This is a sentence-transformers model finetuned from distilbert/distilbert-base-uncased on the msmarco dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: distilbert/distilbert-base-uncased
Maximum Sequence Length: 300 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Dot Product
Supported Modality: Text
Training Dataset:
- msmarco
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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'DistilBertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("kwondw/distilbert-base-uncased-msmarco-margin-mse-1000000")
# Run inference
queries = [
    'what is a dilated aorta',
]
documents = [
    'All about the Dilated Aorta. A dilated aorta is nothing to sneeze at; it is a serious condition that could result in death if left untreated. In fact, every year more than 10,000 Americans die from problems resulting from a dilated aorta.ymptoms of a Dilated Aorta. Although the vast majority of aneurysms donâ\x80\x99t present any symptoms until they rupture or lead to other severe problems, aneurysms can present certain signs. Abdominal aneurysms for example, will cause pain in the abdomen or numbness in the leg.',
    'Dilation is a medical term meaning that the internal diameter of something got larger. Like the pupils dilated or the cervix dilated. Mydriasis is dilation of the pupils. Ectasis is the medical term meaning dilation or expansion of a hollow organ. -ectasis is also the medical terminology combining form meaning dilation or expansion.',
    'Adj. 1. preceding-existing or coming before. antecedent-preceding in time or order. succeeding-coming after or following. previous-Preceding means occurring immediately before the time of the utterance, while previous means occurring at some time before the utterance..',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[88.0153, 81.6854, 63.3136]])

Evaluation

Metrics

Information Retrieval

Datasets: NanoClimateFEVER, NanoDBPedia, NanoFEVER, NanoFiQA2018, NanoHotpotQA, NanoMSMARCO, NanoNFCorpus, NanoNQ, NanoQuoraRetrieval, NanoSCIDOCS, NanoArguAna, NanoSciFact, NanoTouche2020, NanoMSMARCO, NanoNFCorpus and NanoNQ
Evaluated with InformationRetrievalEvaluator

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
dot_accuracy@1	0.22	0.68	0.7	0.3	0.74	0.32	0.38	0.38	0.82	0.32	0.08	0.32	0.6735
dot_accuracy@3	0.36	0.8	0.94	0.42	0.86	0.56	0.5	0.62	0.94	0.5	0.38	0.52	0.8571
dot_accuracy@5	0.46	0.84	0.96	0.52	0.9	0.64	0.56	0.72	0.94	0.64	0.46	0.56	0.898
dot_accuracy@10	0.64	0.92	0.98	0.64	0.96	0.82	0.62	0.76	0.98	0.72	0.54	0.6	1.0
dot_precision@1	0.22	0.68	0.7	0.3	0.74	0.32	0.38	0.38	0.82	0.32	0.08	0.32	0.6735
dot_precision@3	0.1267	0.52	0.3133	0.18	0.3733	0.1867	0.3267	0.2067	0.38	0.2267	0.1267	0.1867	0.5578
dot_precision@5	0.1	0.48	0.196	0.144	0.252	0.128	0.308	0.144	0.232	0.196	0.092	0.128	0.5224
dot_precision@10	0.08	0.434	0.104	0.088	0.14	0.082	0.228	0.076	0.124	0.128	0.054	0.068	0.4204
dot_recall@1	0.1167	0.0573	0.6567	0.161	0.37	0.32	0.0415	0.36	0.7207	0.065	0.08	0.295	0.0491
dot_recall@3	0.1657	0.1321	0.8867	0.2634	0.56	0.56	0.0731	0.58	0.8887	0.138	0.38	0.5	0.1172
dot_recall@5	0.2123	0.1892	0.9067	0.3614	0.63	0.64	0.0941	0.68	0.8927	0.2027	0.46	0.55	0.1795
dot_recall@10	0.3247	0.3039	0.9467	0.4534	0.7	0.82	0.1106	0.71	0.9493	0.2637	0.54	0.59	0.2723
dot_ndcg@10	0.2499	0.5309	0.8294	0.3433	0.657	0.5594	0.2891	0.5511	0.8815	0.256	0.3084	0.4543	0.4849
dot_mrr@10	0.3238	0.7583	0.8175	0.3876	0.8133	0.4776	0.4443	0.5184	0.884	0.4413	0.2338	0.4181	0.7798
dot_map@100	0.1869	0.3571	0.7778	0.2813	0.5714	0.4847	0.12	0.4994	0.8524	0.1837	0.2441	0.4158	0.3502

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with NanoBEIREvaluator with these parameters:
json
1{ 2 "dataset_names": [ 3 "climatefever", 4 "dbpedia", 5 "fever", 6 "fiqa2018", 7 "hotpotqa", 8 "msmarco", 9 "nfcorpus", 10 "nq", 11 "quoraretrieval", 12 "scidocs", 13 "arguana", 14 "scifact", 15 "touche2020" 16 ], 17 "dataset_id": "sentence-transformers/NanoBEIR-en" 18}

Metric	Value
dot_accuracy@1	0.4595
dot_accuracy@3	0.6367
dot_accuracy@5	0.7045
dot_accuracy@10	0.7862
dot_precision@1	0.4595
dot_precision@3	0.2865
dot_precision@5	0.2248
dot_precision@10	0.1565
dot_recall@1	0.2564
dot_recall@3	0.4065
dot_recall@5	0.4643
dot_recall@10	0.5388
dot_ndcg@10	0.4945
dot_mrr@10	0.5643
dot_map@100	0.4122

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with NanoBEIREvaluator with these parameters:
json
1{ 2 "dataset_names": [ 3 "msmarco", 4 "nfcorpus", 5 "nq" 6 ], 7 "dataset_id": "sentence-transformers/NanoBEIR-en" 8}

Metric	Value
dot_accuracy@1	0.36
dot_accuracy@3	0.56
dot_accuracy@5	0.64
dot_accuracy@10	0.7333
dot_precision@1	0.36
dot_precision@3	0.24
dot_precision@5	0.1933
dot_precision@10	0.1287
dot_recall@1	0.2405
dot_recall@3	0.4044
dot_recall@5	0.4714
dot_recall@10	0.5469
dot_ndcg@10	0.4665
dot_mrr@10	0.4801
dot_map@100	0.368

Training Details

Training Dataset

msmarco

Dataset: msmarco
Size: 1,000,000 training samples
Columns: score, query, positive, and negative

Approximate statistics based on the first 1000 samples:

	score	query	positive	negative
type	float	string	string	string
details	min: -1.45 mean: 13.32 max: 22.35	min: 4 tokens mean: 8.99 tokens max: 22 tokens	min: 19 tokens mean: 81.77 tokens max: 282 tokens	min: 20 tokens mean: 77.38 tokens max: 233 tokens

Samples:

score	query	positive	negative
`18.26768692334493`	`weisskopf syndrome`	`Dinno-Shearer-Weisskopf syndrome: Introduction. Dinno-Shearer-Weisskopf syndrome: A very rare syndrome characterized mainly by long limbs, tall stature, large head, ataxia and facial anomalies. More detailed information about the symptoms, causes, and treatments of Dinno-Shearer-Weisskopf syndrome is available below.`	`Related posts: 1 Charles Bonnet Syndrome - Treatment, Symptoms and Causes. 2 Refeeding Syndrome - Symptoms, Causes, Diagnosis, Treatment Guidelines. 3 Dubowitz Syndrome.`
`21.609440167744957`	`weather in beirut, lebanon`	`Beirut: Annual Weather Averages. August is the hottest month in Beirut with an average temperature of 28Â°C (82Â°F) and the coldest is February at 13Â°C (55Â°F) with the most daily sunshine hours at 14 in July. The wettest month is January with an average of 130mm of rain.`	`When Brant and his Mohawk warriors joined the fortunes. of the Johnson family in Canada, the influence of President. Whelock, of Lebanon Institute, where Brant had received his. early education, was brought to bear upon the crisis.`
`15.881475607554119`	`what are the clots in my period`	`Blood Clots during Period. It is normal to pass blood clots during menses, as along with the blood the thickened lining of the uterus is also being shed and expelled outside the body. In case the abnormal blood clots during period occur, visit your gynecologist as it may then be an indication of other serious medical illnesses.`	`Heparin lock flush is used for: Preventing blood clots from forming in intravenous (IV) lines or catheters. Heparin lock flush is an anticoagulant. It works by preventing blood clots from forming in intravenous lines when they are not in use. Do NOT use heparin lock flush if:`

Loss: MarginMSELoss with these parameters:
json
1{ 2 "similarity_fct": "pairwise_dot_score" 3}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 1
warmup_steps: 0.1
fp16: True

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-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: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0.1
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: True
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10
-1	-1	-	0.0287	0.1150	0.0609	0.0030	0.1216	0.0683	0.0357	0.0396	0.4537	0.0803	0.0655	0.0398	0.0380	0.0885
0.0100	157	125.0139	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0201	314	57.8215	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0301	471	37.5933	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0402	628	32.1223	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0502	785	28.5499	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0603	942	26.6565	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0703	1099	25.4484	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0804	1256	25.0233	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0904	1413	24.8356	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1000	1563	-	-	-	-	-	-	0.4934	0.2385	0.4696	-	-	-	-	-	0.4005
0.1005	1570	23.6095	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1105	1727	23.4501	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1206	1884	22.9823	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1306	2041	22.2927	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1407	2198	21.5744	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1507	2355	20.5316	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1608	2512	20.3872	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1708	2669	20.2891	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1809	2826	19.6792	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1909	2983	19.5291	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2001	3126	-	-	-	-	-	-	0.5066	0.2273	0.5615	-	-	-	-	-	0.4318
0.2010	3140	19.1046	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2110	3297	19.1824	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2211	3454	18.6768	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2311	3611	18.7842	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2412	3768	18.5221	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2512	3925	17.8466	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2612	4082	17.6848	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2713	4239	17.0217	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2813	4396	17.2403	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2914	4553	17.0281	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3001	4689	-	-	-	-	-	-	0.4878	0.2428	0.5579	-	-	-	-	-	0.4295
0.3014	4710	16.7359	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3115	4867	16.7857	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3215	5024	16.5008	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3316	5181	16.1776	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3416	5338	15.8373	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3517	5495	15.6419	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3617	5652	15.7686	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3718	5809	15.6115	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3818	5966	15.1947	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3919	6123	15.1458	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4001	6252	-	-	-	-	-	-	0.5167	0.2677	0.5432	-	-	-	-	-	0.4425
0.4019	6280	14.8312	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4120	6437	15.2316	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4220	6594	14.7763	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4321	6751	14.3289	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4421	6908	14.0054	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4522	7065	14.1846	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4622	7222	14.5495	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4723	7379	14.0617	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4823	7536	14.2223	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4924	7693	14.0808	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5002	7815	-	-	-	-	-	-	0.5205	0.2669	0.5379	-	-	-	-	-	0.4418
0.5024	7850	13.9463	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5124	8007	13.8219	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5225	8164	13.7626	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5325	8321	13.5244	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5426	8478	13.4886	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5526	8635	13.1473	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5627	8792	13.1645	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5727	8949	13.2830	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5828	9106	13.0105	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5928	9263	13.2103	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6002	9378	-	-	-	-	-	-	0.5733	0.2699	0.4915	-	-	-	-	-	0.4449
0.6029	9420	12.8509	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6129	9577	12.4861	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6230	9734	12.5345	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6330	9891	12.4092	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6431	10048	12.3442	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6531	10205	12.0587	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6632	10362	12.1469	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6732	10519	11.8134	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6833	10676	12.0869	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6933	10833	12.2764	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7002	10941	-	-	-	-	-	-	0.5573	0.2921	0.5426	-	-	-	-	-	0.4640
0.7034	10990	12.0590	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7134	11147	11.9389	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7235	11304	11.6815	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7335	11461	11.8178	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7436	11618	11.7649	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7536	11775	11.6105	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7636	11932	11.4717	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7737	12089	11.6274	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7837	12246	11.1198	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7938	12403	11.4835	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8003	12504	-	-	-	-	-	-	0.5822	0.2952	0.5524	-	-	-	-	-	0.4766
0.8038	12560	11.4060	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8139	12717	11.1658	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8239	12874	11.5364	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8340	13031	11.2028	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8440	13188	11.1378	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8541	13345	11.0250	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8641	13502	10.9993	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8742	13659	11.1054	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8842	13816	11.3049	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8943	13973	10.9286	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9003	14067	-	-	-	-	-	-	0.5594	0.2891	0.5511	-	-	-	-	-	0.4665
0.9043	14130	10.7830	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9144	14287	10.8300	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9244	14444	10.8568	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9345	14601	10.8062	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9445	14758	10.2965	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9546	14915	10.6109	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9646	15072	10.4024	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9747	15229	10.7121	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9847	15386	10.8008	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9948	15543	10.5087	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	0.2499	0.5309	0.8294	0.3433	0.6570	0.5834	0.2929	0.5567	0.8815	0.2560	0.3084	0.4543	0.4849	0.4945

Training Time

Training: 1.5 hours
Evaluation: 2.2 minutes
Total: 1.5 hours

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 5.0.0
Tokenizers: 0.22.2

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",
}

MarginMSELoss

bibtex

@misc{hofstätter2021improving,
    title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
    author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
    year={2021},
    eprint={2010.02666},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}