PHNeutre/all-MiniLM-L6-v2_finetuned_20251119_174549

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'evaluate, inbound, AD1, LTM, performance metrics',
    'STRAT | Growth Engine Performance - Inbound AD1/LTM: Purpose The dashboard suite STRAT  Growth Engine Performance is designed to monitor and analyze sales performance KPIs across the sales funnel This dashboard titled STRAT  Growth Engine Performance  Inbound AD1LTM is designed to track and analyze the performance of the AD1 and LTM sales funnels  Audience The target audience includes sales managers performance analysts and stakeholders involved in monitoring and optimizing sales activities and growth strategies  Good to know The dashboard suite integrates multiple sheets each focusing on specific aspects of sales performance eg CVR  SQLs and meetings  STRAT  Growth Engine Performance  Channel Cockpit  STRAT  Growth Engine Performance  Inbound AD1LTM  STRAT  Growth Engine Performance  Inbound SQLs  STRAT  Growth Engine Performance  Meetings created  STRAT  Growth Engine Performance  Meetings done and planned  STRAT  Growth Engine Performance  Cancellation rate  STRAT  Growth Engine Performance  Quotes Signed  STRAT  Growth Engine Performance  Size  Length Opp  STRAT  Growth Engine Performance  Time to Close  STRAT  Growth Engine Performance  Time to Pitch  STRAT  Growth Engine Performance  CVR  Content Metrics Key metrics include  SQLs attacked day 1 AD1  Share of relevant leads attacked by sales on the day of their creation  SQL to meeting rate LTM  Share of relevant leads linked to opportunities that convert into meetings not canceled Dimensions Key dimensions include  Lead Origin and Lead Origin category  Cluster Name  Country  Cost Center and team hierarchy  Source The data is sourced from   datasetlead  Data Update The data is updated daily with an SLA ensuring availability by 800 AM',
    'accounts_agendas_eligibility_helpers: This table contains eligibility helpers for accounts and agendas  retention   s3subfolder C5harddeleteaccounts rowstodelete leftjoinclauses  schematable dtmproductchurnersproaccountschurneddeleted joincondition accountsagendaseligibilityhelpersaccountid  proaccountschurneddeletedproaccountid where proaccountschurneddeletedproaccountid IS NOT NULL s3retention keep0day  s3subfolder C5harddeleteorganizations rowstodelete leftjoinclauses  schematable dtmproductchurnersorganizationschurneddeleted joincondition accountsagendaseligibilityhelpersorganizationid  organizationschurneddeletedorganizationid where organizationschurneddeletedorganizationid IS NOT NULL s3retention keep0day',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.5342, -0.0627],
#         [ 0.5342,  1.0000,  0.0066],
#         [-0.0627,  0.0066,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,319 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: 3 tokens mean: 9.72 tokens max: 21 tokens	min: 12 tokens mean: 95.3 tokens max: 256 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Patient appointment requests	Appointment Requests: Business description Appointment requestis a feature that allows patients to send requests for booking Appointments Its only dedicated for Hospitals and for very specific use cases Appointment request is link to an Appointments Appointment requestis only available on certain Visit Motivesregarding Appointment Requests Visit Motive Activation Rules When an appointment requestis raised then an Appointment Requests Entry is created Each Entry is composed by Comments Pain points Patient qualification for some visit motives patients need to be properly qualified ie need to check that what patients need matches with what the hospitals can offer or check that the prerequisites for reimbursement by health insurance are met This is only possible when a HCP from the hospital usually a Doctor reviews the appointment request and then decides if the request should be handled There is currently no easy way to reject appointments via Doctolib so hospitals prefer not to have t...	1.0
  prescriptions missed renewals treatment	treatment_missed_renewals: Table about prescription that have missed treatments renewals PK treatmentuuid	1.0
  integrated, feature, data, PRM, scope	prm: Track data from features integrated to PRM scope	1.0

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 2
• 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: 16
• per_device_eval_batch_size: 16
• 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: 2
• 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
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• 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
• 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
• hub_revision: None
• 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
• include_tokens_per_second: False
• 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
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Framework Versions

• Python: 3.13.7
• Sentence Transformers: 5.1.1
• Transformers: 4.57.0
• PyTorch: 2.8.0
• Accelerate: 1.11.0
• Datasets: 4.4.0
• Tokenizers: 0.22.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}