README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:499184
  - loss:MultipleNegativesRankingLoss
base_model: answerdotai/ModernBERT-large
widget:
  - source_sentence: how long will rotisserie chicken keep in refridgerator
    sentences:
      - >-
        1 Meats with gravy or sauces: 1 to 2 days refrigerator or 6 months
        (freezer). 2  Rotisserie chicken: 3 to 4 days (refrigerator) or 2 to 3
        months (freezer). 3  Opened package of hot dogs: 1 week (refrigerator)
        or 1 to 2 months (freezer).4  Opened package of deli meat: 3 to 4 days
        (refrigerator) or 1 to 2 months (freezer). Rotisserie chicken: 3 to 4
        days (refrigerator) or 2 to 3 months (freezer). 2  Opened package of hot
        dogs: 1 week (refrigerator) or 1 to 2 months (freezer). 3  Opened
        package of deli meat: 3 to 4 days (refrigerator) or 1 to 2 months
        (freezer).
      - >-
        Can Spinach Cause Constipation? Those who have problems with
        constipation will want to stay away from certain foods including
        spinach. Because spinach has so much fiber in it, it can cause
        constipation in some people, especially those who are already prone to
        it. Other foods which you will want to avoid if you problems with
        constipation include apples, peaches, raw carrots, zucchini, kidney
        beans, lima beans, and whole-grain cereal.
      - >-
        Brush the chickens with oil and season the outside and cavities with
        salt and pepper. Skewer the chickens onto the rotisserie rod and grill,
        on the rotisserie, for 30 to 35 minutes, or until the chicken is golden
        brown and just cooked through. Remove from grill and let rest for 10
        minutes before serving.
  - source_sentence: empyema causes
    sentences:
      - "Causes of an Empyema. Most cases of an empyema are related to bacterial pneumonia (infection of the lung). Pneumonia tends to cause a pleural effusion â\x80\x93 para-pneumonic effusion. This can be uncomplicated (containing exudate), complicated (exudate with high concentrations of neurophils) or empyema thoracis (pus in the pleural space)."
      - >-
        empyema - a collection of pus in a body cavity (especially in the lung
        cavity) inflammatory disease - a disease characterized by inflammation.
        purulent pleurisy - a collection of pus in the lung cavity.
        Translations.
      - >-
        Laminar Flow. The resistance to flow in a liquid can be characterized in
        terms of the viscosity of the fluid if the flow is smooth. In the case
        of a moving plate in a liquid, it is found that there is a layer or
        lamina which moves with the plate, and a layer which is essentially
        stationary if it is next to a stationary plate.
  - source_sentence: why is coal found in layers
    sentences:
      - >-
        Email the author | Follow on Twitter. on March 06, 2015 at 6:03 PM,
        updated March 06, 2015 at 6:35 PM. Comments. CLEVELAND, Ohio -- The
        first day of spring 2015 will be on March 20, with winter officially
        ending at 6:45 p.m. that day. Summer 2015 will begin on June 21, fall on
        Sept. 23 and winter on Dec. 21.
      - >-
        EXPERT ANSWER. Coal if formed when dead animals and plants got buried
        inside the layer of Earth. The layers increase form time to time and
        more dead plants and animals get buried in the layers.Therefore, coal is
        found in layers.For example, let us consider the layers of sandwich, on
        the first bread we apply the toppings and cover it another slice. Then
        some more topping is added to second slice and is covered by third
        slide.XPERT ANSWER. Coal if formed when dead animals and plants got
        buried inside the layer of Earth. The layers increase form time to time
        and more dead plants and animals get buried in the layers.
      - >-
        Why is Coal not classified as a Mineral? July 8, 2011, shiela, Leave a
        comment. Why is Coal not classified as a Mineral? Coal is not a mineral
        because it does not qualify to be one. A mineral is made of rocks. It is
        non-living and made up of atoms of elements. Coals on the other hand are
        carbon-based and came from fossilized plants. By just looking into the
        origin of coals, these are not qualified to be minerals because they
        come from organic material and it has no definite chemical composition.
        Minerals are not formed from living things such as plants or animals.
        They are building blocks of rocks and are formed thousands of years ago.
        Coals on the other hand came from dead plants and animals. The coals are
        formed when these living creatures will decay. Again, it takes thousands
        of years to form a coal.
  - source_sentence: where is the ford edge built
    sentences:
      - >-
        Amongst fruit-bearing cherry trees, there are two main types: Prunus
        avium (sweet cherries), which are the kind sold in produce sections for
        eating, and Prunus cerasus (sour cherries), which are the kind used in
        cooking and baking.mongst fruit-bearing cherry trees, there are two main
        types: Prunus avium (sweet cherries), which are the kind sold in produce
        sections for eating, and Prunus cerasus (sour cherries), which are the
        kind used in cooking and baking.
      - >-
        Ford is recalling 204,448 Edge and Lincoln MKX crossovers in North
        America for fuel-tank brackets that can rust and cause gas to leak, the
        automaker said.
      - >-
        Ford Edge to be built at new $760 million plant in China. DETROIT, MI -
        Ford Motor Co. announced Tuesday it has opened its sixth assembly plant
        in China, with a $760 million investment for the Changan Ford Hangzhou
        Plant.
  - source_sentence: what is a tensilon universal testing instrument
    sentences:
      - >-
        Universal Material Testing Instrument. The TENSILON RTF is our newest
        universal testing machine offering innovative measuring possibilities,
        based on A&D's newly-developed and extensive technological knowledge.The
        RTF Series is a world-class Class 0.5 testing machine.Having improved
        the overall design and structure of the machine, we achieved a very
        strong load frame stiffness enabling super-high accuracy in
        measurement.he RTF Series is a world-class Class 0.5 testing machine.
        Having improved the overall design and structure of the machine, we
        achieved a very strong load frame stiffness enabling super-high accuracy
        in measurement.
      - >-
        The term ectopic pregnancy frequently refers to a pregnancy that has
        occurred in one of the fallopian tubes, instead of the uterus. This is
        the case about 95 percent of the time, but ectopic pregnancies can also
        be abdominal, ovarian, cornual, or cervical.
      - >-
        The McDonald Patent Universal String Tension Calculator (MPUSTC) is a
        handy calculator to figure string tensions in steel-string instruments.
        If you plug in your scale length, string gauges and tuning, it will give
        you a readout of the tension on each of the strings. This is useful when
        you're trying to fine-tune a set of custom gauges, or when you're
        working out how far you can push a drop tuning before it becomes
        unmanageable.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
license: mit

SentenceTransformer based on answerdotai/ModernBERT-large

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-large. 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: answerdotai/ModernBERT-large
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

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: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'what is a tensilon universal testing instrument',
    "Universal Material Testing Instrument. The TENSILON RTF is our newest universal testing machine offering innovative measuring possibilities, based on A&D's newly-developed and extensive technological knowledge.The RTF Series is a world-class Class 0.5 testing machine.Having improved the overall design and structure of the machine, we achieved a very strong load frame stiffness enabling super-high accuracy in measurement.he RTF Series is a world-class Class 0.5 testing machine. Having improved the overall design and structure of the machine, we achieved a very strong load frame stiffness enabling super-high accuracy in measurement.",
    "The McDonald Patent Universal String Tension Calculator (MPUSTC) is a handy calculator to figure string tensions in steel-string instruments. If you plug in your scale length, string gauges and tuning, it will give you a readout of the tension on each of the strings. This is useful when you're trying to fine-tune a set of custom gauges, or when you're working out how far you can push a drop tuning before it becomes unmanageable.",
]
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]

Training Details

Training Dataset

Unnamed Dataset

• Size: 499,184 training samples
• Columns: sentence_0, sentence_1, and sentence_2
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  details	min: 4 tokens mean: 9.07 tokens max: 21 tokens	min: 17 tokens mean: 80.89 tokens max: 254 tokens	min: 20 tokens mean: 79.05 tokens max: 226 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  what is a dependent person	1. depending on a person or thing for aid, support, life, etc. 2. (postpositive; foll by on or upon) influenced or conditioned (by); contingent (on) 3. subordinate; subject: a dependent prince. 4. obsolete hanging down.	Dependent personality disorder (DPD) is one of the most frequently diagnosed personality disorders. It occurs equally in men and women, usually becoming apparent in young adulthood or later as important adult relationships form. People with DPD become emotionally dependent on other people and spend great effort trying to please others. People with DPD tend to display needy, passive, and clinging behavior, and have a fear of separation. Other common characteristics of this personality disorder include:
  what is the hat trick in hockey	Definition of hat trick. 1 1 : the retiring of three batsmen with three consecutive balls by a bowler in cricket. 2 2 : the scoring of three goals in one game (as of hockey or soccer) by a single player. 3 3 : a series of three victories, successes, or related accomplishments scored a hat trick when her three best steers corralled top honors — People.	Hat trick was first recorded in print in the 1870s, but has since been widened to apply to any sport in which the person competing carries off some feat three times in quick succession, such as scoring three goals in one game of soccer.
  what is an egalitarian	An egalitarian is defined as a person who believes all people were created equal and should be treated equal. An example of an egalitarian is a person who fights for civil rights, like Martin Luther King Jr.	About Egalitarian Companies. In the tradition hierarchical corporate structure, each employee operates under a specific job description. Each employee also reports to a superior who monitors his progress and issues instructions. Egalitarian-style companies eliminate most of this structure. Employees in an egalitarian company have general job descriptions, rather than specific ones. Instead of reporting to a superior, all employees in an egalitarian company work collaboratively on tasks and behave as equals.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 10
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: False
• fp16: True
• 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}
• tp_size: 0
• 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: 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
• 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: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0321	500	1.1178
0.0641	1000	0.293
0.0962	1500	0.2542
0.1282	2000	0.2357
0.1603	2500	0.2187
0.1923	3000	0.2107
0.2244	3500	0.1959
0.2564	4000	0.2049
0.2885	4500	0.1945
0.3205	5000	0.1848
0.3526	5500	0.1846
0.3846	6000	0.1736
0.4167	6500	0.1795
0.4487	7000	0.1767
0.4808	7500	0.1727
0.5128	8000	0.1688
0.5449	8500	0.1708
0.5769	9000	0.1663
0.6090	9500	0.1654
0.6410	10000	0.1637
0.6731	10500	0.1651
0.7051	11000	0.1625
0.7372	11500	0.1584
0.7692	12000	0.1607
0.8013	12500	0.156
0.8333	13000	0.1548
0.8654	13500	0.1484
0.8974	14000	0.1527
0.9295	14500	0.1555
0.9615	15000	0.1528
0.9936	15500	0.1533
1.0256	16000	0.0827
1.0577	16500	0.0597
1.0897	17000	0.0599
1.1218	17500	0.0592
1.1538	18000	0.0592
1.1859	18500	0.0584
1.2179	19000	0.0615
1.25	19500	0.0589
1.2821	20000	0.0612
1.3141	20500	0.0618
1.3462	21000	0.0606
1.3782	21500	0.0587
1.4103	22000	0.0611
1.4423	22500	0.0616
1.4744	23000	0.0623
1.5064	23500	0.0615
1.5385	24000	0.0602
1.5705	24500	0.0658
1.6026	25000	0.068
1.6346	25500	0.0649
1.6667	26000	0.0645
1.6987	26500	0.0652
1.7308	27000	0.0632
1.7628	27500	0.0631
1.7949	28000	0.0655
1.8269	28500	0.0633
1.8590	29000	0.0607
1.8910	29500	0.0633
1.9231	30000	0.0612
1.9551	30500	0.0631
1.9872	31000	0.0616
2.0192	31500	0.0382
2.0513	32000	0.0178
2.0833	32500	0.0177
2.1154	33000	0.0178
2.1474	33500	0.0171
2.1795	34000	0.0188
2.2115	34500	0.0186
2.2436	35000	0.0177
2.2756	35500	0.0183
2.3077	36000	0.0195
2.3397	36500	0.0202
2.3718	37000	0.0199
2.4038	37500	0.0197
2.4359	38000	0.019
2.4679	38500	0.021
2.5	39000	0.0195
2.5321	39500	0.0211
2.5641	40000	0.0205
2.5962	40500	0.0207
2.6282	41000	0.0222
2.6603	41500	0.0204
2.6923	42000	0.0205
2.7244	42500	0.0211
2.7564	43000	0.0232
2.7885	43500	0.0202
2.8205	44000	0.0207
2.8526	44500	0.0225
2.8846	45000	0.0224
2.9167	45500	0.0203
2.9487	46000	0.0215
2.9808	46500	0.0218
3.0128	47000	0.0159
3.0449	47500	0.0064
3.0769	48000	0.0069
3.1090	48500	0.0074
3.1410	49000	0.0075
3.1731	49500	0.0066
3.2051	50000	0.0076
3.2372	50500	0.0073
3.2692	51000	0.0077
3.3013	51500	0.0075
3.3333	52000	0.0079
3.3654	52500	0.008
3.3974	53000	0.0087
3.4295	53500	0.0077
3.4615	54000	0.0084
3.4936	54500	0.0086
3.5256	55000	0.009
3.5577	55500	0.0082
3.5897	56000	0.0084
3.6218	56500	0.0084
3.6538	57000	0.008
3.6859	57500	0.0079
3.7179	58000	0.0085
3.75	58500	0.0096
3.7821	59000	0.0087
3.8141	59500	0.0086
3.8462	60000	0.0089
3.8782	60500	0.0081
3.9103	61000	0.0087
3.9423	61500	0.0085
3.9744	62000	0.0082
4.0064	62500	0.0076
4.0385	63000	0.0037
4.0705	63500	0.0035
4.1026	64000	0.0037
4.1346	64500	0.004
4.1667	65000	0.0037
4.1987	65500	0.0036
4.2308	66000	0.0042
4.2628	66500	0.0044
4.2949	67000	0.0041
4.3269	67500	0.004
4.3590	68000	0.0037
4.3910	68500	0.0043
4.4231	69000	0.0035
4.4551	69500	0.0045
4.4872	70000	0.0042
4.5192	70500	0.0043
4.5513	71000	0.0042
4.5833	71500	0.0049
4.6154	72000	0.0041
4.6474	72500	0.0041
4.6795	73000	0.0044
4.7115	73500	0.0038
4.7436	74000	0.0039
4.7756	74500	0.0049
4.8077	75000	0.0041
4.8397	75500	0.0044
4.8718	76000	0.0043
4.9038	76500	0.0053
4.9359	77000	0.0043
4.9679	77500	0.0049
5.0	78000	0.0042
5.0321	78500	0.0022
5.0641	79000	0.0023
5.0962	79500	0.0021
5.1282	80000	0.003
5.1603	80500	0.0024
5.1923	81000	0.0022
5.2244	81500	0.0023
5.2564	82000	0.0022
5.2885	82500	0.0027
5.3205	83000	0.0023
5.3526	83500	0.0029
5.3846	84000	0.0027
5.4167	84500	0.0025
5.4487	85000	0.0029
5.4808	85500	0.0029
5.5128	86000	0.0024
5.5449	86500	0.0026
5.5769	87000	0.0026
5.6090	87500	0.0028
5.6410	88000	0.0025
5.6731	88500	0.0026
5.7051	89000	0.0023
5.7372	89500	0.0029
5.7692	90000	0.0027
5.8013	90500	0.0019
5.8333	91000	0.0023
5.8654	91500	0.0022
5.8974	92000	0.003
5.9295	92500	0.0023
5.9615	93000	0.0026
5.9936	93500	0.0027
6.0256	94000	0.0015
6.0577	94500	0.0012
6.0897	95000	0.0016
6.1218	95500	0.0018
6.1538	96000	0.0017
6.1859	96500	0.0014
6.2179	97000	0.0013
6.25	97500	0.0022
6.2821	98000	0.0015
6.3141	98500	0.002
6.3462	99000	0.0021
6.3782	99500	0.0016
6.4103	100000	0.0024
6.4423	100500	0.002
6.4744	101000	0.0014
6.5064	101500	0.0019
6.5385	102000	0.0017
6.5705	102500	0.0019
6.6026	103000	0.0016
6.6346	103500	0.0013
6.6667	104000	0.0012
6.6987	104500	0.0015
6.7308	105000	0.0015
6.7628	105500	0.0018
6.7949	106000	0.0018
6.8269	106500	0.0016
6.8590	107000	0.0018
6.8910	107500	0.0026
6.9231	108000	0.0013
6.9551	108500	0.0019
6.9872	109000	0.0015
7.0192	109500	0.0014
7.0513	110000	0.0009
7.0833	110500	0.0012
7.1154	111000	0.0016
7.1474	111500	0.0014
7.1795	112000	0.0013
7.2115	112500	0.0009
7.2436	113000	0.0015
7.2756	113500	0.0011
7.3077	114000	0.0011
7.3397	114500	0.0011
7.3718	115000	0.0013
7.4038	115500	0.001
7.4359	116000	0.0012
7.4679	116500	0.0012
7.5	117000	0.0013
7.5321	117500	0.0014
7.5641	118000	0.0013
7.5962	118500	0.0013
7.6282	119000	0.0014
7.6603	119500	0.001
7.6923	120000	0.0012
7.7244	120500	0.0018
7.7564	121000	0.001
7.7885	121500	0.0014
7.8205	122000	0.0011
7.8526	122500	0.0012
7.8846	123000	0.0012
7.9167	123500	0.0008
7.9487	124000	0.0013
7.9808	124500	0.0014
8.0128	125000	0.001
8.0449	125500	0.0007
8.0769	126000	0.001
8.1090	126500	0.0009
8.1410	127000	0.0007
8.1731	127500	0.0007
8.2051	128000	0.001
8.2372	128500	0.0011
8.2692	129000	0.0008
8.3013	129500	0.0007
8.3333	130000	0.0013
8.3654	130500	0.0012
8.3974	131000	0.001
8.4295	131500	0.001
8.4615	132000	0.0007
8.4936	132500	0.001
8.5256	133000	0.001
8.5577	133500	0.001
8.5897	134000	0.0011
8.6218	134500	0.0013
8.6538	135000	0.0007
8.6859	135500	0.001
8.7179	136000	0.0008
8.75	136500	0.001
8.7821	137000	0.0008
8.8141	137500	0.0006
8.8462	138000	0.0006
8.8782	138500	0.0009
8.9103	139000	0.0007
8.9423	139500	0.0009
8.9744	140000	0.0006
9.0064	140500	0.0018
9.0385	141000	0.0008
9.0705	141500	0.0008
9.1026	142000	0.0009
9.1346	142500	0.0006
9.1667	143000	0.0009
9.1987	143500	0.0007
9.2308	144000	0.0007
9.2628	144500	0.0006
9.2949	145000	0.0008
9.3269	145500	0.0009
9.3590	146000	0.0005
9.3910	146500	0.001
9.4231	147000	0.001
9.4551	147500	0.0011
9.4872	148000	0.0011
9.5192	148500	0.0012
9.5513	149000	0.0011
9.5833	149500	0.0007
9.6154	150000	0.0008
9.6474	150500	0.0005
9.6795	151000	0.0007
9.7115	151500	0.0008
9.7436	152000	0.0007
9.7756	152500	0.0009
9.8077	153000	0.0007
9.8397	153500	0.0012
9.8718	154000	0.0005
9.9038	154500	0.0008
9.9359	155000	0.0007
9.9679	155500	0.0007
10.0	156000	0.0011

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.50.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.2
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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",
}

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}
}