Hugging Face's logo

redis
/
model-b-structured

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:111470
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
model-b-structured / README.md
radoslavralev's picture
radoslavralev
Training in progress, step 5000
2d155b6 verified
preview code
|
raw
history blame
13.2 kB
metadata 
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:100000
  - loss:MultipleNegativesRankingLoss
base_model: prajjwal1/bert-small
widget:
  - source_sentence: How do I calculate IQ?
    sentences:
      - What is the easiest way to know my IQ?
      - How do I calculate not IQ ?
      - >-
        What are some creative and innovative business ideas with less
        investment in India?
  - source_sentence: How can I learn martial arts in my home?
    sentences:
      - How can I learn martial arts by myself?
      - What are the advantages and disadvantages of investing in gold?
      - >-
        Can people see that I have looked at their pictures on instagram if I am
        not following them?
  - source_sentence: When Enterprise picks you up do you have to take them back?
    sentences:
      - Are there any software Training institute in Tuticorin?
      - When Enterprise picks you up do you have to take them back?
      - When Enterprise picks you up do them have to take youback?
  - source_sentence: What are some non-capital goods?
    sentences:
      - What are capital goods?
      - How is the value of [math]\pi[/math] calculated?
      - What are some non-capital goods?
  - source_sentence: What is the QuickBooks technical support phone number in New York?
    sentences:
      - What caused the Great Depression?
      - Can I apply for PR in Canada?
      - Which is the best QuickBooks Hosting Support Number in New York?
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on prajjwal1/bert-small

This is a sentence-transformers model finetuned from prajjwal1/bert-small. It maps sentences & paragraphs to a 512-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: prajjwal1/bert-small
  • Maximum Sequence Length: 128 tokens
  • Output Dimensionality: 512 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 512, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'What is the QuickBooks technical support phone number in New York?',
    'Which is the best QuickBooks Hosting Support Number in New York?',
    'Can I apply for PR in Canada?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8563, 0.0594],
#         [0.8563, 1.0000, 0.1245],
#         [0.0594, 0.1245, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 100,000 training samples
  • Columns: sentence_0, sentence_1, and sentence_2
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 sentence_2
    type string string string
    details
    • min: 6 tokens
    • mean: 15.79 tokens
    • max: 66 tokens
    • min: 6 tokens
    • mean: 15.68 tokens
    • max: 66 tokens
    • min: 7 tokens
    • mean: 16.37 tokens
    • max: 67 tokens
  • Samples:
    sentence_0 sentence_1 sentence_2
    Is masturbating bad for boys? Is masturbating bad for boys? How harmful or unhealthy is masturbation?
    Does a train engine move in reverse? Does a train engine move in reverse? Time moves forward, not in reverse. Doesn't that make time a vector?
    What is the most badass thing anyone has ever done? What is the most badass thing anyone has ever done? anyone is the most badass thing Whathas ever done?
  • 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: 64
  • per_device_eval_batch_size: 64
  • fp16: True
  • 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
  • bf16: False
  • fp16: True
  • 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: {}

Training Logs

Epoch Step Training Loss
0.3199 500 0.4294
0.6398 1000 0.1268
0.9597 1500 0.1
1.2796 2000 0.0792
1.5995 2500 0.0706
1.9194 3000 0.0687
2.2393 3500 0.0584
2.5592 4000 0.057
2.8791 4500 0.0581

Framework Versions

  • Python: 3.10.18
  • Sentence Transformers: 5.2.0
  • Transformers: 4.57.3
  • PyTorch: 2.9.1+cu128
  • Accelerate: 1.12.0
  • Datasets: 4.4.2
  • 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}
}