revtestuser/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("revtestuser/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Net cash used in financing activities totaled $2,614 in 2023, compared to $4,283 in 2022.',
    'What was the net cash used in financing activities in 2023 and how does it compare to 2022?',
    "What are Chipotle's key strategies for business growth as discussed in their strategy?",
]
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	0.6971
cosine_accuracy@3	0.82
cosine_accuracy@5	0.8686
cosine_accuracy@10	0.9057
cosine_precision@1	0.6971
cosine_precision@3	0.2733
cosine_precision@5	0.1737
cosine_precision@10	0.0906
cosine_recall@1	0.6971
cosine_recall@3	0.82
cosine_recall@5	0.8686
cosine_recall@10	0.9057
cosine_ndcg@10	0.8036
cosine_mrr@10	0.7707
cosine_map@100	0.7749

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6957
cosine_accuracy@3	0.8229
cosine_accuracy@5	0.8643
cosine_accuracy@10	0.9043
cosine_precision@1	0.6957
cosine_precision@3	0.2743
cosine_precision@5	0.1729
cosine_precision@10	0.0904
cosine_recall@1	0.6957
cosine_recall@3	0.8229
cosine_recall@5	0.8643
cosine_recall@10	0.9043
cosine_ndcg@10	0.8028
cosine_mrr@10	0.7701
cosine_map@100	0.7744

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6871
cosine_accuracy@3	0.8186
cosine_accuracy@5	0.8529
cosine_accuracy@10	0.8986
cosine_precision@1	0.6871
cosine_precision@3	0.2729
cosine_precision@5	0.1706
cosine_precision@10	0.0899
cosine_recall@1	0.6871
cosine_recall@3	0.8186
cosine_recall@5	0.8529
cosine_recall@10	0.8986
cosine_ndcg@10	0.7952
cosine_mrr@10	0.762
cosine_map@100	0.7664

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6686
cosine_accuracy@3	0.8129
cosine_accuracy@5	0.8429
cosine_accuracy@10	0.8943
cosine_precision@1	0.6686
cosine_precision@3	0.271
cosine_precision@5	0.1686
cosine_precision@10	0.0894
cosine_recall@1	0.6686
cosine_recall@3	0.8129
cosine_recall@5	0.8429
cosine_recall@10	0.8943
cosine_ndcg@10	0.7841
cosine_mrr@10	0.7487
cosine_map@100	0.7527

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6471
cosine_accuracy@3	0.7829
cosine_accuracy@5	0.8243
cosine_accuracy@10	0.8686
cosine_precision@1	0.6471
cosine_precision@3	0.261
cosine_precision@5	0.1649
cosine_precision@10	0.0869
cosine_recall@1	0.6471
cosine_recall@3	0.7829
cosine_recall@5	0.8243
cosine_recall@10	0.8686
cosine_ndcg@10	0.7602
cosine_mrr@10	0.7253
cosine_map@100	0.7303

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: 44.91 tokens max: 246 tokens	min: 8 tokens mean: 20.43 tokens max: 43 tokens

• Samples:

  positive	anchor
  Certain provisions of the final rule become effective on April 1, 2024, but the majority of the final rule’s operative provisions (including the revisions to the definition of “limited purpose bank”) become effective on January 1, 2026, with additional data collection and reporting requirements becoming effective on January 1, 2027.	What are the effective dates for the main provisions and additional data collection and reporting requirements of the final rule impacting AENB's compliance obligations?
  Our total revenue for 2023 was $134.90 billion, an increase of 16% compared to 2022.	What was the total revenue for the year 2023 and the percentage increase from 2022?
  As of December 31, 2023, our domestic Chief Medical Officer leads a team of 22 nephrologists in our physician leadership team as part of our domestic Office of the Chief Medical Officer.	How many physicians are part of the domestic Office of the Chief Medical Officer at DaVita as of 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
• fp16: True
• tf32: False
• 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: False
• 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	1.6288	-	-	-	-	-
0.9746	12	-	0.7384	0.7485	0.7508	0.7013	0.7561
1.6244	20	0.6896	-	-	-	-	-
1.9492	24	-	0.7499	0.7621	0.7676	0.7220	0.7704
2.4365	30	0.4965	-	-	-	-	-
2.9239	36	-	0.7529	0.7669	0.7739	0.7302	0.7754
3.2487	40	0.415	-	-	-	-	-
3.8985	48	-	0.7527	0.7664	0.7744	0.7303	0.7749

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.34.2
• 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}
}