BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from intfloat/e5-base. 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: intfloat/e5-base
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': False}) with Transformer model: BertModel 
  (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("ValentinaKim/bge-base-automobile-matryoshka")
# Run inference
sentences = [
    "클러스터 조명 밝기 조절은 시동 'ON' 상태에서 인포테인먼트 시스템의 설정> 클러스터/HUD > 화면 밝기를 차례로 선택하면 클러스터의 밝기를 조절할 수 있습니다. 인포테인먼트 시스템 화면에 표시되는 조명밝기 조절 정도를 참고하여 원하는 밝기로 조절하십시오.",
    '클러스터 조명 밝기 조절은 어떻게 하나요?',
    '하이브리드 자동차의 저압 타이어 경고등이 켜졌을 때의 조치는 무엇입니까?',
]
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	0.5556
cosine_accuracy@3	0.8148
cosine_accuracy@5	0.8519
cosine_accuracy@10	0.9259
cosine_precision@1	0.5556
cosine_precision@3	0.2716
cosine_precision@5	0.1704
cosine_precision@10	0.0926
cosine_recall@1	0.5556
cosine_recall@3	0.8148
cosine_recall@5	0.8519
cosine_recall@10	0.9259
cosine_ndcg@10	0.7436
cosine_mrr@10	0.6849
cosine_map@100	0.689

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5556
cosine_accuracy@3	0.7778
cosine_accuracy@5	0.8519
cosine_accuracy@10	0.8889
cosine_precision@1	0.5556
cosine_precision@3	0.2593
cosine_precision@5	0.1704
cosine_precision@10	0.0889
cosine_recall@1	0.5556
cosine_recall@3	0.7778
cosine_recall@5	0.8519
cosine_recall@10	0.8889
cosine_ndcg@10	0.7335
cosine_mrr@10	0.6825
cosine_map@100	0.6897

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5926
cosine_accuracy@3	0.7778
cosine_accuracy@5	0.8148
cosine_accuracy@10	0.8889
cosine_precision@1	0.5926
cosine_precision@3	0.2593
cosine_precision@5	0.163
cosine_precision@10	0.0889
cosine_recall@1	0.5926
cosine_recall@3	0.7778
cosine_recall@5	0.8148
cosine_recall@10	0.8889
cosine_ndcg@10	0.7461
cosine_mrr@10	0.6997
cosine_map@100	0.7074

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5926
cosine_accuracy@3	0.7407
cosine_accuracy@5	0.8519
cosine_accuracy@10	0.8889
cosine_precision@1	0.5926
cosine_precision@3	0.2469
cosine_precision@5	0.1704
cosine_precision@10	0.0889
cosine_recall@1	0.5926
cosine_recall@3	0.7407
cosine_recall@5	0.8519
cosine_recall@10	0.8889
cosine_ndcg@10	0.7391
cosine_mrr@10	0.691
cosine_map@100	0.6993

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5926
cosine_accuracy@3	0.7407
cosine_accuracy@5	0.8519
cosine_accuracy@10	0.9259
cosine_precision@1	0.5926
cosine_precision@3	0.2469
cosine_precision@5	0.1704
cosine_precision@10	0.0926
cosine_recall@1	0.5926
cosine_recall@3	0.7407
cosine_recall@5	0.8519
cosine_recall@10	0.9259
cosine_ndcg@10	0.7456
cosine_mrr@10	0.6892
cosine_map@100	0.6933

Training Details

Training Dataset

Unnamed Dataset

Size: 63 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 89 tokens
mean: 181.76 tokens
max: 365 tokens

min: 22 tokens
mean: 46.21 tokens
max: 72 tokens

	positive	anchor
type	string	string
details	min: 89 tokens mean: 181.76 tokens max: 365 tokens	min: 22 tokens mean: 46.21 tokens max: 72 tokens

Samples:

positive	anchor
`하이브리드 자동차의 전방 차량 출발 알림 기능의 제한 사항은 과격하게 운전할 경우, 빈번하게 차선을 침범할 경우, 차로 이탈방지 보조 등 다른 운전자 보조에 의해 차량이 제어될 경우 등입니다.`	`하이브리드 자동차의 전방 차량 출발 알림 기능의 제한 사항은 무엇입니까?`
`파워 트렁크가 정상적으로 작동하지 않으면 무리한 힘을 가하지 마십시오. 파워 트렁크가 손상될 수 있습니다. 반드시 당사 직영 하이테크센터나 블루핸즈에서 점검을 받으십시오.`	`파워 트렁크가 정상적으로 작동하지 않으면 어떻게 해야 하나요?`
`에어백 경고 라벨의 주의 사항은 13세 미만의 어린이는 에어백의 팽창 충격으로 다칠 수 있습니다. 어린이에게는 뒷좌석이 안전할 수 있습니다. 유아용 보조 좌석은 동승석에 설치하지 마십시오. 에어백에서 가능한 떨어져 앉으십시오. 좌석 안전벨트와 어린이 보호 장치를 사용하십시오.`	`에어백 경고 라벨의 주의 사항은 무엇입니까?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
gradient_accumulation_steps: 64
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
tf32: False
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 64
eval_accumulation_steps: None
learning_rate: 2e-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: 4
max_steps: -1
lr_scheduler_type: cosine
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: False
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: False
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_fused
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
batch_sampler: no_duplicates
multi_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
1.0	1	0.4923	0.5456	0.5549	0.4722	0.5450
2.0	2	0.6184	0.6751	0.7085	0.6313	0.7072
3.0	3	0.6810	0.6825	0.6916	0.6933	0.6840
4.0	4	0.6993	0.7074	0.6897	0.6933	0.689

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.33.0
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}
}

ValentinaKim
/

bge-base-automobile-matryoshka

BGE base Financial Matryoshka

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Information Retrieval

Information Retrieval

Information Retrieval

Information Retrieval

Information Retrieval

Training Details

Training Dataset

Unnamed Dataset

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MatryoshkaLoss

MultipleNegativesRankingLoss

Model tree for ValentinaKim/bge-base-automobile-matryoshka

Evaluation results