README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2640
  - loss:MultipleNegativesRankingLoss
  - loss:CosineSimilarityLoss
base_model: jinaai/jina-embedding-b-en-v1
widget:
  - source_sentence: Can you tell me how my portfolio did last week?
    sentences:
      - Suggest recommendations for me
      - Do you have any insights on my portfolio
      - How did my portfolio perform last week ?
  - source_sentence: What are my most risky holdings?
    sentences:
      - View my holdings
      - Show my market cap breakdown
      - Show my riskiest holdings
  - source_sentence: What profits do I have in my portfolio?
    sentences:
      - How can I swap my stocks for mutual funds?
      - Show me the cash in my portfolio?
      - What are the profits I have gained in my portfolio
  - source_sentence: >-
      I'm curious, which investments have the highest volatility in my
      portfolio?
    sentences:
      - Which sector do I invest most in?
      - is there anything wrong with my investments?
      - Which of my investments have the highest volatility?
  - source_sentence: Sort my investment portfolio by ESG rating, please.
    sentences:
      - What stock makes up the largest percentage of my portfolio?
      - Can you show my worst performing holdings
      - Show my investments sorted by ESG rating.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on jinaai/jina-embedding-b-en-v1
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: test eval
          type: test-eval
        metrics:
          - type: cosine_accuracy@1
            value: 0.8636363636363636
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9924242424242424
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8636363636363636
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3308080808080807
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09999999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8636363636363636
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9924242424242424
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9436916551342168
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9242424242424244
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9242424242424242
            name: Cosine Map@100

SentenceTransformer based on jinaai/jina-embedding-b-en-v1

This is a sentence-transformers model finetuned from jinaai/jina-embedding-b-en-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: jinaai/jina-embedding-b-en-v1
• Maximum Sequence Length: 512 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': 512, 'do_lower_case': False}) with Transformer model: T5EncoderModel 
  (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})
)

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 = [
    'Sort my investment portfolio by ESG rating, please.',
    'Show my investments sorted by ESG rating.',
    'Can you show my worst performing holdings',
]
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

Information Retrieval

• Dataset: test-eval
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8636
cosine_accuracy@3	0.9924
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.8636
cosine_precision@3	0.3308
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.8636
cosine_recall@3	0.9924
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9437
cosine_mrr@10	0.9242
cosine_map@100	0.9242

Training Details

Training Datasets

Unnamed Dataset

• Size: 1,320 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: 4 tokens mean: 10.62 tokens max: 20 tokens	min: 4 tokens mean: 9.06 tokens max: 17 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  How does my portfolio score look?	What is my portfolio score?	1.0
  Show me the risk profile of my portfolio.	Details on my portfolio risk	1.0
  Which of my shares are the most erratic?	Which of my stocks are most volatile?	1.0

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Unnamed Dataset

• Size: 1,320 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: 4 tokens mean: 10.62 tokens max: 22 tokens	min: 4 tokens mean: 9.05 tokens max: 17 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  What holdings carry the least risk in my portfolio?	What are the least risky holdings in my portfolio?	1.0
  How have my investments fared over the previous year?	How has my portfolio performed over the last year?	1.0
  How well is my portfolio performing?	How is my portfolio performing	1.0

• Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 15
• 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: 32
• per_device_eval_batch_size: 32
• 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: 15
• 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
• 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	test-eval_cosine_ndcg@10
1.0	84	-	0.8877
2.0	168	-	0.8944
3.0	252	-	0.9042
4.0	336	-	0.9123
5.0	420	-	0.9241
5.9524	500	0.2478	0.9209
6.0	504	-	0.9209
7.0	588	-	0.9261
8.0	672	-	0.9327
9.0	756	-	0.9364
10.0	840	-	0.9370
11.0	924	-	0.9437

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.7.0
• Accelerate: 1.6.0
• 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",
}

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}
}