metadata

base_model: BAAI/bge-m3
language:
  - ko
library_name: sentence-transformers
license: apache-2.0
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:1K<n<10K
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: 하이브리다이저란 무엇인가요?
    sentences:
      - 하이퍼바이저는 보안에서 어떤 역할을 합니까?
      - 지난 몇 년간 CUDA 생태계는 어떻게 발전해 왔나요?
      - 로컬 메모리 액세스 성능을 결정하는 요소는 무엇입니까?
  - source_sentence: 임시 구독의 용도는 무엇입니까?
    sentences:
      - 메모리 액세스 최적화에서 프리패치의 역할은 무엇입니까?
      - CUDA 인식 MPI는 확장 측면에서 어떻게 작동합니까?
      - CUDA 8이 해결하는 계산상의 과제에는 어떤 것이 있습니까?
  - source_sentence: '''saxpy''는 무엇을 뜻하나요?'
    sentences:
      - CUDA C/C++의 맥락에서 SAXPY는 무엇입니까?
      - Numba는 다른 GPU 가속 방법과 어떻게 다른가요?
      - 장치 LTO는 CUDA 애플리케이션에 어떤 이점을 제공합니까?
  - source_sentence: USD/Hydra란 무엇인가요?
    sentences:
      - 쿠다란 무엇인가요?
      - y 미분 계산에 사용되는 접근 방식의 단점은 무엇입니까?
      - Pascal 아키텍처는 통합 메모리를 어떻게 개선합니까?
  - source_sentence: CUDAcast란 무엇인가요?
    sentences:
      - CUDACast 시리즈에서는 어떤 주제를 다룰 예정인가요?
      - 이 게시물에 기여한 것으로 인정받은 사람은 누구입니까?
      - WSL 2에서 NVML의 목적은 무엇입니까?
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.5443037974683544
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7749648382559775
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8523206751054853
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9409282700421941
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5443037974683544
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2583216127519925
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17046413502109703
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09409282700421939
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5443037974683544
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7749648382559775
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8523206751054853
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9409282700421941
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7411108924386547
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.677065054807671
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6802131506478553
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.5386779184247539
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7749648382559775
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8593530239099859
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9451476793248945
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5386779184247539
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2583216127519925
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17187060478199717
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09451476793248943
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5386779184247539
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7749648382559775
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8593530239099859
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9451476793248945
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7413571133247474
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6759917844306029
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.678939165210132
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.540084388185654
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7791842475386779
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8621659634317862
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9423347398030942
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.540084388185654
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.25972808251289264
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1724331926863572
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09423347398030943
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.540084388185654
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7791842475386779
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8621659634317862
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9423347398030942
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7403981257690416
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6756379344986938
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6787046866761269
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.5218002812939522
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7679324894514767
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8635724331926864
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9367088607594937
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5218002812939522
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2559774964838256
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17271448663853725
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09367088607594935
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5218002812939522
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7679324894514767
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8635724331926864
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9367088607594937
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7305864977688176
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6641673922264634
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6671648971944116
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.509142053445851
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7426160337552743
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8284106891701828
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9310829817158931
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.509142053445851
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.24753867791842477
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16568213783403654
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09310829817158929
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.509142053445851
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7426160337552743
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8284106891701828
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9310829817158931
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7135661304090457
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6444829549259928
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6474431148702396
            name: Cosine Map@100

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-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-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'CUDAcast란 무엇인가요?',
    'CUDACast 시리즈에서는 어떤 주제를 다룰 예정인가요?',
    '이 게시물에 기여한 것으로 인정받은 사람은 누구입니까?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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	0.5443
cosine_accuracy@3	0.775
cosine_accuracy@5	0.8523
cosine_accuracy@10	0.9409
cosine_precision@1	0.5443
cosine_precision@3	0.2583
cosine_precision@5	0.1705
cosine_precision@10	0.0941
cosine_recall@1	0.5443
cosine_recall@3	0.775
cosine_recall@5	0.8523
cosine_recall@10	0.9409
cosine_ndcg@10	0.7411
cosine_mrr@10	0.6771
cosine_map@100	0.6802

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5387
cosine_accuracy@3	0.775
cosine_accuracy@5	0.8594
cosine_accuracy@10	0.9451
cosine_precision@1	0.5387
cosine_precision@3	0.2583
cosine_precision@5	0.1719
cosine_precision@10	0.0945
cosine_recall@1	0.5387
cosine_recall@3	0.775
cosine_recall@5	0.8594
cosine_recall@10	0.9451
cosine_ndcg@10	0.7414
cosine_mrr@10	0.676
cosine_map@100	0.6789

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5401
cosine_accuracy@3	0.7792
cosine_accuracy@5	0.8622
cosine_accuracy@10	0.9423
cosine_precision@1	0.5401
cosine_precision@3	0.2597
cosine_precision@5	0.1724
cosine_precision@10	0.0942
cosine_recall@1	0.5401
cosine_recall@3	0.7792
cosine_recall@5	0.8622
cosine_recall@10	0.9423
cosine_ndcg@10	0.7404
cosine_mrr@10	0.6756
cosine_map@100	0.6787

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5218
cosine_accuracy@3	0.7679
cosine_accuracy@5	0.8636
cosine_accuracy@10	0.9367
cosine_precision@1	0.5218
cosine_precision@3	0.256
cosine_precision@5	0.1727
cosine_precision@10	0.0937
cosine_recall@1	0.5218
cosine_recall@3	0.7679
cosine_recall@5	0.8636
cosine_recall@10	0.9367
cosine_ndcg@10	0.7306
cosine_mrr@10	0.6642
cosine_map@100	0.6672

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5091
cosine_accuracy@3	0.7426
cosine_accuracy@5	0.8284
cosine_accuracy@10	0.9311
cosine_precision@1	0.5091
cosine_precision@3	0.2475
cosine_precision@5	0.1657
cosine_precision@10	0.0931
cosine_recall@1	0.5091
cosine_recall@3	0.7426
cosine_recall@5	0.8284
cosine_recall@10	0.9311
cosine_ndcg@10	0.7136
cosine_mrr@10	0.6445
cosine_map@100	0.6474

Training Details

Training Dataset

Unnamed Dataset

Size: 6,397 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 11 tokens
mean: 48.46 tokens
max: 107 tokens

min: 9 tokens
mean: 21.0 tokens
max: 48 tokens

	positive	anchor
type	string	string
details	min: 11 tokens mean: 48.46 tokens max: 107 tokens	min: 9 tokens mean: 21.0 tokens max: 48 tokens

Samples:

positive	anchor
`Warp-stride 및 block-stride 루프는 스레드 동작을 재구성하고 공유 메모리 액세스 패턴을 최적화하는 데 사용되었습니다.`	`코드에서 공유 메모리 액세스 패턴을 최적화하기 위해 어떤 유형의 루프가 사용되었습니까?`
`Nsight Compute의 규칙은 성능 병목 현상을 식별하기 위한 구조화된 프레임워크를 제공하고 최적화 프로세스를 간소화하기 위한 실행 가능한 통찰력을 제공합니다.`	`Nsight Compute의 맥락에서 규칙이 중요한 이유는 무엇입니까?`
`NVIDIA Nsight와 같은 도구의 가용성으로 인해 개발자가 단일 GPU에서 디버깅할 수 있게 되어 CUDA 개발 속도가 크게 향상되었습니다. CUDA 메모리 검사기는 메모리 액세스 문제를 식별하여 코드 품질을 향상시키는 데 도움이 됩니다.`	`디버깅 도구의 가용성이 CUDA 개발에 어떤 영향을 미쳤습니까?`

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
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
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: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
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: 3
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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	Training Loss	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
0.8	10	1.3103	-	-	-	-	-
0.96	12	-	0.6512	0.6539	0.6688	0.6172	0.6679
1.6	20	0.4148	-	-	-	-	-
2.0	25	-	0.6615	0.6688	0.6783	0.6417	0.6763
2.4	30	0.2683	-	-	-	-	-
2.88	36	-	0.6672	0.6787	0.6789	0.6474	0.6802

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.0
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.31.0
Datasets: 2.18.0
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}
}