metadata

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_ndcg@100
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10000
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      Cashless transactions such as online transactions, credit card
      transactions, and mobile wallet are becoming more popular in financial
      transactions nowadays. With increased number of such cashless transaction,
      number of fraudulent transactions are also increasing. Fraud can be
      distinguished by analyzing spending behavior of customers (users) from
      previous transaction data. If any deviation is noticed in spending
      behavior from available patterns, it is possibly of fraudulent
      transaction. To detect fraud behavior, bank and credit card companies are
      using various methods of data mining such as decision tree, rule based
      mining, neural network, fuzzy clustering approach, hidden markov model or
      hybrid approach of these methods. Any of these methods is applied to find
      out normal usage pattern of customers (users) based on their past
      activities. The objective of this paper is to provide comparative study of
      different techniques to detect fraud.
    sentences:
      - how fraud detection is done
      - deep cnn image analysis definition
      - what are intermediate representations
  - source_sentence: >-
      We present a novel convolutional neural network (CNN) based approach for
      one-class classification. The idea is to use a zero centered Gaussian
      noise in the latent space as the pseudo-negative class and train the
      network using the cross-entropy loss to learn a good representation as
      well as the decision boundary for the given class. A key feature of the
      proposed approach is that any pre-trained CNN can be used as the base
      network for one-class classification. The proposed one-class CNN is
      evaluated on the UMDAA-02 Face, Abnormality-1001, and FounderType-200
      datasets. These datasets are related to a variety of one-class application
      problems such as user authentication, abnormality detection, and novelty
      detection. Extensive experiments demonstrate that the proposed method
      achieves significant improvements over the recent state-of-the-art
      methods. The source code is available at: github.com/otkupjnoz/oc-cnn.
    sentences:
      - what is one class convolutional neural networks
      - what is the use for sic carbide
      - what is bayesopt
  - source_sentence: >-
      While the field of educational data mining (EDM) has generated many
      innovations for improving educational software and student learning, the
      mining of student data has recently come under a great deal of scrutiny.
      Many stakeholder groups, including public officials, media outlets, and
      parents, have voiced concern over the privacy of student data and their
      efforts have garnered national attention. The momentum behind and scrutiny
      of student privacy has made it increasingly difficult for EDM applications
      to transition from academia to industry. Based on experience as academic
      researchers transitioning into industry, we present three primary areas of
      concern related to student privacy in practice: policy, corporate social
      responsibility, and public opinion. Our discussion will describe the key
      challenges faced within these categories, strategies for overcoming them,
      and ways in which the academic EDM community can support the adoption of
      innovative technologies in large-scale production.
    sentences:
      - what is the purpose of artificial intelligence firewalls
      - genetic crossover operator
      - why is privacy important for students
  - source_sentence: >-
      Autonomous vehicle research has been prevalent for well over a decade but
      only recently has there been a small amount of research conducted on the
      human interaction that occurs in autonomous vehicles. Although functional
      software and sensor technology is essential for safe operation, which has
      been the main focus of autonomous vehicle research, handling all elements
      of human interaction is also a very salient aspect of their success. This
      paper will provide an overview of the importance of human vehicle
      interaction in autonomous vehicles, while considering relevant related
      factors that are likely to impact adoption. Particular attention will be
      given to prior research conducted on germane areas relating to control in
      the automobile, in addition to the different elements that are expected to
      affect the likelihood of success for these vehicles initially developed
      for human operation. This paper will also include a discussion of the
      limited research conducted to consider interactions with humans and the
      current state of published functioning software and sensor technology that
      exists.
    sentences:
      - when are human interaction in autonomous vehicles
      - what is the purpose of evaluator guidelines
      - definition of collaborative filtering
  - source_sentence: >-
      J. Appl. Phys. 111, 07E328 (2012) A single-solenoid pulsed-magnet system
      for single-crystal scattering studies Rev. Sci. Instrum. 83, 035101 (2012)
      Solution to the problem of E-cored coil above a layered half-space using
      the method of truncated region eigenfunction expansion J. Appl. Phys. 111,
      07E717 (2012) Array of 12 coils to measure the position, alignment, and
      sensitivity of magnetic sensors over temperature J. Appl. Phys. 111,
      07E501 (2012) Skin effect suppression for Cu/CoZrNb multilayered inductor
      J. Appl. Phys. 111, 07A501 (2012)
    sentences:
      - which inductor can be used for multilayer scattering studies?
      - which patch antennas use a microstrip line
      - what kind of interaction is in mobile
model-index:
  - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.4995
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7685
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8205
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.873
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4995
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2561666666666667
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16410000000000002
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08730000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.4995
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7685
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8205
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.873
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7001286552732331
            name: Cosine Ndcg@10
          - type: cosine_ndcg@100
            value: 0.7182557103824586
            name: Cosine Ndcg@100
          - type: cosine_mrr@10
            value: 0.6433079365079365
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6472568310800184
            name: Cosine Map@100

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from 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
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
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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("MugheesAwan11/bge-base-scidocs-dataset-10k-2k-e1")
# Run inference
sentences = [
    'J. Appl. Phys. 111, 07E328 (2012) A single-solenoid pulsed-magnet system for single-crystal scattering studies Rev. Sci. Instrum. 83, 035101 (2012) Solution to the problem of E-cored coil above a layered half-space using the method of truncated region eigenfunction expansion J. Appl. Phys. 111, 07E717 (2012) Array of 12 coils to measure the position, alignment, and sensitivity of magnetic sensors over temperature J. Appl. Phys. 111, 07E501 (2012) Skin effect suppression for Cu/CoZrNb multilayered inductor J. Appl. Phys. 111, 07A501 (2012)',
    'which inductor can be used for multilayer scattering studies?',
    'what kind of interaction is in mobile',
]
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

Metric	Value
cosine_accuracy@1	0.4995
cosine_accuracy@3	0.7685
cosine_accuracy@5	0.8205
cosine_accuracy@10	0.873
cosine_precision@1	0.4995
cosine_precision@3	0.2562
cosine_precision@5	0.1641
cosine_precision@10	0.0873
cosine_recall@1	0.4995
cosine_recall@3	0.7685
cosine_recall@5	0.8205
cosine_recall@10	0.873
cosine_ndcg@10	0.7001
cosine_ndcg@100	0.7183
cosine_mrr@10	0.6433
cosine_map@100	0.6473

Training Details

Training Dataset

Unnamed Dataset

Size: 10,000 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 2 tokens
mean: 210.86 tokens
max: 512 tokens

min: 4 tokens
mean: 9.51 tokens
max: 33 tokens

	positive	anchor
type	string	string
details	min: 2 tokens mean: 210.86 tokens max: 512 tokens	min: 4 tokens mean: 9.51 tokens max: 33 tokens

Samples:

positive	anchor
This article introduces a sentiment analysis approach that adopts the way humans read, interpret, and extract sentiment from text. Our motivation builds on the assumption that human interpretation should lead to the most accurate assessment of sentiment in text. We call this automated process Human Reading for Sentiment (HRS). Previous research in sentiment analysis has produced many frameworks that can fit one or more of the HRS aspects; however, none of these methods has addressed them all in one approach. HRS provides a meta-framework for developing new sentiment analysis methods or improving existing ones. The proposed framework provides a theoretical lens for zooming in and evaluating aspects of any sentiment analysis method to identify gaps for improvements towards matching the human reading process. Key steps in HRS include the automation of humans low-level and high-level cognitive text processing. This methodology paves the way towards the integration of psychology with computational linguistics and machine learning to employ models of pragmatics and discourse analysis for sentiment analysis. HRS is tested with two state-of-the-art methods; one is based on feature engineering, and the other is based on deep learning. HRS highlighted the gaps in both methods and showed improvements for both.	`definition of sentiment analysis`
Although commonly used in both commercial and experimental information retrieval systems, thesauri have not demonstrated consistent beneets for retrieval performance, and it is diicult to construct a thesaurus automatically for large text databases. In this paper, an approach, called PhraseFinder, is proposed to construct collection-dependent association thesauri automatically using large full-text document collections. The association thesaurus can be accessed through natural language queries in INQUERY, an information retrieval system based on the probabilistic inference network. Experiments are conducted in IN-QUERY to evaluate diierent types of association thesauri, and thesauri constructed for a variety of collections.	`what is association thesaurus`
The choice of transfer functions may strongly influence complexity and performance of neural networks. Although sigmoidal transfer functions are the most common there is no a priori reason why models based on such functions should always provide optimal decision borders. A large number of alternative transfer functions has been described in the literature. A taxonomy of activation and output functions is proposed, and advantages of various non-local and local neural transfer functions are discussed. Several less-known types of transfer functions and new combinations of activation/output functions are described. Universal transfer functions, parametrized to change from localized to delocalized type, are of greatest interest. Other types of neural transfer functions discussed here include functions with activations based on nonEuclidean distance measures, bicentral functions, formed from products or linear combinations of pairs of sigmoids, and extensions of such functions making rotations of localized decision borders in highly dimensional spaces practical. Nonlinear input preprocessing techniques are briefly described, offering an alternative way to change the shapes of decision borders.	`types of neural transfer functions`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768
    ],
    "matryoshka_weights": [
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 1
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
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: 1
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: 1
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_map@100
0.0319	10	0.6581	-
0.0639	20	0.4842	-
0.0958	30	0.3555	-
0.1278	40	0.2398	-
0.1597	50	0.2917	-
0.1917	60	0.2286	-
0.2236	70	0.1903	-
0.2556	80	0.1832	-
0.2875	90	0.2899	-
0.3195	100	0.1744	-
0.3514	110	0.2148	-
0.3834	120	0.1379	-
0.4153	130	0.2123	-
0.4473	140	0.2445	-
0.4792	150	0.1481	-
0.5112	160	0.1392	-
0.5431	170	0.2218	-
0.5751	180	0.2225	-
0.6070	190	0.2874	-
0.6390	200	0.1927	-
0.6709	210	0.2469	-
0.7029	220	0.1915	-
0.7348	230	0.1711	-
0.7668	240	0.1982	-
0.7987	250	0.1783	-
0.8307	260	0.2016	-
0.8626	270	0.211	-
0.8946	280	0.1962	-
0.9265	290	0.1867	-
0.9585	300	0.195	-
0.9904	310	0.2161	-
1.0	313	-	0.6473

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.31.0
Datasets: 2.19.1
Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

@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

@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}
}