metadata

base_model: sentence-transformers/LaBSE
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:81836
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: ( аның ӱчӱн мындағылар андағ мӧңіс паза чочыстығ полтырлар ).
    sentences:
      - >-
        так как он не пришел , младший брат идет сам . когда младший брат пришел
        , один старик привязал обоих братьев , а сам прислонился к огню , грея
        спину свою .
      - шлёпать по грязи
      - ( именно это и привело все общество в мрачное и тревожное настроение ).
  - source_sentence: пір чӧптіг
    sentences:
      - его болезнь осложняется .
      - единомышленники
      - ощутить озноб , дрожь .
  - source_sentence: анаң вторник кӱн уже килтір .
    sentences:
      - фашистский концлагерь .
      - быть сплочёнными и единодушными .
      - во вторник уже приехал .
  - source_sentence: батальон командирі
    sentences:
      - >-
        и говорит ему иисус : истинно говорю тебе , что ты ныне , в эту ночь ,
        прежде нежели дважды пропоёт петух , трижды отречёшься от меня .
      - батальонный командир
      - >-
        в это время мальчик , как суслик , выскочивший из норы , потеряв дар
        речи , умывался опрокинутым на него молоком .
  - source_sentence: прай сынынҷа андағ .
    sentences:
      - >-
        иисус говорит ей : не прикасайся ко мне , ибо я ещё не восшел к отцу
        моему ; а иди к братьям моим и скажи им : восхожу к отцу моему и отцу
        вашему , и к богу моему и богу вашему .
      - эх , не поверит !
      - по всей высоте такая .

SentenceTransformer based on sentence-transformers/LaBSE

This is a sentence-transformers model finetuned from sentence-transformers/LaBSE. 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: sentence-transformers/LaBSE
Maximum Sequence Length: 256 tokens
Output Dimensionality: 768 tokens
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': 256, 'do_lower_case': False}) 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): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): 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 = [
    'прай сынынҷа андағ .',
    'по всей высоте такая .',
    'эх , не поверит !',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 81,836 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: 4 tokens
mean: 18.67 tokens
max: 114 tokens

min: 3 tokens
mean: 13.81 tokens
max: 71 tokens

min: 1.0
mean: 1.0
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 4 tokens mean: 18.67 tokens max: 114 tokens	min: 3 tokens mean: 13.81 tokens max: 71 tokens	min: 1.0 mean: 1.0 max: 1.0

Samples:

sentence_0	sentence_1	label
`– че , чоохтазаар анаң , исчем .`	`– ну , говорите же , слушаю .`	`1.0`
`чииттер агитбригадазы`	`молодёжная агитбригада .`	`1.0`
`че ипчі алчатхан оол орайлатчатханда , прайзы , сабыхсып , узубысхан .`	`и как жених замедлил , то задремали все и уснули .`	`1.0`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
num_train_epochs: 1
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
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: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: False
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: 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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.0098	100	-
0.0196	200	-
0.0293	300	-
0.0391	400	-
0.0489	500	0.5082
0.0587	600	-
0.0684	700	-
0.0782	800	-
0.0880	900	-
0.0978	1000	0.2939
0.1075	1100	-
0.1173	1200	-
0.1271	1300	-
0.1369	1400	-
0.1466	1500	0.272
0.1564	1600	-
0.1662	1700	-
0.1760	1800	-
0.1857	1900	-
0.1955	2000	0.2019
0.2053	2100	-
0.2151	2200	-
0.2248	2300	-
0.2346	2400	-
0.2444	2500	0.1543
0.2542	2600	-
0.2639	2700	-
0.2737	2800	-
0.2835	2900	-
0.2933	3000	0.1632
0.3030	3100	-
0.3128	3200	-
0.3226	3300	-
0.3324	3400	-
0.3421	3500	0.1483
0.3519	3600	-
0.3617	3700	-
0.3715	3800	-
0.3812	3900	-
0.3910	4000	0.136
0.4008	4100	-
0.4106	4200	-
0.4203	4300	-
0.4301	4400	-
0.4399	4500	0.1341
0.4497	4600	-
0.4594	4700	-
0.4692	4800	-

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.1.1
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
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",
}

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}
}