---
base_model: BAAI/bge-base-en-v1.5
datasets: []
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:700
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: Workforce Solutions is our largest reportable segment, contributing
44% of total operating revenue for 2023.
sentences:
- How much did GameStop Corp's valuation allowances increase during fiscal 2022?
- What percentage of total operating revenue for 2023 was represented by the Workforce
Solutions segment?
- Where are the majority of NIKE's footwear and apparel products manufactured?
- source_sentence: The effects of actual results differing from our assumptions and
the effects of changing assumptions are considered actuarial gains or losses.
We utilize a mark-to-market approach in recognizing actuarial gains or losses
immediately through earnings upon the annual remeasurement in the fourth quarter,
or on an interim basis as triggering events warrant remeasurement.
sentences:
- How are the company's postretirement benefit plan actuarial gains or losses recognized?
- What specific procedures did the auditors perform related to the Critical Audit
Matter of medical care services Incurred but not Reported (IBNR)?
- What strategies does the company use to manage product costs and supply?
- source_sentence: To improve the in-store shopping experience, the company invested
in wayfinding signage, store refresh packages, self-service lockers, and enhanced
checkout areas, aiming to provide easier navigation and increased convenience.
sentences:
- What are the expectations the company has for its employees in aligning with the
Code of Conduct?
- What strategies are employed to improve the in-store shopping experience?
- Where does the 10-K filing direct readers for specifics on legal proceedings involving
the company?
- source_sentence: In 2023, under pre-approved share repurchase programs, The Hershey
Company repurchased shares valued at $27.4 million.
sentences:
- What is the value of shares repurchased under the pre-approved program as stated
in The Hershey Company's 2023 Form 10-K, for the year 2023?
- What critical accounting estimates were identified as having the greatest potential
impact on the financial statements?
- What was the total net sales in fiscal 2022?
- source_sentence: During September 2023, the Company entered into a third amended
and restated revolving credit agreement with Bank of America, N.A., as administrative
agent, swing line lender and a letter of credit issuer and lender and certain
other financial institutions, as lenders thereto (the 'Amended Revolving Credit
Agreement'), which provides the Company with commitments having a maximum aggregate
principal amount of $1.25 billion, effective as of September 5, 2023. The Amended
Revolving Credit Agreement also provides for a potential additional incremental
commitment increase of up to $500.0 million subject to agreement of the lenders.
The Amended Revolving Credit Agreement contains certain financial covenants setting
forth leverage and coverage requirements, and certain other limitations typical
of an investment grade facility, including with respect to liens, mergers and
incurrence of indebtedness. The Amended Revolving Credit Agreement extends through
September 5, 2028.
sentences:
- What constitutes the largest expense in the company's various expense categories?
- What is the function of the amended revolving credit agreement that the Company
entered into with Bank of America in September 2023?
- What position does Brad D. Smith currently hold?
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: 0.6617460317460317
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7933333333333333
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8365079365079365
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8850793650793651
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6617460317460317
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2644444444444444
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1673015873015873
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08850793650793651
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.6617460317460317
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7933333333333333
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8365079365079365
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8850793650793651
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7731048434378245
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.737306437389771
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7413478623467549
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.660952380952381
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7880952380952381
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8352380952380952
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8834920634920634
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.660952380952381
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2626984126984127
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.16704761904761903
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08834920634920633
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.660952380952381
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7880952380952381
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8352380952380952
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8834920634920634
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7712996524525622
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7355047871000246
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7396551248138244
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.6507936507936508
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7795238095238095
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.823968253968254
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.873968253968254
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6507936507936508
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2598412698412698
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.16479365079365077
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08739682539682538
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.6507936507936508
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7795238095238095
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.823968253968254
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.873968253968254
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7614205489576108
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7255282186948864
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.729844180658852
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.6217460317460317
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7541269841269841
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.7987301587301587
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8546031746031746
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6217460317460317
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.25137566137566136
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.15974603174603175
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08546031746031746
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.6217460317460317
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7541269841269841
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.7987301587301587
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8546031746031746
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7368786132926283
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6994103048626867
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.704308796361143
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.5647619047619048
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7026984126984127
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.7477777777777778
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8012698412698412
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.5647619047619048
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2342328042328042
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.14955555555555555
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08012698412698412
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.5647619047619048
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7026984126984127
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.7477777777777778
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8012698412698412
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.6817715934378692
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6436686192995734
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6495479778469232
name: Cosine Map@100
---
# BGE base Financial Matryoshka
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co./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.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co./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](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co./models?library=sentence-transformers)
### 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:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("IlhamEbdesk/bge-base-financial-matryoshka")
# Run inference
sentences = [
"During September 2023, the Company entered into a third amended and restated revolving credit agreement with Bank of America, N.A., as administrative agent, swing line lender and a letter of credit issuer and lender and certain other financial institutions, as lenders thereto (the 'Amended Revolving Credit Agreement'), which provides the Company with commitments having a maximum aggregate principal amount of $1.25 billion, effective as of September 5, 2023. The Amended Revolving Credit Agreement also provides for a potential additional incremental commitment increase of up to $500.0 million subject to agreement of the lenders. The Amended Revolving Credit Agreement contains certain financial covenants setting forth leverage and coverage requirements, and certain other limitations typical of an investment grade facility, including with respect to liens, mergers and incurrence of indebtedness. The Amended Revolving Credit Agreement extends through September 5, 2028.",
'What is the function of the amended revolving credit agreement that the Company entered into with Bank of America in September 2023?',
'What position does Brad D. Smith currently hold?',
]
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](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.6617 |
| cosine_accuracy@3 | 0.7933 |
| cosine_accuracy@5 | 0.8365 |
| cosine_accuracy@10 | 0.8851 |
| cosine_precision@1 | 0.6617 |
| cosine_precision@3 | 0.2644 |
| cosine_precision@5 | 0.1673 |
| cosine_precision@10 | 0.0885 |
| cosine_recall@1 | 0.6617 |
| cosine_recall@3 | 0.7933 |
| cosine_recall@5 | 0.8365 |
| cosine_recall@10 | 0.8851 |
| cosine_ndcg@10 | 0.7731 |
| cosine_mrr@10 | 0.7373 |
| **cosine_map@100** | **0.7413** |
#### Information Retrieval
* Dataset: `dim_512`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.661 |
| cosine_accuracy@3 | 0.7881 |
| cosine_accuracy@5 | 0.8352 |
| cosine_accuracy@10 | 0.8835 |
| cosine_precision@1 | 0.661 |
| cosine_precision@3 | 0.2627 |
| cosine_precision@5 | 0.167 |
| cosine_precision@10 | 0.0883 |
| cosine_recall@1 | 0.661 |
| cosine_recall@3 | 0.7881 |
| cosine_recall@5 | 0.8352 |
| cosine_recall@10 | 0.8835 |
| cosine_ndcg@10 | 0.7713 |
| cosine_mrr@10 | 0.7355 |
| **cosine_map@100** | **0.7397** |
#### Information Retrieval
* Dataset: `dim_256`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.6508 |
| cosine_accuracy@3 | 0.7795 |
| cosine_accuracy@5 | 0.824 |
| cosine_accuracy@10 | 0.874 |
| cosine_precision@1 | 0.6508 |
| cosine_precision@3 | 0.2598 |
| cosine_precision@5 | 0.1648 |
| cosine_precision@10 | 0.0874 |
| cosine_recall@1 | 0.6508 |
| cosine_recall@3 | 0.7795 |
| cosine_recall@5 | 0.824 |
| cosine_recall@10 | 0.874 |
| cosine_ndcg@10 | 0.7614 |
| cosine_mrr@10 | 0.7255 |
| **cosine_map@100** | **0.7298** |
#### Information Retrieval
* Dataset: `dim_128`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.6217 |
| cosine_accuracy@3 | 0.7541 |
| cosine_accuracy@5 | 0.7987 |
| cosine_accuracy@10 | 0.8546 |
| cosine_precision@1 | 0.6217 |
| cosine_precision@3 | 0.2514 |
| cosine_precision@5 | 0.1597 |
| cosine_precision@10 | 0.0855 |
| cosine_recall@1 | 0.6217 |
| cosine_recall@3 | 0.7541 |
| cosine_recall@5 | 0.7987 |
| cosine_recall@10 | 0.8546 |
| cosine_ndcg@10 | 0.7369 |
| cosine_mrr@10 | 0.6994 |
| **cosine_map@100** | **0.7043** |
#### Information Retrieval
* Dataset: `dim_64`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.5648 |
| cosine_accuracy@3 | 0.7027 |
| cosine_accuracy@5 | 0.7478 |
| cosine_accuracy@10 | 0.8013 |
| cosine_precision@1 | 0.5648 |
| cosine_precision@3 | 0.2342 |
| cosine_precision@5 | 0.1496 |
| cosine_precision@10 | 0.0801 |
| cosine_recall@1 | 0.5648 |
| cosine_recall@3 | 0.7027 |
| cosine_recall@5 | 0.7478 |
| cosine_recall@10 | 0.8013 |
| cosine_ndcg@10 | 0.6818 |
| cosine_mrr@10 | 0.6437 |
| **cosine_map@100** | **0.6495** |
## Training Details
### 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
- `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`: False
- `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