Smrfhdl/ruri-large-v2-triplet-fine-tuned-v5

SentenceTransformer based on cl-nagoya/ruri-large-v2

This is a sentence-transformers model finetuned from cl-nagoya/ruri-large-v2 on the json dataset. It maps sentences & paragraphs to a 1024-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: cl-nagoya/ruri-large-v2
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("Smrfhdl/ruri-large-v2-triplet-fine-tuned-v5")
# Run inference
sentences = [
    '払込票の期限が11月末で切れており支払いができない状態',
    '11月払込票の有効期限が過ぎ、新しい払込票が必要な状況',
    '11月満期保険金の受取期限が過ぎ、新規請求手続きが必要な状態',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Triplet

• Datasets: train-eval, dev-eval and test-eval
• Evaluated with TripletEvaluator

Metric	train-eval	dev-eval	test-eval
cosine_accuracy	1.0	0.97	0.98

Training Details

Training Dataset

json

• Dataset: json
• Size: 800 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 800 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 8 tokens mean: 21.52 tokens max: 40 tokens	min: 8 tokens mean: 24.07 tokens max: 43 tokens	min: 6 tokens mean: 20.14 tokens max: 38 tokens

• Samples:

  anchor	positive	negative
  赤坂桃子さんの手術給付金請求条件を教えて	1991年7月生まれの契約者のパーキンソン病手術保障	佐野千恵様の死亡保険給付遅延の理由を説明
  給付金請求書を11月19日に発送したのですが、到着は確認されていますか？	先月19日に投函した請求書類、既に事務所には届きましたか	保険料のコンビニ支払い用紙はいつ頃届く予定ですか？
  妻が肝炎で入院し保険金を請求したいが必要書類が不明	主人が膵炎で手術入院した際の給付申請で診断書不足に困った	妻が肝炎で入院したため健康保険の資格喪失手続きをしたい

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.COSINE",
      "triplet_margin": 0.2
  }
  

Evaluation Dataset

json

• Dataset: json
• Size: 100 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 100 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 10 tokens mean: 21.4 tokens max: 41 tokens	min: 12 tokens mean: 23.57 tokens max: 40 tokens	min: 9 tokens mean: 19.11 tokens max: 32 tokens

• Samples:

  anchor	positive	negative
  11月19日に送った書類の到着は確認済みですか？	先月下旬に郵送した請求書類の受領状況を確かめるには？	保険証券の紛失届を出したいのですが手続きを教えてください
  歯根たん切除手術の保険適用について確認したい	歯科治療の支払いが保険の対象かどうかを教えてほしい	生命保険の契約内容を変更したいのですが
  クレジットカード番号変更による保険料支払い継続手続き	新しいクレジットカードへ切替えて保険料引き落とし継続する手順	銀行口座変更による給与天引きの停止申請方法

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.COSINE",
      "triplet_margin": 0.2
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 30
• warmup_ratio: 0.05
• fp16: True
• dataloader_num_workers: 4
• load_best_model_at_end: True

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: 1.0
• num_train_epochs: 30
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.05
• 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: True
• 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: 4
• 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: 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: False
• resume_from_checkpoint: None
• hub_model_id: None
• 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
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	train-eval_cosine_accuracy	dev-eval_cosine_accuracy	test-eval_cosine_accuracy
0.3077	4	0.1013	0.0764	0.9525	0.9300	-
0.6154	8	0.075	0.0372	0.9625	0.9300	-
0.9231	12	0.0345	0.0225	0.9700	0.9500	-
1.2308	16	0.0206	0.0185	0.9675	0.9700	-
1.5385	20	0.0199	0.0157	0.9837	0.9700	-
1.8462	24	0.0201	0.0176	0.9937	0.9800	-
2.1538	28	0.0125	0.0163	1.0	0.9600	-
2.4615	32	0.0053	0.0118	1.0	0.9700	-
-1	-1	-	-	-	-	0.9800

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 4.1.0
• Transformers: 4.52.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.8.1
• Datasets: 3.6.0
• Tokenizers: 0.21.2

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",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}