JFernandoGRE/gtelarge-colombian-elitenames-righttail

SentenceTransformer based on JFernandoGRE/bert-ner-colombian-elitenames

This is a sentence-transformers model finetuned from JFernandoGRE/bert-ner-colombian-elitenames. 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: JFernandoGRE/bert-ner-colombian-elitenames
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 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': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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("JFernandoGRE/gtelarge-colombian-elitenames-righttail")
# Run inference
sentences = [
    'STEVEN ANDRES SANCHEZ HERNANDEZ',
    'BRYAN MANUEL SANCHEZ HERNANDEZ',
    'JHONN JAIRO GOMEZ RAMIREZ',
]
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, 0.5568, 0.3681],
#         [0.5568, 1.0000, 0.3804],
#         [0.3681, 0.3804, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 10,629 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 4 tokens mean: 8.5 tokens max: 15 tokens	min: 4 tokens mean: 8.85 tokens max: 15 tokens	0: ~83.10% 1: ~16.90%

• Samples:

  sentence1	sentence2	label
  JUAN CARLOS CORTES GONZALEZ	JEAN CARLOS CORTES GONZALEZ	0
  SERGIO ANTONIO PACHECO AHUMAITRE	SERGIO ANTONIO PACHECO AUMAITRE	1
  JOSÉ MAURICIO ZULUAGA TOBÓN	JOSE HERNANDO ZULUAGA MARIN	0

• Loss: OnlineContrastiveLoss

Evaluation Dataset

Unnamed Dataset

• Size: 2,658 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 4 tokens mean: 8.55 tokens max: 13 tokens	min: 5 tokens mean: 8.88 tokens max: 15 tokens	0: ~81.50% 1: ~18.50%

• Samples:

  sentence1	sentence2	label
  YEIMIN DARIO PEREZ MOLINA	YESSIKA YULIETH PEREZ MOLINA	0
  CARLOS HUMBERTO MARTINEZ ALZATE	CARLOS HUMBERTO MARTINEZ PATIÑO	0
  CRISTHIAN DAVID BERMUDEZ TORRES	CRISTHIAN DAVID FORERO TORRES	0

• Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 1e-05
• num_train_epochs: 5
• warmup_ratio: 0.182
• fp16: 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: 16
• per_device_eval_batch_size: 16
• 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: 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: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.182
• 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
• 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: 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
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.1504	100	0.3195	0.6335
0.3008	200	0.3014	0.5719
0.4511	300	0.2717	0.4428
0.6015	400	0.2156	0.2780
0.7519	500	0.1779	0.2302
0.9023	600	0.1264	0.1554
1.0526	700	0.1178	0.1374
1.2030	800	0.1093	0.0901
1.3534	900	0.1025	0.1134
1.5038	1000	0.0988	0.0862
1.6541	1100	0.0876	0.0876
1.8045	1200	0.1004	0.0781
1.9549	1300	0.0669	0.0896
2.1053	1400	0.0765	0.0745
2.2556	1500	0.0623	0.0798
2.4060	1600	0.0705	0.0671
2.5564	1700	0.0429	0.0678
2.7068	1800	0.0612	0.0780
2.8571	1900	0.0605	0.0594
3.0075	2000	0.0541	0.0654
3.1579	2100	0.0554	0.0544
3.3083	2200	0.0423	0.0528
3.4586	2300	0.0379	0.0552
3.6090	2400	0.0384	0.0541
3.7594	2500	0.0312	0.0534
3.9098	2600	0.0508	0.0569
4.0602	2700	0.0374	0.0548
4.2105	2800	0.0239	0.0495
4.3609	2900	0.034	0.0489
4.5113	3000	0.0419	0.0504
4.6617	3100	0.0248	0.0489
4.8120	3200	0.0437	0.0482
4.9624	3300	0.0357	0.0492

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.0
• Transformers: 4.57.3
• PyTorch: 2.9.1+cu128
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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",
}