test / README.md
sachinyerrawar's picture
End of training
1a0ab86 verified
|
Raw History Blame Contribute Delete
27.4 kB
---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:206460
- loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
- source_sentence: " What factor significantly influences the rate of technology adoption\
\ and provides an example of a technology that experienced a boost in adoption\
\ due to its improved usability? \n"
sentences:
- ' The potential benefits include having coverage to pay off the mortgage in case
of an unfortunate event and getting the benefit of returned premiums if the policy
is never used. The costs mentioned in the passage are between $16 and $35 a month
for a healthy woman in her early 30s seeking $300,000 to $500,000 in term coverage
for 30 years.'
- ' Network effects strongly influence the rate of adoption, and the rapid growth
of the Internet, facilitated by the development of web browsers, is an example
of a technology that experienced a boost in adoption due to its improved usability.'
- ' Yes, your Social Security benefits may be subject to income tax depending on
your overall income, as mentioned in the passage. Up to 85% of your Social Security
benefits could be taxable.'
- source_sentence: " What type of company is described as owning or controlling multiple\
\ commercial banks while being subject to more regulations and oversight? \n"
sentences:
- ' The purpose of full trading authorization for clients is to empower an agent
to conduct all activities that the client themselves could perform. This is often
used by investors with limited knowledge, lacking confidence, busy schedules,
or those who find the process of researching and monitoring trading activities
too stressful or time-consuming. Trust in the agent or broker is crucial for investors
granting full trading authorization.'
- ' The document is "Securities and Exchange Commission, 17 CFR Parts 200 and 240:
Final Rule, Amendments to the Tender Offer Best-Price Rules," and relevant information
can be found on pages 10 and 11, 13, and 58, as well as pages 4 and 5.'
- ' A multibank holding company'
- source_sentence: " Why does the wage rate fall in the given text passage about labor\
\ supply and new workers? \n"
sentences:
- ' You''re eligible to receive full retirement benefits at age 66 if you were born
between 1943 and 1954. For those born in 1955 or later, your full retirement age
is determined by how long after 1954 you were born. If you claim benefits before
reaching your full retirement age, your annual benefits will be less.'
- ' Understanding an industry''s churn rate versus that of a business helps determine
if a churn rate is acceptable or poor.'
- ' The wage rate falls in the given text passage because of the increase in the
availability of new workers, which creates downward pressure on the wage rate.'
- source_sentence: " What event led to the potential increase in labor costs for studios?\
\ \n"
sentences:
- ' Landlords should stay on top of maintenance when renting out their property
because upkeep and repairs that might be overlooked when only the owner is living
there can become liabilities when a renter is present.'
- ' Brett received his bachelor''s degree in exercise science from Illinois State
University.'
- ' The tentative agreement between the union and SAG-AFTRA contributed to the potential
increase in labor costs for studios as the strike comes to a close.'
- source_sentence: " What are the main differences between term life insurance and\
\ whole life insurance in terms of coverage duration, premiums, and guaranteed\
\ payout? \n"
sentences:
- ' 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.'
datasets:
- FinLang/investopedia-embedding-dataset
pipeline_tag: sentence-similarity
library_name: sentence-transformers
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
model-index:
- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: val
type: val
metrics:
- type: cosine_accuracy@1
value: 0.7972972972972973
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8783347863993025
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9038360941586748
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9326503923278117
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7972972972972973
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2927782621331009
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.18076721883173494
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09326503923278116
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7972972972972973
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8783347863993025
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9038360941586748
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9326503923278117
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8651726981708079
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8435601154149589
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8460407348927453
name: Cosine Map@100
---
# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the [investopedia-embedding-dataset](https://huggingface.co/datasets/FinLang/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 Type:** Sentence Transformer
- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 1110a243fdf4706b3f48f1d95db1a4f5529b4d41 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 384 dimensions
- **Similarity Function:** Cosine Similarity
- **Supported Modality:** Text
- **Training Dataset:**
- [investopedia-embedding-dataset](https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset)
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### 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:
```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("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]])
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `val`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.InformationRetrievalEvaluator)
| 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 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### investopedia-embedding-dataset
* Dataset: [investopedia-embedding-dataset](https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset) at [c29a3a9](https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset/tree/c29a3a95a0b074c48a893f139a3bf3c3aeb6bf8b)
* Size: 206,460 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 100 samples:
| | anchor | positive |
|:---------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| modality | text | text |
| details | <ul><li>min: 13 tokens</li><li>mean: 24.73 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 47.75 tokens</li><li>max: 120 tokens</li></ul> |
* Samples:
| anchor | positive |
|:----------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code> In the given passage, how are residual values calculated for an unnamed experiment with a linear equation yest = 1x + 2? <br></code> | <code> 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.</code> |
| <code> What are some advantages of using a home equity loan for a home remodel compared to unsecured options like personal loans? <br></code> | <code> 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.</code> |
| <code> Which companies has AWS partnered with to broaden its space capabilities? <br></code> | <code> AWS has partnered with Capella Space and Maxar Technologies Inc. (MAXR) to broaden its space capabilities.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"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](https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset) at [c29a3a9](https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset/tree/c29a3a95a0b074c48a893f139a3bf3c3aeb6bf8b)
* Size: 22,940 evaluation samples
* Columns: <code>Question</code> and <code>Answer</code>
* Approximate statistics based on the first 100 samples:
| | Question | Answer |
|:---------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| modality | text | text |
| details | <ul><li>min: 13 tokens</li><li>mean: 24.73 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 47.75 tokens</li><li>max: 120 tokens</li></ul> |
* Samples:
| Question | Answer |
|:----------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code> In the given passage, how are residual values calculated for an unnamed experiment with a linear equation yest = 1x + 2? <br></code> | <code> 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.</code> |
| <code> What are some advantages of using a home equity loan for a home remodel compared to unsecured options like personal loans? <br></code> | <code> 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.</code> |
| <code> Which companies has AWS partnered with to broaden its space capabilities? <br></code> | <code> AWS has partnered with Capella Space and Maxar Technologies Inc. (MAXR) to broaden its space capabilities.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"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
<details><summary>Click to expand</summary>
- `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
</details>
### 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
- [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models.
- [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss.
- [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors.
- [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API.
- [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough.
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@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
```bibtex
@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},
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->