yklymchuk-rztk/multilingual-e5-base-matryoshka2d-mnr-4-continue

SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base on the 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 dimensions
• Similarity Function: Dot Product
• Training Dataset:
  • rozetka_positive_pairs

Model Sources

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

Full Model Architecture

RZTKSentenceTransformer(
  (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("yklymchuk-rztk/multilingual-e5-base-matryoshka2d-mnr-4-continue")
# Run inference
sentences = [
    'query: сумочка женская',
    'passage: Сумки Без бренда Для кого Для женщин Цвет Черный Стиль Повседневные Модель сумки Кросс-боди Материал Экокожа Страна регистрации бренда Украина Страна-производитель товара Китай Количество отделений 3 Форма Трапеция Застежка Магнит',
    'passage: Пенали Kite Гарантія 14 днів Колір Бірюзовий Стать Для дівчаток Матеріал Поліестер Кількість відділень 1 Кількість вантажних місць 1 Країна реєстрації бренда Німеччина Країна-виробник товару Китай Вага, г 350 Тип гарантійного талона Гарантія по чеку Особливості З наповненням Форма Книжка',
]
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

• Datasets: bm-full, core-uk-title, core-ru-title, core-uk-options, core-ru-options, options-uk-title, options-ru-title, options-uk-options, options-ru-options, rusisms-uk-title, rusisms-ru-title, rusisms-uk-options, rusisms-ru-options, rusisms_corrected-uk-title, rusisms_corrected-ru-title, rusisms_corrected-uk-options, rusisms_corrected-ru-options, core_typos-uk-title, core_typos-ru-title, core_typos-uk-options and core_typos-ru-options
• Evaluated with InformationRetrievalEvaluator

Metric	bm-full	core-uk-title	core-ru-title	core-uk-options	core-ru-options	options-uk-title	options-ru-title	options-uk-options	options-ru-options	rusisms-uk-title	rusisms-ru-title	rusisms-uk-options	rusisms-ru-options	rusisms_corrected-uk-title	rusisms_corrected-ru-title	rusisms_corrected-uk-options	rusisms_corrected-ru-options	core_typos-uk-title	core_typos-ru-title	core_typos-uk-options	core_typos-ru-options
dot_accuracy@1	0.4784	0.6304	0.6417	0.4949	0.4877	0.7572	0.7706	0.6325	0.637	0.6413	0.6698	0.5079	0.4984	0.712	0.7089	0.5538	0.5728	0.5452	0.5678	0.4251	0.423
dot_accuracy@3	0.6553	0.8542	0.8563	0.7464	0.7505	0.9376	0.931	0.8441	0.8374	0.7905	0.7778	0.6286	0.6476	0.8196	0.8291	0.7278	0.7215	0.7875	0.7803	0.6478	0.6509
dot_accuracy@5	0.7332	0.924	0.923	0.8378	0.8368	0.9666	0.9666	0.9109	0.8931	0.8286	0.8349	0.7175	0.7492	0.8703	0.8703	0.7848	0.7848	0.8491	0.8491	0.7433	0.7464
dot_accuracy@10	0.8284	0.9733	0.9692	0.9322	0.9292	0.9933	0.9933	0.9488	0.9465	0.8857	0.8921	0.7905	0.8063	0.9114	0.9114	0.8544	0.8608	0.9117	0.9076	0.8429	0.846
dot_precision@1	0.4784	0.6304	0.6417	0.4949	0.4877	0.7572	0.7706	0.6325	0.637	0.6413	0.6698	0.5079	0.4984	0.712	0.7089	0.5538	0.5728	0.5452	0.5678	0.4251	0.423
dot_precision@3	0.4862	0.6379	0.6472	0.499	0.4986	0.7491	0.7468	0.6221	0.6355	0.6635	0.6646	0.5058	0.5196	0.7184	0.7162	0.5738	0.5823	0.5493	0.5534	0.4182	0.4223
dot_precision@5	0.4876	0.6246	0.6333	0.4951	0.4975	0.7118	0.7122	0.6027	0.6071	0.6552	0.6578	0.5162	0.5276	0.7082	0.7038	0.5759	0.581	0.5277	0.5355	0.417	0.4158
dot_precision@10	0.491	0.5196	0.5253	0.454	0.452	0.5541	0.5506	0.4964	0.494	0.6235	0.626	0.5111	0.5178	0.6684	0.663	0.5646	0.5655	0.4459	0.4522	0.38	0.3767
dot_recall@1	0.0114	0.0643	0.0657	0.0496	0.0485	0.1154	0.1182	0.0925	0.0936	0.0413	0.0443	0.0327	0.032	0.0497	0.0489	0.0399	0.0391	0.0555	0.0579	0.0428	0.0421
dot_recall@3	0.0345	0.1942	0.1973	0.1508	0.1495	0.342	0.341	0.2759	0.2827	0.1171	0.117	0.0849	0.0855	0.1274	0.1283	0.1062	0.102	0.168	0.1699	0.1263	0.1276
dot_recall@5	0.0577	0.3155	0.3208	0.2482	0.2482	0.537	0.536	0.4409	0.4455	0.1783	0.1774	0.1413	0.1417	0.1973	0.1999	0.1658	0.163	0.2674	0.2724	0.2089	0.2077
dot_recall@10	0.1145	0.5135	0.519	0.4471	0.4449	0.7925	0.7883	0.6951	0.6956	0.3101	0.3078	0.2518	0.2545	0.341	0.3356	0.2843	0.2808	0.442	0.4493	0.3754	0.3729
dot_ndcg@10	0.4893	0.5825	0.5898	0.4895	0.4883	0.765	0.7638	0.659	0.661	0.6648	0.6683	0.5372	0.5433	0.7195	0.7127	0.5966	0.5987	0.501	0.5093	0.4117	0.4101
dot_mrr@10	0.5828	0.7525	0.7593	0.6383	0.6368	0.8501	0.8558	0.748	0.7464	0.7269	0.7408	0.5902	0.5972	0.7809	0.7793	0.6513	0.6614	0.6745	0.6865	0.5581	0.5589
dot_map@100	0.3628	0.5641	0.5729	0.4956	0.4952	0.7381	0.7395	0.6415	0.6452	0.5854	0.5923	0.4987	0.5053	0.6389	0.6395	0.5595	0.5634	0.4757	0.483	0.4095	0.4085

Information Retrieval

• Datasets: bm-full--matryoshka_dim-768--, bm-full--matryoshka_dim-512--, bm-full--matryoshka_dim-256-- and bm-full--matryoshka_dim-128--
• Evaluated with InformationRetrievalEvaluator

Metric	bm-full--matryoshka_dim-768--	bm-full--matryoshka_dim-512--	bm-full--matryoshka_dim-256--	bm-full--matryoshka_dim-128--
dot_accuracy@1	0.4784	0.4759	0.4759	0.4522
dot_precision@1	0.4784	0.4759	0.4759	0.4522
dot_recall@1	0.0114	0.0114	0.0114	0.0106
dot_ndcg@1	0.4784	0.4759	0.4759	0.4522
dot_mrr@1	0.4784	0.4759	0.4759	0.4522
dot_map@100	0.3628	0.3601	0.3488	0.3247

Training Details

Training Dataset

rozetka_positive_pairs

• Dataset: rozetka_positive_pairs
• Size: 18,644,575 training samples
• Columns: query and text
• Approximate statistics based on the first 1000 samples:

  	query	text
  type	string	string
  details	min: 6 tokens mean: 12.04 tokens max: 30 tokens	min: 8 tokens mean: 55.98 tokens max: 512 tokens

• Samples:

  query	text
  query: xsiomi 9c скло	passage: Защитные стекла Назначение Для мобильных телефонов Цвет Черный Теги Теги Наличие рамки C рамкой Форм-фактор Плоское Клеевой слой По всей поверхности
  query: xsiomi 9c скло	passage: Захисне скло Glass Full Glue для Xiaomi Redmi 9A/9C/10A (Чорний)
  query: xsiomi 9c скло	passage: Захисне скло Призначення Для мобільних телефонів Колір Чорний Теги Теги Наявність рамки З рамкою Форм-фактор Плоске Клейовий шар По всій поверхні

• 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

rozetka_positive_pairs

• Dataset: rozetka_positive_pairs
• Size: 202,564 evaluation samples
• Columns: query and text
• Approximate statistics based on the first 1000 samples:

  	query	text
  type	string	string
  details	min: 6 tokens mean: 8.57 tokens max: 17 tokens	min: 8 tokens mean: 53.17 tokens max: 512 tokens

• Samples:

  query	text
  query: создаем нейронную сеть	passage: Створюємо нейронну мережу
  query: создаем нейронную сеть	passage: Научная и техническая литература Переплет Мягкий
  query: создаем нейронную сеть	passage: Создаем нейронную сеть (1666498)

• 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: 88
• per_device_eval_batch_size: 88
• learning_rate: 2e-05
• num_train_epochs: 5.0
• warmup_ratio: 0.1
• bf16: True
• bf16_full_eval: True
• tf32: True
• dataloader_num_workers: 8
• load_best_model_at_end: True
• optim: adafactor
• push_to_hub: True
• hub_model_id: yklymchuk-rztk/multilingual-e5-base-matryoshka2d-mnr-4-continue
• hub_private_repo: True
• prompts: {'query': 'query: ', 'text': 'passage: '}
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 88
• per_device_eval_batch_size: 88
• 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: 5.0
• 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: 8
• 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: yklymchuk-rztk/multilingual-e5-base-matryoshka2d-mnr-4-continue
• hub_strategy: every_save
• hub_private_repo: True
• 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: {'query': 'query: ', 'text': 'passage: '}
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• ddp_static_graph: False
• ddp_comm_hook: bf16
• gradient_as_bucket_view: False
• num_proc: 30

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	bm-full_dot_ndcg@10	core-uk-title_dot_ndcg@10	core-ru-title_dot_ndcg@10	core-uk-options_dot_ndcg@10	core-ru-options_dot_ndcg@10	options-uk-title_dot_ndcg@10	options-ru-title_dot_ndcg@10	options-uk-options_dot_ndcg@10	options-ru-options_dot_ndcg@10	rusisms-uk-title_dot_ndcg@10	rusisms-ru-title_dot_ndcg@10	rusisms-uk-options_dot_ndcg@10	rusisms-ru-options_dot_ndcg@10	rusisms_corrected-uk-title_dot_ndcg@10	rusisms_corrected-ru-title_dot_ndcg@10	rusisms_corrected-uk-options_dot_ndcg@10	rusisms_corrected-ru-options_dot_ndcg@10	core_typos-uk-title_dot_ndcg@10	core_typos-ru-title_dot_ndcg@10	core_typos-uk-options_dot_ndcg@10	core_typos-ru-options_dot_ndcg@10	bm-full--matryoshka_dim-768--_dot_ndcg@1	bm-full--matryoshka_dim-512--_dot_ndcg@1	bm-full--matryoshka_dim-256--_dot_ndcg@1	bm-full--matryoshka_dim-128--_dot_ndcg@1
2.7017	143100	0.7397	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7167	143895	0.7745	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7317	144690	0.8018	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7467	145485	0.7712	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7617	146280	0.7634	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7767	147075	0.7801	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7917	147870	0.7608	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8067	148665	0.7886	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8218	149460	0.7534	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8368	150255	0.7848	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8518	151050	0.7657	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8668	151845	0.7943	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8818	152640	0.7683	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8968	153435	0.7555	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9118	154230	0.7575	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9268	155025	0.7253	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9418	155820	0.7538	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9568	156615	0.7708	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9719	157410	0.7582	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9869	158205	0.7987	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0002	158910	-	0.4537	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0019	159000	0.7604	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0169	159795	0.7485	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0319	160590	0.7761	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0469	161385	0.7606	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0619	162180	0.7752	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0769	162975	0.7624	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.0919	163770	0.7764	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1070	164565	0.7714	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1220	165360	0.7916	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1370	166155	0.7484	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1520	166950	0.7751	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1670	167745	0.7634	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1820	168540	0.7549	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.1970	169335	0.7538	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2120	170130	0.7545	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2270	170925	0.7738	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2420	171720	0.7513	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2570	172515	0.7479	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2721	173310	0.751	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.2871	174105	0.7583	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3002	174801	-	0.4436	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3021	174900	0.7593	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3171	175695	0.7346	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3321	176490	0.759	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3471	177285	0.7639	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3621	178080	0.7699	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3771	178875	0.7463	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.3921	179670	0.7659	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4071	180465	0.7811	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4221	181260	0.7658	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4372	182055	0.7529	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4522	182850	0.7448	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4672	183645	0.7308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4822	184440	0.7567	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.4972	185235	0.7634	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5122	186030	0.7619	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5272	186825	0.7184	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5422	187620	0.7555	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5572	188415	0.7801	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5722	189210	0.7764	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.5873	190005	0.7659	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6002	190692	-	0.4584	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6023	190800	0.7329	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6173	191595	0.7439	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6323	192390	0.7605	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6473	193185	0.7511	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6623	193980	0.7458	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6773	194775	0.7508	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.6923	195570	0.7467	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7073	196365	0.7463	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7223	197160	0.7389	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7373	197955	0.772	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7524	198750	0.7859	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7674	199545	0.7543	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7824	200340	0.7635	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.7974	201135	0.7706	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8124	201930	0.7748	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8274	202725	0.7552	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8424	203520	0.7484	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8574	204315	0.7535	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8724	205110	0.7615	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.8874	205905	0.7536	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9002	206583	-	0.4789	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9024	206700	0.7566	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9175	207495	0.7747	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9325	208290	0.7526	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9475	209085	0.759	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9625	209880	0.7477	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9775	210675	0.7632	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
3.9925	211470	0.7625	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0075	212265	0.7535	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0225	213060	0.745	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0376	213855	0.7311	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0526	214650	0.7327	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0676	215445	0.7385	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0826	216240	0.7521	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.0976	217035	0.7579	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1126	217830	0.7378	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1276	218625	0.7641	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1426	219420	0.7637	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1576	220215	0.7676	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1726	221010	0.7789	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.1876	221805	0.7677	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2003	222474	-	0.4703	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2027	222600	0.77	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2177	223395	0.7386	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2327	224190	0.7432	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2477	224985	0.7436	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2627	225780	0.7366	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2777	226575	0.7254	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.2927	227370	0.7594	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3077	228165	0.7646	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3227	228960	0.7524	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3377	229755	0.7625	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3527	230550	0.7647	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3678	231345	0.7425	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3828	232140	0.7568	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.3978	232935	0.7809	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4128	233730	0.7762	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4278	234525	0.7579	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4428	235320	0.7625	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4578	236115	0.7664	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4728	236910	0.7357	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.4878	237705	0.7316	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5003	238365	-	0.4811	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5028	238500	0.7568	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5179	239295	0.7522	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5329	240090	0.7529	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5479	240885	0.7468	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5629	241680	0.7304	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5779	242475	0.749	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.5929	243270	0.7391	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6079	244065	0.7483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6229	244860	0.7682	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6379	245655	0.7636	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6529	246450	0.7705	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6679	247245	0.7516	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6830	248040	0.7632	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.6980	248835	0.7659	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7130	249630	0.7254	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7280	250425	0.7163	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7430	251220	0.7552	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7580	252015	0.7654	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7730	252810	0.7308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.7880	253605	0.7513	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
4.8003	254256	-	0.4811	0.4893	0.5825	0.5898	0.4895	0.4883	0.7650	0.7638	0.6590	0.6610	0.6648	0.6683	0.5372	0.5433	0.7195	0.7127	0.5966	0.5987	0.5010	0.5093	0.4117	0.4101	0.4784	0.4759	0.4759	0.4522

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.10
• Sentence Transformers: 3.3.0
• Transformers: 4.46.3
• PyTorch: 2.5.1+cu124
• Accelerate: 1.1.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

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",
}