DungHugging/sacombank-bge-m3-full

SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. 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: BAAI/bge-m3
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 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': 'PeftModelForFeatureExtraction'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

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("DungHugging/sacombank-bge-m3-full")
# Run inference
sentences = [
    'ưu đãi Buffet hải sản giá rẻ tại Saigon Seafood',
    'hồ sơ vay tín chấp được duyệt nhanh qua App trong 1 giờ',
    'Áp dụng tiêu chuẩn CRS (Common Reporting Standard) trong trao đổi thông tin thuế quốc tế.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4611, 0.4808],
#         [0.4611, 1.0000, 0.6015],
#         [0.4808, 0.6015, 1.0000]])

Evaluation

Metrics

Semantic Similarity

• Datasets: spec_sim and final_evaluation
• Evaluated with EmbeddingSimilarityEvaluator

Metric	spec_sim	final_evaluation
pearson_cosine	0.5078	0.5078
spearman_cosine	0.5003	0.5003

Binary Classification

• Dataset: spec_bin
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.7399
cosine_accuracy_threshold	0.7662
cosine_f1	0.7705
cosine_f1_threshold	0.7137
cosine_precision	0.6714
cosine_recall	0.9038
cosine_ap	0.7812
cosine_mcc	0.452

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,665 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 6 tokens mean: 14.79 tokens max: 30 tokens	min: 8 tokens mean: 18.25 tokens max: 49 tokens	min: 0.0 mean: 0.5 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Lãi suất cơ sở (Base Rate) - dùng làm mốc tham chiếu để tính lãi vay khách hàng.	Lãi suất qua đêm (Overnight Rate) - lãi suất vay nóng giữa các ngân hàng trên thị trường liên ngân hàng.	0.0
  Khoản thanh toán lớn vào cuối kỳ hạn vay.	Khoản vay có cấu trúc Balloon Payment tại thời điểm đáo hạn.	1.0
  Bảo hiểm trách nhiệm dân sự chủ doanh nghiệp	Bảo hiểm tai nạn con người 24/7	0.0

• Loss: ContrastiveLoss with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 10
• multi_dataset_batch_sampler: round_robin

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: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: 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: 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: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	spec_sim_spearman_cosine	spec_bin_cosine_ap	final_evaluation_spearman_cosine
0.4970	83	-	-0.1802	0.4537	-
0.9940	166	-	-0.0618	0.4928	-
1.0	167	-	-0.0598	0.4935	-
1.4910	249	-	0.0678	0.5431	-
1.9880	332	-	0.1480	0.5821	-
2.0	334	-	0.1500	0.5829	-
2.4850	415	-	0.2448	0.6273	-
2.9820	498	-	0.3185	0.6705	-
2.9940	500	0.0327	-	-	-
3.0	501	-	0.3199	0.6715	-
3.4790	581	-	0.3650	0.7018	-
3.9760	664	-	0.3993	0.7226	-
4.0	668	-	0.3986	0.7222	-
4.4731	747	-	0.4210	0.7354	-
4.9701	830	-	0.4380	0.7469	-
5.0	835	-	0.4375	0.7467	-
5.4671	913	-	0.4514	0.7525	-
5.9641	996	-	0.4606	0.7584	-
5.9880	1000	0.0241	-	-	-
6.0	1002	-	0.4613	0.7591	-
6.4611	1079	-	0.4717	0.7648	-
6.9581	1162	-	0.4791	0.7684	-
7.0	1169	-	0.4799	0.7689	-
7.4551	1245	-	0.4848	0.7712	-
7.9521	1328	-	0.4910	0.7750	-
8.0	1336	-	0.4915	0.7760	-
8.4491	1411	-	0.4955	0.7780	-
8.9461	1494	-	0.4972	0.7796	-
8.9820	1500	0.0217	-	-	-
9.0	1503	-	0.4972	0.7796	-
9.4431	1577	-	0.4995	0.7807	-
9.9401	1660	-	0.5003	0.7812	-
10.0	1670	-	0.5003	0.7812	-
-1	-1	-	-	-	0.5003

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.1
• Transformers: 4.57.1
• PyTorch: 2.8.0+cu126
• Accelerate: 1.11.0
• Datasets: 4.4.2
• 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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}