tomaarsen/bert-base-nq-prompts

BERT base trained on Natural Questions pairs

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased on the natural-questions dataset. 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.

This model was trained using the script from the Training with Prompts Sentence Transformers documentation.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: google-bert/bert-base-uncased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • natural-questions
• 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})
)

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("tomaarsen/bert-base-nq-prompts")
# Run inference
sentences = [
    'query: where does the last name francisco come from',
    'document: Francisco Francisco is the Spanish and Portuguese form of the masculine given name Franciscus (corresponding to English Francis).',
    'document: Book of Esther The Book of Esther, also known in Hebrew as "the Scroll" (Megillah), is a book in the third section (Ketuvim, "Writings") of the Jewish Tanakh (the Hebrew Bible) and in the Christian Old Testament. It is one of the five Scrolls (Megillot) in the Hebrew Bible. It relates the story of a Hebrew woman in Persia, born as Hadassah but known as Esther, who becomes queen of Persia and thwarts a genocide of her people. The story forms the core of the Jewish festival of Purim, during which it is read aloud twice: once in the evening and again the following morning. The books of Esther and Song of Songs are the only books in the Hebrew Bible that do not explicitly mention God.[2]',
]
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

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

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
cosine_accuracy@1	0.28	0.62	0.52	0.2	0.54	0.22	0.36	0.44	0.8	0.32	0.18	0.38	0.4694
cosine_accuracy@3	0.42	0.78	0.68	0.32	0.68	0.48	0.44	0.58	0.92	0.48	0.62	0.54	0.7755
cosine_accuracy@5	0.52	0.82	0.68	0.38	0.72	0.54	0.5	0.64	0.96	0.54	0.72	0.56	0.898
cosine_accuracy@10	0.6	0.92	0.78	0.44	0.8	0.72	0.58	0.72	0.98	0.64	0.86	0.6	0.9796
cosine_precision@1	0.28	0.62	0.52	0.2	0.54	0.22	0.36	0.44	0.8	0.32	0.18	0.38	0.4694
cosine_precision@3	0.1733	0.4867	0.2267	0.1267	0.2733	0.16	0.2733	0.1933	0.36	0.2333	0.2067	0.1933	0.4422
cosine_precision@5	0.136	0.436	0.136	0.112	0.192	0.108	0.204	0.128	0.232	0.196	0.144	0.124	0.4408
cosine_precision@10	0.08	0.408	0.082	0.07	0.114	0.072	0.174	0.074	0.132	0.15	0.086	0.068	0.3796
cosine_recall@1	0.1433	0.0654	0.51	0.1031	0.27	0.22	0.0244	0.43	0.704	0.0677	0.18	0.345	0.0364
cosine_recall@3	0.2283	0.1216	0.65	0.1607	0.41	0.48	0.0705	0.56	0.8687	0.1457	0.62	0.51	0.1028
cosine_recall@5	0.2757	0.1586	0.65	0.2197	0.48	0.54	0.0785	0.62	0.906	0.2027	0.72	0.54	0.1638
cosine_recall@10	0.3207	0.2691	0.77	0.2817	0.57	0.72	0.0938	0.7	0.9667	0.3097	0.86	0.585	0.2589
cosine_ndcg@10	0.2878	0.4934	0.633	0.2266	0.5034	0.4571	0.228	0.5664	0.8785	0.2843	0.5152	0.4802	0.42
cosine_mrr@10	0.3809	0.7205	0.5985	0.2786	0.6131	0.3756	0.4164	0.5322	0.862	0.4187	0.405	0.457	0.6389
cosine_map@100	0.2429	0.3576	0.5919	0.1922	0.4306	0.3858	0.0884	0.5288	0.845	0.2157	0.4131	0.4494	0.3258

Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with NanoBEIREvaluator

Metric	Value
cosine_accuracy@1	0.41
cosine_accuracy@3	0.5935
cosine_accuracy@5	0.6522
cosine_accuracy@10	0.74
cosine_precision@1	0.41
cosine_precision@3	0.2576
cosine_precision@5	0.1991
cosine_precision@10	0.1454
cosine_recall@1	0.2384
cosine_recall@3	0.3791
cosine_recall@5	0.4273
cosine_recall@10	0.5158
cosine_ndcg@10	0.4595
cosine_mrr@10	0.5152
cosine_map@100	0.3898

Training Details

Training Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 100,231 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 12 tokens mean: 13.74 tokens max: 26 tokens	min: 17 tokens mean: 139.2 tokens max: 510 tokens

• Samples:

  query	answer
  query: who is required to report according to the hmda	document: Home Mortgage Disclosure Act US financial institutions must report HMDA data to their regulator if they meet certain criteria, such as having assets above a specific threshold. The criteria is different for depository and non-depository institutions and are available on the FFIEC website.[4] In 2012, there were 7,400 institutions that reported a total of 18.7 million HMDA records.[5]
  query: what is the definition of endoplasmic reticulum in biology	document: Endoplasmic reticulum The endoplasmic reticulum (ER) is a type of organelle in eukaryotic cells that forms an interconnected network of flattened, membrane-enclosed sacs or tube-like structures known as cisternae. The membranes of the ER are continuous with the outer nuclear membrane. The endoplasmic reticulum occurs in most types of eukaryotic cells, but is absent from red blood cells and spermatozoa. There are two types of endoplasmic reticulum: rough and smooth. The outer (cytosolic) face of the rough endoplasmic reticulum is studded with ribosomes that are the sites of protein synthesis. The rough endoplasmic reticulum is especially prominent in cells such as hepatocytes. The smooth endoplasmic reticulum lacks ribosomes and functions in lipid manufacture and metabolism, the production of steroid hormones, and detoxification.[1] The smooth ER is especially abundant in mammalian liver and gonad cells. The lacy membranes of the endoplasmic reticulum were first seen in 1945 u...
  query: what does the ski mean in polish names	document: Polish name Since the High Middle Ages, Polish-sounding surnames ending with the masculine -ski suffix, including -cki and -dzki, and the corresponding feminine suffix -ska/-cka/-dzka were associated with the nobility (Polish szlachta), which alone, in the early years, had such suffix distinctions.[1] They are widely popular today.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 100,231 evaluation samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 12 tokens mean: 13.78 tokens max: 24 tokens	min: 13 tokens mean: 137.63 tokens max: 512 tokens

• Samples:

  query	answer
  query: difference between russian blue and british blue cat	document: Russian Blue The coat is known as a "double coat", with the undercoat being soft, downy and equal in length to the guard hairs, which are an even blue with silver tips. However, the tail may have a few very dull, almost unnoticeable stripes. The coat is described as thick, plush and soft to the touch. The feeling is softer than the softest silk. The silver tips give the coat a shimmering appearance. Its eyes are almost always a dark and vivid green. Any white patches of fur or yellow eyes in adulthood are seen as flaws in show cats.[3] Russian Blues should not be confused with British Blues (which are not a distinct breed, but rather a British Shorthair with a blue coat as the British Shorthair breed itself comes in a wide variety of colors and patterns), nor the Chartreux or Korat which are two other naturally occurring breeds of blue cats, although they have similar traits.
  query: who played the little girl on mrs doubtfire	document: Mara Wilson Mara Elizabeth Wilson[2] (born July 24, 1987) is an American writer and former child actress. She is known for playing Natalie Hillard in Mrs. Doubtfire (1993), Susan Walker in Miracle on 34th Street (1994), Matilda Wormwood in Matilda (1996) and Lily Stone in Thomas and the Magic Railroad (2000). Since retiring from film acting, Wilson has focused on writing.
  query: what year did the movie the sound of music come out	document: The Sound of Music (film) The film was released on March 2, 1965 in the United States, initially as a limited roadshow theatrical release. Although critical response to the film was widely mixed, the film was a major commercial success, becoming the number one box office movie after four weeks, and the highest-grossing film of 1965. By November 1966, The Sound of Music had become the highest-grossing film of all-time—surpassing Gone with the Wind—and held that distinction for five years. The film was just as popular throughout the world, breaking previous box-office records in twenty-nine countries. Following an initial theatrical release that lasted four and a half years, and two successful re-releases, the film sold 283 million admissions worldwide and earned a total worldwide gross of $286,000,000.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• prompts: {'query': 'query: ', 'answer': 'document: '}
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• 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: 1
• max_steps: -1
• lr_scheduler_type: linear
• 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: 12
• 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: None
• 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: False
• 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
• 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
• 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
• 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
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: {'query': 'query: ', 'answer': 'document: '}
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoClimateFEVER_cosine_ndcg@10	NanoDBPedia_cosine_ndcg@10	NanoFEVER_cosine_ndcg@10	NanoFiQA2018_cosine_ndcg@10	NanoHotpotQA_cosine_ndcg@10	NanoMSMARCO_cosine_ndcg@10	NanoNFCorpus_cosine_ndcg@10	NanoNQ_cosine_ndcg@10	NanoQuoraRetrieval_cosine_ndcg@10	NanoSCIDOCS_cosine_ndcg@10	NanoArguAna_cosine_ndcg@10	NanoSciFact_cosine_ndcg@10	NanoTouche2020_cosine_ndcg@10	NanoBEIR_mean_cosine_ndcg@10
0	0	-	-	0.1042	0.1641	0.1239	0.0397	0.2320	0.1682	0.0526	0.0678	0.7440	0.1153	0.2443	0.1516	0.1010	0.1776
0.0026	1	3.2174	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0129	5	3.2181	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0258	10	2.9101	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0387	15	2.2308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0515	20	1.5687	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0644	25	1.1955	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0773	30	0.9679	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0902	35	0.787	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1031	40	0.6266	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1160	45	0.4877	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1289	50	0.344	0.3217	0.2374	0.4663	0.6383	0.2397	0.4848	0.4183	0.2096	0.4839	0.8519	0.2619	0.4823	0.4781	0.4308	0.4372
0.1418	55	0.3294	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1546	60	0.2493	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1675	65	0.257	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1804	70	0.1839	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1933	75	0.2339	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2062	80	0.2095	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2191	85	0.2052	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2320	90	0.199	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2448	95	0.1867	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2577	100	0.1959	0.1771	0.2796	0.4858	0.6150	0.2331	0.4745	0.4345	0.2158	0.5154	0.8756	0.2827	0.5131	0.4839	0.4315	0.4493
0.2706	105	0.1759	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2835	110	0.1727	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2964	115	0.1773	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3093	120	0.1708	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3222	125	0.1881	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3351	130	0.1465	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3479	135	0.1583	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3608	140	0.1658	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3737	145	0.1547	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3866	150	0.1262	0.1482	0.2755	0.4955	0.6403	0.2358	0.4871	0.4548	0.2329	0.5372	0.8873	0.2821	0.5173	0.4658	0.4217	0.4564
0.3995	155	0.1522	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4124	160	0.1486	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4253	165	0.1277	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4381	170	0.1491	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4510	175	0.1308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4639	180	0.102	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4768	185	0.117	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4897	190	0.1748	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5026	195	0.1431	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5155	200	0.1684	0.1378	0.3042	0.4804	0.6335	0.2329	0.5004	0.4184	0.2284	0.5609	0.8885	0.2742	0.5192	0.4788	0.4193	0.4569
0.5284	205	0.1593	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5412	210	0.1331	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5541	215	0.1498	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5670	220	0.1467	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5799	225	0.139	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5928	230	0.1346	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6057	235	0.1738	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6186	240	0.146	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6314	245	0.1685	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6443	250	0.1327	0.1318	0.2967	0.4921	0.6348	0.2225	0.4917	0.4437	0.2301	0.5628	0.8889	0.2769	0.5166	0.4754	0.4135	0.4573
0.6572	255	0.1517	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6701	260	0.1521	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6830	265	0.1349	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6959	270	0.1127	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7088	275	0.1141	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7216	280	0.1273	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7345	285	0.1168	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7474	290	0.1223	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7603	295	0.1444	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7732	300	0.1153	0.1242	0.2892	0.4960	0.6431	0.2189	0.5059	0.4589	0.2280	0.5635	0.8784	0.2847	0.5048	0.4788	0.4157	0.4589
0.7861	305	0.1337	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7990	310	0.0992	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8119	315	0.1206	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8247	320	0.1272	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8376	325	0.1354	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8505	330	0.1298	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8634	335	0.1289	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8763	340	0.1291	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8892	345	0.1187	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9021	350	0.1173	0.1196	0.2891	0.4945	0.6421	0.2191	0.5113	0.4600	0.2289	0.5667	0.8785	0.2835	0.5134	0.4804	0.4201	0.4606
0.9149	355	0.1197	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9278	360	0.1257	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9407	365	0.1242	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9536	370	0.1479	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9665	375	0.1298	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9794	380	0.143	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9923	385	0.1026	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0	388	-	-	0.2878	0.4934	0.6330	0.2266	0.5034	0.4571	0.2280	0.5664	0.8785	0.2843	0.5152	0.4802	0.4200	0.4595

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.269 kWh
• Carbon Emitted: 0.104 kg of CO2
• Hours Used: 0.777 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 3.3.0.dev0
• Transformers: 4.46.2
• PyTorch: 2.5.0+cu121
• Accelerate: 1.0.0
• Datasets: 2.20.0
• Tokenizers: 0.20.3

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}