cahya / last-sts

SentenceTransformer

This is a sentence-transformers model trained. 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
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Language: en

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: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("cahya/last-sts")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man plays the guitar.',
]
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

Semantic Similarity

• Datasets: sts-dev and sts-test
• Evaluated with EmbeddingSimilarityEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 353,831 training samples
• Columns: sentence1 , sentence2 , and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 5 tokens mean: 38.53 tokens max: 151 tokens	min: 5 tokens mean: 38.78 tokens max: 145 tokens	min: 0.0 mean: 0.91 max: 1.0

• Samples:

  sentence1	sentence2	score
  A long-term researcher into diabetes, he achieved significant notability with his 1988 Banting Lecture (organized annually by the American Diabetes Association in memory of Frederick Banting).	A renowned expert on diabetes, he gained widespread acclaim for his 1988 Banting Lecture, which is presented annually by the American Diabetes Association to commemorate Frederick Banting.	0.926345705986023
  investigators claim the british company was a cia cover.	russian investigators stated that the british company was a cia cover.	0.88
  Albert Weber (21 November 1888, in Berlin – 17 September 1940) was a German amateur football (soccer) player who competed in the 1912 Summer Olympics.	Albert Weber (21 November 1888, in Berlin – 17 September 1940) was a German amateur footballer who participated in the 1912 Summer Olympics.	0.904914379119873

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

stsb

• Dataset: stsb at ab7a5ac
• Size: 1,500 evaluation samples
• Columns: sentence1 , sentence2 , and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 5 tokens mean: 15.44 tokens max: 44 tokens	min: 6 tokens mean: 15.43 tokens max: 58 tokens	min: 0.0 mean: 0.42 max: 1.0

• Samples:

  sentence1	sentence2	score
  A man with a hard hat is dancing.	A man wearing a hard hat is dancing.	1.0
  A young child is riding a horse.	A child is riding a horse.	0.95
  A man is feeding a mouse to a snake.	The man is feeding a mouse to the snake.	1.0

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy : steps
• per_device_train_batch_size : 64
• per_device_eval_batch_size : 64
• num_train_epochs : 10
• warmup_ratio : 0.1
• bf16 : True

All Hyperparameters

Training Logs

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 3.4.1
• Transformers: 4.49.0
• PyTorch: 2.5.1+cu124
• Accelerate: 0.34.2
• Datasets: 2.19.2
• Tokenizers: 0.21.0

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",
}