tomaarsen/multivector-ModernBERT-base-msmarco-contrastive

ColBERT ModernBERT-base trained on MS MARCO triplets

This is a Multi-Vector Encoder model finetuned from answerdotai/ModernBERT-base on the msmarco-bm25 dataset using the sentence-transformers library. It maps inputs to sequences of 128-dimensional token-level vectors and scores them with late interaction (MaxSim), useful for semantic search with late interaction.

Model Details

Model Description

• Model Type: Multi-Vector Encoder
• Base model: answerdotai/ModernBERT-base
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 128 dimensions
• Similarity Function: maxsim
• Supported Modality: Text
• Training Dataset:
  • msmarco-bm25
• Language: en
• License: apache-2.0

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Multi-Vector Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Multi-Vector Encoders on Hugging Face

Full Model Architecture

MultiVectorEncoder(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'query_expansion': {'strategy': 'min', 'attend': False, 'token': None, 'length': 32}, 'architecture': 'ModernBertModel'})
  (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
  (2): MultiVectorMask({'skiplist_words': [], 'keep_only_token_ids': None})
  (3): Normalize({'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
)

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 MultiVectorEncoder

# Download from the 🤗 Hub
model = MultiVectorEncoder("tomaarsen/multivector-ModernBERT-base-msmarco")
# Run inference: each input becomes a sequence of per-token vectors (variable length).
queries = [
    'what does marijuana cost per joint',
]
documents = [
    'With a 50-50 ratio of marijuana to tobacco, the cost of producing a pack of 20 pre-rolled joints could be brought down to just a little more than $20â\x80\x94so a $40 pack at the store. It isnâ\x80\x99t as easy as it seems, though. The government has a vested interest in producing income from the selling of marijuana.nother solution: mix the marijuana with tobacco. If marijuana cigarettes were to be mixed with tobacco, at a 50-50 ratio, it would bring the cost down significantly. Many tobacco farmers will wholesale a pound of their product for less than $2.',
    'What does a dime,dub,eigth,quarter,and a zip of marijuana look like and cost?',
    'In January of 1980, residents decided to incorporate by an overwhelming margin. The Town of Farragut was incorporated on January 16, 1980, with the first board of Mayor and Alderman elected on April 1, 1980.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (32, 128) (129, 128)

# Get the MaxSim similarity scores
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[24.6630, 18.9976,  9.6529]])

Evaluation

Metrics

Multi Vector Information Retrieval

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

Metric	NanoMSMARCO	NanoNQ	NanoFiQA2018	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoHotpotQA	NanoNFCorpus	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
maxsim_accuracy@1	0.24	0.4	0.26	0.2	0.54	0.66	0.78	0.38	0.88	0.34	0.08	0.5	0.4898
maxsim_accuracy@3	0.44	0.58	0.42	0.38	0.76	0.88	0.9	0.38	0.94	0.58	0.4	0.66	0.6531
maxsim_accuracy@5	0.5	0.62	0.5	0.5	0.8	0.92	0.9	0.46	0.98	0.7	0.44	0.68	0.7551
maxsim_accuracy@10	0.68	0.68	0.58	0.58	0.82	0.98	0.96	0.54	0.98	0.76	0.54	0.74	0.9184
maxsim_precision@1	0.24	0.4	0.26	0.2	0.54	0.66	0.78	0.38	0.88	0.34	0.08	0.5	0.4898
maxsim_precision@3	0.1467	0.1933	0.22	0.1533	0.4467	0.3	0.4067	0.28	0.38	0.2533	0.1333	0.2333	0.4422
maxsim_precision@5	0.1	0.128	0.156	0.116	0.432	0.192	0.26	0.288	0.244	0.232	0.088	0.148	0.4449
maxsim_precision@10	0.068	0.072	0.094	0.076	0.366	0.102	0.148	0.206	0.126	0.14	0.054	0.084	0.3837
maxsim_recall@1	0.24	0.36	0.1144	0.075	0.0944	0.63	0.39	0.0225	0.7707	0.0717	0.08	0.475	0.0397
maxsim_recall@3	0.44	0.52	0.2988	0.175	0.1441	0.84	0.61	0.0464	0.9087	0.1567	0.4	0.65	0.1074
maxsim_recall@5	0.5	0.57	0.3593	0.2073	0.1835	0.89	0.65	0.0695	0.946	0.2397	0.44	0.675	0.1734
maxsim_recall@10	0.68	0.64	0.424	0.264	0.255	0.95	0.74	0.1088	0.9527	0.2877	0.54	0.74	0.2789
maxsim_ndcg@10	0.4402	0.5113	0.3248	0.2202	0.4674	0.8037	0.6954	0.2565	0.9141	0.2823	0.3199	0.6161	0.4284
maxsim_mrr@10	0.3661	0.4976	0.3581	0.3192	0.6592	0.7737	0.8424	0.4087	0.919	0.48	0.2487	0.5779	0.6056
maxsim_map@100	0.3813	0.4707	0.2696	0.1697	0.3728	0.7486	0.6149	0.1015	0.8956	0.2099	0.2618	0.5797	0.3786

Multi Vector Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with MultiVectorNanoBEIREvaluator with these parameters:

  {
      "dataset_names": [
          "msmarco",
          "nq",
          "fiqa2018"
      ],
      "dataset_id": "sentence-transformers/NanoBEIR-en"
  }
  

Metric	Value
maxsim_accuracy@1	0.2733
maxsim_accuracy@3	0.42
maxsim_accuracy@5	0.5133
maxsim_accuracy@10	0.66
maxsim_precision@1	0.2733
maxsim_precision@3	0.16
maxsim_precision@5	0.1173
maxsim_precision@10	0.076
maxsim_recall@1	0.2177
maxsim_recall@3	0.3769
maxsim_recall@5	0.4572
maxsim_recall@10	0.5778
maxsim_ndcg@10	0.4047
maxsim_mrr@10	0.3809
maxsim_map@100	0.3492

Multi Vector Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with MultiVectorNanoBEIREvaluator with these parameters:

  {
      "dataset_names": [
          "climatefever",
          "dbpedia",
          "fever",
          "fiqa2018",
          "hotpotqa",
          "msmarco",
          "nfcorpus",
          "nq",
          "quoraretrieval",
          "scidocs",
          "arguana",
          "scifact",
          "touche2020"
      ],
      "dataset_id": "sentence-transformers/NanoBEIR-en"
  }
  

Metric	Value
maxsim_accuracy@1	0.4423
maxsim_accuracy@3	0.6133
maxsim_accuracy@5	0.6735
maxsim_accuracy@10	0.7506
maxsim_precision@1	0.4423
maxsim_precision@3	0.2761
maxsim_precision@5	0.2176
maxsim_precision@10	0.1477
maxsim_recall@1	0.2587
maxsim_recall@3	0.4075
maxsim_recall@5	0.4541
maxsim_recall@10	0.5278
maxsim_ndcg@10	0.4831
maxsim_mrr@10	0.5428
maxsim_map@100	0.4196

Training Details

Training Dataset

msmarco-bm25

• Dataset: msmarco-bm25 at ce8a493
• Size: 50,000 training samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 100 samples:

  	query	positive	negative
  type	string	string	string
  modality	text	text	text
  details	min: 5 tokens mean: 9.2 tokens max: 23 tokens	min: 24 tokens mean: 85.21 tokens max: 234 tokens	min: 24 tokens mean: 78.79 tokens max: 189 tokens

• Samples:

  query	positive	negative
  how many days to renew philippine passport to usa	The United States requires non-citizens to keep a foreign passport that is valid for six months beyond their date of departure. If you are in the United States legally, then you can renew your Philippine passport at the consulate general's office in Los Angeles.	How much does it cost to renew a Philippines passport? Philippine Passport Fees for Renewal is P 950 for 15 working days and 1,200 for 7 working days. This is according to the Department of Freign Affairs website.
  which sexually transmitted diseases can lead to infections inside joint spaces?	Gonorrhea is a sexually transmitted disease (STD) that can infect both men and women. It can cause infections in the genitals, rectum, and throat.It is a very common infection, especially among young people ages 15-24 years.omen with gonorrhea are at risk of developing serious complications from the infection, even if they don’t have any symptoms. Symptoms in women can include: 1 Painful or burning sensation when urinating; 2 Increased vaginal discharge; 3 Vaginal bleeding between periods.	STDs and Infertility. Sexually transmitted diseases, STDs, also called sexually transmitted infections or STIs, can cause immediate, annoying symptoms with long-lasting, serious repercussions. Few people realize that these sexually transmitted diseases can cause damage that may eventually lead to infertility.
  when was eviva amore constructed	Nasher Sculpture Center Press Images Back of the garden, Nasher Sculpture Center; photo by Tim Hursley. Mark di Suvero, Eviva Amore, 2001 in gardens of Nasher Sculpture Center; photo by Tim Hursley. Jaume Plensa, The Long Night (From Ausias March to Vincent Andres Andrés) , estelles, estellés 2007 At Nasher; sculpture center Photo By. tim hursley	Richard Serra, My Curves Are Not Mad, 1987 and Augustus Rodin, Eve, 1881 (cast before 1932) at Nasher Sculpture Center; photo by Tim Hursley. Mark di Suvero, Eviva Amore, 2001 at dusk in gardens of Nasher Sculpture Center; photo by Tim Hursley. Jeremy Strick, Director of the Nasher Sculpture.

• Loss: MultiVectorMultipleNegativesRankingLoss with these parameters:

  {
      "score_metric": "colbert_scores",
      "scale": 1.0,
      "score_mini_batch_size": null,
      "size_average": true,
      "gather_across_devices": false
  }
  

Evaluation Dataset

msmarco-bm25

• Dataset: msmarco-bm25 at ce8a493
• Size: 1,000 evaluation samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 100 samples:

  	query	positive	negative
  type	string	string	string
  modality	text	text	text
  details	min: 4 tokens mean: 9.15 tokens max: 19 tokens	min: 39 tokens mean: 82.03 tokens max: 199 tokens	min: 27 tokens mean: 81.62 tokens max: 157 tokens

• Samples:

  query	positive	negative
  what is chor means	• CHORE (noun) The noun CHORE has 1 sense: 1. a specific piece of work required to be done as a duty or for a specific fee. Familiarity information: CHORE used as a noun is very rare.	Any two different languages and not just English and other language. Example 1. Chore (pronounced as cHor) means 'a routine task' in English language. Whereas Chor {चोर} (also pronounced as CHor) means a thief or a burglar in both Hindi and Marathi language.
  how is gravity measured	The gravity of Earth, which is denoted by g, refers to the acceleration that the Earth imparts to objects on or near its surface due to gravity. In SI units this acceleration is measured in metres per second squared (in symbols, m/s2 or m·s−2) or equivalently in newtons per kilogram (N/kg or N·kg−1).	When the wort is first added to the yeast, the specific gravity of the mixture is measured. Later, the specific gravity may be measured again to determine how much alcohol is in the beer, and to know when to stop the fermentation.hen the wort is first added to the yeast, the specific gravity of the mixture is measured. Later, the specific gravity may be measured again to determine how much alcohol is in the beer, and to know when to stop the fermentation.
  salary of doctor during fellowship	Average fellowship salary and wage. The median expected salary for a Fellowship physician in the United States averages to about $150,353 per annum and an average hourly wage is around $20 per hour. fellowship physician in USA receives an average yearly salary ranging from between $34,225 – $59,542. In addition, a yearly bonus of around $4,888 will be included as part of the annual salary package.	Medical Fellowship Salary. Medical Fellowship average salary is $55,008, median salary is $- with a salary range from $- to $-.Medical Fellowship salaries are collected from government agencies and companies. Each salary is associated with a real job position.Medical Fellowship salary statistics is not exclusive and is for reference only.They are presented as is and updated regularly.edical Fellowship salaries are collected from government agencies and companies. Each salary is associated with a real job position. Medical Fellowship salary statistics is not exclusive and is for reference only. They are presented as is and updated regularly.

• Loss: MultiVectorMultipleNegativesRankingLoss with these parameters:

  {
      "score_metric": "colbert_scores",
      "scale": 1.0,
      "score_mini_batch_size": null,
      "size_average": true,
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• num_train_epochs: 1
• learning_rate: 3e-05
• warmup_steps: 0.05
• bf16: True
• per_device_eval_batch_size: 32
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• per_device_train_batch_size: 32
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 3e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.05
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 32
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: True
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: 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
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}
• max_length: None

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_maxsim_ndcg@10	NanoNQ_maxsim_ndcg@10	NanoFiQA2018_maxsim_ndcg@10	NanoBEIR_mean_maxsim_ndcg@10	NanoClimateFEVER_maxsim_ndcg@10	NanoDBPedia_maxsim_ndcg@10	NanoFEVER_maxsim_ndcg@10	NanoHotpotQA_maxsim_ndcg@10	NanoNFCorpus_maxsim_ndcg@10	NanoQuoraRetrieval_maxsim_ndcg@10	NanoSCIDOCS_maxsim_ndcg@10	NanoArguAna_maxsim_ndcg@10	NanoSciFact_maxsim_ndcg@10	NanoTouche2020_maxsim_ndcg@10
-1	-1	-	-	0.1303	0.1511	0.1199	0.1338	-	-	-	-	-	-	-	-	-	-
0.0102	16	3.6732	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0205	32	3.0244	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0307	48	1.5109	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0409	64	1.1722	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0512	80	0.9115	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0614	96	0.7757	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0717	112	0.7379	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0819	128	0.6656	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0921	144	0.6483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1004	157	-	0.5983	0.3333	0.4185	0.3137	0.3552	-	-	-	-	-	-	-	-	-	-
0.1024	160	0.6068	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1126	176	0.5612	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1228	192	0.5895	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1331	208	0.5259	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1433	224	0.5220	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1536	240	0.5796	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1638	256	0.5323	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1740	272	0.4822	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1843	288	0.4744	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1945	304	0.4783	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2009	314	-	0.4760	0.3674	0.4583	0.3000	0.3752	-	-	-	-	-	-	-	-	-	-
0.2047	320	0.4934	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2150	336	0.5239	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2252	352	0.4966	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2354	368	0.4654	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2457	384	0.4376	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2559	400	0.4111	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2662	416	0.4436	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2764	432	0.4264	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2866	448	0.4314	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2969	464	0.4734	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3013	471	-	0.4415	0.4402	0.5113	0.3248	0.4254	-	-	-	-	-	-	-	-	-	-
0.3071	480	0.4472	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3173	496	0.4224	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3276	512	0.4314	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3378	528	0.4672	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3480	544	0.4412	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3583	560	0.4373	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3685	576	0.4138	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3788	592	0.4166	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3890	608	0.3813	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3992	624	0.4356	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4018	628	-	0.4192	0.3871	0.4032	0.3164	0.3689	-	-	-	-	-	-	-	-	-	-
0.4095	640	0.4481	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4197	656	0.4175	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4299	672	0.4030	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4402	688	0.4001	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4504	704	0.3959	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4607	720	0.3671	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4709	736	0.3704	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4811	752	0.4485	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4914	768	0.3961	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5016	784	0.3745	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5022	785	-	0.4021	0.4256	0.4600	0.3332	0.4063	-	-	-	-	-	-	-	-	-	-
0.5118	800	0.4706	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5221	816	0.3739	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5323	832	0.4585	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5425	848	0.4443	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5528	864	0.3540	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5630	880	0.4194	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5733	896	0.3575	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5835	912	0.3704	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5937	928	0.4418	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6027	942	-	0.3917	0.4215	0.4744	0.3221	0.4060	-	-	-	-	-	-	-	-	-	-
0.6040	944	0.3390	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6142	960	0.3696	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6244	976	0.3890	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6347	992	0.4109	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6449	1008	0.3243	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6552	1024	0.3245	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6654	1040	0.3633	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6756	1056	0.3689	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6859	1072	0.3683	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6961	1088	0.3132	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7031	1099	-	0.3703	0.4057	0.4874	0.3386	0.4106	-	-	-	-	-	-	-	-	-	-
0.7063	1104	0.4024	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7166	1120	0.3044	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7268	1136	0.3814	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7370	1152	0.3438	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7473	1168	0.3330	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7575	1184	0.3761	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7678	1200	0.3380	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7780	1216	0.3873	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7882	1232	0.4262	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7985	1248	0.3443	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8036	1256	-	0.3499	0.4139	0.4803	0.3418	0.4120	-	-	-	-	-	-	-	-	-	-
0.8087	1264	0.3796	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8189	1280	0.4014	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8292	1296	0.3196	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8394	1312	0.3576	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8496	1328	0.3573	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8599	1344	0.3175	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8701	1360	0.3311	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8804	1376	0.3436	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8906	1392	0.3588	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9008	1408	0.3525	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9040	1413	-	0.3515	0.4252	0.4629	0.3273	0.4051	-	-	-	-	-	-	-	-	-	-
0.9111	1424	0.3312	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9213	1440	0.3827	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9315	1456	0.3467	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9418	1472	0.3310	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9520	1488	0.3676	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9623	1504	0.3966	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9725	1520	0.3184	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9827	1536	0.3871	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9930	1552	0.3543	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0	1563	-	0.3474	0.4194	0.4618	0.3329	0.4047	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.4402	0.5113	0.3248	0.4831	0.2202	0.4674	0.8037	0.6954	0.2565	0.9141	0.2823	0.3199	0.6161	0.4284

• The bold row denotes the saved checkpoint.

Training Time

• Training: 13.6 minutes
• Evaluation: 5.1 minutes
• Total: 18.7 minutes

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.7.0.dev0
• Transformers: 5.14.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.5.2
• Datasets: 3.5.0
• Tokenizers: 0.22.2

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",
}

MultiVectorMultipleNegativesRankingLoss

@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}
}