README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:19985
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: 'A trigger of contamination OCD: own hands'
    sentences:
      - 'A trigger of contamination OCD: parking lot buttons'
      - 'A trigger of contamination OCD: touched by strangers'
      - 'A trigger of contamination OCD: using public toilets'
  - source_sentence: 'A trigger of contamination OCD: coughing and sneezing'
    sentences:
      - 'A trigger of contamination OCD: disenfecting'
      - 'A trigger of contamination OCD: masks not worn or not worn correctly'
      - 'A trigger of contamination OCD: hands full of corona viruses'
  - source_sentence: 'A trigger of contamination OCD: after using the toilet at home'
    sentences:
      - 'A trigger of contamination OCD: object coming from outside'
      - 'A trigger of contamination OCD: thoughts of dirty toilet'
      - 'A trigger of contamination OCD: sniffing children'
  - source_sentence: 'A trigger of contamination OCD: masks not worn'
    sentences:
      - 'A trigger of contamination OCD: manicure'
      - >-
        A trigger of contamination OCD: touching objects or surfaces in public
        spaces
      - 'A trigger of contamination OCD: people not wearing a mask'
  - source_sentence: 'A trigger of contamination OCD: money problem'
    sentences:
      - 'A trigger of contamination OCD: typing parking lot number'
      - 'A trigger of contamination OCD: someone touching his nose'
      - 'A trigger of contamination OCD: touching waste in the city'
pipeline_tag: sentence-similarity
library_name: sentence-transformers

dwulff/mpnet-cocs

This is a sentence-transformers model that generates 768-dimensional semantic vectors of triggers of contamination obsessive compulsive symptoms (C-OCS).

The base model (all-mpnet-base-v2) has been fine-tuned on 20k pairs of C-OCS triggers rated for similarity by Llama-3.3-70b-Instruct.

See PREPRINT for details.

Usage

Make sure sentence-transformers is installed:

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: sentence-transformers/all-mpnet-base-v2
• Maximum Sequence Length: 384 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (2): Normalize()
)

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("dwulff/mpnet-cocs")
# Run inference
sentences = [
    'A trigger of contamination OCD: money problem',
    'A trigger of contamination OCD: someone touching his nose',
    'A trigger of contamination OCD: touching waste in the city',
]
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]

Training Details

Training Dataset

Unnamed Dataset

• Size: 19,985 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 10 tokens mean: 13.15 tokens max: 33 tokens	min: 10 tokens mean: 13.31 tokens max: 39 tokens	min: 0.0 mean: 0.37 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  A trigger of contamination OCD: odor	A trigger of contamination OCD: wearing a mask	0.2
  A trigger of contamination OCD: distance not respected	A trigger of contamination OCD: person not respecting personal distance	0.9
  A trigger of contamination OCD: incongruous colors	A trigger of contamination OCD: my work	0.0

• Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• 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
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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}
• tp_size: 0
• 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: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
1.5974	500	0.0231

Framework Versions

• Python: 3.13.2
• Sentence Transformers: 4.0.2
• Transformers: 4.50.0.dev0
• PyTorch: 2.6.0
• Accelerate: 1.5.2
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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",
}