finetuned-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 <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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("bishaln/finetuned-bge-base-en")
# Run inference
sentences = [
    '\nName : CloudFlare Inc.\nCategory: Internet & Network Services, SaaS\nDepartment: IT Operations\nLocation: New York, NY\nAmount: 2000.0\nCard: Annual Cloud Services Budget\nTrip Name: unknown\n',
    '\nName : TechSavvy Solutions\nCategory: Software Services, Online Subscription\nDepartment: Engineering\nLocation: Austin, TX\nAmount: 1200.0\nCard: Annual Engineering Tools Budget\nTrip Name: unknown\n',
    '\nName : Vitality Systems\nCategory: Facility Management, Health Services\nDepartment: Office Administration\nLocation: Chicago, IL\nAmount: 347.29\nCard: Office Wellness Initiative\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]

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Triplet

• Dataset: bge-base-en-train
• Evaluated with <code>TripletEvaluator</code>

Triplet

• Dataset: bge-base-en-eval
• Evaluated with <code>TripletEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 208 training samples
• Columns: <code>sentence</code> and <code>label</code>
• Approximate statistics based on the first 208 samples:

  	sentence	label
  type	string	int
  details	<ul><li>min: 33 tokens</li><li>mean: 39.81 tokens</li><li>max: 49 tokens</li></ul>	<ul><li>0: ~3.85%</li><li>1: ~3.37%</li><li>2: ~3.85%</li><li>3: ~2.40%</li><li>4: ~5.29%</li><li>5: ~4.33%</li><li>6: ~4.33%</li><li>7: ~3.37%</li><li>8: ~3.85%</li><li>9: ~4.33%</li><li>10: ~3.37%</li><li>11: ~3.85%</li><li>12: ~2.40%</li><li>13: ~5.29%</li><li>14: ~3.37%</li><li>15: ~5.77%</li><li>16: ~4.33%</li><li>17: ~2.40%</li><li>18: ~2.88%</li><li>19: ~3.37%</li><li>20: ~3.85%</li><li>21: ~4.33%</li><li>22: ~2.88%</li><li>23: ~4.33%</li><li>24: ~4.81%</li><li>25: ~1.92%</li><li>26: ~1.92%</li></ul>

• Samples:

  sentence	label
  <code><br>Name : Transcend<br>Category: Upskilling<br>Department: Human Resource<br>Location: London, UK<br>Amount: 859.47<br>Card: Technology Skills Enhancement<br>Trip Name: unknown<br></code>	<code>0</code>
  <code><br>Name : Ayden<br>Category: Financial Software<br>Department: Finance<br>Location: Berlin, DE<br>Amount: 1273.45<br>Card: Enterprise Technology Services<br>Trip Name: unknown<br></code>	<code>1</code>
  <code><br>Name : Urban Sphere<br>Category: Utilities Management, Facility Services<br>Department: Office Administration<br>Location: New York, NY<br>Amount: 937.32<br>Card: Monthly Operations Budget<br>Trip Name: unknown<br></code>	<code>2</code>

• Loss: <code>BatchSemiHardTripletLoss</code>

Evaluation Dataset

Unnamed Dataset

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

  	sentence	label
  type	string	int
  details	<ul><li>min: 32 tokens</li><li>mean: 38.37 tokens</li><li>max: 43 tokens</li></ul>	<ul><li>0: ~1.92%</li><li>4: ~1.92%</li><li>5: ~11.54%</li><li>7: ~5.77%</li><li>8: ~5.77%</li><li>10: ~7.69%</li><li>11: ~3.85%</li><li>12: ~3.85%</li><li>13: ~1.92%</li><li>16: ~3.85%</li><li>17: ~1.92%</li><li>18: ~13.46%</li><li>19: ~5.77%</li><li>20: ~3.85%</li><li>21: ~3.85%</li><li>22: ~7.69%</li><li>23: ~3.85%</li><li>24: ~5.77%</li><li>25: ~5.77%</li></ul>

• Samples:

  sentence	label
  <code><br>Name : Tooly<br>Category: Survey Software, SaaS<br>Department: Marketing<br>Location: San Francisco, CA<br>Amount: 2000.0<br>Card: Annual Marketing Technology Budget<br>Trip Name: unknown<br></code>	<code>10</code>
  <code><br>Name : CloudFlare Inc.<br>Category: Internet & Network Services, SaaS<br>Department: IT Operations<br>Location: New York, NY<br>Amount: 2000.0<br>Card: Annual Cloud Services Budget<br>Trip Name: unknown<br></code>	<code>21</code>
  <code><br>Name : Gartner & Associates<br>Category: Consulting, Business Services<br>Department: Legal<br>Location: San Francisco, CA<br>Amount: 5000.0<br>Card: Legal Consultation Fund<br>Trip Name: unknown<br></code>	<code>5</code>

• Loss: <code>BatchSemiHardTripletLoss</code>

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

<details><summary>Click to expand</summary>

• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 3.1.1
• Transformers: 4.45.2
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.20.3

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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->