metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:5600
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-small-en-v1.5
widget:
  - source_sentence: What is the main factor of signal interference in MCFs?
    sentences:
      - >-
        The main factor of signal interference in MCFs is crosstalk, which is
        the leakage of a fraction of the signal power from a given core to its
        neighboring core.
      - >-
        An integrity group temporal key (IGTK) is a random value used to protect
        group addressed medium access control (MAC) management protocol data
        units (MMPDUs) from a broadcast/multicast source station (STA).
      - >-
        Wireless sensing through the combined use of radio wave and AI
        technologies aims to identify objects and recognize actions with high
        precision.
  - source_sentence: >-
      What types of drones can be used to construct multi-tier drone-cell
      networks?
    sentences:
      - >-
        The coupling coefficient represents the tightness of coupling between
        transmit and receive coils in wireless charging systems.
      - >-
        A cheap, slow photodiode placed next to the rear face of the laser
        package is commonly used as the monitor detector in laser drive
        circuits.
      - >-
        Multi-tier drone-cell networks can be constructed by utilizing several
        drone types, similar to terrestrial HetNets with macro-, small-,
        femtocells, and relays.
  - source_sentence: >-
      Which technology was explored for high capacity last mile and
      pre-aggregation backhaul in small cell networks?
    sentences:
      - >-
        According to Pearl's Ladder of Causation, counterfactual questions can
        only be answered if information from all other levels (associational and
        interventional) is available. Counterfactuals subsume interventional and
        associational questions, and therefore sit at the top of the hierarchy.
      - >-
        Shannon's classical source coding theorem provides the minimum
        distortion achievable in encoding a Gaussian stationary input signal.
      - >-
        The passage mentions that 60 GHz and 70-80 GHz millimeter wave
        communication technologies were explored for high capacity last mile and
        pre-aggregation backhaul in small cell networks.
  - source_sentence: >-
      What is the main output of the design procedure for a passive lossless
      Huygens metasurface?
    sentences:
      - >-
        Entanglement distillation is the process of purifying imperfect
        entangled states to obtain maximally entangled states.
      - >-
        The main output of the design procedure is the transmitted fields as
        well as the surface impedance and admittance.
      - >-
        The component of IoT responsible for sensing and collecting data is the
        sensors.
  - source_sentence: >-
      What is the formula for the relative entropy between two probability
      density functions?
    sentences:
      - >-
        The consequence of the fact that the total power radiated varies as the
        square of the frequency of the oscillation is that shorter wavelength
        (higher frequency) light is scattered much more strongly than longer
        wavelength (lower frequency) light.
      - >-
        Hybrid infrastructures are comprised of various proximate and distant
        computing nodes, either mobile or immobile.
      - >-
        The relative entropy between two probability density functions f and g
        is equal to the negative integral of f(x) multiplied by the logarithm of
        the ratio of f(x) and g(x), with respect to x.
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_recall@1
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on BAAI/bge-small-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: telecom ir eval
          type: telecom-ir-eval
        metrics:
          - type: cosine_accuracy@1
            value: 0.9733333333333334
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.995
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.995
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.995
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.9733333333333334
            name: Cosine Precision@1
          - type: cosine_recall@1
            value: 0.9733333333333334
            name: Cosine Recall@1
          - type: cosine_ndcg@10
            value: 0.985912396714286
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9827777777777778
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9831452173557438
            name: Cosine Map@100

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

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5 on the csv dataset. It maps sentences & paragraphs to a 384-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-small-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- csv

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': 384, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'What is the formula for the relative entropy between two probability density functions?',
    'The relative entropy between two probability density functions f and g is equal to the negative integral of f(x) multiplied by the logarithm of the ratio of f(x) and g(x), with respect to x.',
    'The consequence of the fact that the total power radiated varies as the square of the frequency of the oscillation is that shorter wavelength (higher frequency) light is scattered much more strongly than longer wavelength (lower frequency) light.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: telecom-ir-eval
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9733
cosine_accuracy@3	0.995
cosine_accuracy@5	0.995
cosine_accuracy@10	0.995
cosine_precision@1	0.9733
cosine_recall@1	0.9733
cosine_ndcg@10	0.9859
cosine_mrr@10	0.9828
cosine_map@100	0.9831

Training Details

Training Dataset

csv

Dataset: csv
Size: 5,600 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 4 tokens
mean: 18.48 tokens
max: 56 tokens

min: 8 tokens
mean: 29.0 tokens
max: 85 tokens

	anchor	positive
type	string	string
details	min: 4 tokens mean: 18.48 tokens max: 56 tokens	min: 8 tokens mean: 29.0 tokens max: 85 tokens

Samples:

anchor	positive
`How can the unique decodability of a code be tested using the Sardinas and Patterson test?`	`The Sardinas and Patterson test for unique decodability involves checking if no codewords are prefixes of any other codewords.`
`What is the purpose of encapsulation in the OSI (Open System Interconnection) model?`	`Encapsulation is used to add control information and transform data units into protocol data units.`
`What advantages do measurements from user equipment (UE) have over drive tests in disaster small cell networks?`	`Measurements from user equipment (UE) have the advantages of reduced labor intensity, measurements obtained from additional locations, such as inside buildings, and better adaptation to specific characteristics and requirements in disaster scenarios.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

csv

Dataset: csv
Size: 1,400 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 4 tokens
mean: 18.92 tokens
max: 49 tokens

min: 8 tokens
mean: 29.0 tokens
max: 96 tokens

	anchor	positive
type	string	string
details	min: 4 tokens mean: 18.92 tokens max: 49 tokens	min: 8 tokens mean: 29.0 tokens max: 96 tokens

Samples:

anchor	positive
`What are the three major steps in SLAM-based techniques for THz localization?`	`SLAM-based techniques for THz localization involve imaging the environment, estimating ranges to the user, and fusing the images with the estimated ranges.`
`What is the service time distribution in the M/M(X)/1 model?`	`In the M/M(X)/1 model, the service time distribution is exponential with parameter µ.`
`What is the main advantage of the ensemble patch method in generating adversarial patches?`	`The main advantage of the ensemble patch method is that it achieves a higher attack success rate compared to single patches.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
weight_decay: 0.01
num_train_epochs: 5
lr_scheduler_type: cosine_with_restarts
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: cosine_with_restarts
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: None
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
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	Validation Loss	telecom-ir-eval_cosine_ndcg@10
1.1364	50	0.2567	0.0419	0.9844
2.2727	100	0.0502	0.0397	0.9859
3.4091	150	0.0277	0.0399	0.9846
4.5455	200	0.0231	0.0406	0.9840
5.0	220	-	-	0.9859

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
Transformers: 4.47.1
PyTorch: 2.5.1+cu121
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.0

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}
}