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

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")
# Run inference
sentences = [
    'Small cargo area',
    'See listings',
    '2010 MINI Cooper',
]
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	0.9585

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.2151
silhouette_euclidean	0.2116

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9626

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.2281
silhouette_euclidean	0.2266

Training Details

Training Dataset

Unnamed Dataset

• Size: 26,649 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: 8.37 tokens max: 64 tokens	min: 3 tokens mean: 8.34 tokens max: 64 tokens	min: 3 tokens mean: 8.97 tokens max: 64 tokens	min: 3 tokens mean: 3.29 tokens max: 5 tokens	min: 3 tokens mean: 3.19 tokens max: 5 tokens	0: ~3.10% 1: ~2.70% 2: ~4.20% 3: ~3.00% 4: ~5.10% 5: ~57.70% 6: ~5.80% 7: ~5.00% 8: ~8.30% 9: ~5.10%

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  $23,340	Visibility	$23,340	engine	price	5
  Engine: 6.7L V-12 DOHC with variable valve timing and four valves per cylinder	Engine: 5.7L V 8 overhead valve ; two valves per cylinder)	New 2011 BMW ActiveHybrid 7 750LI Sedan Performance Specs	engine	model	7
  $20,995	$67,200	Fuel consumption: city= 20 (mpg); highway= 28 (mpg); combined= 23 (mpg); vehicle range: 377 miles	price	fuel_economy	7

• Loss: TripletLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 2,961 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: 8.34 tokens max: 64 tokens	min: 3 tokens mean: 8.42 tokens max: 64 tokens	min: 3 tokens mean: 8.49 tokens max: 64 tokens	min: 3 tokens mean: 3.29 tokens max: 5 tokens	min: 3 tokens mean: 3.2 tokens max: 5 tokens	0: ~3.40% 1: ~2.20% 2: ~5.30% 3: ~2.60% 4: ~4.80% 5: ~55.90% 6: ~5.50% 7: ~4.70% 8: ~9.90% 9: ~5.70%

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name	website_id
  6.0L Gas V8, 360 HP	2.4L Gas I4, 185 HP	18 mpg City, 26 mpg Hwy	engine	fuel_economy	4
  $37,770	$23,995	2010 Mercedes-Benz C-Class	engine	model	5
  •	Destination Charge: $725	2010 Honda Pilot	engine	model	5

• 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	-	-	0.5968	0.1930
1.0	209	0.6134	0.6043	0.9517	0.1809
2.0	418	0.1704	0.5569	0.9554	0.2491
3.0	627	0.1261	0.5098	0.9588	0.2111
4.0	836	0.1042	0.5363	0.9558	0.2272
5.0	1045	0.0868	0.5157	0.9585	0.2151
-1	-1	-	-	0.9626	0.2281

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}
}