ppuva1 / bge-base-en

SentenceTransformer based on BAAI/bge-base-en

This is a sentence-transformers model finetuned from BAAI/bge-base-en . 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: BAAI/bge-base-en
• 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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("bge-base-en")
# Run inference
sentences = [
    '\nName : FTC\nCategory: Regulatory Compliance Services, Business Consulting\nDepartment: Legal\nLocation: Toronto, Canada\nAmount: 3594.76\nCard: Annual Compliance Assessment\nTrip Name: unknown\n',
    '\nName : Luxe Stay and Events\nCategory: Hospitality Services, Event Planning\nDepartment: Marketing\nLocation: London, UK\nAmount: 1138.75\nCard: Annual Retreat Planning\nTrip Name: Team Building Retreat\n',
    '\nName : Inkflow Media Solutions\nCategory: Content Distribution Services, Print Media Supplies\nDepartment: Marketing\nLocation: Amsterdam, Netherlands\nAmount: 1598.32\nCard: Print and Digital Campaign Integration\nTrip Name: unknown\n',
]
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]

Evaluation

Metrics

Triplet

• Dataset: bge-base-en-train
• Evaluated with TripletEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 212 training samples
• Columns: sentence and label
• Approximate statistics based on the first 212 samples:

  	sentence	label
  type	string	int
  details	min: 33 tokens mean: 39.92 tokens max: 49 tokens	0: ~4.72% 1: ~3.30% 2: ~2.83% 3: ~5.19% 4: ~3.30% 5: ~3.77% 6: ~3.30% 7: ~2.83% 8: ~5.66% 9: ~3.30% 10: ~2.83% 11: ~2.36% 12: ~4.72% 13: ~5.19% 14: ~3.30% 15: ~3.30% 16: ~5.66% 17: ~1.42% 18: ~4.25% 19: ~3.30% 20: ~2.36% 21: ~4.72% 22: ~5.19% 23: ~3.30% 24: ~2.36% 25: ~4.25% 26: ~3.30%

• Samples:

  sentence	label
  Name : Defendra Systems Category: Advanced IT Solutions, Network Security Management Department: Information Security Location: Berlin, Germany Amount: 1298.75 Card: Comprehensive Network Security Enhancement Trip Name: unknown	0
  Name : CypherDefense Systems Ltd. Category: IT Security Solutions, Cloud Security Technologies Department: Information Security Location: Amsterdam, Netherlands Amount: 1349.92 Card: Modernization & Protection Strategy Trip Name: unknown	0
  Name : NexusGuard Solutions Category: Data Protection Tools, IT Support Services Department: Information Security Location: New York, USA Amount: 1957.85 Card: Enterprise Security Revamp Trip Name: unknown	0

• Loss: BatchSemiHardTripletLoss

Evaluation Dataset

Unnamed Dataset

• Size: 52 evaluation samples
• Columns: sentence and label
• Approximate statistics based on the first 52 samples:

  	sentence	label
  type	string	int
  details	min: 32 tokens mean: 38.83 tokens max: 44 tokens	0: ~1.92% 1: ~7.69% 2: ~5.77% 3: ~5.77% 4: ~5.77% 5: ~5.77% 6: ~7.69% 7: ~1.92% 9: ~3.85% 10: ~3.85% 12: ~7.69% 13: ~1.92% 14: ~3.85% 15: ~3.85% 16: ~1.92% 17: ~3.85% 18: ~3.85% 19: ~5.77% 20: ~7.69% 22: ~1.92% 23: ~1.92% 24: ~1.92% 25: ~1.92% 26: ~1.92%

• Samples:

  sentence	label
  Name : Vista Cascades Resort Category: Hospitality, Event Hosting Department: Sales Location: Orlando, FL Amount: 1823.45 Card: Annual Sales Retreat Trip Name: Q3 Strategy Session	1
  Name : LearnTech Innovations Category: Educational Software, Professional Development Solutions Department: IT Operations Location: Tokyo, Japan Amount: 1523.45 Card: Technology Faculty Enhancement Series Trip Name: unknown	2
  Name : Luxe Stay and Events Category: Hospitality Services, Event Planning Department: Marketing Location: London, UK Amount: 1138.75 Card: Annual Retreat Planning Trip Name: Team Building Retreat	1

• Loss: BatchSemiHardTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy : steps
• per_device_train_batch_size : 16
• per_device_eval_batch_size : 16
• learning_rate : 2e-05
• num_train_epochs : 5
• warmup_ratio : 0.1
• batch_sampler : no_duplicates

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 : 2e-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 : 0.1
• 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 : 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}
• 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
• 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

Training Logs

Framework Versions

• Python: 3.11.8
• Sentence Transformers: 3.4.1
• Transformers: 4.48.2
• PyTorch: 2.6.0
• Accelerate: 1.3.0
• 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",
}

BatchSemiHardTripletLoss

@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}
}