SentenceTransformer based on letijo03/lts-xlmr-domain

This is a sentence-transformers model finetuned from letijo03/lts-xlmr-domain. It maps inputs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: letijo03/lts-xlmr-domain
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("letijo03/lts-xlmr-similarity")
# Run inference
sentences = [
    'livelihood para sa farmers',
    'ACCREDITING THE ISDAON FARMERS AGRICULTURE COOPERATIVE (IFACO)',
    'ACCREDITING THE AGUSAN PLANTATION INCORPORATED- AGRARIAN REFORM BENEFICIARIES MULTI-PURPOSE COOPERATIVE (API-ARB MPC)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9139, 0.8640],
#         [0.9139, 1.0000, 0.9454],
#         [0.8640, 0.9454, 1.0000]])

Evaluation

Metrics

Semantic Similarity

• Dataset: lts_val
• Evaluated with EmbeddingSimilarityEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 3,368 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 100 samples:

  	sentence_0	sentence_1
  type	string	string
  modality	text	text
  details	min: 4 tokensmean: 78.61 tokensmax: 256 tokens	min: 26 tokensmean: 123.38 tokensmax: 256 tokens

• Samples:

  sentence_0	sentence_1
  RESOLUTION AUTHORIZING THE HONORABLE GOVERNOR ADOLPH EDWARD G. PLAZA, FOR AND IN BEHALF OF THE PROVINCIAL GOVERNMENT OF AGUSAN DEL SUR, TO DONATE A UNIT OF OTOSCOPE APPARATUS TO THE MUNICIPAL HEALTH OFFICE OF PROSPERIDAD, THIS PROVINCE, REPRESENTED BY MAYOR ALBIN D. MAGDAMIT	RESOLUTION AUTHORIZING THE HONORABLE GOVERNOR ADOLPH EDWARD G. PLAZA, FOR AND IN BEHALF OF THE PROVINCIAL GOVERNMENT OF AGUSAN DEL SUR, TO ENTER INTO A MEMORANDUM OF AGREEMENT WITH THE MUNICIPALITY OF ESPERANZA REPRESENTED BY MAYOR DEO P. MANPATILAN, JR., THE BARANGAY OF ORO REPRESENTED BY BARANGAY CAPTAIN CELSO A. CUBILLAS, AND THE ORO FARMERS ASSOCIATION REPRESENTED BY CHAIRMAN/PRESIDENT EDWIN J. GAVIOLA, FOR THE PROVISION OF PUMP IRRIGATION SYSTEM OPEN SOURCE (PISOS) TO THE RECEPIENT ASSOCIATION
  RESOLUTION CONSTITUTING THE DIFFERENT STANDING COMMITTEES OF THE SIXTEENTH (16TH) SANGGUNIANG PANLALAWIGAN OF AGUSAN DEL SUR	CONSTITUTING THE DIFFERENT STANDING COMMITTEES OF THE SANGGUNIANG PANLALAWIGAN OF AGUSAN DEL SUR, 2022-2025
  RESOLUTION DECLARING MUNICIPAL RESOLUTION NO. 057, SERIES OF 2019 OF VERUELA, AGUSAN DEL SUR, ENTITLED: "FOR THE ADOPTION OF MDC RESOLUTION NO. 1 SERIES OF 2019-RESOLUTION APPROVING THE ANNUAL INVESTMENT PLAN FOR BUDGET YEAR 2020 OF THE MUNICIPALITY OF VERUELA, AGUSAN DEL SUR WITH AN ESTIMATED TOTAL AMOUNT OF TWO HUNDRED NINETY TWO MILLION FOUR HUNDRED FIVE THOUSAND FIVE HUNDRED EIGHTY PESOS AND 50/100 (292,405,580.50)", VALID BY VIRTUE OF SECTION 56 (d) OF REPUBLIC ACT 7160, OTHERWISE KNOWN AS THE LOCAL GOVERNMENT CODE OF 1991	DECLARING MUNICIPAL ORDINANCE NO. 057, SERIES OF 2025 OF VERUELA, AGUSAN DEL SUR TITLED: "AN ORDINANCE ENACTING ‘A-LALAY KANG LOLO UG LOLA’ PROGRAM-PROMOTING COMPASSIONATE GOVERNANCE FOR INCLUSIVE AND CULTURALLY SENSITIVE DEVELOPMENT FOR SENIOR CITIZENS", VALID AND OPERATIVE

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• num_train_epochs: 5
• per_device_eval_batch_size: 32
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

• per_device_train_batch_size: 32
• num_train_epochs: 5
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1
• label_smoothing_factor: 0.0
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 32
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• 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
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• dataloader_multiprocessing_context: None
• dataloader_in_order: True
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}
• warmup_ratio: None

Training Logs

Training Time

• Training: 4.8 minutes

Framework Versions

• Python: 3.13.15
• Sentence Transformers: 6.0.1
• Transformers: 5.16.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 5.0.1
• Tokenizers: 0.23.1

Additional Resources

• Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
• Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
• Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
• Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
• Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}