albertus-sussex/veriscrape-sbert-auto-wo-ref-deepseek-chat-0324

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
• Maximum Sequence Length: 64 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': 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-deepseek-chat-0324")
# Run inference
sentences = [
    '$27,174',
    'The data provided by Autodata is provided AS IS without warranty or guarantee of any kind, and Autodata disclaims all warranties or conditions of any kind, expressed or implied, with respect to such data, including the implied warranties of merchantable quality and fitness for a particular purpose.',
    '$39,890',
]
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

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9837

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.405
silhouette_euclidean	0.321

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9793

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.4049
silhouette_euclidean	0.3216

Training Details

Training Dataset

Unnamed Dataset

• Size: 35,294 training samples
• Columns: anchor, positive, negative, pos_attr_name, neg_attr_name, and website_id
• 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	min: 3 tokens mean: 8.16 tokens max: 64 tokens	min: 3 tokens mean: 8.98 tokens max: 64 tokens	min: 3 tokens mean: 9.5 tokens max: 64 tokens	min: 3 tokens mean: 3.27 tokens max: 5 tokens	min: 3 tokens mean: 3.59 tokens max: 5 tokens	0: ~4.00% 1: ~2.10% 2: ~3.50% 3: ~3.60% 4: ~4.70% 5: ~63.80% 6: ~3.20% 7: ~3.50% 8: ~7.50% 9: ~4.10%

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  $34,270	$22,240	Lexus GX 460 Base 4dr AWD	price	model	0
  FWD or AWD	-	GT-R	engine	model	5
  -	$15,195	City: 11   Highway: 17 – 18	engine	fuel_economy	5

• Loss: TripletLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 3,922 evaluation samples
• Columns: anchor, positive, negative, pos_attr_name, neg_attr_name, and website_id
• 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	min: 3 tokens mean: 8.4 tokens max: 64 tokens	min: 3 tokens mean: 8.63 tokens max: 64 tokens	min: 3 tokens mean: 9.54 tokens max: 64 tokens	min: 3 tokens mean: 3.21 tokens max: 5 tokens	min: 3 tokens mean: 3.63 tokens max: 5 tokens	0: ~3.70% 1: ~2.50% 2: ~3.80% 3: ~3.30% 4: ~5.00% 5: ~62.20% 6: ~4.40% 7: ~3.90% 8: ~7.70% 9: ~3.50%

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  $23,215	$95,465	$245,000	engine	price	5
  Visit our partners:			$32,000 – $38,000	engine	price
  $44,605	$22,530	22 mpg city / 33 mpg hwy	price	fuel_economy	9

• Loss: TripletLoss 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

Click to expand

• 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

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_accuracy	silhouette_cosine
-1	-1	-	-	0.5342	0.1323
1.0	276	0.5187	0.2374	0.9829	0.3699
2.0	552	0.0959	0.1561	0.9880	0.3959
3.0	828	0.0714	0.1738	0.9878	0.4028
4.0	1104	0.0594	0.1711	0.9875	0.4159
5.0	1380	0.05	0.2089	0.9837	0.4050
-1	-1	-	-	0.9793	0.4049

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 4.1.0
• 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}
}