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 ๐ค Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
"I'd like to know the percentage of large cap in my investments.",
'Can you show what percentage of my portfolio consists of large cap',
'Show my riskiest 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 | 0.8626 |
cosine_accuracy@3 | 0.9962 |
cosine_accuracy@5 | 1.0 |
cosine_accuracy@10 | 1.0 |
cosine_precision@1 | 0.8626 |
cosine_precision@3 | 0.3321 |
cosine_precision@5 | 0.2 |
cosine_precision@10 | 0.1 |
cosine_recall@1 | 0.8626 |
cosine_recall@3 | 0.9962 |
cosine_recall@5 | 1.0 |
cosine_recall@10 | 1.0 |
cosine_ndcg@10 | 0.946 |
cosine_mrr@10 | 0.9272 |
cosine_map@100 | 0.9272 |
Training Details
Training Datasets
Unnamed Dataset
- Size: 1,310 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- 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: 9.06 tokens
- max: 17 tokens
- min: 1.0
- mean: 1.0
- max: 1.0
- Samples:
sentence_0 sentence_1 label are there any of my funds that are lagging behind
do I hold any funds that haven't been performing well
1.0
Which sectors are performing the best in my portfolio?
What are my best performing sectors?
1.0
List some of my top holdings
Show some of my best performing holdings
1.0
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Unnamed Dataset
- Size: 1,310 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 4 tokens
- mean: 10.68 tokens
- max: 22 tokens
- min: 4 tokens
- mean: 9.13 tokens
- max: 17 tokens
- min: 1.0
- mean: 1.0
- max: 1.0
- Samples:
sentence_0 sentence_1 label I need my portfolio to hit 1000% returns by next month
make my portfolio return 1000% by next month
1.0
What are my stocks?
Show my stocks
1.0
I'd like to know my sector distribution.
What is my sector allocation?
1.0
- Loss:
CosineSimilarityLoss
with these parameters:{ "loss_fct": "torch.nn.modules.loss.MSELoss" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 32per_device_eval_batch_size
: 32num_train_epochs
: 15multi_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 32per_device_eval_batch_size
: 32per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1num_train_epochs
: 15max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}tp_size
: 0fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Nonehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseinclude_for_metrics
: []eval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseuse_liger_kernel
: Falseeval_use_gather_object
: Falseaverage_tokens_across_devices
: Falseprompts
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: round_robin
Training Logs
Epoch | Step | Training Loss | test-eval_cosine_ndcg@10 |
---|---|---|---|
1.0 | 82 | - | 0.8929 |
2.0 | 164 | - | 0.9007 |
3.0 | 246 | - | 0.9112 |
4.0 | 328 | - | 0.9188 |
5.0 | 410 | - | 0.9285 |
6.0 | 492 | - | 0.9286 |
6.0976 | 500 | 0.2352 | 0.9291 |
7.0 | 574 | - | 0.9356 |
8.0 | 656 | - | 0.9404 |
9.0 | 738 | - | 0.9406 |
10.0 | 820 | - | 0.9434 |
11.0 | 902 | - | 0.9424 |
12.0 | 984 | - | 0.9455 |
12.1951 | 1000 | 0.164 | 0.9460 |
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}
}
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for 1shoomun/semant-cache-updated
Base model
jinaai/jina-embedding-b-en-v1Evaluation results
- Cosine Accuracy@1 on test evalself-reported0.863
- Cosine Accuracy@3 on test evalself-reported0.996
- Cosine Accuracy@5 on test evalself-reported1.000
- Cosine Accuracy@10 on test evalself-reported1.000
- Cosine Precision@1 on test evalself-reported0.863
- Cosine Precision@3 on test evalself-reported0.332
- Cosine Precision@5 on test evalself-reported0.200
- Cosine Precision@10 on test evalself-reported0.100
- Cosine Recall@1 on test evalself-reported0.863
- Cosine Recall@3 on test evalself-reported0.996