SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base on the rztk/rozetka_positive_pairs dataset. 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: intfloat/multilingual-e5-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- rztk/rozetka_positive_pairs

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': 768, '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 = [
    'поилка для детей',
    "<category>Поїльники та непроливайки</category><brand>Nuk</brand><options><option_title>Стать дитини</option_title><option_value>Хлопчик</option_value><option_title>Стать дитини</option_title><option_value>Дівчинка</option_value><option_title>Кількість вантажних місць</option_title><option_value>1</option_value><option_title>Країна реєстрації бренда</option_title><option_value>Німеччина</option_value><option_title>Країна-виробник товару</option_title><option_value>Німеччина</option_value><option_title>Об'єм, мл</option_title><option_value>300</option_value><option_title>Матеріал</option_title><option_value>Пластик</option_value><option_title>Колір</option_title><option_value>Блакитний</option_value><option_title>Тип</option_title><option_value>Поїльник</option_value><option_title>Тип гарантійного талона</option_title><option_value>Гарантія по чеку</option_value><option_title>Доставка Premium</option_title></options>",
    'Шафа розпашній Fenster Оксфорд Лагуна',
]
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: rusisms-uk-title
Evaluated with InformationRetrievalEvaluator

Metric	Value
dot_accuracy@1	0.5429
dot_accuracy@3	0.6889
dot_accuracy@5	0.7492
dot_accuracy@10	0.8
dot_precision@1	0.5429
dot_precision@3	0.5217
dot_precision@5	0.5035
dot_precision@10	0.4768
dot_recall@1	0.0092
dot_recall@3	0.0238
dot_recall@5	0.0351
dot_recall@10	0.0599
dot_ndcg@10	0.4937
dot_mrr@10	0.6287
dot_map@100	0.1404

Information Retrieval

Dataset: rusisms-uk-title--matryoshka_dim-768--
Evaluated with InformationRetrievalEvaluator

Metric	Value
dot_accuracy@1	0.1619
dot_precision@1	0.1619
dot_recall@1	0.002
dot_ndcg@1	0.1619
dot_mrr@1	0.1619
dot_map@100	0.0213

Information Retrieval

Dataset: rusisms-uk-title--matryoshka_dim-512--
Evaluated with InformationRetrievalEvaluator

Metric	Value
dot_accuracy@1	0.146
dot_precision@1	0.146
dot_recall@1	0.0017
dot_ndcg@1	0.146
dot_mrr@1	0.146
dot_map@100	0.0152

Information Retrieval

Dataset: rusisms-uk-title--matryoshka_dim-256--
Evaluated with InformationRetrievalEvaluator

Metric	Value
dot_accuracy@1	0.1016
dot_precision@1	0.1016
dot_recall@1	0.0013
dot_ndcg@1	0.1016
dot_mrr@1	0.1016
dot_map@100	0.012

Information Retrieval

Dataset: rusisms-uk-title--matryoshka_dim-128--
Evaluated with InformationRetrievalEvaluator

Metric	Value
dot_accuracy@1	0.054
dot_precision@1	0.054
dot_recall@1	0.0007
dot_ndcg@1	0.054
dot_mrr@1	0.054
dot_map@100	0.0054

Training Details

Training Dataset

rztk/rozetka_positive_pairs

Dataset: rztk/rozetka_positive_pairs
Size: 44,800 training samples
Columns: query and text
Approximate statistics based on the first 1000 samples:
query text
type string string
details
min: 3 tokens
mean: 7.18 tokens
max: 16 tokens

min: 9 tokens
mean: 158.88 tokens
max: 512 tokens

	query	text
type	string	string
details	min: 3 tokens mean: 7.18 tokens max: 16 tokens	min: 9 tokens mean: 158.88 tokens max: 512 tokens

Samples:

query	text
`p smart z`	`TPU чехол Ultrathin Series 0,33 mm для Huawei P Smart Z Безбарвний (прозорий)`
`p smart z`	`Чохли для мобільних телефонівМатеріалСиліконКолірTransparentСумісна модельP Smart Z`
`p smart z`	`TPU чехол Ultrathin Series 0,33mm для Huawei P Smart Z Бесцветный (прозрачный)`

Loss: sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss with these parameters:

{
    "loss": "RZTKMultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1.0,
    "prior_layers_weight": 1.0,
    "kl_div_weight": 1.0,
    "kl_temperature": 0.3,
    "matryoshka_dims": [
        768,
        512,
        256,
        128
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": 1
}

Evaluation Dataset

rztk/rozetka_positive_pairs

Dataset: rztk/rozetka_positive_pairs
Size: 4,480 evaluation samples
Columns: query and text
Approximate statistics based on the first 1000 samples:
query text
type string string
details
min: 3 tokens
mean: 6.29 tokens
max: 11 tokens

min: 12 tokens
mean: 161.36 tokens
max: 512 tokens

	query	text
type	string	string
details	min: 3 tokens mean: 6.29 tokens max: 11 tokens	min: 12 tokens mean: 161.36 tokens max: 512 tokens

Samples:

query	text
`кошелек женский`	`Портмоне BAELLERRY Forever N2345 Черный (020354)`
`кошелек женский`	`ГаманціBaellerryДля когоДля жінокВидПортмонеМатеріалШтучна шкіраКраїна-виробник товаруКитай`
`кошелек женский`	`Портмоне BAELLERRY Forever N2345 Черный (020354)`

Loss: sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss with these parameters:

{
    "loss": "RZTKMultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1.0,
    "prior_layers_weight": 1.0,
    "kl_div_weight": 1.0,
    "kl_temperature": 0.3,
    "matryoshka_dims": [
        768,
        512,
        256,
        128
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": 1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 112
per_device_eval_batch_size: 112
torch_empty_cache_steps: 30
learning_rate: 2e-05
num_train_epochs: 1.0
warmup_ratio: 0.1
bf16: True
bf16_full_eval: True
tf32: True
dataloader_num_workers: 2
load_best_model_at_end: True
optim: adafactor
push_to_hub: 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: 112
per_device_eval_batch_size: 112
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: 30
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: 1.0
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: 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: True
fp16_full_eval: False
tf32: True
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: True
dataloader_num_workers: 2
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: adafactor
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: True
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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
ddp_static_graph: False
ddp_comm_hook: bf16
gradient_as_bucket_view: False

Training Logs

Epoch	Step	Training Loss	loss	rusisms-uk-title--matryoshka_dim-128--_dot_map@100	rusisms-uk-title--matryoshka_dim-256--_dot_map@100	rusisms-uk-title--matryoshka_dim-512--_dot_map@100	rusisms-uk-title--matryoshka_dim-768--_dot_map@100	rusisms-uk-title_dot_map@100
0.1	10	6.6103	-	-	-	-	-	-
0.2	20	5.524	-	-	-	-	-	-
0.3	30	4.759	3.6444	-	-	-	-	-
0.4	40	4.5195	-	-	-	-	-	-
0.5	50	3.6598	-	-	-	-	-	-
0.6	60	3.7912	2.8962	-	-	-	-	-
0.7	70	3.9935	-	-	-	-	-	-
0.8	80	3.3929	-	-	-	-	-	-
0.9	90	3.6101	2.6889	-	-	-	-	-
1.0	100	3.8753	-	0.0054	0.0120	0.0152	0.0213	0.1404

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.6
Sentence Transformers: 3.0.1
Transformers: 4.45.1
PyTorch: 2.4.1
Accelerate: 0.34.2
Datasets: 3.0.0
Tokenizers: 0.20.0

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",
}

Downloads last month: 5

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for rztk-bohdanbilonoh/multilingual-e5-base-test

Base model

intfloat/multilingual-e5-base

Finetuned

(101)

this model

Evaluation results

Dot Accuracy@1 on rusisms uk title
self-reported

0.543
Dot Accuracy@3 on rusisms uk title
self-reported

0.689
Dot Accuracy@5 on rusisms uk title
self-reported

0.749
Dot Accuracy@10 on rusisms uk title
self-reported

0.800
Dot Precision@1 on rusisms uk title
self-reported

0.543
Dot Precision@3 on rusisms uk title
self-reported

0.522
Dot Precision@5 on rusisms uk title
self-reported

0.503
Dot Precision@10 on rusisms uk title
self-reported

0.477
Dot Recall@1 on rusisms uk title
self-reported

0.009
Dot Recall@3 on rusisms uk title
self-reported

0.024

View on Papers With Code