BGE base Financial Matryoshka
This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 tokens
- Similarity Function: Cosine Similarity
- Language: en
- License: apache-2.0
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': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, '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})
(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("IlhamEbdesk/bge-base-financial-matryoshka_test")
# Run inference
sentences = [
'During fiscal year 2023, we repurchased 10.4 million shares for approximately $1,295 million.',
'What total amount was spent on share repurchases during fiscal year 2023?',
'What judicial decision occurred in August 2023 regarding the antitrust lawsuits against the airlines?',
]
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:
dim_768
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.6743 |
cosine_accuracy@3 | 0.8052 |
cosine_accuracy@5 | 0.8459 |
cosine_accuracy@10 | 0.8933 |
cosine_precision@1 | 0.6743 |
cosine_precision@3 | 0.2684 |
cosine_precision@5 | 0.1692 |
cosine_precision@10 | 0.0893 |
cosine_recall@1 | 0.6743 |
cosine_recall@3 | 0.8052 |
cosine_recall@5 | 0.8459 |
cosine_recall@10 | 0.8933 |
cosine_ndcg@10 | 0.7838 |
cosine_mrr@10 | 0.7487 |
cosine_map@100 | 0.7524 |
Information Retrieval
- Dataset:
dim_512
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.669 |
cosine_accuracy@3 | 0.8024 |
cosine_accuracy@5 | 0.8444 |
cosine_accuracy@10 | 0.893 |
cosine_precision@1 | 0.669 |
cosine_precision@3 | 0.2675 |
cosine_precision@5 | 0.1689 |
cosine_precision@10 | 0.0893 |
cosine_recall@1 | 0.669 |
cosine_recall@3 | 0.8024 |
cosine_recall@5 | 0.8444 |
cosine_recall@10 | 0.893 |
cosine_ndcg@10 | 0.7806 |
cosine_mrr@10 | 0.7446 |
cosine_map@100 | 0.7484 |
Information Retrieval
- Dataset:
dim_256
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.6624 |
cosine_accuracy@3 | 0.7933 |
cosine_accuracy@5 | 0.8335 |
cosine_accuracy@10 | 0.8832 |
cosine_precision@1 | 0.6624 |
cosine_precision@3 | 0.2644 |
cosine_precision@5 | 0.1667 |
cosine_precision@10 | 0.0883 |
cosine_recall@1 | 0.6624 |
cosine_recall@3 | 0.7933 |
cosine_recall@5 | 0.8335 |
cosine_recall@10 | 0.8832 |
cosine_ndcg@10 | 0.7726 |
cosine_mrr@10 | 0.7372 |
cosine_map@100 | 0.7413 |
Information Retrieval
- Dataset:
dim_128
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.6419 |
cosine_accuracy@3 | 0.7698 |
cosine_accuracy@5 | 0.8132 |
cosine_accuracy@10 | 0.8629 |
cosine_precision@1 | 0.6419 |
cosine_precision@3 | 0.2566 |
cosine_precision@5 | 0.1626 |
cosine_precision@10 | 0.0863 |
cosine_recall@1 | 0.6419 |
cosine_recall@3 | 0.7698 |
cosine_recall@5 | 0.8132 |
cosine_recall@10 | 0.8629 |
cosine_ndcg@10 | 0.7522 |
cosine_mrr@10 | 0.7168 |
cosine_map@100 | 0.7217 |
Information Retrieval
- Dataset:
dim_64
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.5902 |
cosine_accuracy@3 | 0.7241 |
cosine_accuracy@5 | 0.7662 |
cosine_accuracy@10 | 0.8186 |
cosine_precision@1 | 0.5902 |
cosine_precision@3 | 0.2414 |
cosine_precision@5 | 0.1532 |
cosine_precision@10 | 0.0819 |
cosine_recall@1 | 0.5902 |
cosine_recall@3 | 0.7241 |
cosine_recall@5 | 0.7662 |
cosine_recall@10 | 0.8186 |
cosine_ndcg@10 | 0.7039 |
cosine_mrr@10 | 0.6674 |
cosine_map@100 | 0.6732 |
Training Details
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: epochper_device_train_batch_size
: 32per_device_eval_batch_size
: 16gradient_accumulation_steps
: 16learning_rate
: 2e-05num_train_epochs
: 4lr_scheduler_type
: cosinewarmup_ratio
: 0.1tf32
: Falseload_best_model_at_end
: Trueoptim
: adamw_torch_fusedbatch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: epochprediction_loss_only
: Trueper_device_train_batch_size
: 32per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 16eval_accumulation_steps
: Nonelearning_rate
: 2e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 4max_steps
: -1lr_scheduler_type
: cosinelr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_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
: Falselocal_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
: Trueignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_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_torch_fusedoptim_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
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_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
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falsebatch_sampler
: no_duplicatesmulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
---|---|---|---|---|---|---|
0.7273 | 1 | 0.6718 | 0.7044 | 0.7160 | 0.6086 | 0.7194 |
1.4545 | 2 | 0.6897 | 0.7192 | 0.7298 | 0.6329 | 0.7314 |
2.9091 | 4 | 0.7051 | 0.7292 | 0.7387 | 0.6504 | 0.7409 |
0.7273 | 1 | 0.7051 | 0.7292 | 0.7387 | 0.6504 | 0.7409 |
1.4545 | 2 | 0.7148 | 0.7366 | 0.7446 | 0.6636 | 0.7473 |
2.9091 | 4 | 0.7217 | 0.7413 | 0.7484 | 0.6732 | 0.7524 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.1.2+cu121
- Accelerate: 0.32.1
- Datasets: 2.19.1
- 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",
}
MatryoshkaLoss
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
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
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for IlhamEbdesk/bge-base-financial-matryoshka_test
Base model
BAAI/bge-base-en-v1.5
Finetuned
this model
Evaluation results
- Cosine Accuracy@1 on dim 768self-reported0.674
- Cosine Accuracy@3 on dim 768self-reported0.805
- Cosine Accuracy@5 on dim 768self-reported0.846
- Cosine Accuracy@10 on dim 768self-reported0.893
- Cosine Precision@1 on dim 768self-reported0.674
- Cosine Precision@3 on dim 768self-reported0.268
- Cosine Precision@5 on dim 768self-reported0.169
- Cosine Precision@10 on dim 768self-reported0.089
- Cosine Recall@1 on dim 768self-reported0.674
- Cosine Recall@3 on dim 768self-reported0.805