metadata

base_model: BAAI/bge-base-en-v1.5
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Item 8 includes Financial Statements and Supplementary Data.
    sentences:
      - >-
        What does the FDA label update for Yescarta include as of the latest
        approval?
      - What information can be found in Item 8 of a document?
      - When does the Company's fiscal year end?
  - source_sentence: >-
      Item 8 in a financial document is designated for Financial Statements and
      Supplementary Data.
    sentences:
      - What are the primary goals of AutoZone's store management system?
      - What information is contained in Item 8 of a financial document?
      - >-
        What were the pre-tax earnings of the manufacturing sector in 2023,
        2022, and 2021?
  - source_sentence: >-
      of approximately $1.0 billion in IBNR liabilities, producing a
      corresponding decrease in pre-tax earnings. We believe it is reasonably
      possible for these assumptions to increase at these rates.
    sentences:
      - >-
        What was the decrease in pre-tax earnings due to the $1.0 billion in
        IBNR liabilities?
      - >-
        What was the total long-term debt, including the current portion, for
        AbbVie as of December 31, 2023?
      - >-
        What feature dedicated AI hardware in an x86 processor and uses the XDNA
        architecture?
  - source_sentence: >-
      In the year ended December 31, 2023, sellers generated GMS of $13.2
      billion, approximately 68% of which came from purchases made on mobile
      devices.
    sentences:
      - >-
        What was the change in the total balance of revolving credits from
        December 31, 2022, to December 31, 2023?
      - What are the purposes of borrowings under the 2021 credit facility?
      - >-
        What percentage of Etsy's Gross Merchandise Sales (GMS) in 2023 came
        from mobile purchases?
  - source_sentence: >-
      As of December 31, 2023, approximately $1.80 billion is available to be
      repatriated from Mainland China to the U.S.
    sentences:
      - >-
        What is the total amount of unrestricted cash available for repatriation
        from Mainland China to the U.S. as of the end of 2023?
      - What is the focus of the company's research and development efforts?
      - >-
        Where does the Report of Independent Registered Public Accounting Firm
        begin in this report?
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.6771428571428572
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8142857142857143
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8642857142857143
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9142857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6771428571428572
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2714285714285714
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17285714285714282
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09142857142857141
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6771428571428572
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8142857142857143
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8642857142857143
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9142857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7948920706768223
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7568055555555551
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7601580985784901
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6714285714285714
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8157142857142857
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8657142857142858
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.92
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6714285714285714
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27190476190476187
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17314285714285713
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09199999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6714285714285714
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8157142857142857
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8657142857142858
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.92
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7936366054643341
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7534455782312921
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.756388193211117
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6714285714285714
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8157142857142857
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8585714285714285
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9157142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6714285714285714
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27190476190476187
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1717142857142857
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09157142857142857
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6714285714285714
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8157142857142857
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8585714285714285
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9157142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7926136922070053
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7535062358276641
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7564593466816174
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6614285714285715
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8414285714285714
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8885714285714286
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6614285714285715
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16828571428571426
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08885714285714286
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6614285714285715
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8414285714285714
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8885714285714286
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7767052058983972
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7407840136054418
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7454236920389576
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6357142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7742857142857142
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8185714285714286
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8642857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6357142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2580952380952381
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1637142857142857
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08642857142857142
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6357142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7742857142857142
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8185714285714286
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8642857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7511926722277801
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7148713151927435
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7199017346952273
            name: Cosine Map@100

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 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': 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("SMARTICT/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'As of December 31, 2023, approximately $1.80 billion is available to be repatriated from Mainland China to the U.S.',
    'What is the total amount of unrestricted cash available for repatriation from Mainland China to the U.S. as of the end of 2023?',
    "What is the focus of the company's research and development efforts?",
]
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

Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.6771	0.6714	0.6714	0.6614	0.6357
cosine_accuracy@3	0.8143	0.8157	0.8157	0.8	0.7743
cosine_accuracy@5	0.8643	0.8657	0.8586	0.8414	0.8186
cosine_accuracy@10	0.9143	0.92	0.9157	0.8886	0.8643
cosine_precision@1	0.6771	0.6714	0.6714	0.6614	0.6357
cosine_precision@3	0.2714	0.2719	0.2719	0.2667	0.2581
cosine_precision@5	0.1729	0.1731	0.1717	0.1683	0.1637
cosine_precision@10	0.0914	0.092	0.0916	0.0889	0.0864
cosine_recall@1	0.6771	0.6714	0.6714	0.6614	0.6357
cosine_recall@3	0.8143	0.8157	0.8157	0.8	0.7743
cosine_recall@5	0.8643	0.8657	0.8586	0.8414	0.8186
cosine_recall@10	0.9143	0.92	0.9157	0.8886	0.8643
cosine_ndcg@10	0.7949	0.7936	0.7926	0.7767	0.7512
cosine_mrr@10	0.7568	0.7534	0.7535	0.7408	0.7149
cosine_map@100	0.7602	0.7564	0.7565	0.7454	0.7199

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: 4 tokens
mean: 46.71 tokens
max: 281 tokens

min: 7 tokens
mean: 20.48 tokens
max: 43 tokens

	positive	anchor
type	string	string
details	min: 4 tokens mean: 46.71 tokens max: 281 tokens	min: 7 tokens mean: 20.48 tokens max: 43 tokens

Samples:

positive	anchor
`Information on legal proceedings is included in Note 15 to the Consolidated Financial Statements.`	`What note in the Consolidated Financial Statements provides details on legal proceedings?`
`As of December 31, 2023, approximately $1.80 billion is available to be repatriated from Mainland China to the U.S.`	`What is the total amount of unrestricted cash available for repatriation from Mainland China to the U.S. as of the end of 2023?`
`Bank deposits amounted to $289,953 million as of December 31, 2023.`	`What was the balance of bank deposits at Charles Schwab Corporation 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
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
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
0.8122	10	1.5517	-	-	-	-	-
0.9746	12	-	0.7830	0.7842	0.7814	0.7623	0.7215
1.6244	20	0.6616	-	-	-	-	-
1.9492	24	-	0.7918	0.7924	0.7884	0.7737	0.7429
2.4365	30	0.46	-	-	-	-	-
2.9239	36	-	0.7941	0.7920	0.7930	0.7764	0.7482
3.2487	40	0.3917	-	-	-	-	-
3.8985	48	-	0.7949	0.7936	0.7926	0.7767	0.7512

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
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}
}