metadata

base_model: jinaai/jina-embeddings-v3
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:498970
  - loss:BPRLoss
widget:
  - source_sentence: meaning of the prefix em
    sentences:
      - >-
        Word Origin and History for em- Expand. from French assimilation of en-
        to following labial (see en- (1)). Also a prefix used to form verbs from
        adjectives and nouns. representing Latin ex- assimilated to following
        -m- (see ex-).
      - >-
        Hawaii: Aloha! Whether you are hoping to travel to Hawaii for a tropical
        green Christmas or you are hoping to make this island paradise your
        home, we can help you find the information you need! The state of
        Hawaii, located in the middle of the Pacific Ocean, is farther away from
        any other landmass than any other island on the earth.
      - >-
        Prefixes: Un, Dis, Im, Mis. A prefix is placed at the beginning of a
        word to change its meaning. For example, the suffix re- means either
        again or back as in return, repeat or refurbish. The following 4
        prefixes are easy to confuse because they all have a negative meaning.
        un-.
  - source_sentence: how long does engine take to cool down
    sentences:
      - >-
        It takes roughly 30 minutes for the laptop to cool down to a normal
        state.Or if you want to use it soon it could take I guess 10-15 minutes.
      - "Turn off the engine. If you can pop the hood from the driverâ\x80\x99s seat, do so â\x80\x94 but donâ\x80\x99t risk opening it by hand until the engine has cooled, especially if you see steam wafting off the engine. It typically takes a solid 30 minutes for an engine to cool down enough for it to be safe to handle."
      - >-
        Zeppelin was invented in 1900 by a military officer of German origin
        named Count Ferdinand von Zeppelin.It was a stiff framed airship, LZ-I
        that flew on 2nd July, 1900 carrying five passengers near Lake Constance
        in Germany. Zeppelins were used in the times of peace as well as
        war.eppelin was invented in 1900 by a military officer of German origin
        named Count Ferdinand von Zeppelin.
  - source_sentence: how long does it take to get an undergraduate
    sentences:
      - >-
        How Long Does It Take To Become a Nurse Anesthetist (CRNA)? How Long
        Does It Take To Become a Nurse Practitioner? How Long Does It Take To
        Become a Nutritionist? How Long Does It Take To Become A Pharmacist? How
        Long Does It Take To Become a Physician Assistant? How Long Does It Take
        To Become a Social Worker? (ANSWERED) How Long Does It Take To Become a
        Vet Tech? How Long Does It Take To Become An LPN? How Long Does It Take
        To Become an OB/GYN? How Long Does It Take To Become an Ultrasound
        Technician? How Long Does It Take To Get a Medical Degree? How Long Does
        It Take To Get a Nursing Degree? Your first stepping stone toward a
        rewarding nursing career is completing the education and becoming
        registered. Ill answer the age old question about how long it takes to
        get a registered nursing degree.
      - >-
        A depositary receipt (DR) is a type of negotiable (transferable)
        financial security that is traded on a local stock exchange but
        represents a security, usually in the form of equity, that is issued by
        a foreign publicly listed company. U.S. broker may also sell ADRs back
        into the local Russian market. This is known as cross-border trading.
        When this happens, an amount of ADRs is canceled by the depository and
        the local shares are released from the custodian bank and delivered back
        to the Russian broker who bought them.
      - >-
        Undergraduate Studies. To become a doctor, a student must first complete
        high school, then go on to college. During the typical four-year
        undergraduate period, the aspiring doctor will study topics such as
        anatomy, physiology, biology, chemistry and other college courses
        necessary for a degree, such as English or math.
  - source_sentence: fees definition
    sentences:
      - >-
        fees. 1  veterinarians' charges rendered to clients for services. 2 
        Justifiable professional fees are based on the amount of time spent on
        the case, with a varying fee per hour depending on the difficulty and
        complexity of the problem, and on the specialist superiority of the
        veterinarian.
      - >-
        Summary: The Catbird Seat by James Thurber is about Mr. Martin who has
        decided he must kill Mrs Barrows because she is destroying the firm he
        works for, but in the end he tricks his boss into thinking she has had a
        mental breakdown.
      - >-
        Cost, in common usage, the monetary value of goods and services that
        producers and consumers purchase. In a basic economic sense, cost is the
        measure of the alternative opportunities foregone in the choice of one
        good or activity over others.
  - source_sentence: what is a fermentation lock used for
    sentences:
      - "Remember, fermentation is a method of preserving food. Leaving it on your counter gives it more time for the LAB activity to increase â\x80\x94 which, in turn, lowers pH â\x80\x94 and prevents spoilage. As long as your jar can keep out the oxygen, you shouldnâ\x80\x99t be worried. Which leads me toâ\x80¦."
      - >-
        The fermentation lock or airlock is a device used in beer brewing and
        wine making that allows carbon dioxide released by the beer to escape
        the fermenter, while not allowing air to enter the fermenter, thus
        avoiding oxidation. There are two main designs for the fermentation
        lock, or airlock.
      - >-
        The New River is formed by the confluence of the South Fork New River
        and the North Fork New River in Ashe County, North Carolina. It then
        flows north into southwestern Virginia, passing near Galax, Virginia and
        through a gorge in the Iron Mountains. Continuing north, the river
        enters Pulaski County, Virginia, where it is impounded by Claytor Dam,
        creating Claytor Lake.

SentenceTransformer based on jinaai/jina-embeddings-v3

This is a sentence-transformers model finetuned from jinaai/jina-embeddings-v3. 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

Finetuned from jinaai/jina-embeddings-v3 (trained with msmarco-v3 dataset).

Model Description

Model Type: Sentence Transformer
Base model: jinaai/jina-embeddings-v3
Maximum Sequence Length: 8194 tokens
Output Dimensionality: 1024 tokens
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(
  (transformer): Transformer(
    (auto_model): XLMRobertaLoRA(
      (roberta): XLMRobertaModel(
        (embeddings): XLMRobertaEmbeddings(
          (word_embeddings): ParametrizedEmbedding(
            250002, 1024, padding_idx=1
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
          (token_type_embeddings): ParametrizedEmbedding(
            1, 1024
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
        )
        (emb_drop): Dropout(p=0.1, inplace=False)
        (emb_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        (encoder): XLMRobertaEncoder(
          (layers): ModuleList(
            (0-23): 24 x Block(
              (mixer): MHA(
                (rotary_emb): RotaryEmbedding()
                (Wqkv): ParametrizedLinearResidual(
                  in_features=1024, out_features=3072, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
                (inner_attn): FlashSelfAttention(
                  (drop): Dropout(p=0.1, inplace=False)
                )
                (inner_cross_attn): FlashCrossAttention(
                  (drop): Dropout(p=0.1, inplace=False)
                )
                (out_proj): ParametrizedLinear(
                  in_features=1024, out_features=1024, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
              )
              (dropout1): Dropout(p=0.1, inplace=False)
              (drop_path1): StochasticDepth(p=0.0, mode=row)
              (norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              (mlp): Mlp(
                (fc1): ParametrizedLinear(
                  in_features=1024, out_features=4096, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
                (fc2): ParametrizedLinear(
                  in_features=4096, out_features=1024, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
              )
              (dropout2): Dropout(p=0.1, inplace=False)
              (drop_path2): StochasticDepth(p=0.0, mode=row)
              (norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            )
          )
        )
        (pooler): XLMRobertaPooler(
          (dense): ParametrizedLinear(
            in_features=1024, out_features=1024, bias=True
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
          (activation): Tanh()
        )
      )
    )
  )
  (pooler): 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})
  (normalizer): 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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("BlackBeenie/jina-embeddings-v3-msmarco-v3-bpr")
# Run inference
sentences = [
    'what is a fermentation lock used for',
    'The fermentation lock or airlock is a device used in beer brewing and wine making that allows carbon dioxide released by the beer to escape the fermenter, while not allowing air to enter the fermenter, thus avoiding oxidation. There are two main designs for the fermentation lock, or airlock.',
    'Remember, fermentation is a method of preserving food. Leaving it on your counter gives it more time for the LAB activity to increase â\x80\x94 which, in turn, lowers pH â\x80\x94 and prevents spoilage. As long as your jar can keep out the oxygen, you shouldnâ\x80\x99t be worried. Which leads me toâ\x80¦.',
]
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: 498,970 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: 9.93 tokens max: 37 tokens	min: 17 tokens mean: 90.01 tokens max: 239 tokens	min: 23 tokens mean: 88.24 tokens max: 258 tokens

Samples:

sentence_0	sentence_1	sentence_2
`how much does it cost to paint a interior house`	Interior House Painting Cost Factors. Generally, it will take a minimum of two gallons of paint to cover a room. At the highest end, paint will cost anywhere between $30 and $60 per gallon and come in three different finishes: flat, semi-gloss or high-gloss.Flat finishes are the least shiny and are best suited for areas requiring frequent cleaning.rovide a few details about your project and receive competitive quotes from local pros. The average national cost to paint a home interior is $1,671, with most homeowners spending between $966 and $2,426.	`Question DetailsAsked on 3/12/2014. Guest_... How much does it cost per square foot to paint the interior of a house? We just bought roughly a 1500 sg ft townhouse and want to get the entire house, including ceilings painted (including a roughly 400 sq ft finished basement not included in square footage).`
`when is s corp taxes due`	`If you form a corporate entity for your small business, regardless of whether it's taxed as a C or S corporation, a tax return must be filed with the Internal Revenue Service on its due date each year. Corporate tax returns are always due on the 15th day of the third month following the close of the tax year. The actual day that the tax return filing deadline falls on, however, isn't the same for every corporation.`	`Before Jan. 1, 2026 After Dec. 31, 2025 Starting with 2016 tax returns, all. other C corps besides Dec. 31 and. June 30 year-ends (including those with. other fiscal year-ends) will be due on. the 15th of the 4th month after the.`
`what are disaccharides`	Disaccharides are formed when two monosaccharides are joined together and a molecule of water is removed, a process known as dehydration reaction. For example; milk sugar (lactose) is made from glucose and galactose whereas the sugar from sugar cane and sugar beets (sucrose) is made from glucose and fructose.altose, another notable disaccharide, is made up of two glucose molecules. The two monosaccharides are bonded via a dehydration reaction (also called a condensation reaction or dehydration synthesis) that leads to the loss of a molecule of water and formation of a glycosidic bond.	`Disaccharides- Another type of carbohydrate. How many sugar units are disaccharides composed of?_____ What elements make up disaccharides? _____ How does the body use disaccharides? _____ There is no chemical test for disaccharides. Table sugar (white granulated sugar) is an example of a disaccharide. List some foods that contain a lot of disaccharides: _____`

Loss: beir.losses.bpr_loss.BPRLoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 8
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
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: 8
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: 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
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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0321	500	1.7204
0.0641	1000	0.6847
0.0962	1500	0.4782
0.1283	2000	0.4001
0.1603	2500	0.3773
0.1924	3000	0.3538
0.2245	3500	0.3424
0.2565	4000	0.3375
0.2886	4500	0.3286
0.3207	5000	0.3289
0.3527	5500	0.3266
0.3848	6000	0.3226
0.4169	6500	0.3266
0.4489	7000	0.3262
0.4810	7500	0.3241
0.5131	8000	0.3216
0.5451	8500	0.3232
0.5772	9000	0.3186
0.6092	9500	0.3194
0.6413	10000	0.314
0.6734	10500	0.3217
0.7054	11000	0.3156
0.7375	11500	0.3244
0.7696	12000	0.3189
0.8016	12500	0.3235
0.8337	13000	0.3305
0.8658	13500	0.3284
0.8978	14000	0.3213
0.9299	14500	0.3283
0.9620	15000	0.3219
0.9940	15500	0.3247
1.0	15593	-
1.0261	16000	0.3287
1.0582	16500	0.3346
1.0902	17000	0.3245
1.1223	17500	0.3202
1.1544	18000	0.332
1.1864	18500	0.3298
1.2185	19000	0.332
1.2506	19500	0.3258
1.2826	20000	0.3291
1.3147	20500	0.334
1.3468	21000	0.3328
1.3788	21500	0.3362
1.4109	22000	0.3348
1.4430	22500	0.3402
1.4750	23000	0.3346
1.5071	23500	0.339
1.5392	24000	0.3406
1.5712	24500	0.3239
1.6033	25000	0.3275
1.6353	25500	0.3287
1.6674	26000	0.3271
1.6995	26500	0.3337
1.7315	27000	0.3352
1.7636	27500	0.3244
1.7957	28000	0.3418
1.8277	28500	0.349
1.8598	29000	0.3395
1.8919	29500	0.3386
1.9239	30000	0.3379
1.9560	30500	0.3412
1.9881	31000	0.3364
2.0	31186	-
2.0201	31500	0.3386
2.0522	32000	0.3417
2.0843	32500	0.3362
2.1163	33000	0.3251
2.1484	33500	0.3563
2.1805	34000	0.3341
2.2125	34500	0.3478
2.2446	35000	0.3389
2.2767	35500	0.342
2.3087	36000	0.3467
2.3408	36500	0.3419
2.3729	37000	0.3513
2.4049	37500	0.3441
2.4370	38000	0.3484
2.4691	38500	0.3457
2.5011	39000	0.3503
2.5332	39500	0.3446
2.5653	40000	0.3461
2.5973	40500	0.3399
2.6294	41000	0.3405
2.6615	41500	0.3382
2.6935	42000	0.3388
2.7256	42500	0.3378
2.7576	43000	0.336
2.7897	43500	0.3471
2.8218	44000	0.3563
2.8538	44500	0.3465
2.8859	45000	0.3501
2.9180	45500	0.3439
2.9500	46000	0.3546
2.9821	46500	0.3414
3.0	46779	-
3.0142	47000	0.3498
3.0462	47500	0.3484
3.0783	48000	0.3496
3.1104	48500	0.3392
3.1424	49000	0.3583
3.1745	49500	0.3505
3.2066	50000	0.3547
3.2386	50500	0.3469
3.2707	51000	0.3489
3.3028	51500	0.3473
3.3348	52000	0.3579
3.3669	52500	0.3523
3.3990	53000	0.3427
3.4310	53500	0.3685
3.4631	54000	0.3479
3.4952	54500	0.355
3.5272	55000	0.3464
3.5593	55500	0.3473
3.5914	56000	0.348
3.6234	56500	0.3426
3.6555	57000	0.3394
3.6876	57500	0.3454
3.7196	58000	0.345
3.7517	58500	0.3411
3.7837	59000	0.3557
3.8158	59500	0.3505
3.8479	60000	0.3605
3.8799	60500	0.3554
3.9120	61000	0.349
3.9441	61500	0.3629
3.9761	62000	0.3456
4.0	62372	-
4.0082	62500	0.3562
4.0403	63000	0.3531
4.0723	63500	0.3569
4.1044	64000	0.3494
4.1365	64500	0.3513
4.1685	65000	0.3599
4.2006	65500	0.3487
4.2327	66000	0.3561
4.2647	66500	0.3583
4.2968	67000	0.3539
4.3289	67500	0.3614
4.3609	68000	0.3558
4.3930	68500	0.3485
4.4251	69000	0.3715
4.4571	69500	0.3585
4.4892	70000	0.3571
4.5213	70500	0.3498
4.5533	71000	0.3576
4.5854	71500	0.3498
4.6175	72000	0.3507
4.6495	72500	0.3436
4.6816	73000	0.3461
4.7137	73500	0.3451
4.7457	74000	0.3554
4.7778	74500	0.354
4.8099	75000	0.3514
4.8419	75500	0.3688
4.8740	76000	0.3573
4.9060	76500	0.3557
4.9381	77000	0.3607
4.9702	77500	0.3488
5.0	77965	-
5.0022	78000	0.3555
5.0343	78500	0.3596
5.0664	79000	0.3572
5.0984	79500	0.355
5.1305	80000	0.3427
5.1626	80500	0.3669
5.1946	81000	0.3578
5.2267	81500	0.3589
5.2588	82000	0.3586
5.2908	82500	0.3581
5.3229	83000	0.3607
5.3550	83500	0.3563
5.3870	84000	0.3597
5.4191	84500	0.3712
5.4512	85000	0.3574
5.4832	85500	0.359
5.5153	86000	0.3598
5.5474	86500	0.3604
5.5794	87000	0.3535
5.6115	87500	0.3606
5.6436	88000	0.3469
5.6756	88500	0.3568
5.7077	89000	0.3497
5.7398	89500	0.3597
5.7718	90000	0.3582
5.8039	90500	0.3556
5.8360	91000	0.3716
5.8680	91500	0.3615
5.9001	92000	0.3532
5.9321	92500	0.3747
5.9642	93000	0.3521
5.9963	93500	0.362
6.0	93558	-
6.0283	94000	0.3701
6.0604	94500	0.3636
6.0925	95000	0.3556
6.1245	95500	0.3508
6.1566	96000	0.3626
6.1887	96500	0.3618
6.2207	97000	0.3683
6.2528	97500	0.362
6.2849	98000	0.3534
6.3169	98500	0.3643
6.3490	99000	0.36
6.3811	99500	0.3592
6.4131	100000	0.3606
6.4452	100500	0.369
6.4773	101000	0.3607
6.5093	101500	0.3683
6.5414	102000	0.3648
6.5735	102500	0.3481
6.6055	103000	0.3565
6.6376	103500	0.3555
6.6697	104000	0.347
6.7017	104500	0.3585
6.7338	105000	0.3553
6.7659	105500	0.3539
6.7979	106000	0.3638
6.8300	106500	0.3674
6.8621	107000	0.3674
6.8941	107500	0.3617
6.9262	108000	0.3655
6.9583	108500	0.3593
6.9903	109000	0.3603
7.0	109151	-
7.0224	109500	0.3614
7.0544	110000	0.3655
7.0865	110500	0.3597
7.1186	111000	0.3443
7.1506	111500	0.3781
7.1827	112000	0.3587
7.2148	112500	0.3676
7.2468	113000	0.357
7.2789	113500	0.3639
7.3110	114000	0.3691
7.3430	114500	0.3606
7.3751	115000	0.3679
7.4072	115500	0.3697
7.4392	116000	0.3726
7.4713	116500	0.3603
7.5034	117000	0.3655
7.5354	117500	0.3639
7.5675	118000	0.3557
7.5996	118500	0.358
7.6316	119000	0.3526
7.6637	119500	0.3579
7.6958	120000	0.3584
7.7278	120500	0.3507
7.7599	121000	0.3472
7.7920	121500	0.3757
7.8240	122000	0.3717
7.8561	122500	0.3646
7.8882	123000	0.3662
7.9202	123500	0.3668
7.9523	124000	0.3677
7.9844	124500	0.3588
8.0	124744	-

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.0
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
Tokenizers: 0.19.1

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",
}