.7.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

MatryoshkaLoss

MultipleNegativesRankingLoss