all-MiniLM-L6-v81-pair_score

This is a sentence-transformers model finetuned from KhaledReda/all-MiniLM-L6-v80-pair_score on the pairs_with_scores_v65 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: KhaledReda/all-MiniLM-L6-v80-pair_score
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • pairs_with_scores_v65
• 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 = [
    'off body shirt',
    'arki soup bowl arki bowl bowl soup bowl arki bowl bowl soup bowl',
    'jbl partybox 100 speaker jbl speaker partybox partybox',
]
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, -0.1563, -0.1154],
#         [-0.1563,  1.0000,  0.0439],
#         [-0.1154,  0.0439,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v65

• Dataset: pairs_with_scores_v65 at e93c4eb
• Size: 69,786,324 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: 6.71 tokens max: 24 tokens	min: 5 tokens mean: 45.08 tokens max: 256 tokens	min: 0.0 mean: 0.04 max: 1.0

• Samples:

  sentence1	sentence2	score
  winter duvet microfiber 350 gsm	terracotta clay pizza stone plate - 35cm terracotta pizza platter clay pizza platter seving pizza platter kitchen pizza platter kitchen dining clay pizza plate pizza plate plate terracotta pizza plate clay pizza plate pizza plate plate terracotta pizza plate	0.25
  pepper sauce steak	teppanyaki salmon hot teppanyaki salmon teppanyaki teppanyaki salmon teppanyaki teppanyaki salmon	0.25
  oval shaped table	28 cm oval dutch oven grif dutch oven cast iron dutch oven brass lid knob dutch oven dutch oven oval dutch oven 28 cm oval dutch stove dutch stove oval dutch stove dutch oven oval dutch oven 28 cm oval dutch stove dutch stove oval dutch stove	0.25

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_with_scores_v65

• Dataset: pairs_with_scores_v65 at e93c4eb
• Size: 350,686 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: 6.79 tokens max: 25 tokens	min: 5 tokens mean: 45.07 tokens max: 256 tokens	min: 0.0 mean: 0.05 max: 1.0

• Samples:

  sentence1	sentence2	score
  ceramic coating hair volumizer	prostanorm - supplement with zinc gluconate saw palmetto berry stinging nettle extracts - 30 capsules prostanorm capsules prostanorm prostanorm supplement saw palmetto berry supplement stinging nettle extracts supplement zinc gluconate supplement prostanorm prostanorm supplement saw palmetto berry supplement stinging nettle extracts supplement zinc gluconate supplement	0.0
  summer blue beverage	octagam 5 2.5gm 50ml 1/vial octagam octagam	0.0
  abert rinascimento spoon	macrame boho stool rustic stool bohemian stool cotton stool rustic stool bohemian stool macrame stool boho stool macrame stool stool boho stool macrame stool stool	0.25

• 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
0.7742	422100	3.1981
0.7744	422200	2.5378
0.7746	422300	2.001
0.7748	422400	2.9412
0.7749	422500	2.2478
0.7751	422600	1.8472
0.7753	422700	3.1986
0.7755	422800	2.0106
0.7757	422900	2.7909
0.7759	423000	2.4219
0.7760	423100	2.1166
0.7762	423200	2.3957
0.7764	423300	2.5634
0.7766	423400	2.6026
0.7768	423500	2.1906
0.7770	423600	2.3296
0.7771	423700	2.6538
0.7773	423800	2.2883
0.7775	423900	2.4736
0.7777	424000	2.3549
0.7779	424100	2.2288
0.7781	424200	2.4633
0.7782	424300	2.1951
0.7784	424400	2.2346
0.7786	424500	2.3788
0.7788	424600	2.2253
0.7790	424700	1.8647
0.7792	424800	2.4706
0.7793	424900	2.6833
0.7795	425000	2.4375
0.7797	425100	1.883
0.7799	425200	2.7053
0.7801	425300	2.3413
0.7803	425400	2.3488
0.7804	425500	2.0803
0.7806	425600	1.9036
0.7808	425700	1.7651
0.7810	425800	2.9331
0.7812	425900	2.478
0.7814	426000	1.6058
0.7815	426100	2.1397
0.7817	426200	2.5323
0.7819	426300	2.5303
0.7821	426400	2.0874
0.7823	426500	2.1103
0.7825	426600	2.5195
0.7826	426700	2.3854
0.7828	426800	2.1161
0.7830	426900	2.2109
0.7832	427000	2.5735
0.7834	427100	2.7394
0.7836	427200	2.2572
0.7837	427300	2.6251
0.7839	427400	2.294
0.7841	427500	2.3134
0.7843	427600	2.2118
0.7845	427700	2.4642
0.7847	427800	2.1233
0.7848	427900	2.9304
0.7850	428000	2.3453
0.7852	428100	2.7102
0.7854	428200	2.0714
0.7856	428300	2.154
0.7858	428400	2.6458
0.7859	428500	2.7364
0.7861	428600	2.7569
0.7863	428700	2.6374
0.7865	428800	2.4936
0.7867	428900	2.3364
0.7869	429000	2.1943
0.7870	429100	2.5986
0.7872	429200	2.01
0.7874	429300	2.4762
0.7876	429400	2.0316
0.7878	429500	2.4138
0.7880	429600	2.4856
0.7881	429700	2.3043
0.7883	429800	2.627
0.7885	429900	2.8077
0.7887	430000	2.0302
0.7889	430100	2.1234
0.7891	430200	2.0399
0.7892	430300	2.2041
0.7894	430400	2.4141
0.7896	430500	2.3842
0.7898	430600	1.7498
0.7900	430700	2.8699
0.7902	430800	2.98
0.7903	430900	2.2981
0.7905	431000	2.1989
0.7907	431100	2.3669
0.7909	431200	2.5146
0.7911	431300	2.2489
0.7913	431400	2.2853
0.7914	431500	2.434
0.7916	431600	3.1587
0.7918	431700	2.3869
0.7920	431800	2.0928
0.7922	431900	2.208
0.7924	432000	2.5647
0.7925	432100	2.1393
0.7927	432200	2.562
0.7929	432300	3.245
0.7931	432400	2.6561
0.7933	432500	2.2876
0.7935	432600	2.0899
0.7936	432700	2.0496
0.7938	432800	2.4118
0.7940	432900	1.8742
0.7942	433000	2.4013
0.7944	433100	3.2155
0.7946	433200	2.4333
0.7947	433300	2.8981
0.7949	433400	2.4289
0.7951	433500	2.0661
0.7953	433600	1.7868
0.7955	433700	2.3078
0.7957	433800	2.405
0.7958	433900	2.1595
0.7960	434000	2.6248
0.7962	434100	2.1861
0.7964	434200	2.463
0.7966	434300	2.1822
0.7968	434400	2.2497
0.7969	434500	2.5078
0.7971	434600	2.0192
0.7973	434700	1.945
0.7975	434800	2.2119
0.7977	434900	2.2727
0.7979	435000	2.2693
0.7980	435100	2.0268
0.7982	435200	2.5878
0.7984	435300	2.6358
0.7986	435400	2.4412
0.7988	435500	2.3451
0.7990	435600	2.4077
0.7991	435700	2.0718
0.7993	435800	2.7766
0.7995	435900	2.7427
0.7997	436000	2.2231
0.7999	436100	2.2716
0.8001	436200	2.8716
0.8002	436300	2.4332
0.8004	436400	2.0
0.8006	436500	2.6308
0.8008	436600	2.2262
0.8010	436700	2.3776
0.8012	436800	2.3391
0.8013	436900	2.4184
0.8015	437000	2.2222
0.8017	437100	2.2011
0.8019	437200	2.1882
0.8021	437300	2.6975
0.8023	437400	2.1517
0.8024	437500	2.4148
0.8026	437600	2.0734
0.8028	437700	2.6197
0.8030	437800	2.8064
0.8032	437900	2.1377
0.8034	438000	2.7781
0.8035	438100	2.329
0.8037	438200	2.9034
0.8039	438300	2.61
0.8041	438400	2.1798
0.8043	438500	2.8537
0.8045	438600	2.6643
0.8046	438700	2.1642
0.8048	438800	2.1605
0.8050	438900	2.5535
0.8052	439000	2.4855
0.8054	439100	2.399
0.8056	439200	2.4752
0.8058	439300	2.4198
0.8059	439400	2.3881
0.8061	439500	2.5824
0.8063	439600	2.9733
0.8065	439700	2.3947
0.8067	439800	2.3509
0.8069	439900	2.299
0.8070	440000	2.9237
0.8072	440100	2.0621
0.8074	440200	2.6399
0.8076	440300	2.5627
0.8078	440400	2.3198
0.8080	440500	2.8219
0.8081	440600	2.5095
0.8083	440700	2.7951
0.8085	440800	2.2176
0.8087	440900	2.5232
0.8089	441000	2.022
0.8091	441100	2.7884
0.8092	441200	2.9646
0.8094	441300	2.6315
0.8096	441400	2.1814
0.8098	441500	2.7233
0.8100	441600	2.4166
0.8102	441700	2.0529
0.8103	441800	2.3833
0.8105	441900	2.5452
0.8107	442000	2.3203
0.8109	442100	2.4506
0.8111	442200	2.2288
0.8113	442300	2.2359
0.8114	442400	2.8787
0.8116	442500	1.8011
0.8118	442600	2.7652
0.8120	442700	2.2884
0.8122	442800	2.6212
0.8124	442900	2.2887
0.8125	443000	2.4804
0.8127	443100	2.0223
0.8129	443200	1.8621
0.8131	443300	2.1063
0.8133	443400	2.497
0.8135	443500	2.0801
0.8136	443600	2.6279
0.8138	443700	2.5892
0.8140	443800	2.7212
0.8142	443900	2.356
0.8144	444000	2.279
0.8146	444100	2.1923
0.8147	444200	2.4158
0.8149	444300	2.5369
0.8151	444400	2.3112
0.8153	444500	2.6004
0.8155	444600	2.6526
0.8157	444700	2.7526
0.8158	444800	2.7424
0.8160	444900	2.0994
0.8162	445000	2.4723
0.8164	445100	2.07
0.8166	445200	2.5081
0.8168	445300	2.5184
0.8169	445400	1.8881
0.8171	445500	2.7184
0.8173	445600	2.0384
0.8175	445700	2.783
0.8177	445800	2.0309
0.8179	445900	2.703
0.8180	446000	2.1943
0.8182	446100	2.0668
0.8184	446200	2.7282
0.8186	446300	2.0885
0.8188	446400	2.4366
0.8190	446500	2.7913
0.8191	446600	2.8382
0.8193	446700	2.4208
0.8195	446800	2.7876
0.8197	446900	2.6256
0.8199	447000	1.9549
0.8201	447100	2.6593
0.8202	447200	2.4387
0.8204	447300	2.1711
0.8206	447400	2.1903
0.8208	447500	2.363
0.8210	447600	2.1716
0.8212	447700	2.4667
0.8213	447800	2.0852
0.8215	447900	2.1925
0.8217	448000	2.2917
0.8219	448100	2.1962
0.8221	448200	2.2006
0.8223	448300	2.6774
0.8224	448400	2.1002
0.8226	448500	2.2737
0.8228	448600	2.7223
0.8230	448700	2.4663
0.8232	448800	2.6379
0.8234	448900	2.487
0.8235	449000	2.2936
0.8237	449100	2.6291
0.8239	449200	2.6051
0.8241	449300	2.1561
0.8243	449400	2.0727
0.8245	449500	2.59
0.8246	449600	2.4789
0.8248	449700	1.9421
0.8250	449800	1.9578
0.8252	449900	2.5276
0.8254	450000	2.9049
0.8256	450100	2.2506
0.8257	450200	2.0666
0.8259	450300	2.8288
0.8261	450400	2.276
0.8263	450500	2.1151
0.8265	450600	2.505
0.8267	450700	2.5993
0.8268	450800	2.1562
0.8270	450900	2.3937
0.8272	451000	2.5341
0.8274	451100	2.1448
0.8276	451200	2.5566
0.8278	451300	2.2659
0.8279	451400	1.9576
0.8281	451500	2.348
0.8283	451600	2.1327
0.8285	451700	2.1615
0.8287	451800	2.8349
0.8289	451900	2.3983
0.8290	452000	2.2244
0.8292	452100	2.4202
0.8294	452200	2.1508
0.8296	452300	2.5709
0.8298	452400	2.6471
0.8300	452500	2.6767
0.8301	452600	1.9623
0.8303	452700	2.0586
0.8305	452800	1.938
0.8307	452900	2.128
0.8309	453000	2.1779
0.8311	453100	2.5373
0.8312	453200	2.5258
0.8314	453300	2.1737
0.8316	453400	2.4502
0.8318	453500	2.1059
0.8320	453600	2.2383
0.8322	453700	2.6447
0.8323	453800	2.3142
0.8325	453900	2.7144
0.8327	454000	2.8969
0.8329	454100	2.1948
0.8331	454200	2.4538
0.8333	454300	2.4563
0.8334	454400	2.1275
0.8336	454500	2.5044
0.8338	454600	2.673
0.8340	454700	2.2557
0.8342	454800	2.5275
0.8344	454900	2.5723
0.8345	455000	2.4573
0.8347	455100	2.7751
0.8349	455200	2.3293
0.8351	455300	2.7323
0.8353	455400	2.9497
0.8355	455500	2.1685
0.8356	455600	2.2434
0.8358	455700	2.4724
0.8360	455800	2.4285
0.8362	455900	2.2643
0.8364	456000	2.5158
0.8366	456100	2.4
0.8367	456200	2.6386
0.8369	456300	2.2304
0.8371	456400	2.6156
0.8373	456500	1.83
0.8375	456600	2.4332
0.8377	456700	2.1978
0.8378	456800	2.1795
0.8380	456900	1.5394
0.8382	457000	2.6926
0.8384	457100	2.3798
0.8386	457200	2.9645
0.8388	457300	2.6721
0.8389	457400	2.2582
0.8391	457500	2.5091
0.8393	457600	2.5231
0.8395	457700	2.546
0.8397	457800	2.617
0.8399	457900	2.3847
0.8400	458000	2.027
0.8402	458100	2.0813
0.8404	458200	1.8261
0.8406	458300	2.0342
0.8408	458400	2.0202
0.8410	458500	2.6981
0.8411	458600	2.2303
0.8413	458700	2.7091
0.8415	458800	2.4616
0.8417	458900	2.49
0.8419	459000	2.4287
0.8421	459100	2.0199
0.8423	459200	2.5339
0.8424	459300	2.3615
0.8426	459400	2.4897
0.8428	459500	1.9008
0.8430	459600	2.3034
0.8432	459700	2.2447
0.8434	459800	2.6692
0.8435	459900	2.1071
0.8437	460000	2.0124
0.8439	460100	2.6661
0.8441	460200	2.3418
0.8443	460300	2.9599
0.8445	460400	2.5786
0.8446	460500	2.1848
0.8448	460600	2.1195
0.8450	460700	2.4121
0.8452	460800	2.0961
0.8454	460900	2.5276
0.8456	461000	2.2237
0.8457	461100	2.3271
0.8459	461200	2.1383
0.8461	461300	2.9147
0.8463	461400	2.5974
0.8465	461500	2.5836
0.8467	461600	1.963
0.8468	461700	1.8958
0.8470	461800	2.4468
0.8472	461900	2.6451
0.8474	462000	2.1112
0.8476	462100	2.4145
0.8478	462200	2.5929
0.8479	462300	2.3178
0.8481	462400	1.9571
0.8483	462500	2.6474
0.8485	462600	2.5288
0.8487	462700	1.8675
0.8489	462800	2.4938
0.8490	462900	2.1948
0.8492	463000	2.8314
0.8494	463100	3.033
0.8496	463200	2.1917
0.8498	463300	2.5057
0.8500	463400	2.4405
0.8501	463500	2.2552
0.8503	463600	2.5084
0.8505	463700	1.9233
0.8507	463800	3.0066
0.8509	463900	2.642
0.8511	464000	2.9018
0.8512	464100	2.4746
0.8514	464200	2.4596
0.8516	464300	2.6027
0.8518	464400	2.6145
0.8520	464500	2.1761
0.8522	464600	2.6713
0.8523	464700	2.3985
0.8525	464800	2.3422
0.8527	464900	2.5514
0.8529	465000	2.3431
0.8531	465100	1.9496
0.8533	465200	2.4861
0.8534	465300	2.3968
0.8536	465400	2.1514
0.8538	465500	2.3124
0.8540	465600	2.2029
0.8542	465700	2.5687
0.8544	465800	2.2817
0.8545	465900	2.2591
0.8547	466000	2.512
0.8549	466100	2.4873
0.8551	466200	2.7064
0.8553	466300	2.3927
0.8555	466400	2.0026
0.8556	466500	2.1474
0.8558	466600	2.1344
0.8560	466700	2.9085
0.8562	466800	2.18
0.8564	466900	2.4645
0.8566	467000	2.3317
0.8567	467100	2.6731
0.8569	467200	2.8022
0.8571	467300	2.6128
0.8573	467400	2.4744
0.8575	467500	2.1361
0.8577	467600	2.1902
0.8578	467700	2.4121
0.8580	467800	2.6009
0.8582	467900	2.3876
0.8584	468000	2.7322
0.8586	468100	2.5528
0.8588	468200	2.5138
0.8589	468300	2.8529
0.8591	468400	2.2702
0.8593	468500	2.2524
0.8595	468600	2.3629
0.8597	468700	2.5128
0.8599	468800	2.6769
0.8600	468900	2.105
0.8602	469000	1.9685
0.8604	469100	2.2432
0.8606	469200	2.5017
0.8608	469300	2.583
0.8610	469400	2.0248
0.8611	469500	2.5898
0.8613	469600	2.7894
0.8615	469700	1.8813
0.8617	469800	2.5104
0.8619	469900	1.9766
0.8621	470000	2.1816
0.8622	470100	2.0613
0.8624	470200	2.1961
0.8626	470300	2.2585
0.8628	470400	2.1809
0.8630	470500	2.3165
0.8632	470600	2.7537
0.8633	470700	2.897
0.8635	470800	2.1737
0.8637	470900	1.9626
0.8639	471000	2.7641
0.8641	471100	2.9126
0.8643	471200	2.275
0.8644	471300	3.1151
0.8646	471400	2.6607
0.8648	471500	2.3224
0.8650	471600	2.5346
0.8652	471700	1.8555
0.8654	471800	2.659
0.8655	471900	2.5696
0.8657	472000	2.2454
0.8659	472100	2.6375
0.8661	472200	2.0222
0.8663	472300	2.4164
0.8665	472400	2.1537
0.8666	472500	2.608
0.8668	472600	2.2451
0.8670	472700	2.6607
0.8672	472800	2.2688
0.8674	472900	2.6879
0.8676	473000	2.7601
0.8677	473100	2.8017
0.8679	473200	2.7306
0.8681	473300	1.8579
0.8683	473400	2.6513
0.8685	473500	2.3766
0.8687	473600	2.432
0.8688	473700	2.2644
0.8690	473800	2.3779
0.8692	473900	2.6319
0.8694	474000	2.346
0.8696	474100	2.6933
0.8698	474200	2.5583
0.8699	474300	2.3407
0.8701	474400	2.3119
0.8703	474500	2.6652
0.8705	474600	2.372
0.8707	474700	2.3159
0.8709	474800	2.259
0.8710	474900	2.3156
0.8712	475000	2.2365
0.8714	475100	2.8673
0.8716	475200	2.5969
0.8718	475300	2.1146
0.8720	475400	2.2487
0.8721	475500	2.3763
0.8723	475600	2.2522
0.8725	475700	2.0845
0.8727	475800	2.4512
0.8729	475900	2.146
0.8731	476000	2.515
0.8732	476100	2.4593
0.8734	476200	2.13
0.8736	476300	3.0262
0.8738	476400	1.8686
0.8740	476500	1.6255
0.8742	476600	2.2925
0.8743	476700	2.4025
0.8745	476800	2.5032
0.8747	476900	2.1018
0.8749	477000	2.525
0.8751	477100	1.9472
0.8753	477200	2.4302
0.8754	477300	2.3191
0.8756	477400	2.7615
0.8758	477500	2.3238
0.8760	477600	2.8947
0.8762	477700	2.3697
0.8764	477800	2.1821
0.8765	477900	2.0648
0.8767	478000	2.4281
0.8769	478100	2.1097
0.8771	478200	2.4905
0.8773	478300	2.1752
0.8775	478400	2.0028
0.8776	478500	2.3897
0.8778	478600	2.0272
0.8780	478700	2.6264
0.8782	478800	2.3343
0.8784	478900	2.7705
0.8786	479000	2.4272
0.8788	479100	2.2066
0.8789	479200	2.3627
0.8791	479300	2.2118
0.8793	479400	2.3691
0.8795	479500	2.0731
0.8797	479600	2.2417
0.8799	479700	2.5359
0.8800	479800	3.4817
0.8802	479900	2.2791
0.8804	480000	1.8987
0.8806	480100	2.4711
0.8808	480200	2.5374
0.8810	480300	2.8291
0.8811	480400	2.5386
0.8813	480500	2.4466
0.8815	480600	2.4526
0.8817	480700	2.232
0.8819	480800	2.3034
0.8821	480900	2.2435
0.8822	481000	2.3568
0.8824	481100	2.5153
0.8826	481200	2.7732
0.8828	481300	2.1689
0.8830	481400	2.6229
0.8832	481500	2.2322
0.8833	481600	1.9013
0.8835	481700	2.3982
0.8837	481800	2.0989
0.8839	481900	2.2737
0.8841	482000	2.7849
0.8843	482100	2.2874
0.8844	482200	2.4009
0.8846	482300	2.2565
0.8848	482400	2.126
0.8850	482500	2.0436
0.8852	482600	2.0529
0.8854	482700	2.5171
0.8855	482800	2.4947
0.8857	482900	2.3701
0.8859	483000	2.4609
0.8861	483100	2.3175
0.8863	483200	2.2425
0.8865	483300	2.0857
0.8866	483400	2.1952
0.8868	483500	2.8657
0.8870	483600	2.8636
0.8872	483700	2.2769
0.8874	483800	1.6854
0.8876	483900	2.1904
0.8877	484000	2.7391
0.8879	484100	2.2409
0.8881	484200	2.3814
0.8883	484300	2.5439
0.8885	484400	2.6445
0.8887	484500	1.9279
0.8888	484600	2.4614
0.8890	484700	2.3336
0.8892	484800	2.9529
0.8894	484900	2.4276
0.8896	485000	2.3226
0.8898	485100	2.7302
0.8899	485200	2.3418
0.8901	485300	2.0326
0.8903	485400	3.2647
0.8905	485500	2.329
0.8907	485600	2.0593
0.8909	485700	2.2648
0.8910	485800	2.2975
0.8912	485900	2.2593
0.8914	486000	2.4622
0.8916	486100	2.3267
0.8918	486200	2.8931
0.8920	486300	2.6024
0.8921	486400	2.2887
0.8923	486500	2.5904
0.8925	486600	2.8431
0.8927	486700	2.2044
0.8929	486800	2.3983
0.8931	486900	2.3773
0.8932	487000	2.7059
0.8934	487100	2.8182
0.8936	487200	2.049
0.8938	487300	2.561
0.8940	487400	2.3603
0.8942	487500	2.1528
0.8943	487600	2.0982
0.8945	487700	1.9975
0.8947	487800	2.5195
0.8949	487900	3.1827
0.8951	488000	2.8137
0.8953	488100	2.221
0.8954	488200	2.0115
0.8956	488300	1.9297
0.8958	488400	2.4969
0.8960	488500	2.4977
0.8962	488600	2.0577
0.8964	488700	2.1927
0.8965	488800	2.4272
0.8967	488900	2.5895
0.8969	489000	2.0195
0.8971	489100	2.8188
0.8973	489200	3.1166
0.8975	489300	2.708
0.8976	489400	2.5836
0.8978	489500	2.4182
0.8980	489600	2.4799
0.8982	489700	2.7024
0.8984	489800	2.6443
0.8986	489900	2.3569
0.8987	490000	2.4124
0.8989	490100	2.1545
0.8991	490200	2.2205
0.8993	490300	2.2386
0.8995	490400	2.7084
0.8997	490500	2.8009
0.8998	490600	1.8743
0.9000	490700	2.3211
0.9002	490800	2.7557
0.9004	490900	2.4558
0.9006	491000	2.0696
0.9008	491100	2.7958
0.9009	491200	2.2555
0.9011	491300	2.6482
0.9013	491400	2.5122
0.9015	491500	2.6975
0.9017	491600	2.0958
0.9019	491700	2.7115
0.9020	491800	2.4163
0.9022	491900	2.6431
0.9024	492000	2.4929
0.9026	492100	2.4373
0.9028	492200	2.2481
0.9030	492300	2.3693
0.9031	492400	2.3798
0.9033	492500	2.3419
0.9035	492600	2.7378
0.9037	492700	2.7015
0.9039	492800	2.1255
0.9041	492900	2.247
0.9042	493000	2.0516
0.9044	493100	2.357
0.9046	493200	2.4684
0.9048	493300	2.9561
0.9050	493400	2.4145
0.9052	493500	2.2319
0.9053	493600	2.6655
0.9055	493700	2.3543
0.9057	493800	2.2099
0.9059	493900	2.2616
0.9061	494000	2.2054
0.9063	494100	2.7245
0.9064	494200	2.5294
0.9066	494300	1.9695
0.9068	494400	2.4862
0.9070	494500	2.5753
0.9072	494600	2.363
0.9074	494700	2.4689
0.9075	494800	2.8519
0.9077	494900	2.3638
0.9079	495000	2.337
0.9081	495100	2.2678
0.9083	495200	2.5466
0.9085	495300	2.1967
0.9086	495400	2.3849
0.9088	495500	2.4988
0.9090	495600	2.5159
0.9092	495700	2.3554
0.9094	495800	1.9832
0.9096	495900	2.4345
0.9097	496000	2.3796
0.9099	496100	1.8551
0.9101	496200	2.2061
0.9103	496300	2.3423
0.9105	496400	3.0251
0.9107	496500	1.9858
0.9108	496600	2.4761
0.9110	496700	2.4116
0.9112	496800	2.2965
0.9114	496900	2.6763
0.9116	497000	2.5283
0.9118	497100	2.497
0.9119	497200	2.1662
0.9121	497300	2.0512
0.9123	497400	2.0818
0.9125	497500	2.1171
0.9127	497600	2.9069
0.9129	497700	2.3794
0.9130	497800	2.5655
0.9132	497900	2.4988
0.9134	498000	2.8051
0.9136	498100	2.604
0.9138	498200	2.1247
0.9140	498300	2.7158
0.9141	498400	2.5626
0.9143	498500	2.3096
0.9145	498600	2.2664
0.9147	498700	2.2782
0.9149	498800	2.6743
0.9151	498900	2.3624
0.9153	499000	2.8941
0.9154	499100	2.3377
0.9156	499200	2.0605
0.9158	499300	2.3629
0.9160	499400	2.5695
0.9162	499500	2.2535
0.9164	499600	2.9781
0.9165	499700	2.554
0.9167	499800	2.4571
0.9169	499900	2.4486
0.9171	500000	2.4951
0.9173	500100	2.2018
0.9175	500200	2.3188
0.9176	500300	2.0272
0.9178	500400	2.6686
0.9180	500500	2.3985
0.9182	500600	2.0506
0.9184	500700	2.3321
0.9186	500800	2.7462
0.9187	500900	2.5168
0.9189	501000	2.5396
0.9191	501100	2.3668
0.9193	501200	2.2553
0.9195	501300	1.9541
0.9197	501400	2.3411
0.9198	501500	2.7508
0.9200	501600	3.0018
0.9202	501700	2.3188
0.9204	501800	2.0488
0.9206	501900	2.3166
0.9208	502000	1.6908
0.9209	502100	1.8654
0.9211	502200	2.6538
0.9213	502300	2.484
0.9215	502400	2.7265
0.9217	502500	2.4264
0.9219	502600	2.0017
0.9220	502700	2.3818
0.9222	502800	2.2659
0.9224	502900	2.409
0.9226	503000	2.1097
0.9228	503100	2.7288
0.9230	503200	2.1635
0.9231	503300	2.3764
0.9233	503400	2.5452
0.9235	503500	2.5577
0.9237	503600	2.224
0.9239	503700	2.7891
0.9241	503800	2.5191
0.9242	503900	2.2327
0.9244	504000	2.2211
0.9246	504100	2.5718
0.9248	504200	2.2106
0.9250	504300	2.5414
0.9252	504400	2.515
0.9253	504500	2.5649
0.9255	504600	2.4995
0.9257	504700	2.5536
0.9259	504800	3.1829
0.9261	504900	2.2862
0.9263	505000	2.4996
0.9264	505100	2.6471
0.9266	505200	2.367
0.9268	505300	2.1198
0.9270	505400	2.8329
0.9272	505500	2.6164
0.9274	505600	2.3568
0.9275	505700	1.9096
0.9277	505800	2.3712
0.9279	505900	2.0136
0.9281	506000	2.2948
0.9283	506100	2.1653
0.9285	506200	2.5897
0.9286	506300	2.3885
0.9288	506400	2.5138
0.9290	506500	2.15
0.9292	506600	2.0809
0.9294	506700	2.9092
0.9296	506800	1.9996
0.9297	506900	2.1418
0.9299	507000	2.2681
0.9301	507100	2.4233
0.9303	507200	2.3408
0.9305	507300	2.3753
0.9307	507400	2.4672
0.9308	507500	2.2433
0.9310	507600	2.0576
0.9312	507700	2.6525
0.9314	507800	1.9315
0.9316	507900	2.3915
0.9318	508000	2.4859
0.9319	508100	2.6132
0.9321	508200	2.5351
0.9323	508300	1.7546
0.9325	508400	2.3799
0.9327	508500	2.2962
0.9329	508600	2.8809
0.9330	508700	2.3729
0.9332	508800	2.5563
0.9334	508900	2.5067
0.9336	509000	2.4471
0.9338	509100	2.1183
0.9340	509200	1.8209
0.9341	509300	2.2568
0.9343	509400	2.7924
0.9345	509500	2.1597
0.9347	509600	1.9074
0.9349	509700	2.4246
0.9351	509800	2.4144
0.9352	509900	2.2345
0.9354	510000	1.8096
0.9356	510100	2.6078
0.9358	510200	2.1456
0.9360	510300	2.5527
0.9362	510400	2.1484
0.9363	510500	2.7273
0.9365	510600	2.217
0.9367	510700	2.2558
0.9369	510800	2.5117
0.9371	510900	2.5057
0.9373	511000	2.1597
0.9374	511100	2.3522
0.9376	511200	2.5875
0.9378	511300	2.5895
0.9380	511400	2.5014
0.9382	511500	2.0515
0.9384	511600	2.3955
0.9385	511700	2.6733
0.9387	511800	2.4486
0.9389	511900	2.3052
0.9391	512000	2.3994
0.9393	512100	2.697
0.9395	512200	2.2642
0.9396	512300	2.2791
0.9398	512400	2.09
0.9400	512500	2.1475
0.9402	512600	2.3813
0.9404	512700	1.9696
0.9406	512800	2.3201
0.9407	512900	2.3288
0.9409	513000	2.0957
0.9411	513100	2.4177
0.9413	513200	2.481
0.9415	513300	2.2615
0.9417	513400	2.1442
0.9418	513500	2.2091
0.9420	513600	2.3398
0.9422	513700	2.4369
0.9424	513800	2.2964
0.9426	513900	2.8264
0.9428	514000	2.2521
0.9429	514100	2.5057
0.9431	514200	2.3722
0.9433	514300	2.0672
0.9435	514400	2.4801
0.9437	514500	2.3996
0.9439	514600	2.0779
0.9440	514700	2.4243
0.9442	514800	2.1838
0.9444	514900	2.4393
0.9446	515000	2.189
0.9448	515100	2.2115
0.9450	515200	2.0387
0.9451	515300	2.518
0.9453	515400	2.2981
0.9455	515500	1.9995
0.9457	515600	2.1067
0.9459	515700	2.6937
0.9461	515800	2.5934
0.9462	515900	2.5349
0.9464	516000	2.1164
0.9466	516100	2.389
0.9468	516200	2.8075
0.9470	516300	2.4171
0.9472	516400	2.0724
0.9473	516500	2.2634
0.9475	516600	2.4211
0.9477	516700	3.077
0.9479	516800	2.7045
0.9481	516900	2.2057
0.9483	517000	1.9144
0.9484	517100	2.2615
0.9486	517200	2.3007
0.9488	517300	3.2674
0.9490	517400	2.3742
0.9492	517500	2.5865
0.9494	517600	2.7246
0.9495	517700	2.6551
0.9497	517800	2.5323
0.9499	517900	2.2867
0.9501	518000	1.9847
0.9503	518100	2.0762
0.9505	518200	2.1956
0.9506	518300	2.3596
0.9508	518400	2.0063
0.9510	518500	2.2616
0.9512	518600	2.8372
0.9514	518700	2.1217
0.9516	518800	2.0881
0.9518	518900	2.5988
0.9519	519000	2.6922
0.9521	519100	2.316
0.9523	519200	2.6079
0.9525	519300	2.1092
0.9527	519400	2.2886
0.9529	519500	2.363
0.9530	519600	2.6436
0.9532	519700	2.5648
0.9534	519800	2.6193
0.9536	519900	2.3864
0.9538	520000	2.6172
0.9540	520100	2.8113
0.9541	520200	2.3029
0.9543	520300	2.5371
0.9545	520400	2.3672
0.9547	520500	2.4953
0.9549	520600	2.4171
0.9551	520700	2.8953
0.9552	520800	2.2455
0.9554	520900	2.4023
0.9556	521000	2.4508
0.9558	521100	2.4516
0.9560	521200	2.5246
0.9562	521300	2.2124
0.9563	521400	2.0049
0.9565	521500	2.8501
0.9567	521600	1.8354
0.9569	521700	2.1975
0.9571	521800	2.3267
0.9573	521900	2.5964
0.9574	522000	2.9884
0.9576	522100	2.1439
0.9578	522200	2.6289
0.9580	522300	2.7398
0.9582	522400	2.4254
0.9584	522500	2.4017
0.9585	522600	2.373
0.9587	522700	2.5451
0.9589	522800	2.4444
0.9591	522900	2.885
0.9593	523000	2.1499
0.9595	523100	2.8272
0.9596	523200	1.9494
0.9598	523300	2.3387
0.9600	523400	2.9512
0.9602	523500	2.3632
0.9604	523600	2.7552
0.9606	523700	2.1313
0.9607	523800	2.484
0.9609	523900	2.5346
0.9611	524000	2.2023
0.9613	524100	2.4526
0.9615	524200	2.3295
0.9617	524300	2.7197
0.9618	524400	3.1494
0.9620	524500	2.2993
0.9622	524600	2.4856
0.9624	524700	3.1181
0.9626	524800	2.0901
0.9628	524900	2.524
0.9629	525000	2.3689
0.9631	525100	1.9559
0.9633	525200	2.2136
0.9635	525300	2.26
0.9637	525400	2.9065
0.9639	525500	2.2419
0.9640	525600	2.0188
0.9642	525700	2.8786
0.9644	525800	2.1736
0.9646	525900	2.8585
0.9648	526000	2.1875
0.9650	526100	2.8456
0.9651	526200	1.7979
0.9653	526300	2.2705
0.9655	526400	2.0771
0.9657	526500	1.8899
0.9659	526600	2.5358
0.9661	526700	2.0201
0.9662	526800	2.1312
0.9664	526900	2.5881
0.9666	527000	2.7432
0.9668	527100	2.4633
0.9670	527200	2.0749
0.9672	527300	2.4142
0.9673	527400	2.8227
0.9675	527500	3.1565
0.9677	527600	2.1062
0.9679	527700	2.1163
0.9681	527800	2.2387
0.9683	527900	2.1769
0.9684	528000	2.356
0.9686	528100	2.1603
0.9688	528200	2.8688
0.9690	528300	1.8859
0.9692	528400	2.9923
0.9694	528500	2.1055
0.9695	528600	2.304
0.9697	528700	2.6354
0.9699	528800	2.184
0.9701	528900	2.623
0.9703	529000	2.8783
0.9705	529100	2.25
0.9706	529200	2.2932
0.9708	529300	2.4481
0.9710	529400	2.6158
0.9712	529500	2.5323
0.9714	529600	2.3241
0.9716	529700	2.5184
0.9717	529800	2.0259
0.9719	529900	1.9669
0.9721	530000	2.8751
0.9723	530100	2.5943
0.9725	530200	2.2566
0.9727	530300	2.9718
0.9728	530400	2.292
0.9730	530500	2.2478
0.9732	530600	2.3508
0.9734	530700	2.6655
0.9736	530800	3.1384
0.9738	530900	2.1286
0.9739	531000	2.5867
0.9741	531100	2.2557
0.9743	531200	2.5407
0.9745	531300	2.678
0.9747	531400	2.1183
0.9749	531500	2.5112
0.9750	531600	2.3979
0.9752	531700	2.1557
0.9754	531800	2.7304
0.9756	531900	1.7734
0.9758	532000	2.3893
0.9760	532100	2.1216
0.9761	532200	2.1927
0.9763	532300	2.1188
0.9765	532400	2.1039
0.9767	532500	1.8682
0.9769	532600	2.2283
0.9771	532700	3.0675
0.9772	532800	2.1335
0.9774	532900	2.4237
0.9776	533000	2.2491
0.9778	533100	2.7363
0.9780	533200	2.4125
0.9782	533300	1.9634
0.9783	533400	2.6671
0.9785	533500	2.8175
0.9787	533600	1.9954
0.9789	533700	2.303
0.9791	533800	2.6712
0.9793	533900	2.1118
0.9794	534000	2.3042
0.9796	534100	2.8386
0.9798	534200	2.3309
0.9800	534300	2.4642
0.9802	534400	2.118
0.9804	534500	2.8164
0.9805	534600	2.5979
0.9807	534700	2.1601
0.9809	534800	2.875
0.9811	534900	1.9155
0.9813	535000	2.3561
0.9815	535100	1.8337
0.9816	535200	2.4947
0.9818	535300	2.0986
0.9820	535400	1.8943
0.9822	535500	2.1433
0.9824	535600	2.1059
0.9826	535700	2.3893
0.9827	535800	2.2622
0.9829	535900	2.3891
0.9831	536000	2.7848
0.9833	536100	2.4318
0.9835	536200	2.2516
0.9837	536300	2.0171
0.9838	536400	2.0269
0.9840	536500	2.0522
0.9842	536600	2.3076
0.9844	536700	2.0446
0.9846	536800	2.8014
0.9848	536900	2.4971
0.9849	537000	2.4954
0.9851	537100	1.9433
0.9853	537200	2.3798
0.9855	537300	2.6056
0.9857	537400	2.0967
0.9859	537500	2.3317
0.9860	537600	2.3945
0.9862	537700	1.9182
0.9864	537800	2.5348
0.9866	537900	2.1333
0.9868	538000	2.446
0.9870	538100	2.2941
0.9871	538200	2.127
0.9873	538300	2.637
0.9875	538400	2.1091
0.9877	538500	2.0091
0.9879	538600	2.5556
0.9881	538700	2.5311
0.9883	538800	2.5942
0.9884	538900	1.9001
0.9886	539000	2.2069
0.9888	539100	2.404
0.9890	539200	2.8899
0.9892	539300	2.1071
0.9894	539400	2.3799
0.9895	539500	1.9583
0.9897	539600	2.2029
0.9899	539700	2.4715
0.9901	539800	2.8491
0.9903	539900	2.7765
0.9905	540000	3.373
0.9906	540100	2.3788
0.9908	540200	2.6292
0.9910	540300	2.1944
0.9912	540400	2.6278
0.9914	540500	2.7566
0.9916	540600	2.5287
0.9917	540700	1.8489
0.9919	540800	2.6806
0.9921	540900	2.2546
0.9923	541000	2.1025
0.9925	541100	2.8178
0.9927	541200	2.3714
0.9928	541300	2.7133
0.9930	541400	2.47
0.9932	541500	2.0834
0.9934	541600	1.7847
0.9936	541700	2.2932
0.9938	541800	2.1465
0.9939	541900	2.4455
0.9941	542000	2.2841
0.9943	542100	2.5734
0.9945	542200	2.6007
0.9947	542300	2.1258
0.9949	542400	2.1573
0.9950	542500	2.4694
0.9952	542600	2.5051
0.9954	542700	2.3263
0.9956	542800	1.9723
0.9958	542900	2.5446
0.9960	543000	2.472
0.9961	543100	2.569
0.9963	543200	2.2012
0.9965	543300	2.5554
0.9967	543400	2.6364
0.9969	543500	2.2866
0.9971	543600	2.7746
0.9972	543700	1.9528
0.9974	543800	1.8165
0.9976	543900	1.937
0.9978	544000	2.6885
0.9980	544100	2.2711
0.9982	544200	2.9047
0.9983	544300	2.5662
0.9985	544400	2.6321
0.9987	544500	2.7837
0.9989	544600	2.7617
0.9991	544700	2.5151
0.9993	544800	2.3399
0.9994	544900	3.0119
0.9996	545000	2.4235
0.9998	545100	2.3808
1.0000	545200	2.3549

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},
}