SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the investopedia-embedding-dataset dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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("sachinyerrawar/test")
# Run inference
queries = [
    ' What are the main differences between term life insurance and whole life insurance in terms of coverage duration, premiums, and guaranteed payout? \n',
]
documents = [
    ' Term life insurance has predetermined coverage that lasts for a specific period, with options like 10-, 15-, 20-, and 30-year terms. Premiums remain level during the term. On the other hand, whole life insurance is a permanent coverage that guarantees a payout to beneficiaries regardless of when the insured person dies, as long as premiums are paid.',
    ' A wedding budget can be affected by locking in costs with a deposit and signed contract, specific wording in the contract, reading the fine print, providing a savings buffer for potential shortfalls, the advice to add 20% for incidentals, and the time of year chosen for the wedding.',
    " To contribute to a spousal IRA, the working/contributing spouse's income must be equal to or exceed the amount contributed for both individuals, and both spouses must file their tax returns jointly.",
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.7948, 0.0477, 0.0509]])

Evaluation

Metrics

Information Retrieval

Metric Value
cosine_accuracy@1 0.7973
cosine_accuracy@3 0.8783
cosine_accuracy@5 0.9038
cosine_accuracy@10 0.9327
cosine_precision@1 0.7973
cosine_precision@3 0.2928
cosine_precision@5 0.1808
cosine_precision@10 0.0933
cosine_recall@1 0.7973
cosine_recall@3 0.8783
cosine_recall@5 0.9038
cosine_recall@10 0.9327
cosine_ndcg@10 0.8652
cosine_mrr@10 0.8436
cosine_map@100 0.846

Training Details

Training Dataset

investopedia-embedding-dataset

  • Dataset: investopedia-embedding-dataset at c29a3a9
  • Size: 206,460 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 100 samples:
    anchor positive
    type string string
    modality text text
    details
    • min: 13 tokens
    • mean: 24.73 tokens
    • max: 54 tokens
    • min: 4 tokens
    • mean: 47.75 tokens
    • max: 120 tokens
  • Samples:
    anchor positive
    In the given passage, how are residual values calculated for an unnamed experiment with a linear equation yest = 1x + 2?
    Residual values for an unnamed experiment are calculated by using the given linear equation yest = 1x + 2 with the observed data provided in the table. For each observation, the residual can be found by comparing the predicted y value (yest) with the observed y value.
    What are some advantages of using a home equity loan for a home remodel compared to unsecured options like personal loans?
    The passage highlights two main advantages: home equity loans generally offer low interest rates when compared to unsecured options like personal loans, which can help save money on home remodel costs. Additionally, they have fixed interest rates, providing stability in monthly payments and protection from rate changes during the entire repayment term.
    Which companies has AWS partnered with to broaden its space capabilities?
    AWS has partnered with Capella Space and Maxar Technologies Inc. (MAXR) to broaden its space capabilities.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false,
        "directions": [
            "query_to_doc"
        ],
        "partition_mode": "joint",
        "hardness_mode": null,
        "hardness_strength": 0.0
    }
    

Evaluation Dataset

investopedia-embedding-dataset

  • Dataset: investopedia-embedding-dataset at c29a3a9
  • Size: 22,940 evaluation samples
  • Columns: Question and Answer
  • Approximate statistics based on the first 100 samples:
    Question Answer
    type string string
    modality text text
    details
    • min: 13 tokens
    • mean: 24.73 tokens
    • max: 54 tokens
    • min: 4 tokens
    • mean: 47.75 tokens
    • max: 120 tokens
  • Samples:
    Question Answer
    In the given passage, how are residual values calculated for an unnamed experiment with a linear equation yest = 1x + 2?
    Residual values for an unnamed experiment are calculated by using the given linear equation yest = 1x + 2 with the observed data provided in the table. For each observation, the residual can be found by comparing the predicted y value (yest) with the observed y value.
    What are some advantages of using a home equity loan for a home remodel compared to unsecured options like personal loans?
    The passage highlights two main advantages: home equity loans generally offer low interest rates when compared to unsecured options like personal loans, which can help save money on home remodel costs. Additionally, they have fixed interest rates, providing stability in monthly payments and protection from rate changes during the entire repayment term.
    Which companies has AWS partnered with to broaden its space capabilities?
    AWS has partnered with Capella Space and Maxar Technologies Inc. (MAXR) to broaden its space capabilities.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false,
        "directions": [
            "query_to_doc"
        ],
        "partition_mode": "joint",
        "hardness_mode": null,
        "hardness_strength": 0.0
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 64
  • num_train_epochs: 2
  • learning_rate: 2e-05
  • warmup_steps: 0.1
  • fp16: True
  • push_to_hub: True
  • hub_model_id: sachinyerrawar/test
  • hub_strategy: end
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • per_device_train_batch_size: 64
  • num_train_epochs: 2
  • max_steps: -1
  • learning_rate: 2e-05
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_steps: 0.1
  • optim: adamw_torch_fused
  • optim_args: None
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • optim_target_modules: None
  • gradient_accumulation_steps: 1
  • average_tokens_across_devices: True
  • max_grad_norm: 1.0
  • label_smoothing_factor: 0.0
  • bf16: False
  • fp16: True
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • use_liger_kernel: False
  • liger_kernel_config: None
  • use_cache: False
  • neftune_noise_alpha: None
  • torch_empty_cache_steps: None
  • auto_find_batch_size: False
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • include_num_input_tokens_seen: no
  • log_level: passive
  • log_level_replica: warning
  • disable_tqdm: False
  • project: huggingface
  • trackio_space_id: None
  • trackio_bucket_id: None
  • trackio_static_space_id: None
  • per_device_eval_batch_size: 8
  • prediction_loss_only: True
  • eval_on_start: False
  • eval_do_concat_batches: True
  • eval_use_gather_object: False
  • eval_accumulation_steps: None
  • include_for_metrics: []
  • batch_eval_metrics: False
  • save_only_model: False
  • save_on_each_node: False
  • enable_jit_checkpoint: False
  • push_to_hub: True
  • hub_private_repo: None
  • hub_model_id: sachinyerrawar/test
  • hub_strategy: end
  • hub_always_push: False
  • hub_revision: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • restore_callback_states_from_checkpoint: False
  • full_determinism: False
  • seed: 42
  • data_seed: None
  • use_cpu: False
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • parallelism_config: None
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • dataloader_prefetch_factor: None
  • dataloader_multiprocessing_context: None
  • dataloader_in_order: True
  • remove_unused_columns: True
  • label_names: None
  • train_sampling_strategy: random
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • ddp_static_graph: None
  • ddp_backend: None
  • ddp_timeout: 1800
  • fsdp: None
  • fsdp_config: None
  • deepspeed: None
  • debug: []
  • skip_memory_metrics: True
  • do_predict: False
  • resume_from_checkpoint: None
  • local_rank: -1
  • prompts: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}
  • warmup_ratio: None

Training Logs

Epoch Step Training Loss Validation Loss val_cosine_ndcg@10
-1 -1 - - 0.7379
1.0 3226 0.0817 0.0082 0.8487
-1 -1 - - 0.8487
1.0 3226 0.0465 0.0058 0.8579
2.0 6452 0.0481 0.0047 0.8652

Training Time

  • Training: 3.6 minutes

Framework Versions

  • Python: 3.13.16
  • Sentence Transformers: 5.7.0
  • Transformers: 5.22.1
  • PyTorch: 2.14.1+cu130
  • Accelerate: 1.15.0
  • Datasets: 4.8.5
  • Tokenizers: 0.23.3

Additional Resources

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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}
Downloads last month
49
Safetensors
Model size
22.7M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sachinyerrawar/test

Dataset used to train sachinyerrawar/test

Papers for sachinyerrawar/test

Evaluation results