x2bee/KoModernBERT_SBERT_compare_mlmlv2

SentenceTransformer based on x2bee/ModernBert_MLM_kotoken_v02

This is a sentence-transformers model finetuned from x2bee/ModernBert_MLM_kotoken_v02 on the korean_nli_dataset 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: x2bee/ModernBert_MLM_kotoken_v02
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • korean_nli_dataset

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: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("x2bee/KoModernBERT_SBERT_compare_mlmlv2")
# Run inference
sentences = [
    '한 여자와 소년이 경찰 오토바이에 앉아 있다.',
    '여자와 소년이 밖에 있다.',
    '한 남자가 물 위에 밧줄을 매고 있다.',
]
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

Semantic Similarity

• Dataset: sts_dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6423
spearman_cosine	0.6388
pearson_euclidean	0.6317
spearman_euclidean	0.6107
pearson_manhattan	0.6325
spearman_manhattan	0.6126
pearson_dot	0.5865
spearman_dot	0.5676
pearson_max	0.6423
spearman_max	0.6388

Training Details

Training Dataset

korean_nli_dataset

• Dataset: korean_nli_dataset at 51cc968
• Size: 550,152 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 8 tokens mean: 21.76 tokens max: 76 tokens	min: 4 tokens mean: 14.36 tokens max: 44 tokens	min: 0.0 mean: 0.49 max: 1.0

• Samples:

  sentence1	sentence2	score
  몸에 맞지 않는 노란색 셔츠와 파란색 플래드 스커트를 입은 나이든 여성이 두 개의 통 옆에 앉아 있다.	여자가 역기를 들어올리고 있다.	0.0
  갈색 코트를 입은 선글라스를 쓴 한 남성이 담배를 피우며 손님들이 길거리 스탠드에서 물건을 구입하자 코를 긁는다.	갈색 코트를 입은 선글라스를 쓴 청년이 담배를 피우며 손님들이 스테이트 스탠드에서 구매하고 있을 때 코를 긁는다.	0.5
  소녀들은 물을 뿌리며 놀면서 킥킥 웃는다.	수도 본관이 고장나서 큰길이 범람했다.	0.0

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

korean_nli_dataset

• Dataset: korean_nli_dataset at 51cc968
• Size: 550,152 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 4 tokens mean: 21.88 tokens max: 76 tokens	min: 5 tokens mean: 14.14 tokens max: 38 tokens	min: 0.0 mean: 0.52 max: 1.0

• Samples:

  sentence1	sentence2	score
  한 역사학자와 그의 친구는 연구를 위해 더 많은 화석을 찾기 위해 광산을 파고 있다.	역사가는 공부를 위해 친구와 함께 땅을 파고 있다.	0.5
  소년은 회전목마에 도움을 받는다.	소년이 당나귀를 타고 있다.	0.0
  세탁실에서 사색적인 포즈를 취하고 있는 남자.	한 남자가 파티오 밖에 있다.	0.0

• Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• gradient_accumulation_steps: 2
• learning_rate: 1e-05
• num_train_epochs: 2
• warmup_ratio: 0.3
• push_to_hub: True
• hub_model_id: x2bee/KoModernBERT_SBERT_compare_mlmlv2
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• 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: 2
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 1e-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: 2
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.3
• 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: True
• 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: True
• resume_from_checkpoint: None
• hub_model_id: x2bee/KoModernBERT_SBERT_compare_mlmlv2
• hub_strategy: every_save
• hub_private_repo: None
• 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: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts_dev_spearman_max
0	0	-	-	0.4039
0.0980	100	0.3204	-	-
0.1960	200	0.1993	-	-
0.2940	300	0.1451	-	-
0.3920	400	0.1332	-	-
0.4900	500	0.1235	-	-
0.5879	600	0.1153	-	-
0.6859	700	0.1109	-	-
0.7839	800	0.1073	-	-
0.8819	900	0.1065	-	-
0.9799	1000	0.1039	-	-
1.0	1021	-	0.1022	0.6360
1.0774	1100	0.1013	-	-
1.1754	1200	0.1009	-	-
1.2734	1300	0.1003	-	-
1.3714	1400	0.0987	-	-
1.4694	1500	0.0985	-	-
1.5674	1600	0.0954	-	-
1.6654	1700	0.0942	-	-
1.7634	1800	0.0932	-	-
1.8613	1900	0.094	-	-
1.9593	2000	0.0937	-	-
1.9985	2040	-	0.0972	0.6388

Framework Versions

• Python: 3.11.10
• Sentence Transformers: 3.3.1
• Transformers: 4.48.0.dev0
• PyTorch: 2.5.1+cu124
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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",
}