This is a sentence-transformers model trained. 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

Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("potsu-potsu/bge-base-mrl-train40k")
# Run inference
sentences = [
    'What is known about the Digit Ratio (2D:4D) cancer?',
    'BACKGROUND: The ratio of the lengths of index and ring fingers (2D:4D) is a \nmarker of prenatal exposure to sex hormones, with low 2D:4D being indicative of \nhigh prenatal androgen action. Recent studies have reported a strong association \nbetween 2D:4D and risk of prostate cancer.\nMETHODS: A total of 6258 men participating in the Melbourne Collaborative Cohort \nStudy had 2D:4D assessed. Of these men, we identified 686 incident prostate \ncancer cases. Hazard ratios (HRs) and confidence intervals (CIs) were estimated \nfor a standard deviation increase in 2D:4D.\nRESULTS: No association was observed between 2D:4D and prostate cancer risk \noverall (HRs 1.00; 95% CIs, 0.92-1.08 for right, 0.93-1.08 for left). We \nobserved a weak inverse association between 2D:4D and risk of prostate cancer \nfor age <60, however 95% CIs included unity for all observed ages.\nCONCLUSION: Our results are not consistent with an association between 2D:4D and \noverall prostate cancer risk, but we cannot exclude a weak inverse association \nbetween 2D:4D and early onset prostate cancer risk.',
    "Proteins undergo conformational changes during their biological function. As \nsuch, a high-resolution structure of a protein's resting conformation provides a \nstarting point for elucidating its reaction mechanism, but provides no direct \ninformation concerning the protein's conformational dynamics. Several X-ray \nmethods have been developed to elucidate those conformational changes that occur \nduring a protein's reaction, including time-resolved Laue diffraction and \nintermediate trapping studies on three-dimensional protein crystals, and \ntime-resolved wide-angle X-ray scattering and X-ray absorption studies on \nproteins in the solution phase. This review emphasizes the scope and limitations \nof these complementary experimental approaches when seeking to understand \nprotein conformational dynamics. These methods are illustrated using a limited \nset of examples including myoglobin and haemoglobin in complex with carbon \nmonoxide, the simple light-driven proton pump bacteriorhodopsin, and the \nsuperoxide scavenger superoxide reductase. In conclusion, likely future \ndevelopments of these methods at synchrotron X-ray sources and the potential \nimpact of emerging X-ray free-electron laser facilities are speculated upon.",
]
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 with these parameters:
json
1{ 2 "truncate_dim": 768 3}

Metric	Value
cosine_accuracy@1	0.7397
cosine_accuracy@3	0.8472
cosine_accuracy@5	0.8925
cosine_accuracy@10	0.9293
cosine_precision@1	0.7397
cosine_precision@3	0.6058
cosine_precision@5	0.5296
cosine_precision@10	0.411
cosine_recall@1	0.2276
cosine_recall@3	0.3939
cosine_recall@5	0.4954
cosine_recall@10	0.6262
cosine_ndcg@10	0.7037
cosine_mrr@10	0.8042
cosine_map@100	0.65

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator with these parameters:
json
1{ 2 "truncate_dim": 512 3}

Metric	Value
cosine_accuracy@1	0.7327
cosine_accuracy@3	0.843
cosine_accuracy@5	0.8883
cosine_accuracy@10	0.9151
cosine_precision@1	0.7327
cosine_precision@3	0.5964
cosine_precision@5	0.5279
cosine_precision@10	0.4099
cosine_recall@1	0.2192
cosine_recall@3	0.3867
cosine_recall@5	0.4915
cosine_recall@10	0.623
cosine_ndcg@10	0.6971
cosine_mrr@10	0.7969
cosine_map@100	0.6403

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator with these parameters:
json
1{ 2 "truncate_dim": 256 3}

Metric	Value
cosine_accuracy@1	0.7228
cosine_accuracy@3	0.8373
cosine_accuracy@5	0.8769
cosine_accuracy@10	0.9109
cosine_precision@1	0.7228
cosine_precision@3	0.5893
cosine_precision@5	0.5132
cosine_precision@10	0.4048
cosine_recall@1	0.2165
cosine_recall@3	0.3844
cosine_recall@5	0.4707
cosine_recall@10	0.6082
cosine_ndcg@10	0.6857
cosine_mrr@10	0.7889
cosine_map@100	0.6255

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator with these parameters:
json
1{ 2 "truncate_dim": 128 3}

Metric	Value
cosine_accuracy@1	0.7072
cosine_accuracy@3	0.8076
cosine_accuracy@5	0.8458
cosine_accuracy@10	0.8967
cosine_precision@1	0.7072
cosine_precision@3	0.5606
cosine_precision@5	0.4877
cosine_precision@10	0.3819
cosine_recall@1	0.2132
cosine_recall@3	0.3572
cosine_recall@5	0.4428
cosine_recall@10	0.5764
cosine_ndcg@10	0.652
cosine_mrr@10	0.7681
cosine_map@100	0.5861

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator with these parameters:
json
1{ 2 "truncate_dim": 64 3}

Metric	Value
cosine_accuracy@1	0.6436
cosine_accuracy@3	0.7666
cosine_accuracy@5	0.8048
cosine_accuracy@10	0.8416
cosine_precision@1	0.6436
cosine_precision@3	0.5116
cosine_precision@5	0.4501
cosine_precision@10	0.3511
cosine_recall@1	0.1851
cosine_recall@3	0.3181
cosine_recall@5	0.3926
cosine_recall@10	0.5118
cosine_ndcg@10	0.5894
cosine_mrr@10	0.7115
cosine_map@100	0.5197

Training Details

Training Dataset

Unnamed Dataset

Size: 40,482 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 6 tokens
mean: 16.0 tokens
max: 32 tokens
min: 4 tokens
mean: 287.89 tokens
max: 512 tokens

Samples:

anchor	positive
`What is the implication of histone lysine methylation in medulloblastoma?`	`Aberrant patterns of H3K4, H3K9, and H3K27 histone lysine methylation were shown to result in histone code alterations, which induce changes in gene expression, and affect the proliferation rate of cells in medulloblastoma.`
`What is the implication of histone lysine methylation in medulloblastoma?`	Recent studies showed frequent mutations in histone H3 lysine 27 (H3K27) [object Object]demethylases in medulloblastomas of Group 3 and Group 4, suggesting a role for [object Object]H3K27 methylation in these tumors. Indeed, trimethylated H3K27 (H3K27me3) levels [object Object]were shown to be higher in Group 3 and 4 tumors compared to WNT and SHH [object Object]medulloblastomas, also in tumors without detectable mutations in demethylases. [object Object]Here, we report that polycomb genes, required for H3K27 methylation, are [object Object]consistently upregulated in Group 3 and 4 tumors. These tumors show high [object Object]expression of the homeobox transcription factor OTX2. Silencing of OTX2 in D425 [object Object]medulloblastoma cells resulted in downregulation of polycomb genes such as EZH2, [object Object]EED, SUZ12 and RBBP4 and upregulation of H3K27 demethylases KDM6A, KDM6B, JARID2 [object Object]and KDM7A. This was accompanied by decreased H3K27me3 and increased H3K27me1 [object Object]levels in promoter regions. Strikingly, the decrease of H3K27me3 was most [object Object]prominent in promoters that bind OTX2. OTX2-bound promoters showe...
`What is the implication of histone lysine methylation in medulloblastoma?`	We used high-resolution SNP genotyping to identify regions of genomic gain and [object Object]loss in the genomes of 212 medulloblastomas, malignant pediatric brain tumors. [object Object]We found focal amplifications of 15 known oncogenes and focal deletions of 20 [object Object]known tumor suppressor genes (TSG), most not previously implicated in [object Object]medulloblastoma. Notably, we identified previously unknown amplifications and [object Object]homozygous deletions, including recurrent, mutually exclusive, highly focal [object Object]genetic events in genes targeting histone lysine methylation, particularly that [object Object]of histone 3, lysine 9 (H3K9). Post-translational modification of histone [object Object]proteins is critical for regulation of gene expression, can participate in [object Object]determination of stem cell fates and has been implicated in carcinogenesis. [object Object]Consistent with our genetic data, restoration of expression of genes controlling [object Object]H3K9 methylation greatly diminishes proliferation of medulloblastoma in vitro. [object Object]Copy number aberrations of genes with critical roles in writing...

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

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
num_train_epochs: 4
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
torch_empty_cache_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: 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: 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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
0.1264	10	65.1116	-	-	-	-	-
0.2528	20	52.0541	-	-	-	-	-
0.3791	30	36.0158	-	-	-	-	-
0.5055	40	26.0258	-	-	-	-	-
0.6319	50	24.2254	-	-	-	-	-
0.7583	60	21.8763	-	-	-	-	-
0.8847	70	18.0685	-	-	-	-	-
1.0	80	17.7443	0.7094	0.7054	0.6895	0.6487	0.5783
1.1264	90	14.5363	-	-	-	-	-
1.2528	100	14.1097	-	-	-	-	-
1.3791	110	13.5251	-	-	-	-	-
1.5055	120	13.3574	-	-	-	-	-
1.6319	130	13.3079	-	-	-	-	-
1.7583	140	12.926	-	-	-	-	-
1.8847	150	12.0388	-	-	-	-	-
2.0	160	10.9161	0.7063	0.7005	0.6880	0.6514	0.5886
2.1264	170	10.7059	-	-	-	-	-
2.2528	180	10.1178	-	-	-	-	-
2.3791	190	10.4664	-	-	-	-	-
2.5055	200	10.4824	-	-	-	-	-
2.6319	210	10.2784	-	-	-	-	-
2.7583	220	9.2031	-	-	-	-	-
2.8847	230	8.9788	-	-	-	-	-
3.0	240	7.5905	0.7027	0.6964	0.6855	0.6515	0.5881
3.1264	250	8.4637	-	-	-	-	-
3.2528	260	9.4921	-	-	-	-	-
3.3791	270	9.0615	-	-	-	-	-
3.5055	280	9.0181	-	-	-	-	-
3.6319	290	8.6193	-	-	-	-	-
3.7583	300	8.3741	-	-	-	-	-
3.8847	310	8.9504	-	-	-	-	-
4.0	320	7.4761	0.7037	0.6971	0.6857	0.652	0.5894

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.6
Sentence Transformers: 4.1.0
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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

bibtex

@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}
}

	anchor	positive
type	string	string
details	min: 6 tokens mean: 16.0 tokens max: 32 tokens	min: 4 tokens mean: 287.89 tokens max: 512 tokens