This is a sentence-transformers model finetuned from deepvk/USER-bge-m3. 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: deepvk/USER-bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("EvgenyBondarenko/BIEncoderRanker")
# Run inference
sentences = [
    'Определение активности амилазы в моче',
    'Амилаза общая в суточной моче',
    'Пенициллин V, IgE, аллерген - c2. Метод: ИФА',
]
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]

Evaluation

Metrics

Binary Classification

Dataset: binary-eval-test
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9442
cosine_accuracy_threshold	0.7781
cosine_f1	0.86
cosine_f1_threshold	0.7725
cosine_precision	0.857
cosine_recall	0.8629
cosine_ap	0.9223
cosine_mcc	0.8248

Training Details

Training Dataset

Unnamed Dataset

Size: 77,455 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 5 tokens
mean: 22.98 tokens
max: 100 tokens
min: 4 tokens
mean: 22.68 tokens
max: 87 tokens
0: ~80.00%
1: ~20.00%

Samples:

sentence1	sentence2	label
`Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам`	`Посев кожи на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный`	`1`
`Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам`	`Посев отделяемого с кожи/раны на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный`	`0`
`Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам`	`Посев отделяемого из глаза на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный`	`0`

Loss: ContrastiveLoss with these parameters:
json
1{ 2 "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", 3 "margin": 0.5, 4 "size_average": true 5}

Evaluation Dataset

Unnamed Dataset

Size: 33,195 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 6 tokens
mean: 21.52 tokens
max: 92 tokens
min: 4 tokens
mean: 23.61 tokens
max: 140 tokens
0: ~80.00%
1: ~20.00%

Samples:

sentence1	sentence2	label
`транскраниальная допплерография`	`УЗИ сосудов головного мозга`	`1`
`транскраниальная допплерография`	`УЗИ сосудов глаза (доплерография)`	`0`
`транскраниальная допплерография`	`Магнитно-резонансная томография головного мозга`	`0`

Loss: ContrastiveLoss with these parameters:
json
1{ 2 "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", 3 "margin": 0.5, 4 "size_average": true 5}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
save_only_model: True
fp16: True
load_best_model_at_end: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 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: linear
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: True
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: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	binary-eval-test_cosine_ap
0.2065	500	0.0125	0.0096	0.8634
0.4131	1000	0.0094	0.0082	0.8940
0.6196	1500	0.0086	0.0073	0.9150
0.8261	2000	0.0078	0.0068	0.9223

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.4.1
Transformers: 4.49.0
PyTorch: 2.6.0+cu118
Accelerate: 1.4.0
Datasets: 3.3.2
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",
}

ContrastiveLoss

bibtex

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}

	sentence1	sentence2	label
type	string	string	int
details	min: 5 tokens mean: 22.98 tokens max: 100 tokens	min: 4 tokens mean: 22.68 tokens max: 87 tokens	0: ~80.00% 1: ~20.00%