metadata
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:594028
- loss:MultipleNegativesRankingLoss
base_model: intfloat/multilingual-e5-large-instruct
widget:
- source_sentence: |-
'আমি' শব্দটি কোন লিঙ্গ?
A. উভয় লিঙ্গ
B. ক্লীব লিঙ্গ
C. পুংলিঙ্গ
D. স্ত্রী লিঙ্গ
sentences:
- >-
F.P. Dobroslavin, tibbin müxtəlif sahələri üzrə tanınmış bir alimdir,
ancaq daha çox baş vermiş tədqiqatlara görə seçilir. Onun əməyinin
sanitar-gigiyenik sahəyə təsiri əhəmiyyətlidir.
- >-
বাংলা ভাষায় শব্দগুলোর লিঙ্গ সাধারণত তিনটি মূল শ্রেণিতে ভাগ হয়:
পুংলিঙ্গ (পুরুষ), স্ত্রী লিঙ্গ (মহিলা), এবং ক্লীব লিঙ্গ (যার কোনো লিঙ্গ
নেই)।
- >-
Waves are disturbances that transfer energy from one place to another
without transferring matter. Think of a ripple on a pond – the water
molecules don't travel across the pond with the ripple; they mostly move
up and down as the energy passes through them.
- source_sentence: |-
企业产品组合中所拥有的产品线数目是
A. 产品组合的宽度
B. 产品组合的相关性
C. 产品组合的深度
D. 产品组合的长度
sentences:
- 产品组合的宽度(Width)是指企业拥有的产品线数目。
- >-
This fluid is produced by the walls of the vagina and the Bartholin's
glands.
- >-
### Assumption of Risk Defined
Assumption of risk is a legal doctrine used in tort law that can limit
or bar recovery in negligence claims. This doctrine suggests that if a
person voluntarily engages in a risky activity, knowing the risks
involved, they cannot hold another party responsible for resulting
injuries. Common scenarios where this applies include contact sports and
recreational activities, where participants understand the inherent
hazards.
### Elements of Assumption of Risk
To successfully argue assumption of risk, certain elements must be
established:
1. **Knowledge of the Risk**: The individual must have actual or
constructive knowledge of the risk involved.
2. **Voluntary Exposure**: The individual must voluntarily choose to
expose themselves to that risk.
3. **Informed Consent**: The individual must have consented to take that
risk despite being aware of it.
### Contributory Negligence
Contributory negligence is a legal concept that exists in some
jurisdictions where a plaintiff's own negligence contributes to their
injury. Under this doctrine, if the plaintiff is found to have played
any part in their injury, they may be barred from recovering damages, or
the damage award could be reduced. It emphasizes the responsibility of
the injured party to exercise reasonable care for their own safety.
### Interaction of Assumption of Risk and Contributory Negligence
In many jurisdictions, both assumption of risk and contributory
negligence can coexist as defenses. However, some legal systems assert
that if a plaintiff is found contributorily negligent, they cannot also
claim assumed risk for the same incident. This overlap can complicate
cases since the determination of the plaintiff's awareness and behavior
prior to the accident can alter the outcome.
### Legal Standard for Warnings and Liability
In negligence cases, the adequacy of warnings provided is crucial.
Courts often assess whether the warnings were sufficient to inform the
individual of the specific hazards present. A simple sign may not meet
the threshold if it fails to clearly communicate the danger involved,
especially if the harm is not immediately obvious or if the context
(e.g., a crowded street) suggests additional risks.
- source_sentence: >-
While shopping at a grocery store, a customer tripped over a broken tile,
fell, and suffered a concussion. A few months after the accident, the
customer's attorney deposed a store employee. In the deposition, the
employee testified, "I'd been telling the store manager for years to get
that broken tile fixed, but he wouldn't do it. " The employee died in an
automobile accident after being deposed. At trial, the deposition should
be
A. admitted, as a dying declaration.
B. admitted, as former testimony.
C. not admitted, because it is hearsay not within any exception.
D. not admitted, because the employee is not available for
cross-examination.
sentences:
- >-
In the context of human evolution, brain size is often compared to body
size in a measurement called the encephalization quotient (EQ). This
measure assesses the expected brain size for an animal of a given body
size compared to actual brain size. An increase in EQ among hominins is
often linked to advancements in cognitive abilities, such as
problem-solving and social interaction.
- >-
Another exception to the hearsay rule, though often with specific
requirements related to the declarant's belief of impending death, is
the dying declaration.
- >-
In assessing moral actions, it is also essential to consider societal
norms. In the U.S. context in 2020, moral standards often emphasize
community well-being and individual rights. An action like diverting
emergency supplies would likely be condemned in most social circles,
while stepping out of rhythm during a line dancewould not commonly
qualify as a serious moral offense. Thus, moral wrongness is often
context-dependent and tied closely to consequences for individuals and
society.
- source_sentence: >-
Recent research on hominid species dating from the Middle Pliocene
indicates there was (as of 2020):
A. multiple hominid species but with limited diversity.
B. a single species with no diversity.
C. decreased species diversity but increased numbers of hammerstones and
flakes, indicating stone tool manufacture.
D. a single dominant species that outcompeted all others, leading to
decreased diversity.
E. increased species diversity due to a prolonged ice age followed by a
severe drought.
F. decreased species diversity due to a prolonged ice age followed by a
severe drought.
G. a great amount of species diversity, or a single species that exhibited
a lot of diversity.
H. increased species diversity but with decreased population numbers due
to harsh climate conditions.
I. increased species diversity but decreased numbers of hammerstones and
flakes, indicating less stone tool manufacture.
J. very little species diversity during this period and very few hominids.
sentences:
- >-
Hammerstones and flakes are artifacts associated with early stone tool
technology. Hammerstones are hard rocks used to strike other stones,
while flakes are the sharp pieces produced from such strikes, which
could be utilized for tasks like cutting or scraping, indicating early
cognitive and manual skills in tool-making among certain species.
- >-
The Doppler effect is a phenomenon that occurs when the source of a wave
and the observer are moving relative to each other. It results in a
change in the observed frequency of the wave compared to the source
frequency.
- >-
Counseling and therapeutic interventions can play a role in addressing
student behavioral issues, but they should be considered within a
broader context of classroom dynamics and educational strategies.
Counseling might help the child develop coping mechanisms, social
skills, and emotional regulation strategies. However, the effectiveness
of counseling is often maximized when the child is supported in the
classroom environment as well, suggesting that changes to the teacher's
approach could lead to improved outcomes.
- source_sentence: |-
Hipotalamusi NUK kontrollon sekretimin e hormoneve:
A. FSH dhe LH
B. te rritjes(GH)
C. ACTH
D. te pankreasit
sentences:
- >-
In the context of estate planning and inheritance law, a will serves as
a legal document outlining how a person's property and assets will be
distributed after their death. The interpretation of a will often hinges
on the intent of the testator, or the person who made the will, which
can affect how property interests are determined.
- >-
State laws that regulate matters of legitimate local concern but have an
incidental effect on interstate commerce are subject to a less strict
balancing test. Under this test, a state law will be upheld unless the
burden imposed on interstate commerce is clearly excessive in relation
to the putative local benefits.
- >-
Hipotalamusi është një pjesë e trurit që ndodhet nën talamusin. Ai luan
një rol kryesor në lidhjen e sistemit nervor me sistemin endokrin përmes
gjëndrës së hipofizës.
datasets:
- DoDucAnh/mcqa-rag-finetune
pipeline_tag: sentence-similarity
library_name: sentence-transformers
SentenceTransformer based on intfloat/multilingual-e5-large-instruct
This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large-instruct on the mcqa-rag-finetune dataset. It maps sentences & paragraphs to a 1024-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: intfloat/multilingual-e5-large-instruct
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 1024 dimensions
- Similarity Function: Cosine Similarity
- Training Dataset:
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': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("sentence_transformers_model_id")
# Run inference
sentences = [
'Hipotalamusi NUK kontrollon sekretimin e hormoneve:\nA. FSH dhe LH\nB. te rritjes(GH)\nC. ACTH\nD. te pankreasit',
'Hipotalamusi është një pjesë e trurit që ndodhet nën talamusin. Ai luan një rol kryesor në lidhjen e sistemit nervor me sistemin endokrin përmes gjëndrës së hipofizës.',
'State laws that regulate matters of legitimate local concern but have an incidental effect on interstate commerce are subject to a less strict balancing test. Under this test, a state law will be upheld unless the burden imposed on interstate commerce is clearly excessive in relation to the putative local benefits.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Training Details
Training Dataset
mcqa-rag-finetune
- Dataset: mcqa-rag-finetune at d1f5446
- Size: 594,028 training samples
- Columns:
anchor
andpositive
- Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 22 tokens
- mean: 105.96 tokens
- max: 512 tokens
- min: 12 tokens
- mean: 70.95 tokens
- max: 478 tokens
- Samples:
anchor positive Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field.
A. 0
B. 1
C. 2
D. 3The notation Z_3 refers to the finite field with three elements, often denoted as {0, 1, 2}. This field operates under modular arithmetic, specifically modulo 3. Elements in Z_3 can be added and multiplied according to the rules of modulo 3, where any number can wrap around upon reaching 3.
Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field.
A. 0
B. 1
C. 2
D. 3A field is a set equipped with two operations, addition and multiplication, satisfying certain properties: associativity, commutativity, distributivity, the existence of additive and multiplicative identities, and the existence of additive inverses and multiplicative inverses (for all elements except the zero element). In order for Z_3[x]/(f(x)) to be a field, the polynomial f(x) must be irreducible over Z_3.
Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field.
A. 0
B. 1
C. 2
D. 3The expression Z_3[x] indicates the set of all polynomials with coefficients in Z_3. A polynomial is said to be irreducible over Z_3 if it cannot be factored into the product of two non-constant polynomials with coefficients in Z_3. In the case of quadratic polynomials like x^2 + c, irreducibility depends on whether it has any roots in the field Z_3.
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Evaluation Dataset
mcqa-rag-finetune
- Dataset: mcqa-rag-finetune at d1f5446
- Size: 1,000 evaluation samples
- Columns:
anchor
andpositive
- Approximate statistics based on the first 1000 samples:
anchor positive type string string details - min: 22 tokens
- mean: 98.74 tokens
- max: 512 tokens
- min: 9 tokens
- mean: 59.88 tokens
- max: 501 tokens
- Samples:
anchor positive ക്രൂരകോഷ്ഠം ഉള്ള ഒരാളിൽ കോപിച്ചിരിക്കുന്ന ദോഷം താഴെപ്പറയുന്നവയിൽ ഏതാണ്?
A. കഫം
B. പിത്തം
C. വാതം
D. രക്തംഓരോ ദോഷത്തിനും അതിന്റേതായ സ്വഭാവങ്ങളും ശരീരത്തിൽ അത് ഉണ്ടാക്കുന്ന ഫലങ്ങളും ഉണ്ട്.
Melyik tényező nem befolyásolja a fagylalt keresleti függvényét?
A. A fagylalt árának változása.
B. Mindegyik tényező befolyásolja.
C. A jégkrém árának változása.
D. A fagylalttölcsér árának változása.A keresleti függvény negatív meredekségű, ami azt jelenti, hogy az ár növekedésével a keresett mennyiség csökken (csökkenő kereslet törvénye).
In contrast to _______, _______ aim to reward favourable behaviour by companies. The success of such campaigns have been heightened through the use of ___________, which allow campaigns to facilitate the company in achieving _________ .
A. Boycotts, Buyalls, Blockchain technology, Increased Sales
B. Buycotts, Boycotts, Digital technology, Decreased Sales
C. Boycotts, Buycotts, Digital technology, Decreased Sales
D. Buycotts, Boycotts, Blockchain technology, Charitable donations
E. Boycotts, Buyalls, Blockchain technology, Charitable donations
F. Boycotts, Buycotts, Digital technology, Increased Sales
G. Buycotts, Boycotts, Digital technology, Increased Sales
H. Boycotts, Buycotts, Physical technology, Increased Sales
I. Buycotts, Buyalls, Blockchain technology, Charitable donations
J. Boycotts, Buycotts, Blockchain technology, Decreased SalesConsumer Activism: This term refers to the actions taken by consumers to promote social, political, or environmental causes. These actions can include boycotting certain companies or buycotting others, influencing market dynamics based on ethical considerations. The effectiveness of consumer activism can vary but has gained prominence in recent years with increased visibility through social media.
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 12per_device_eval_batch_size
: 12learning_rate
: 3e-05num_train_epochs
: 1warmup_steps
: 5000fp16
: Trueload_best_model_at_end
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 12per_device_eval_batch_size
: 12per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 3e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 1max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_steps
: 5000log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Truefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Trueignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Nonehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseinclude_for_metrics
: []eval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseuse_liger_kernel
: Falseeval_use_gather_object
: Falseaverage_tokens_across_devices
: Falseprompts
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.05 | 2476 | 0.1209 | 0.0347 |
0.1000 | 4952 | 0.0737 | 0.0459 |
0.1501 | 7428 | 0.087 | 0.0732 |
0.2001 | 9904 | 0.0825 | 0.1209 |
0.2501 | 12380 | 0.0783 | 0.0934 |
0.3001 | 14856 | 0.071 | 0.0793 |
0.3501 | 17332 | 0.0661 | 0.0855 |
0.4001 | 19808 | 0.0652 | 0.0964 |
0.4502 | 22284 | 0.063 | 0.0892 |
0.5002 | 24760 | 0.056 | 0.0923 |
0.5502 | 27236 | 0.0509 | 0.1016 |
0.6002 | 29712 | 0.045 | 0.0918 |
0.6502 | 32188 | 0.0472 | 0.0896 |
0.7002 | 34664 | 0.0396 | 0.0959 |
0.7503 | 37140 | 0.0371 | 0.0819 |
0.8003 | 39616 | 0.0341 | 0.0845 |
0.8503 | 42092 | 0.0344 | 0.0790 |
0.9003 | 44568 | 0.0288 | 0.0863 |
0.9503 | 47044 | 0.03 | 0.0767 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.11.9
- Sentence Transformers: 4.1.0
- Transformers: 4.52.3
- PyTorch: 2.7.0+cu126
- Accelerate: 1.7.0
- Datasets: 3.6.0
- Tokenizers: 0.21.1
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",
}
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}
}