all-MiniLM-L6-v34-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v20_tag_true_positives_and_false_negatives_description dataset. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • pairs_with_scores_v20_tag_true_positives_and_false_negatives_description
• 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (2): 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'laces boot',
    'nursing covers mustard flowers category kids baby care breastfeeding aid breastfeeding aid tags breathable nursing cover full coverage nursing cover foldable nursing cover pouch nursing cover colorful nursing cover flowers nursing covers mustard nursing covers nursing covers keywords flowers nursing covers mustard nursing covers nursing covers description breastfeeding is one of the most special yet challenging things in motherhood we just wanted to add some more colors to this special moment with all its colors product details soft light breathable fabric machine washable full coverage comes with its pouch foldable in seconds',
    'raw african coffee soap category beauty skincare face soap face soap tags shea butter soap coconut oil soap antioxidant soap firming skin soap dark spots soap coffee soap raw african raw african soap soap ahwa soap kahwa soap kahwah soap qahwa soap raw african ahwa soap raw african kahwa soap raw african kahwah soap raw african qahwa soap keywords coffee soap raw african raw african soap soap ahwa soap kahwa soap kahwah soap qahwa soap raw african ahwa soap raw african kahwa soap raw african kahwah soap raw african qahwa soap description our coffee-based soap bar gives you a boosting and energizing sensation this soap is rich in antioxidants and nutrients that fight age signs firms and tighten the skin and gives you a youthful look. it helps in reducing dark spots and acne scars. for all skin types. this product is free of harsh chemicals like parabens sulphates or mineral oils. we never test our products on animals and we don t deal with suppliers who test their products on animals. ingredients shea butter coconut oil olive oil coffee.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.0395, -0.0577],
#         [ 0.0395,  1.0000, -0.0391],
#         [-0.0577, -0.0391,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v20_tag_true_positives_and_false_negatives_description

• Dataset: pairs_with_scores_v20_tag_true_positives_and_false_negatives_description at 25785dc
• Size: 12,582,766 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 5.59 tokens max: 22 tokens	min: 11 tokens mean: 104.43 tokens max: 256 tokens	min: 0.0 mean: 0.1 max: 1.0

• Samples:

  sentence1	sentence2	score
  bergamot eau de toilette	knitted crop top in beige category fashion casual wear top top tags women top beige top comfort top breathable top fabric top stretch top knitted sets crop top top keywords crop top top attrs gender women brand psych generic name top size s features high-waisted soft breathable cut cropped material knitted color beige occasion beach description elevate your style with our chic knitted set featuring a matching pair of knitted pants and a knitted crop top. designed for comfort and effortless elegance this set is perfect for any occasion. the knitted crop top offers a flattering fit with a touch of stretch while the high-waisted knitted pants provide a sleek silhouette and ultimate comfort. made from soft breathable fabric this set is perfect for both enjoying a day at the beach and stepping out in style. versatile and stylish this knitted set is a must-have addition to your wardrobe. mix and match with your favorite accessories for a look that s uniquely you. model is 177 cm wearing size...	0.0
  wide leg pants	titania solingen no/1063 category beauty cosmetics make-up tool tweezers tags solingen tweezers titania titania tweezers tweezers keywords solingen tweezers titania titania tweezers tweezers	0.0
  women pumps	neurimax 30/cap 2 ex.new category health and nutrition dietary supplements joint supplement joint supplement tags neurimax neurimax supplement keywords neurimax neurimax supplement attrs pharmacies form cap	0.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_with_scores_v20_tag_true_positives_and_false_negatives_description

• Dataset: pairs_with_scores_v20_tag_true_positives_and_false_negatives_description at 25785dc
• Size: 63,230 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 5.51 tokens max: 20 tokens	min: 13 tokens mean: 104.12 tokens max: 256 tokens	min: 0.0 mean: 0.1 max: 1.0

• Samples:

  sentence1	sentence2	score
  always maxi long	american - buffalo chicken hot category restaurants pizza deli pizza tags cheesy american pizza thick pizza mozzarella pizza cheese pizza hot chicken pizza american pizza buffalo chicken pizza chicken pizza pizza keywords american pizza buffalo chicken pizza chicken pizza pizza description a thick pizza with a generous amount of cheese mozzarella tomato sauce chicken buffalo sauce	0.0
  sushi	lemon fluffy set category fashion casual wear outfit outfit tags linen outfit summer outfit women outfit blouse skirt fluffy outfit lemon outfit outfit outfit set keywords fluffy outfit lemon outfit outfit outfit set attrs gender women brand dovera generic name outfit size one size features fluffy outfit style skirt top material linen color lemon season summer description modest comfyand summery set with fluffy skirt and top comes in 3 colors apple green - brown - blue one size. outside materials linen. blouse length 55 cm width 65 cm shoulder 25 cm skirt length 100 cm	0.0
  eyefree lid wipes	disposable - 5 ml syringe - latex free - 1 pcs category pharmacies first aid and medical equipment medical accessory medical accessory tags disposable syringe syringe keywords disposable syringe syringe attrs units 1 pcs 5 millilitre	0.0

• Loss: CoSENTLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• 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: 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}
• 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
• hub_revision: None
• 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
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: 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
0.3164	31100	0.876
0.3174	31200	0.7863
0.3184	31300	0.634
0.3194	31400	0.7684
0.3204	31500	1.0607
0.3215	31600	0.6896
0.3225	31700	0.7144
0.3235	31800	0.5732
0.3245	31900	0.6682
0.3255	32000	0.6833
0.3265	32100	0.7044
0.3276	32200	0.8258
0.3286	32300	0.7588
0.3296	32400	0.6054
0.3306	32500	0.8266
0.3316	32600	0.7191
0.3326	32700	0.61
0.3337	32800	0.7708
0.3347	32900	0.866
0.3357	33000	0.8767
0.3367	33100	0.6903
0.3377	33200	0.8024
0.3387	33300	0.7821
0.3398	33400	0.6532
0.3408	33500	0.6339
0.3418	33600	0.697
0.3428	33700	0.6901
0.3438	33800	0.5962
0.3449	33900	0.8373
0.3459	34000	0.7346
0.3469	34100	0.5562
0.3479	34200	0.775
0.3489	34300	1.0555
0.3499	34400	0.6456
0.3510	34500	0.675
0.3520	34600	0.8256
0.3530	34700	0.9122
0.3540	34800	0.5316
0.3550	34900	0.6905
0.3560	35000	0.6403
0.3571	35100	0.9348
0.3581	35200	0.7172
0.3591	35300	0.6584
0.3601	35400	0.5404
0.3611	35500	0.7632
0.3621	35600	1.0379
0.3632	35700	0.6572
0.3642	35800	0.7546
0.3652	35900	0.9182
0.3662	36000	0.7215
0.3672	36100	0.8358
0.3682	36200	0.7465
0.3693	36300	0.6766
0.3703	36400	0.7989
0.3713	36500	0.7042
0.3723	36600	0.616
0.3733	36700	0.7016
0.3744	36800	0.6057
0.3754	36900	0.6726
0.3764	37000	0.8771
0.3774	37100	0.6327
0.3784	37200	0.6945
0.3794	37300	1.1338
0.3805	37400	0.7285
0.3815	37500	0.513
0.3825	37600	0.7464
0.3835	37700	0.6769
0.3845	37800	0.988
0.3855	37900	0.6725
0.3866	38000	0.8038
0.3876	38100	0.7687
0.3886	38200	0.5629
0.3896	38300	0.8473
0.3906	38400	0.5572
0.3916	38500	0.5902
0.3927	38600	0.8795
0.3937	38700	0.7601
0.3947	38800	0.7136
0.3957	38900	0.6226
0.3967	39000	0.6126
0.3977	39100	0.7451
0.3988	39200	0.6292
0.3998	39300	0.8416
0.4008	39400	0.7661
0.4018	39500	0.7477
0.4028	39600	0.5339
0.4039	39700	0.8635
0.4049	39800	0.773
0.4059	39900	0.8288
0.4069	40000	0.6138
0.4079	40100	0.6304
0.4089	40200	0.6188
0.4100	40300	0.6625
0.4110	40400	0.5617
0.4120	40500	0.6695
0.4130	40600	0.5699
0.4140	40700	0.7278
0.4150	40800	0.5742
0.4161	40900	0.5422
0.4171	41000	0.7337
0.4181	41100	0.7621
0.4191	41200	0.8124
0.4201	41300	0.6639
0.4211	41400	0.6997
0.4222	41500	0.7158
0.4232	41600	0.6757
0.4242	41700	0.5968
0.4252	41800	0.9847
0.4262	41900	0.575
0.4273	42000	0.7115
0.4283	42100	0.5127
0.4293	42200	0.6542
0.4303	42300	0.6691
0.4313	42400	0.7493
0.4323	42500	0.7557
0.4334	42600	0.7336
0.4344	42700	0.6892
0.4354	42800	0.8158
0.4364	42900	0.6478
0.4374	43000	0.8116
0.4384	43100	0.5555
0.4395	43200	0.6921
0.4405	43300	0.599
0.4415	43400	0.7291
0.4425	43500	0.8216
0.4435	43600	0.6568
0.4445	43700	0.8248
0.4456	43800	0.5893
0.4466	43900	0.6014
0.4476	44000	0.716
0.4486	44100	0.6586
0.4496	44200	0.5519
0.4506	44300	0.7303
0.4517	44400	0.6237
0.4527	44500	0.6384
0.4537	44600	0.5283
0.4547	44700	0.7639
0.4557	44800	0.5773
0.4568	44900	0.63
0.4578	45000	0.7546
0.4588	45100	0.7403
0.4598	45200	0.7294
0.4608	45300	0.6743
0.4618	45400	0.8111
0.4629	45500	0.8174
0.4639	45600	0.66
0.4649	45700	0.5984
0.4659	45800	0.5531
0.4669	45900	0.5502
0.4679	46000	0.5015
0.4690	46100	0.6531
0.4700	46200	0.4612
0.4710	46300	0.7435
0.4720	46400	0.5689
0.4730	46500	0.7756
0.4740	46600	0.4821
0.4751	46700	0.5365
0.4761	46800	0.7825
0.4771	46900	0.6327
0.4781	47000	0.6665
0.4791	47100	0.6774
0.4801	47200	0.5711
0.4812	47300	0.4692
0.4822	47400	0.7609
0.4832	47500	0.6014
0.4842	47600	0.63
0.4852	47700	0.6425
0.4863	47800	0.4437
0.4873	47900	0.7719
0.4883	48000	0.7728
0.4893	48100	0.7429
0.4903	48200	0.5815
0.4913	48300	0.4637
0.4924	48400	0.6373
0.4934	48500	0.6516
0.4944	48600	0.5944
0.4954	48700	0.5944
0.4964	48800	0.5783
0.4974	48900	0.4975
0.4985	49000	0.5753
0.4995	49100	0.6536
0.5005	49200	0.6784
0.5015	49300	0.6501
0.5025	49400	0.7375
0.5035	49500	0.7434
0.5046	49600	0.6829
0.5056	49700	0.7138
0.5066	49800	0.6877
0.5076	49900	0.7583
0.5086	50000	0.6367
0.5096	50100	0.7877
0.5107	50200	0.6411
0.5117	50300	0.4858
0.5127	50400	0.6664
0.5137	50500	0.7082
0.5147	50600	0.6797
0.5158	50700	0.5434
0.5168	50800	0.7925
0.5178	50900	0.6718
0.5188	51000	0.6396
0.5198	51100	0.5677
0.5208	51200	0.5502
0.5219	51300	0.5032
0.5229	51400	0.6074
0.5239	51500	0.5556
0.5249	51600	0.5971
0.5259	51700	0.683
0.5269	51800	0.5581
0.5280	51900	0.6527
0.5290	52000	0.4821
0.5300	52100	0.5816
0.5310	52200	0.6682
0.5320	52300	0.5588
0.5330	52400	0.7083
0.5341	52500	0.5202
0.5351	52600	0.8868
0.5361	52700	0.5633
0.5371	52800	0.6765
0.5381	52900	0.6018
0.5391	53000	0.7131
0.5402	53100	0.8285
0.5412	53200	0.5976
0.5422	53300	0.6956
0.5432	53400	0.764
0.5442	53500	0.6361
0.5453	53600	0.771
0.5463	53700	0.6918
0.5473	53800	0.6249
0.5483	53900	0.4598
0.5493	54000	0.4593
0.5503	54100	0.4233
0.5514	54200	0.6872
0.5524	54300	0.6095
0.5534	54400	0.5999
0.5544	54500	0.6825
0.5554	54600	0.7495
0.5564	54700	0.6987
0.5575	54800	0.4759
0.5585	54900	0.6721
0.5595	55000	0.5161
0.5605	55100	0.5478
0.5615	55200	0.658
0.5625	55300	0.4418
0.5636	55400	0.64
0.5646	55500	0.5258
0.5656	55600	0.6109
0.5666	55700	0.609
0.5676	55800	0.5924
0.5686	55900	0.7795
0.5697	56000	0.6582
0.5707	56100	0.606
0.5717	56200	0.7434
0.5727	56300	0.7792
0.5737	56400	0.5786
0.5748	56500	0.7578
0.5758	56600	0.5731
0.5768	56700	0.5815
0.5778	56800	0.6589
0.5788	56900	0.5165
0.5798	57000	0.5465
0.5809	57100	0.6758
0.5819	57200	0.9153
0.5829	57300	0.636
0.5839	57400	0.6939
0.5849	57500	0.5267
0.5859	57600	0.5311
0.5870	57700	0.5839
0.5880	57800	0.6322
0.5890	57900	0.7506
0.5900	58000	0.7357
0.5910	58100	0.637
0.5920	58200	0.5829
0.5931	58300	0.5389
0.5941	58400	0.5745
0.5951	58500	0.5478
0.5961	58600	0.5462
0.5971	58700	0.492
0.5982	58800	0.7698
0.5992	58900	0.7086
0.6002	59000	0.5891
0.6012	59100	0.5708
0.6022	59200	0.5963
0.6032	59300	0.5927
0.6043	59400	0.6745
0.6053	59500	0.7091
0.6063	59600	0.6303
0.6073	59700	0.7122
0.6083	59800	0.5032
0.6093	59900	0.6265
0.6104	60000	0.554
0.6114	60100	0.5268
0.6124	60200	0.5289
0.6134	60300	0.5337
0.6144	60400	0.5181
0.6154	60500	0.642
0.6165	60600	0.5967
0.6175	60700	0.6924
0.6185	60800	0.6162
0.6195	60900	0.4908
0.6205	61000	0.504
0.6215	61100	0.6625
0.6226	61200	0.5503
0.6236	61300	0.6817
0.6246	61400	0.6036
0.6256	61500	0.5236
0.6266	61600	0.8277
0.6277	61700	0.5453
0.6287	61800	0.6393
0.6297	61900	0.5463
0.6307	62000	0.5152
0.6317	62100	0.5717
0.6327	62200	0.5303
0.6338	62300	0.4974
0.6348	62400	0.4543
0.6358	62500	0.5647
0.6368	62600	0.587
0.6378	62700	0.5843
0.6388	62800	0.5795
0.6399	62900	0.7489
0.6409	63000	0.4976
0.6419	63100	0.5291
0.6429	63200	0.4509
0.6439	63300	0.5515
0.6449	63400	0.7273
0.6460	63500	0.6759
0.6470	63600	0.5811
0.6480	63700	0.5488
0.6490	63800	0.541
0.6500	63900	0.4319
0.6510	64000	0.5803
0.6521	64100	0.485
0.6531	64200	0.5366
0.6541	64300	0.5744
0.6551	64400	0.5346
0.6561	64500	0.6252
0.6572	64600	0.5678
0.6582	64700	0.4391
0.6592	64800	0.526
0.6602	64900	0.7272
0.6612	65000	0.5644
0.6622	65100	0.5448
0.6633	65200	0.5306
0.6643	65300	0.6184
0.6653	65400	0.5635
0.6663	65500	0.547
0.6673	65600	0.655
0.6683	65700	0.6952
0.6694	65800	0.5737
0.6704	65900	0.5117
0.6714	66000	0.5947
0.6724	66100	0.5134
0.6734	66200	0.4927
0.6744	66300	0.4579
0.6755	66400	0.6242
0.6765	66500	0.3168
0.6775	66600	0.6052
0.6785	66700	0.5832
0.6795	66800	0.5488
0.6805	66900	0.6921
0.6816	67000	0.6213
0.6826	67100	0.6809
0.6836	67200	0.572
0.6846	67300	0.6091
0.6856	67400	0.4595
0.6867	67500	0.4894
0.6877	67600	0.6226
0.6887	67700	0.5319
0.6897	67800	0.6275
0.6907	67900	0.6168
0.6917	68000	0.4189
0.6928	68100	0.5629
0.6938	68200	0.5264
0.6948	68300	0.5147
0.6958	68400	0.5808
0.6968	68500	0.6342
0.6978	68600	0.5478
0.6989	68700	0.5288
0.6999	68800	0.6481
0.7009	68900	0.4177
0.7019	69000	0.4393
0.7029	69100	0.4718
0.7039	69200	0.5377
0.7050	69300	0.4091
0.7060	69400	0.5024
0.7070	69500	0.7504
0.7080	69600	0.5329
0.7090	69700	0.709
0.7100	69800	0.5535
0.7111	69900	0.5414
0.7121	70000	0.4775
0.7131	70100	0.7058
0.7141	70200	0.4756
0.7151	70300	0.5445
0.7162	70400	0.806
0.7172	70500	0.5131
0.7182	70600	0.4188
0.7192	70700	0.4884
0.7202	70800	0.503
0.7212	70900	0.633
0.7223	71000	0.6739
0.7233	71100	0.4731
0.7243	71200	0.7899
0.7253	71300	0.6123
0.7263	71400	0.7082
0.7273	71500	0.4386
0.7284	71600	0.7333
0.7294	71700	0.5049
0.7304	71800	0.513
0.7314	71900	0.5557
0.7324	72000	0.4583
0.7334	72100	0.6533
0.7345	72200	0.6656
0.7355	72300	0.6688
0.7365	72400	0.5203
0.7375	72500	0.5878
0.7385	72600	0.4206
0.7396	72700	0.5282
0.7406	72800	0.3856
0.7416	72900	0.5058
0.7426	73000	0.5884
0.7436	73100	0.6789
0.7446	73200	0.4926
0.7457	73300	0.7524
0.7467	73400	0.6064
0.7477	73500	0.6051
0.7487	73600	0.5319
0.7497	73700	0.4681
0.7507	73800	0.5665
0.7518	73900	0.4963
0.7528	74000	0.6263
0.7538	74100	0.5081
0.7548	74200	0.5653
0.7558	74300	0.6463
0.7568	74400	0.6821
0.7579	74500	0.6176
0.7589	74600	0.6121
0.7599	74700	0.5915
0.7609	74800	0.6107
0.7619	74900	0.5239
0.7629	75000	0.638
0.7640	75100	0.6635
0.7650	75200	0.5628
0.7660	75300	0.5436
0.7670	75400	0.6263
0.7680	75500	0.6388
0.7691	75600	0.6069
0.7701	75700	0.5026
0.7711	75800	0.5857
0.7721	75900	0.4426
0.7731	76000	0.5456
0.7741	76100	0.6334
0.7752	76200	0.8007
0.7762	76300	0.4533
0.7772	76400	0.545
0.7782	76500	0.503
0.7792	76600	0.589
0.7802	76700	0.4087
0.7813	76800	0.4727
0.7823	76900	0.421
0.7833	77000	0.5352
0.7843	77100	0.5896
0.7853	77200	0.6923
0.7863	77300	0.4792
0.7874	77400	0.4911
0.7884	77500	0.5706
0.7894	77600	0.6354
0.7904	77700	0.5627
0.7914	77800	0.5819
0.7924	77900	0.5113
0.7935	78000	0.5586
0.7945	78100	0.6474
0.7955	78200	0.4289
0.7965	78300	0.4709
0.7975	78400	0.4257
0.7986	78500	0.5433
0.7996	78600	0.438
0.8006	78700	0.5929
0.8016	78800	0.5322
0.8026	78900	0.7181
0.8036	79000	0.5043
0.8047	79100	0.4677
0.8057	79200	0.6363
0.8067	79300	0.5328
0.8077	79400	0.6594
0.8087	79500	0.5374
0.8097	79600	0.4551
0.8108	79700	0.5639
0.8118	79800	0.4964
0.8128	79900	0.6743
0.8138	80000	0.542
0.8148	80100	0.4614
0.8158	80200	0.7254
0.8169	80300	0.5784
0.8179	80400	0.5902
0.8189	80500	0.5918
0.8199	80600	0.5781
0.8209	80700	0.5126
0.8219	80800	0.4936
0.8230	80900	0.6369
0.8240	81000	0.5867
0.8250	81100	0.6276
0.8260	81200	0.4783
0.8270	81300	0.541
0.8281	81400	0.5927
0.8291	81500	0.4463
0.8301	81600	0.4974
0.8311	81700	0.6031
0.8321	81800	0.5113
0.8331	81900	0.6167
0.8342	82000	0.743
0.8352	82100	0.588
0.8362	82200	0.5285
0.8372	82300	0.4808
0.8382	82400	0.4278
0.8392	82500	0.4873
0.8403	82600	0.5184
0.8413	82700	0.6202
0.8423	82800	0.4664
0.8433	82900	0.4105
0.8443	83000	0.4905
0.8453	83100	0.4211
0.8464	83200	0.6084
0.8474	83300	0.7489
0.8484	83400	0.6135
0.8494	83500	0.3633
0.8504	83600	0.5402
0.8514	83700	0.5323
0.8525	83800	0.573
0.8535	83900	0.5125
0.8545	84000	0.523
0.8555	84100	0.6542
0.8565	84200	0.4051
0.8576	84300	0.4939
0.8586	84400	0.5925
0.8596	84500	0.6372
0.8606	84600	0.5709
0.8616	84700	0.461
0.8626	84800	0.6882
0.8637	84900	0.5696
0.8647	85000	0.6738
0.8657	85100	0.4805
0.8667	85200	0.4873
0.8677	85300	0.4229
0.8687	85400	0.5836
0.8698	85500	0.5522
0.8708	85600	0.5547
0.8718	85700	0.6679
0.8728	85800	0.5312
0.8738	85900	0.5473
0.8748	86000	0.4306
0.8759	86100	0.5584
0.8769	86200	0.6964
0.8779	86300	0.4041
0.8789	86400	0.51
0.8799	86500	0.5308
0.8809	86600	0.6508
0.8820	86700	0.3203
0.8830	86800	0.5776
0.8840	86900	0.5668
0.8850	87000	0.5286
0.8860	87100	0.5829
0.8871	87200	0.4664
0.8881	87300	0.5133
0.8891	87400	0.7109
0.8901	87500	0.5021
0.8911	87600	0.7045
0.8921	87700	0.4779
0.8932	87800	0.6719
0.8942	87900	0.5506
0.8952	88000	0.4617
0.8962	88100	0.59
0.8972	88200	0.5293
0.8982	88300	0.6322
0.8993	88400	0.4793
0.9003	88500	0.5075
0.9013	88600	0.5487
0.9023	88700	0.5034
0.9033	88800	0.568
0.9043	88900	0.3517
0.9054	89000	0.4429
0.9064	89100	0.6426
0.9074	89200	0.4489
0.9084	89300	0.6615
0.9094	89400	0.5461
0.9105	89500	0.4188
0.9115	89600	0.5876
0.9125	89700	0.537
0.9135	89800	0.6261
0.9145	89900	0.4547
0.9155	90000	0.4543
0.9166	90100	0.3025
0.9176	90200	0.4654
0.9186	90300	0.532
0.9196	90400	0.4018
0.9206	90500	0.5752
0.9216	90600	0.6861
0.9227	90700	0.4797
0.9237	90800	0.4749
0.9247	90900	0.453
0.9257	91000	0.5453
0.9267	91100	0.5817
0.9277	91200	0.5239
0.9288	91300	0.3685
0.9298	91400	0.7493
0.9308	91500	0.4339
0.9318	91600	0.5713
0.9328	91700	0.6377
0.9338	91800	0.3882
0.9349	91900	0.4041
0.9359	92000	0.4833
0.9369	92100	0.6295
0.9379	92200	0.639
0.9389	92300	0.358
0.9400	92400	0.449
0.9410	92500	0.4682
0.9420	92600	0.5082
0.9430	92700	0.6113
0.9440	92800	0.519
0.9450	92900	0.556
0.9461	93000	0.5274
0.9471	93100	0.5541
0.9481	93200	0.6344
0.9491	93300	0.3831
0.9501	93400	0.3837
0.9511	93500	0.414
0.9522	93600	0.5822
0.9532	93700	0.4977
0.9542	93800	0.501
0.9552	93900	0.5738
0.9562	94000	0.71
0.9572	94100	0.4816
0.9583	94200	0.5004
0.9593	94300	0.3232
0.9603	94400	0.5614
0.9613	94500	0.4866
0.9623	94600	0.5685
0.9633	94700	0.342
0.9644	94800	0.4145
0.9654	94900	0.4993
0.9664	95000	0.5726
0.9674	95100	0.587
0.9684	95200	0.4993
0.9695	95300	0.763
0.9705	95400	0.6
0.9715	95500	0.5082
0.9725	95600	0.4745
0.9735	95700	0.6281
0.9745	95800	0.5973
0.9756	95900	0.621
0.9766	96000	0.441
0.9776	96100	0.5697
0.9786	96200	0.6939
0.9796	96300	0.6116
0.9806	96400	0.3031
0.9817	96500	0.5447
0.9827	96600	0.4614
0.9837	96700	0.4326
0.9847	96800	0.3134
0.9857	96900	0.5931
0.9867	97000	0.4245
0.9878	97100	0.5367
0.9888	97200	0.348
0.9898	97300	0.598
0.9908	97400	0.5788
0.9918	97500	0.5493
0.9928	97600	0.6309
0.9939	97700	0.7681
0.9949	97800	0.4108
0.9959	97900	0.4668
0.9969	98000	0.4214
0.9979	98100	0.449
0.9990	98200	0.5136
1.0000	98300	0.44

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.21.4

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}