You can deploy this model and start earning money today!

Views

No views yet

BGE base Health Insurance Matryoshka

Name: bge-base-insurance-matryoshka
Availability: InStock

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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("ethanteh/bge-base-insurance-matryoshka")
# Run inference
sentences = [
    'Be in control with Active Pricing\n\nSam, age 35 years, purchases PRUMillion Med Active medical plan. With Active Pricing, Sam pays less premiums when he claims less.\n\nSam will enjoy an instant discount of 15% on the medical insurance charges, paying a monthly premium of only RM229 throughout the policy term if there are no claims made and approved.\n\nIn the event Sam makes a claim of less than RM5,000\n\nStack-Up Level Year 8: Premium temporarily increases to RM250 Base Level Year 7: Sam makes a claim of RM 250 Year 9 & onwards: discounted RM4,800 and is approved premium continues at RM229 Discount Level RM 229 RM 229 RM 229 RM 229 RM 229 RM 229 RM 229 RM 229 ...... Year 1 2 3... 7 8 9 10 11 12...\n\nIn the event Sam makes a claim of RM5,000 or more\n\nYear 4 & 5: Premiums temporarily increase to RM287 Year 6: Premium lowers down to RM250 Stack-Up Level RM 287 RM 287 Base Level Year 3: Sam was hospitalised with a serious illness and made a claim of RM80,000 and is approved RM 250 Year 7 & onwards: discounted premium continues at RM229 Discount Level RM 229 RM 229 RM 229 RM 229 RM 229 RM 229 Year 1 2 3 4 5 6 7 8 9... ...',
    "What happens to Sam's premium if he makes a claim of less than RM5,000 with PRUMillion Med Active?",
    'What are the premiums for a RM1,000 sum assured for a 28-year-old male non-smoker?',
]
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	0.0482	0.0602	0.0602	0.0482	0.0843
cosine_accuracy@3	0.5181	0.5301	0.494	0.506	0.4578
cosine_accuracy@5	0.6506	0.6386	0.6627	0.6145	0.5783
cosine_accuracy@10	0.8554	0.8072	0.8072	0.8193	0.7349
cosine_precision@1	0.0482	0.0602	0.0602	0.0482	0.0843
cosine_precision@3	0.1727	0.1767	0.1647	0.1687	0.1526
cosine_precision@5	0.1301	0.1277	0.1325	0.1229	0.1157
cosine_precision@10	0.0855	0.0807	0.0807	0.0819	0.0735
cosine_recall@1	0.0482	0.0602	0.0602	0.0482	0.0843
cosine_recall@3	0.5181	0.5301	0.494	0.506	0.4578
cosine_recall@5	0.6506	0.6386	0.6627	0.6145	0.5783
cosine_recall@10	0.8554	0.8072	0.8072	0.8193	0.7349
cosine_ndcg@10	0.4675	0.4554	0.45	0.444	0.4204
cosine_mrr@10	0.3423	0.341	0.3342	0.3238	0.3191
cosine_map@100	0.3488	0.3511	0.3441	0.3304	0.3297

Training Details

Training Dataset

json

Dataset: json
Size: 739 training samples
Columns: positive and anchor
Approximate statistics based on the first 739 samples:
positive anchor
type string string
details
min: 13 tokens
mean: 264.01 tokens
max: 512 tokens
min: 9 tokens
mean: 20.37 tokens
max: 60 tokens

Samples:

positive	anchor
For your attention[object Object][object Object]1. This brochure contains only a summary of the main features of this product and is not exhaustive. It does not constitute a policy. You are advised to refer to the Sales Illustration and Product Disclosure Sheet for more details of the product before purchasing a policy and refer to the terms and conditions in the policy for details of the features and benefits, exclusions and waiting periods under the policy.[object Object][object Object]2. You should satisfy yourself that this plan will best serve your needs and that the premium payable under this policy is an amount you can afford.[object Object][object Object]If you cancel your policy within the free-look period of 15 days, we will refund to you the full premium less any expenses which may have been incurred for any medical examination (if any).[object Object][object Object]3.[object Object][object Object]4. The premium for A-Life Essential Critical Care and A-Plus Recover is not guaranteed and AIA Bhd. may revise the premium by giving you 30 days’ prior notice in advance. The premium for A-Plus Life Cover is guaranteed...	`Is the premium for all AIA Bhd. plans guaranteed?`
For the mother[object Object][object Object]has existed prior to the risk effective date;[object Object][object Object]is caused directly or indirectly by self-inﬂicted injuries, while sane or insane;[object Object][object Object]is resulted from the mother committing, attempting or provoking an assault or a felony or from any violation of law by the mother;[object Object][object Object]is caused while under the inﬂuence of alcohol or drugs unless taken as prescribed by a doctor. For the avoidance of doubt, a person is considered as under the inﬂuence of alcohol if the breath, blood or urine test result is over the[object Object][object Object]35 mcg of alcohol per 100ml of breath[object Object][object Object]80 mg of alcohol per 100ml of blood[object Object][object Object]107 mg alcohol per 100ml of urine;[object Object][object Object]is caused directly or indirectly by the existence of Acquired Immune Deﬁciency Syndrome (AIDS) or by the presence of any Human Immuno-deﬁciency Virus (HIV) infection. The Company reserves the right to require the mother to undergo a[object Object][object Object]is resulted from the mother choosing to have a termination of pregnancy other than for medical reasons;[object Object][object Object]is caused by any unlawful, criminal o...	`What are the specific blood alcohol content (BAC) levels that would lead to a life insurance claim denial for the mother?`
FOR YOUR ATTENTION[object Object][object Object]1. A-Plus Health 2 is an optional rider attachable to regular premium investment-linked plans, underwritten by AIA Bhd.[object Object][object Object]2. This brochure contains only a summary of the main features of the rider and is not exhaustive. It does not constitute a policy. You are advised to refer to the Sales Illustration and Product Disclosure Sheet for more details of the rider before purchasing, and refer to the terms and conditions in the policy for details of the features and benefits, exclusions and waiting periods under the policy.[object Object][object Object]3. Buying life insurance is a long-term financial commitment. You should satisfy yourself that the policy (including riders, if any) will best serve your needs and that the premium payable under the policy is an amount you can afford. To achieve this, we recommend that you speak to your Life Planner to perform a needs analysis and assist you in making an informed decision. You may also contact AIA Bhd. directly for more information.[object Object][object Object]If you cancel the...	`What company underwrites the A-Plus Health 2 rider?`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 10
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: 8
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_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: 10
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: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: 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
0.8602	5	-	0.5001	0.4738	0.4449	0.4302	0.3912
1.8602	10	40.214	0.4847	0.4733	0.4581	0.4224	0.3882
2.8602	15	-	0.4781	0.4714	0.4585	0.4443	0.4095
3.8602	20	23.1168	0.4825	0.4719	0.4585	0.4496	0.4106
0.8602	5	-	0.5009	0.4815	0.4514	0.4401	0.4205
1.8602	10	11.8217	0.4768	0.4749	0.4672	0.4296	0.4067
2.8602	15	-	0.4846	0.4775	0.4650	0.4276	0.4102
3.8602	20	9.052	0.4771	0.4675	0.4629	0.4290	0.4080
4.8602	25	-	0.4682	0.4596	0.4614	0.4328	0.4104
5.8602	30	8.7536	0.4741	0.4599	0.4473	0.4352	0.4227
6.8602	35	-	0.4732	0.4576	0.4407	0.4316	0.4125
7.8602	40	7.2896	0.4675	0.4554	0.4482	0.4430	0.4249
8.8602	45	-	0.4675	0.4554	0.4456	0.444	0.4204
9.8602	50	7.5527	0.4675	0.4554	0.4500	0.4440	0.4204

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.2
PyTorch: 2.5.1+cu124
Accelerate: 1.2.1
Datasets: 2.19.1
Tokenizers: 0.21.0

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",
}

MatryoshkaLoss

bibtex

@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

bibtex

@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}
}

	positive	anchor
type	string	string
details	min: 13 tokens mean: 264.01 tokens max: 512 tokens	min: 9 tokens mean: 20.37 tokens max: 60 tokens