jarredparrett/fine-tuned-address-model-v0

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 tokens
• 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}) with Transformer model: 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("jarredparrett/fine-tuned-address-model-v0")
# Run inference
sentences = [
    '612 Madison # 2',
    '612 Madison Apt 2',
    '421 Jersey # 1',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

• Dataset: test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6005
spearman_cosine	0.4541
pearson_manhattan	0.4982
spearman_manhattan	0.4519
pearson_euclidean	0.4973
spearman_euclidean	0.4517
pearson_dot	0.6005
spearman_dot	0.4518
pearson_max	0.6005
spearman_max	0.4541

Semantic Similarity

• Dataset: validation
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9429
spearman_cosine	0.6568
pearson_manhattan	0.9703
spearman_manhattan	0.6536
pearson_euclidean	0.9704
spearman_euclidean	0.6536
pearson_dot	0.9429
spearman_dot	0.6536
pearson_max	0.9704
spearman_max	0.6568

Training Details

Training Dataset

Unnamed Dataset

• Size: 17,500 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	int
  details	min: 5 tokens mean: 7.0 tokens max: 12 tokens	min: 5 tokens mean: 7.01 tokens max: 12 tokens	0: ~18.70% 1: ~81.30%

• Samples:

  sentence_0	sentence_1	label
  32 Cinder #17	32 Cinder Unit 17	1
  85 Allen Apt 2R	85 Allen #2R	1
  138 - 162 Martin Luther King Jr Apt 1807	138 - 162 Martin Luther King Jr Apt 1807	1

• Loss: ContrastiveLoss with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 4
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• 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: 4
• 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}
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	test_spearman_max	validation_spearman_max
0	0	-	0.4541	-
0.0914	100	-	-	0.6494
0.1828	200	-	-	0.6567
0.2742	300	-	-	0.6566
0.3656	400	-	-	0.6568
0.4570	500	0.0056	-	0.6568
0.5484	600	-	-	0.6568
0.6399	700	-	-	0.6566
0.7313	800	-	-	0.6568
0.8227	900	-	-	0.6568
0.9141	1000	0.0026	-	0.6570
1.0	1094	-	-	0.6568
1.0055	1100	-	-	0.6568
1.0969	1200	-	-	0.6568
1.1883	1300	-	-	0.6569
1.2797	1400	-	-	0.6569
1.3711	1500	0.0021	-	0.6569
1.4625	1600	-	-	0.6570
1.5539	1700	-	-	0.6570
1.6453	1800	-	-	0.6568
1.7367	1900	-	-	0.6567
1.8282	2000	0.0018	-	0.6569
1.9196	2100	-	-	0.6571
2.0	2188	-	-	0.6571
2.0110	2200	-	-	0.6570
2.1024	2300	-	-	0.6568
2.1938	2400	-	-	0.6569
2.2852	2500	0.0016	-	0.6570
2.3766	2600	-	-	0.6569
2.4680	2700	-	-	0.6570
2.5594	2800	-	-	0.6568
2.6508	2900	-	-	0.6569
2.7422	3000	0.0014	-	0.6568
2.8336	3100	-	-	0.6569
2.9250	3200	-	-	0.6569
3.0	3282	-	-	0.6569
3.0165	3300	-	-	0.6569
3.1079	3400	-	-	0.6568
3.1993	3500	0.0014	-	0.6568
3.2907	3600	-	-	0.6569
3.3821	3700	-	-	0.6569
3.4735	3800	-	-	0.6568
3.5649	3900	-	-	0.6568
3.6563	4000	0.0013	-	0.6568
3.7477	4100	-	-	0.6568
3.8391	4200	-	-	0.6568
3.9305	4300	-	-	0.6568
4.0	4376	-	-	0.6568

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.44.2
• PyTorch: 2.4.0+cu121
• Accelerate: 0.33.0
• Datasets: 2.21.0
• Tokenizers: 0.19.1

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}