README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4192
  - loss:AttributeTripletLoss
base_model: Alibaba-NLP/gte-base-en-v1.5
widget:
  - source_sentence: ': 9780312368784'
    sentences:
      - isbn_13
      - Dean R. Koontz
      - author
      - '9781581210194'
  - source_sentence: Meriwether Publishing Ltd
    sentences:
      - Bantam Classic & Loveswept
      - isbn_13
      - ': 9781400034772'
      - publisher
  - source_sentence: 05/09/2006
    sentences:
      - publication_date
      - 25/11/2010
      - publisher
      - ': Orbit'
  - source_sentence: '9780470994481'
    sentences:
      - isbn_13
      - title
      - The Da Vinci Code
      - ': 9780312531560'
  - source_sentence: Full Tilt
    sentences:
      - Cure for the Common Life
      - Orbit
      - publisher
      - title
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - silhouette_cosine
  - silhouette_euclidean
model-index:
  - name: SentenceTransformer based on Alibaba-NLP/gte-base-en-v1.5
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.9935622215270996
            name: Cosine Accuracy
          - type: cosine_accuracy
            value: 0.9942085146903992
            name: Cosine Accuracy
      - task:
          type: silhouette
          name: Silhouette
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: silhouette_cosine
            value: 0.9179657101631165
            name: Silhouette Cosine
          - type: silhouette_euclidean
            value: 0.820523202419281
            name: Silhouette Euclidean
          - type: silhouette_cosine
            value: 0.9268674850463867
            name: Silhouette Cosine
          - type: silhouette_euclidean
            value: 0.8218178749084473
            name: Silhouette Euclidean

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: 8192 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': 8192, '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-book-test-sbert-bs128_lr0.0002_ep5_euclidean_snTrue_spFalse_hn1_spl100")
# Run inference
sentences = [
    'Full Tilt',
    'Cure for the Common Life',
    'Orbit',
]
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	0.9936

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.918
silhouette_euclidean	0.8205

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9942

Silhouette

• Evaluated with veriscrape.training.SilhouetteEvaluator

Metric	Value
silhouette_cosine	0.9269
silhouette_euclidean	0.8218

Training Details

Training Dataset

Unnamed Dataset

• Size: 4,192 training samples
• Columns: anchor, positive, negative, pos_attr_name, and neg_attr_name
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative	pos_attr_name	neg_attr_name
  type	string	string	string	string	string
  details	min: 3 tokens mean: 7.24 tokens max: 41 tokens	min: 3 tokens mean: 7.05 tokens max: 47 tokens	min: 3 tokens mean: 6.93 tokens max: 23 tokens	min: 3 tokens mean: 3.81 tokens max: 5 tokens	min: 3 tokens mean: 3.79 tokens max: 5 tokens

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name
  14/10/2010	03/01/2011	Evaluation	publication_date	title
  08/15/2009	May 19, 2000	Daily Express	publication_date	author
  10/01/1998	13/05/2010	The Time Machine: An Invention	publication_date	title

• Loss: veriscrape.training.AttributeTripletLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 466 evaluation samples
• Columns: anchor, positive, negative, pos_attr_name, and neg_attr_name
• Approximate statistics based on the first 466 samples:

  	anchor	positive	negative	pos_attr_name	neg_attr_name
  type	string	string	string	string	string
  details	min: 3 tokens mean: 7.15 tokens max: 25 tokens	min: 3 tokens mean: 7.17 tokens max: 47 tokens	min: 3 tokens mean: 7.33 tokens max: 21 tokens	min: 3 tokens mean: 3.81 tokens max: 5 tokens	min: 3 tokens mean: 3.77 tokens max: 5 tokens

• Samples:

  anchor	positive	negative	pos_attr_name	neg_attr_name
  Pierre Dukan	Charlotte Brontë	25/11/2008	author	publication_date
  25/11/2008	29/10/2009	Speak	publication_date	publisher
  Arrow Books Ltd	Pocket Books	Oliver Bowden	publisher	author

• Loss: veriscrape.training.AttributeTripletLoss 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
• learning_rate: 0.0002
• 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: 0.0002
• 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	-	-	0.4721	0.1816
1.0	33	1.068	0.1773	0.9893	0.8219
2.0	66	0.1395	0.0875	0.9936	0.8728
3.0	99	0.0721	0.1006	0.9957	0.9181
4.0	132	0.0372	0.0659	0.9957	0.9216
5.0	165	0.0104	0.0786	0.9936	0.9180
-1	-1	-	-	0.9942	0.9269

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 3.4.1
• Transformers: 4.45.2
• PyTorch: 2.5.1+cu124
• Accelerate: 1.5.2
• 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",
}

AttributeTripletLoss

@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}
}