README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:80
  - loss:CoSENTLoss
base_model: abdeljalilELmajjodi/model
widget:
  - source_sentence: >-
      The school is having a special event in order to show the american culture
      on how other cultures are dealt with in parties.
    sentences:
      - A school is hosting an event.
      - A child with mom and dad, on summer vacation at the beach.
      - There are people just getting on a train
  - source_sentence: Two women who just had lunch hugging and saying goodbye.
    sentences:
      - Two adults walk across a street.
      - A team is trying to tag a runner out.
      - There are two woman in this picture.
  - source_sentence: A boy is jumping on skateboard in the middle of a red bridge.
    sentences:
      - The boy does a skateboarding trick.
      - >-
        The two sisters saw each other across the crowded diner and shared a
        hug, both clutching their doggie bags.
      - The women do not care what clothes they wear.
  - source_sentence: >-
      Woman in white in foreground and a man slightly behind walking with a sign
      for John's Pizza and Gyro in the background.
    sentences:
      - A woman in white.
      - The woman is wearing white.
      - Some people board a train.
  - source_sentence: >-
      A woman is walking across the street eating a banana, while a man is
      following with his briefcase.
    sentences:
      - A man in a restaurant is waiting for his meal to arrive.
      - A married couple is sleeping.
      - An actress and her favorite assistant talk a walk in the city.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on abdeljalilELmajjodi/model
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: pair score evaluator dev
          type: pair-score-evaluator-dev
        metrics:
          - type: pearson_cosine
            value: 0.3132380731765732
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.21958363099039482
            name: Spearman Cosine

SentenceTransformer based on abdeljalilELmajjodi/model

This is a sentence-transformers model finetuned from abdeljalilELmajjodi/model on the all-nli dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: abdeljalilELmajjodi/model
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text
• Training Dataset:
  • all-nli

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'mean', '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'A woman is walking across the street eating a banana, while a man is following with his briefcase.',
    'An actress and her favorite assistant talk a walk in the city.',
    'A man in a restaurant is waiting for his meal to arrive.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9891, 0.9925],
#         [0.9891, 1.0000, 0.9870],
#         [0.9925, 0.9870, 1.0000]])

Evaluation

Metrics

Semantic Similarity

• Dataset: pair-score-evaluator-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.3132
spearman_cosine	0.2196

Training Details

Training Dataset

all-nli

• Dataset: all-nli
• Size: 80 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 80 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 10 tokens mean: 25.59 tokens max: 52 tokens	min: 5 tokens mean: 12.04 tokens max: 29 tokens	min: 0.0 mean: 0.47 max: 1.0

• Samples:

  sentence1	sentence2	score
  Woman in white in foreground and a man slightly behind walking with a sign for John's Pizza and Gyro in the background.	The woman and man are outdoors.	1.0
  An older man sits with his orange juice at a small table in a coffee shop while employees in bright colored shirts smile in the background.	An older man drinks his juice as he waits for his daughter to get off work.	0.5
  Children smiling and waving at camera	There are children present	1.0

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Evaluation Dataset

all-nli

• Dataset: all-nli
• Size: 20 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 20 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 14 tokens mean: 26.3 tokens max: 52 tokens	min: 7 tokens mean: 11.75 tokens max: 29 tokens	min: 0.0 mean: 0.65 max: 1.0

• Samples:

  sentence1	sentence2	score
  High fashion ladies wait outside a tram beside a crowd of people in the city.	The women do not care what clothes they wear.	0.0
  The school is having a special event in order to show the american culture on how other cultures are dealt with in parties.	A school is hosting an event.	1.0
  An older man is drinking orange juice at a restaurant.	A man is drinking juice.	1.0

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 1
• warmup_steps: 0.05
• bf16: True
• fp16_full_eval: True
• load_best_model_at_end: True
• push_to_hub: True
• gradient_checkpointing: True

All Hyperparameters

Click to expand

• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• 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: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: None
• warmup_steps: 0.05
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: True
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: True
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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
• push_to_hub: True
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: None
• include_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	pair-score-evaluator-dev_spearman_cosine
0.1	1	3.0315	-	-
0.5	5	3.0018	-	-
1.0	10	3.7124	2.6509	0.2737
0.1	1	2.8043	-	-
0.5	5	2.9111	-	-
1.0	10	3.1121	2.6923	0.2196

• The bold row denotes the saved checkpoint.

Training Time

• Training: 5.6 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.4.1
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.8.5
• Tokenizers: 0.22.2

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",
}

CoSENTLoss

@article{10531646,
    author={Huang, Xiang and Peng, Hao and Zou, Dongcheng and Liu, Zhiwei and Li, Jianxin and Liu, Kay and Wu, Jia and Su, Jianlin and Yu, Philip S.},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    title={CoSENT: Consistent Sentence Embedding via Similarity Ranking},
    year={2024},
    doi={10.1109/TASLP.2024.3402087}
}