veriscrape-sbert-auto-wo-ref-gpt-4o-mini

SentenceTransformer based on Alibaba-NLP/gte-base-en-v1.5

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-base-en-v1.5. 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: Alibaba-NLP/gte-base-en-v1.5 <!-- at revision a829fd0e060bb84554da0dfd354d0de0f7712b7f -->
• Maximum Sequence Length: 64 tokens
• Output Dimensionality: 768 dimensions
• 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': 64, 'do_lower_case': False}) with Transformer model: NewModel 
  (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})
)

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("albertus-sussex/veriscrape-sbert-auto-wo-ref-gpt-4o-mini")
# Run inference
sentences = [
    'City (mpg)',
    'No data',
    '$46,500\xa0- $60,400',
]
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

• Evaluated with <code>TripletEvaluator</code>

Silhouette

• Evaluated with <code>veriscrape.training.SilhouetteEvaluator</code>

Triplet

• Evaluated with <code>TripletEvaluator</code>

Silhouette

• Evaluated with <code>veriscrape.training.SilhouetteEvaluator</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: 14,400 training samples
• Columns: <code>anchor</code>, <code>positive</code>, <code>negative</code>, <code>pos_attr_name</code>, <code>neg_attr_name</code>, and <code>website_id</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  type	string	string	string	string	string	int
  details	<ul><li>min: 3 tokens</li><li>mean: 11.41 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 11.46 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 12.03 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.53 tokens</li><li>max: 5 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.48 tokens</li><li>max: 5 tokens</li></ul>	<ul><li>0: ~9.80%</li><li>1: ~4.10%</li><li>2: ~3.30%</li><li>3: ~9.70%</li><li>4: ~11.50%</li><li>5: ~9.80%</li><li>6: ~11.50%</li><li>7: ~9.20%</li><li>8: ~16.60%</li><li>9: ~14.50%</li></ul>

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  <code>City (mpg)</code>	<code>City (mpg)</code>	<code>2010 Volkswagen Jetta</code>	<code>fuel_economy</code>	<code>model</code>	<code>8</code>
  <code>18</code>	<code>City (mpg)</code>	<code>2.0L 211 hp I4</code>	<code>fuel_economy</code>	<code>engine</code>	<code>8</code>
  <code>6-Cyl, Twin Turbo Diesel, 3.0 Liter</code>	<code>4-Cyl, 2.9 Liter</code>	<code>$57,000.00</code>	<code>engine</code>	<code>price</code>	<code>6</code>

• Loss: <code>TripletLoss</code> with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
      "triplet_margin": 5
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 1,600 evaluation samples
• Columns: <code>anchor</code>, <code>positive</code>, <code>negative</code>, <code>pos_attr_name</code>, <code>neg_attr_name</code>, and <code>website_id</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  type	string	string	string	string	string	int
  details	<ul><li>min: 3 tokens</li><li>mean: 11.27 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 11.27 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 12.43 tokens</li><li>max: 64 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.53 tokens</li><li>max: 5 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.49 tokens</li><li>max: 5 tokens</li></ul>	<ul><li>0: ~10.80%</li><li>1: ~3.40%</li><li>2: ~4.00%</li><li>3: ~11.60%</li><li>4: ~10.40%</li><li>5: ~8.90%</li><li>6: ~10.40%</li><li>7: ~8.60%</li><li>8: ~16.30%</li><li>9: ~15.60%</li></ul>

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  <code>15 mpg City / 21 mpg Hwy</code>	<code>-</code>	<code>2011 Dodge Durango 4-door Crew Sport Utility</code>	<code>fuel_economy</code>	<code>model</code>	<code>6</code>
  <code>Engine: 3.6L SUBARU BOXER horizontally opposed6 DOHC with variable valve timing and four valves per cylinder</code>	<code>Engine: 4.0L V-6 DOHC with variable valve timing and four valves per cylinder</code>	<code>2011 Subaru Impreza Outback Sport Wagon</code>	<code>engine</code>	<code>model</code>	<code>7</code>
  <code>The Ram 1500 provides something for everyone with the choice of three cab styles (regular, Quad and Crew cabs), three wheelbases, 4x2 or 4x4 drive types, and 3.7-liter V6 or 4.7-liter V8 or 5.7-liter HEMI V8 engines. A multi-link coil spring rear suspension (in place of a traditional leaf spring suspension) improves ride and handling characteristics without sacrificing payload and towing capability. Standard safety features include side curtain airbags, stability control, traction control and trailer sway control. Heated and ventilated front seats, heated rear seats, heated steering wheel, power adjustable pedals, rear parking sensors, and a rear backup camera are available. Electronic and infotainment choices include a multimedia system with 30-gigabyte hard drive, navigation system, SIRIUS Backseat TV and a rear-seat DVD entertainment system. The RamBox cargo management system, available on the Crew cab, includes lockable, illuminated storage bins built into bed rails.</code>	<code>While exterior changes are limited to a new louvered hood, front bumper and grille, most of the 2011 Chevrolet Silverado 2500HD's mechanical and structural components (including frame, engines, transmissions, suspension, and brakes) have been redesigned, strengthened or improved. Like all Silverados, the 2500HD is available in a wide array of bed sizes, wheelbases, drive types and cab sizes, as well as a variety of trim levels.</code>	<code>Dodge Ram 1500 Sport 4x4 Quad Cab 140 in. WB</code>	<code>engine</code>	<code>model</code>	<code>0</code>

• Loss: <code>TripletLoss</code> with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
      "triplet_margin": 5
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• num_train_epochs: 5
• warmup_ratio: 0.1

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• 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: 1.0
• 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
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 4.0.1
• Transformers: 4.45.2
• PyTorch: 2.5.1+cu124
• Accelerate: 1.6.0
• Datasets: 3.1.0
• 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",
}

TripletLoss

@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.* -->