This is a sentence-transformers model finetuned from intfloat/multilingual-e5-small. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: intfloat/multilingual-e5-small
Maximum Sequence Length: 64 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'query: замена подножки на горном веле, старая в хлам',
    'passage: Повреждение подножки (м)',
    'passage: Повреждение переключателя скоростей (перед/зад) (м)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.6081, -0.0086],
#         [ 0.6081,  1.0000,  0.2855],
#         [-0.0086,  0.2855,  1.0000]])

Evaluation

Metrics

Information Retrieval

Dataset: bike-val
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9727
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9727
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9727
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9896
cosine_mrr@1	0.9727
cosine_mrr@5	0.986
cosine_mrr@10	0.986
cosine_map@100	0.986

Training Details

Training Dataset

Unnamed Dataset

Size: 2,643 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 10 tokens
mean: 17.46 tokens
max: 33 tokens
min: 8 tokens
mean: 16.81 tokens
max: 35 tokens
min: 1.0
mean: 1.0
max: 1.0

Samples:

sentence_0	sentence_1	label
`query: электричка дёргается при торможении, заменил датчик`	`passage: Замена датчика тормоза`	`1.0`
`query: Замена спиц без нарушения геометрии колеса(без учета количества)`	`passage: Замена спиц без нарушения геометрии колеса(без учета количества)`	`1.0`
`query: вынос руля на горном веле сломан пополам`	`passage: Повреждение выноса руля (м)`	`1.0`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false, 5 "directions": [ 6 "query_to_doc" 7 ], 8 "partition_mode": "joint", 9 "hardness_mode": null, 10 "hardness_strength": 0.0 11}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 4
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	bike-val_cosine_ndcg@10
0.2381	10	0.9547
0.4762	20	0.9583
0.7143	30	0.9642
0.9524	40	0.9744
1.0	42	0.9744
1.1905	50	0.9776
1.4286	60	0.9809
1.6667	70	0.9816
1.9048	80	0.9820
2.0	84	0.9816
2.1429	90	0.9808
2.3810	100	0.9821
2.6190	110	0.9813
2.8571	120	0.9834
3.0	126	0.9881
3.0952	130	0.9889
3.3333	140	0.9889
3.5714	150	0.9889
3.8095	160	0.9881
4.0	168	0.9896

Training Time

Training: 1.4 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 5.0.0
Tokenizers: 0.22.2

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",
}

MultipleNegativesRankingLoss