HSE-Chukchi-NLP/LaBSE-v2-russian-chukchi

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 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': 256, 'do_lower_case': False, 'architecture': '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 = [
    'Аԓгаԓкэгты вагыргын',
    'Решительность',
    'кострище',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7784, 0.2986],
#         [0.7784, 1.0000, 0.5789],
#         [0.2986, 0.5789, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 63,534 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: 3 tokens mean: 8.58 tokens max: 102 tokens	min: 3 tokens mean: 10.87 tokens max: 96 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Гынмыеп тъычечыпонтоӄаатыркын.	Уже давно хочется кушать аппетитную печень.	1.0
  Гыргочанрыннатватапваам	Узкий верхний распадок моховой реки (Чаунский район)	1.0
  еԓыеԓтъыԓык	болеть, страдать радикулитом	1.0

• Loss: MultipleNegativesRankingLoss with these parameters:

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

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

• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• 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: 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	Training Loss
0.0126	100	-
0.0252	200	-
0.0378	300	-
0.0504	400	-
0.0630	500	1.6379
0.0755	600	-
0.0881	700	-
0.1007	800	-
0.1133	900	-
0.1259	1000	1.1191
0.1385	1100	-
0.1511	1200	-
0.1637	1300	-
0.1763	1400	-
0.1889	1500	1.0301
0.2015	1600	-
0.2141	1700	-
0.2266	1800	-
0.2392	1900	-
0.2518	2000	0.9726
0.2644	2100	-
0.2770	2200	-
0.2896	2300	-
0.3022	2400	-
0.3148	2500	0.9437
0.3274	2600	-
0.3400	2700	-
0.3526	2800	-
0.3651	2900	-
0.3777	3000	0.9032
0.3903	3100	-
0.4029	3200	-
0.4155	3300	-
0.4281	3400	-
0.4407	3500	0.8770
0.4533	3600	-
0.4659	3700	-
0.4785	3800	-
0.4911	3900	-
0.5037	4000	0.8799
0.5162	4100	-
0.5288	4200	-
0.5414	4300	-
0.5540	4400	-
0.5666	4500	0.8544
0.5792	4600	-
0.5918	4700	-
0.6044	4800	-
0.6170	4900	-
0.6296	5000	0.8602
0.6422	5100	-
0.6547	5200	-
0.6673	5300	-
0.6799	5400	-
0.6925	5500	0.8341
0.7051	5600	-
0.7177	5700	-
0.7303	5800	-
0.7429	5900	-
0.7555	6000	0.8317
0.7681	6100	-
0.7807	6200	-
0.7933	6300	-
0.8058	6400	-
0.8184	6500	0.7769
0.8310	6600	-
0.8436	6700	-
0.8562	6800	-
0.8688	6900	-
0.8814	7000	0.8281
0.8940	7100	-
0.9066	7200	-
0.9192	7300	-
0.9318	7400	-
0.9443	7500	0.8322
0.9569	7600	-
0.9695	7700	-
0.9821	7800	-
0.9947	7900	-
1.0	7942	-

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.2
• Transformers: 5.0.0
• PyTorch: 2.9.0+cu128
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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}
}