KoModernBERT_SBERT_compare_mlmlv3

SentenceTransformer based on x2bee/ModernBert_MLM_kotoken_v03

This is a sentence-transformers model finetuned from x2bee/ModernBert_MLM_kotoken_v03 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_v03 <!-- at revision 05b5dfde93d387e6f10d30e0e568d3c8fe354c47 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • korean_nli_dataset

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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_mlmlv3")
# 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]

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Semantic Similarity

• Dataset: sts_dev
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

korean_nli_dataset

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

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

• Samples:

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

• Loss: <code>CosineSimilarityLoss</code> 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: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• Approximate statistics based on the first 1000 samples:

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

• Samples:

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

• Loss: <code>CosineSimilarityLoss</code> 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_mlmlv3
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• 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_mlmlv3
• 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

</details>

Training Logs

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",
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->