ptpedroVortal/nomic_vortal_v3.4

SentenceTransformer based on nomic-ai/nomic-embed-text-v1

This is a sentence-transformers model finetuned from nomic-ai/nomic-embed-text-v1. It maps sentences & paragraphs to a 768-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: nomic-ai/nomic-embed-text-v1
• Maximum Sequence Length: 8192 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
  (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("ptpedroVortal/nomic_vortal_v3.4")
# Run inference
sentences = [
    "Collect the details that are associated with product '' '2202000251 - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C 90CM (CART.)', with quantity 144, unit UN",
    "Details for '2202000251 - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C 90CM (CART.)', with quantity 144, unit UN:\n  - LOTE 73\n  - Price: 644.00 EUR",
    "Item Description: 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit, priced at 651.00 EUR, Origin: National",
]
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]

Evaluation

Metrics

Semantic Similarity

• Evaluated with main.CustomEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,382 training samples
• Columns: query, correct_node, and score
• Approximate statistics based on the first 1000 samples:

  	query	correct_node	score
  type	string	string	int
  details	min: 15 tokens mean: 56.3 tokens max: 154 tokens	min: 15 tokens mean: 49.65 tokens max: 1729 tokens	1: 100.00%

• Samples:

  query	correct_node	score
  Collect the details that are associated with product '' '2202000275 - FIO SUT. POLIAMIDA NÃO ABS. 2/0 MONOF AG. CILIND. 30MM 1/2 LOOP (UNID)', with quantity 216, unit UN	LOTE 98 Description: '2202000275 - FIO SUT. POLIAMIDA NÃO ABS. 2/0 MONOF AG. CILIND. 30MM 1/2 LOOP (UNID)', with quantity 216, unit UN Price: 940.00 EUR	1
  Collect the details that are associated with product '' '2202000294 - FIO SUT. AC. POLIGLIC. ABS. 2/0 MULTIF SEM AGULHA PRÉ CORTADO (UNID)', with quantity 324, unit UN	Product: '2202000294 - FIO SUT. AC. POLIGLIC. ABS. 2/0 MULTIF SEM AGULHA PRÉ CORTADO (UNID)', with quantity 324, unit UN, Estimated Value: 696.00 EUR	1
  Collect the details that are associated with Lot 4 product '' 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit	LOTE 44 Description: 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit Price: 542.00 EUR	1

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 297 evaluation samples
• Columns: query, correct_node, and score
• Approximate statistics based on the first 297 samples:

  	query	correct_node	score
  type	string	string	int
  details	min: 15 tokens mean: 55.37 tokens max: 154 tokens	min: 15 tokens mean: 46.58 tokens max: 435 tokens	1: 100.00%

• Samples:

  query	correct_node	score
  Collect the details that are associated with Lot 7 product '' 'Carro transporte de roupa suja', with quantity 1, unit Subcontracting Unit	Item Description: 'Carro transporte de roupa suja', with quantity 1, unit Subcontracting Unit, priced at 628.00 EUR, Origin: National	1
  Collect the details that are associated with Lot 10 product '' 'Mesas para cirurgia', with quantity 2, unit Subcontracting Unit	Details for 'Mesas para cirurgia', with quantity 2, unit Subcontracting Unit: - LOTE 83 - Price: 940.00 EUR	1
  Collect the details that are associated with Lot 1 product '' 'PAINEL MULTIPLO ALERGENOS RESPIRATORIOS ', with quantity 1152, unit UND	Product: 'PAINEL MULTIPLO ALERGENOS RESPIRATORIOS ', with quantity 1152, unit UND, Estimated Value: 714.00 EUR	1

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 10
• warmup_ratio: 0.1
• bf16: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

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: 1.0
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: True
• 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: True
• 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
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	spearman_cosine
0.6711	100	0.6485	0.4410	nan
1.3356	200	0.5026	0.4399	nan
2.0067	300	0.491	0.4175	nan
2.6711	400	0.442	0.4409	nan
3.3356	500	0.3999	0.4421	nan
4.0067	600	0.367	0.6182	nan
4.6711	700	0.3743	0.6104	nan
5.3356	800	0.1972	0.6115	nan

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 3.3.1
• Transformers: 4.47.0.dev0
• PyTorch: 2.5.1+cu121
• Accelerate: 1.1.1
• Datasets: 3.1.0
• Tokenizers: 0.20.4

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}
}