josangho99/paraphrase-multilingual-MiniLM-L12-v2-kor

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 384-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
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 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': 512, 'do_lower_case': True, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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})
)

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("josangho99/paraphrase-multilingual-MiniLM-L12-v2-kor")
# Run inference
sentences = [
    '학회랑 저널 홍보 메일 중 더 잦은 빈도로 오는 메일은?',
    '바로 엑셀파일을 지메일에서 읽는 방법 좀 알려주겠니?',
    '궁금합니다. 강원영동지역에 비 오는 날이.',
]
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, -0.0377, -0.0055],
#         [-0.0377,  1.0000,  0.1380],
#         [-0.0055,  0.1380,  1.0000]])

Evaluation

Metrics

Semantic Similarity

• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9498
spearman_cosine	0.9107
pearson_euclidean	0.9055
spearman_euclidean	0.8885
pearson_manhattan	0.9045
spearman_manhattan	0.8876
pearson_dot	0.8823
spearman_dot	0.8633
pearson_max	0.9498
spearman_max	0.9107

Training Details

Training Dataset

klue-nli klue-nli-link klue-sts klue-sts-link

Unnamed Dataset

• Size: 10,501 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: 8 tokens mean: 21.47 tokens max: 70 tokens	min: 8 tokens mean: 20.07 tokens max: 68 tokens	min: 0.0 mean: 0.43 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  영국도 한 달 동안 가게, 식당 등의 영업을 중단시켰습니다.	충남 서천군에 위치한 국립생태원은 미디리움, 4D 영상관 등 일부 시설의 운영을 중단한다.	0.08
  비 내릴 때는 다른 것 말고 장화 신도록 해.	한국 단풍 명소가 알고 싶습니다.	0.0
  식사를 거르면 몸에 더 안 좋으니 거르지 마십시오.	바쁘더라도 까먹지 말고 한번 잡은 약속은 꼭 지켜줘.	0.0

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 4
• 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: 32
• per_device_eval_batch_size: 32
• 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: 4
• 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: False
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• 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: None
• hub_always_push: False
• hub_revision: None
• 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
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	spearman_cosine
0.0973	32	-	0.8955
0.1945	64	-	0.8961
0.2918	96	-	0.8973
0.3891	128	-	0.8996
0.4863	160	-	0.9003
0.5836	192	-	0.9028
0.6809	224	-	0.9031
0.7781	256	-	0.9048
0.8754	288	-	0.9048
0.9726	320	-	0.9051
1.0	329	-	0.9059
1.0699	352	-	0.9064
1.1672	384	-	0.9076
1.2644	416	-	0.9084
1.3617	448	-	0.9075
1.4590	480	-	0.9083
1.5198	500	0.0175	-
1.5562	512	-	0.9078
1.6535	544	-	0.9086
1.7508	576	-	0.9082
1.8480	608	-	0.9090
1.9453	640	-	0.9089
2.0	658	-	0.9092
2.0426	672	-	0.9094
2.1398	704	-	0.9089
2.2371	736	-	0.9088
2.3343	768	-	0.9092
2.4316	800	-	0.9094
2.5289	832	-	0.9091
2.6261	864	-	0.9095
2.7234	896	-	0.9098
2.8207	928	-	0.9107

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.0
• Transformers: 4.56.0
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.22.0

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",
}