all-MiniLM-L6-v83-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v67 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_v67
• 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 = [
    'henge chair and bookcase 2',
    'neck free bandana - raindropgrey libra bandana ultragrip bandana workout bandana nonslip bandana velvet bandana bandana neck free bandana raindrop bandana bandana neck free bandana raindrop bandana',
    'bali floor lamp handpick handpick floor lamp rustic floor lamp palm leaves floor lamp black floor lamp metal base floor lamp bali lamp floor lamp lamp bali lamp floor lamp lamp',
]
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, -0.1181,  0.0299],
#         [-0.1181,  1.0000, -0.1149],
#         [ 0.0299, -0.1149,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v67

• Dataset: pairs_with_scores_v67 at 38f07b3
• Size: 65,396,625 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: 7.91 tokens max: 27 tokens	min: 6 tokens mean: 45.72 tokens max: 256 tokens	min: 0.0 mean: 0.01 max: 1.0

• Samples:

  sentence1	sentence2	score
  baladi qeshta plate	optimum nutrition glutamine 300g powder 58 servings ws nutrition glutamine powder glutamine powder boost protein synthesis powder optimum nutrition powder enhance workout performance powder improve muscle recovery powder glutamine glutamine powder muscle builder powder optimum nutrition optimum nutrition glutamine powder optimum nutrition powder glutamine powder muscle builder powder optimum nutrition optimum nutrition glutamine powder optimum nutrition powder	0.0
  diabetic pecan bar	round rose shape cake mold nonstick cake mold healthy cooking cake mold whitford cake mold heatinsulated handles cake mold stainless steel cover cake mold pfoafree cake mold rose cake mold cookware cake mold round cake mold cake mold round cake mold	0.0
  red velvet cupcakes	total plastic fencing shears 22 tools equipment fencing shears plastic shears shears total plastic fencing shears fencing shears plastic shears shears total plastic fencing shears	0.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_with_scores_v67

• Dataset: pairs_with_scores_v67 at 38f07b3
• Size: 328,627 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: 7.8 tokens max: 28 tokens	min: 5 tokens mean: 44.87 tokens max: 256 tokens	min: 0.0 mean: 0.01 max: 1.0

• Samples:

  sentence1	sentence2	score
  mint hot chocolate	baba ghanouj dip v baba ghanouj dip dip vegan baba ghanouj dip baba ghanouj dip dip vegan baba ghanouj dip	0.0
  sponge balls gun toy	multi color rug colorful rugs summer house rugs beach mat multi color rug rug carpet multi color carpet multi nan rug multi color rug rug carpet multi color carpet multi nan rug	0.0
  the knit jumpsuit	spinaci alla paradiso spinach pasta mushroom fettuccine red bell pepper pasta garlic fettuccine creamy fettuccine parmigiano pasta olive oil fettuccine parmesan garlic fettuccine vegetarian pasta fettuccine italian pasta pasta spinaci alla paradiso pasta italian macarona macarona spinaci alla paradiso macarona italian pasta pasta spinaci alla paradiso pasta italian macarona macarona spinaci alla paradiso macarona	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
0.8252	421600	0.527
0.8254	421700	0.6867
0.8256	421800	0.4095
0.8258	421900	0.7812
0.8260	422000	0.5856
0.8262	422100	0.5347
0.8264	422200	0.4451
0.8266	422300	0.7198
0.8268	422400	0.6055
0.8270	422500	0.7236
0.8271	422600	0.45
0.8273	422700	0.5446
0.8275	422800	0.722
0.8277	422900	0.3036
0.8279	423000	0.3999
0.8281	423100	0.6977
0.8283	423200	0.5578
0.8285	423300	0.5552
0.8287	423400	0.7329
0.8289	423500	0.3628
0.8291	423600	0.4266
0.8293	423700	0.3921
0.8295	423800	0.4769
0.8297	423900	0.7314
0.8299	424000	0.6847
0.8301	424100	0.5028
0.8303	424200	0.5677
0.8305	424300	0.3816
0.8307	424400	0.3268
0.8309	424500	0.3446
0.8311	424600	0.5317
0.8313	424700	0.4947
0.8315	424800	0.688
0.8317	424900	0.6102
0.8318	425000	0.2036
0.8320	425100	0.463
0.8322	425200	0.6932
0.8324	425300	0.4799
0.8326	425400	0.4226
0.8328	425500	0.3707
0.8330	425600	0.4785
0.8332	425700	0.6319
0.8334	425800	0.598
0.8336	425900	0.4734
0.8338	426000	0.5288
0.8340	426100	0.5372
0.8342	426200	0.1846
0.8344	426300	0.5916
0.8346	426400	0.4158
0.8348	426500	0.2081
0.8350	426600	0.5584
0.8352	426700	0.4774
0.8354	426800	0.3597
0.8356	426900	0.5778
0.8358	427000	0.4236
0.8360	427100	0.2655
0.8362	427200	0.6163
0.8363	427300	0.3875
0.8365	427400	0.6192
0.8367	427500	0.6791
0.8369	427600	0.6027
0.8371	427700	0.6457
0.8373	427800	0.5807
0.8375	427900	0.418
0.8377	428000	0.3965
0.8379	428100	0.6073
0.8381	428200	0.8342
0.8383	428300	0.7769
0.8385	428400	0.5848
0.8387	428500	0.5223
0.8389	428600	0.484
0.8391	428700	0.4575
0.8393	428800	0.2749
0.8395	428900	0.7591
0.8397	429000	0.4901
0.8399	429100	0.4881
0.8401	429200	0.3394
0.8403	429300	0.3203
0.8405	429400	0.6151
0.8407	429500	0.5295
0.8408	429600	0.3161
0.8410	429700	0.4494
0.8412	429800	0.3431
0.8414	429900	0.5481
0.8416	430000	0.3513
0.8418	430100	0.4721
0.8420	430200	0.4604
0.8422	430300	0.6932
0.8424	430400	0.4066
0.8426	430500	0.4241
0.8428	430600	0.3459
0.8430	430700	0.7091
0.8432	430800	0.5081
0.8434	430900	0.364
0.8436	431000	0.2193
0.8438	431100	0.5851
0.8440	431200	0.8647
0.8442	431300	0.5695
0.8444	431400	0.4309
0.8446	431500	0.3964
0.8448	431600	0.5092
0.8450	431700	0.4192
0.8452	431800	0.3321
0.8454	431900	0.4958
0.8455	432000	0.4573
0.8457	432100	0.4274
0.8459	432200	0.707
0.8461	432300	0.3366
0.8463	432400	0.407
0.8465	432500	0.4362
0.8467	432600	0.3785
0.8469	432700	0.646
0.8471	432800	0.2711
0.8473	432900	0.3797
0.8475	433000	0.4421
0.8477	433100	0.3746
0.8479	433200	0.3833
0.8481	433300	0.6702
0.8483	433400	0.3983
0.8485	433500	0.5933
0.8487	433600	0.4656
0.8489	433700	0.3944
0.8491	433800	0.5212
0.8493	433900	0.5147
0.8495	434000	0.398
0.8497	434100	0.4007
0.8499	434200	0.7725
0.8500	434300	0.3312
0.8502	434400	0.5865
0.8504	434500	0.3492
0.8506	434600	0.4566
0.8508	434700	0.3579
0.8510	434800	0.5918
0.8512	434900	0.6588
0.8514	435000	0.3922
0.8516	435100	0.7168
0.8518	435200	0.4758
0.8520	435300	0.5858
0.8522	435400	0.3031
0.8524	435500	0.3105
0.8526	435600	0.7408
0.8528	435700	0.7323
0.8530	435800	0.4258
0.8532	435900	0.6648
0.8534	436000	0.502
0.8536	436100	0.53
0.8538	436200	0.5774
0.8540	436300	0.3993
0.8542	436400	0.708
0.8544	436500	0.35
0.8546	436600	0.4202
0.8547	436700	0.254
0.8549	436800	0.5858
0.8551	436900	0.6767
0.8553	437000	0.7262
0.8555	437100	0.3766
0.8557	437200	0.4347
0.8559	437300	0.4218
0.8561	437400	0.2354
0.8563	437500	0.3322
0.8565	437600	0.3691
0.8567	437700	0.5201
0.8569	437800	0.5213
0.8571	437900	0.478
0.8573	438000	0.7821
0.8575	438100	0.571
0.8577	438200	0.2786
0.8579	438300	0.5798
0.8581	438400	0.4769
0.8583	438500	0.6041
0.8585	438600	0.7343
0.8587	438700	0.4441
0.8589	438800	0.5972
0.8591	438900	0.4738
0.8592	439000	0.4362
0.8594	439100	0.5589
0.8596	439200	0.536
0.8598	439300	0.5039
0.8600	439400	0.677
0.8602	439500	0.5364
0.8604	439600	0.2835
0.8606	439700	0.4349
0.8608	439800	0.5116
0.8610	439900	0.5744
0.8612	440000	0.5407
0.8614	440100	0.6611
0.8616	440200	0.2599
0.8618	440300	0.4689
0.8620	440400	0.1809
0.8622	440500	0.4187
0.8624	440600	0.5378
0.8626	440700	0.6532
0.8628	440800	0.7364
0.8630	440900	0.5049
0.8632	441000	0.2622
0.8634	441100	0.5027
0.8636	441200	0.4732
0.8637	441300	0.4473
0.8639	441400	0.5057
0.8641	441500	0.5872
0.8643	441600	0.6098
0.8645	441700	0.2273
0.8647	441800	0.6347
0.8649	441900	0.4795
0.8651	442000	0.2208
0.8653	442100	0.4943
0.8655	442200	0.514
0.8657	442300	0.6228
0.8659	442400	0.3219
0.8661	442500	0.4201
0.8663	442600	0.6866
0.8665	442700	0.6909
0.8667	442800	0.341
0.8669	442900	0.7984
0.8671	443000	0.4511
0.8673	443100	0.3439
0.8675	443200	0.2702
0.8677	443300	0.3269
0.8679	443400	0.3773
0.8681	443500	0.508
0.8683	443600	0.3347
0.8684	443700	0.3746
0.8686	443800	0.4986
0.8688	443900	0.3823
0.8690	444000	0.248
0.8692	444100	0.5019
0.8694	444200	0.5071
0.8696	444300	0.6675
0.8698	444400	0.5142
0.8700	444500	0.6392
0.8702	444600	0.3778
0.8704	444700	0.2867
0.8706	444800	0.4262
0.8708	444900	0.6659
0.8710	445000	0.8329
0.8712	445100	0.4115
0.8714	445200	0.3488
0.8716	445300	0.6665
0.8718	445400	0.4603
0.8720	445500	0.3891
0.8722	445600	0.4256
0.8724	445700	0.6711
0.8726	445800	0.393
0.8728	445900	0.2396
0.8729	446000	0.418
0.8731	446100	0.3636
0.8733	446200	0.2813
0.8735	446300	0.2291
0.8737	446400	0.3761
0.8739	446500	0.5519
0.8741	446600	0.2789
0.8743	446700	0.3791
0.8745	446800	0.5674
0.8747	446900	0.4339
0.8749	447000	0.3097
0.8751	447100	0.4902
0.8753	447200	0.6218
0.8755	447300	0.393
0.8757	447400	0.8822
0.8759	447500	0.4705
0.8761	447600	0.8486
0.8763	447700	0.5264
0.8765	447800	0.3055
0.8767	447900	0.266
0.8769	448000	0.5581
0.8771	448100	0.4763
0.8773	448200	0.6294
0.8775	448300	0.4108
0.8776	448400	0.4608
0.8778	448500	0.4401
0.8780	448600	0.551
0.8782	448700	0.62
0.8784	448800	0.5487
0.8786	448900	0.4898
0.8788	449000	0.2627
0.8790	449100	0.5949
0.8792	449200	0.4488
0.8794	449300	0.419
0.8796	449400	0.4093
0.8798	449500	0.4124
0.8800	449600	0.5581
0.8802	449700	0.2496
0.8804	449800	0.5165
0.8806	449900	0.3358
0.8808	450000	0.4713
0.8810	450100	0.469
0.8812	450200	0.346
0.8814	450300	0.3739
0.8816	450400	0.5054
0.8818	450500	0.4999
0.8820	450600	0.3815
0.8821	450700	0.5401
0.8823	450800	0.5148
0.8825	450900	0.4219
0.8827	451000	0.5426
0.8829	451100	0.4648
0.8831	451200	0.4022
0.8833	451300	0.5034
0.8835	451400	0.6318
0.8837	451500	0.4865
0.8839	451600	0.3905
0.8841	451700	0.4396
0.8843	451800	0.4778
0.8845	451900	0.6824
0.8847	452000	0.42
0.8849	452100	0.4478
0.8851	452200	0.4188
0.8853	452300	0.703
0.8855	452400	0.5908
0.8857	452500	0.3153
0.8859	452600	0.57
0.8861	452700	0.4793
0.8863	452800	0.5454
0.8865	452900	0.6144
0.8866	453000	0.433
0.8868	453100	0.1715
0.8870	453200	0.5829
0.8872	453300	0.604
0.8874	453400	0.572
0.8876	453500	0.6259
0.8878	453600	0.4585
0.8880	453700	0.5841
0.8882	453800	0.5502
0.8884	453900	0.7073
0.8886	454000	0.3995
0.8888	454100	0.4625
0.8890	454200	0.6379
0.8892	454300	0.4435
0.8894	454400	0.4153
0.8896	454500	0.4956
0.8898	454600	0.4053
0.8900	454700	0.3189
0.8902	454800	0.6763
0.8904	454900	0.2707
0.8906	455000	0.4454
0.8908	455100	0.6353
0.8910	455200	0.4824
0.8912	455300	0.3994
0.8913	455400	0.456
0.8915	455500	0.466
0.8917	455600	0.448
0.8919	455700	0.3536
0.8921	455800	0.5261
0.8923	455900	0.4858
0.8925	456000	0.5906
0.8927	456100	0.6586
0.8929	456200	0.6121
0.8931	456300	0.5187
0.8933	456400	0.387
0.8935	456500	0.46
0.8937	456600	0.4955
0.8939	456700	0.6318
0.8941	456800	0.7264
0.8943	456900	0.4383
0.8945	457000	0.5132
0.8947	457100	0.2948
0.8949	457200	0.2761
0.8951	457300	0.42
0.8953	457400	0.3544
0.8955	457500	0.3391
0.8957	457600	0.5411
0.8958	457700	0.3267
0.8960	457800	0.5672
0.8962	457900	0.5252
0.8964	458000	0.91
0.8966	458100	0.3517
0.8968	458200	0.565
0.8970	458300	0.5799
0.8972	458400	0.4932
0.8974	458500	0.7191
0.8976	458600	0.4632
0.8978	458700	0.3785
0.8980	458800	0.4641
0.8982	458900	0.3703
0.8984	459000	0.508
0.8986	459100	0.7238
0.8988	459200	0.512
0.8990	459300	0.6716
0.8992	459400	0.276
0.8994	459500	0.5
0.8996	459600	0.749
0.8998	459700	0.2815
0.9000	459800	0.4261
0.9002	459900	0.4092
0.9004	460000	0.4665
0.9005	460100	0.565
0.9007	460200	0.432
0.9009	460300	0.3478
0.9011	460400	0.6396
0.9013	460500	0.3599
0.9015	460600	0.4756
0.9017	460700	0.2947
0.9019	460800	0.4467
0.9021	460900	0.5046
0.9023	461000	0.6621
0.9025	461100	0.4906
0.9027	461200	0.5637
0.9029	461300	0.3635
0.9031	461400	0.5931
0.9033	461500	0.4679
0.9035	461600	0.6651
0.9037	461700	0.4696
0.9039	461800	0.6805
0.9041	461900	0.3048
0.9043	462000	0.4992
0.9045	462100	0.5021
0.9047	462200	0.5696
0.9049	462300	0.466
0.9050	462400	0.4057
0.9052	462500	0.4309
0.9054	462600	0.4747
0.9056	462700	0.3036
0.9058	462800	0.7552
0.9060	462900	0.4432
0.9062	463000	0.434
0.9064	463100	0.3852
0.9066	463200	0.2399
0.9068	463300	0.2525
0.9070	463400	0.5292
0.9072	463500	0.5165
0.9074	463600	0.636
0.9076	463700	0.4585
0.9078	463800	0.467
0.9080	463900	0.3354
0.9082	464000	0.5645
0.9084	464100	0.4106
0.9086	464200	0.3041
0.9088	464300	0.295
0.9090	464400	0.4788
0.9092	464500	0.3753
0.9094	464600	0.468
0.9095	464700	0.5996
0.9097	464800	0.4116
0.9099	464900	0.5058
0.9101	465000	0.5695
0.9103	465100	0.2807
0.9105	465200	0.5025
0.9107	465300	0.4251
0.9109	465400	0.4816
0.9111	465500	0.5366
0.9113	465600	0.3668
0.9115	465700	0.2608
0.9117	465800	0.377
0.9119	465900	0.5972
0.9121	466000	0.3592
0.9123	466100	0.1636
0.9125	466200	0.5718
0.9127	466300	0.4446
0.9129	466400	0.5606
0.9131	466500	0.5096
0.9133	466600	0.5348
0.9135	466700	0.4165
0.9137	466800	0.5285
0.9139	466900	0.6643
0.9141	467000	0.3291
0.9142	467100	0.5175
0.9144	467200	0.414
0.9146	467300	0.207
0.9148	467400	0.4597
0.9150	467500	0.4428
0.9152	467600	0.6733
0.9154	467700	0.43
0.9156	467800	0.4921
0.9158	467900	0.4403
0.9160	468000	0.6157
0.9162	468100	0.6347
0.9164	468200	0.5704
0.9166	468300	0.4769
0.9168	468400	0.4922
0.9170	468500	0.5701
0.9172	468600	0.4095
0.9174	468700	0.6853
0.9176	468800	0.5165
0.9178	468900	0.3356
0.9180	469000	0.4852
0.9182	469100	0.3786
0.9184	469200	0.5004
0.9186	469300	0.5494
0.9187	469400	0.5013
0.9189	469500	0.4574
0.9191	469600	0.2865
0.9193	469700	0.6342
0.9195	469800	0.5186
0.9197	469900	0.2282
0.9199	470000	0.4409
0.9201	470100	0.4963
0.9203	470200	0.4018
0.9205	470300	0.5724
0.9207	470400	0.2774
0.9209	470500	0.4137
0.9211	470600	0.5786
0.9213	470700	0.1981
0.9215	470800	0.4571
0.9217	470900	0.5272
0.9219	471000	0.51
0.9221	471100	0.5813
0.9223	471200	0.4677
0.9225	471300	0.2005
0.9227	471400	0.517
0.9229	471500	0.4571
0.9231	471600	0.3768
0.9233	471700	0.5788
0.9234	471800	0.5202
0.9236	471900	0.5319
0.9238	472000	0.4892
0.9240	472100	0.3811
0.9242	472200	0.5094
0.9244	472300	0.4268
0.9246	472400	0.6923
0.9248	472500	0.5328
0.9250	472600	0.4234
0.9252	472700	0.4665
0.9254	472800	0.4783
0.9256	472900	0.5302
0.9258	473000	0.4576
0.9260	473100	0.4784
0.9262	473200	0.6641
0.9264	473300	0.6046
0.9266	473400	0.5142
0.9268	473500	0.7186
0.9270	473600	0.5169
0.9272	473700	0.5231
0.9274	473800	0.6647
0.9276	473900	0.6718
0.9278	474000	0.7383
0.9279	474100	0.6124
0.9281	474200	0.5707
0.9283	474300	0.4976
0.9285	474400	0.5868
0.9287	474500	0.4727
0.9289	474600	0.3197
0.9291	474700	0.5164
0.9293	474800	0.5052
0.9295	474900	0.3765
0.9297	475000	0.6181
0.9299	475100	0.4057
0.9301	475200	0.4594
0.9303	475300	0.7327
0.9305	475400	0.4382
0.9307	475500	0.2938
0.9309	475600	0.2228
0.9311	475700	0.5859
0.9313	475800	0.5893
0.9315	475900	0.249
0.9317	476000	0.863
0.9319	476100	0.6779
0.9321	476200	0.4547
0.9323	476300	0.3713
0.9325	476400	0.434
0.9326	476500	0.312
0.9328	476600	0.589
0.9330	476700	0.3038
0.9332	476800	0.3404
0.9334	476900	0.4664
0.9336	477000	0.359
0.9338	477100	0.5907
0.9340	477200	0.4026
0.9342	477300	0.3311
0.9344	477400	0.4857
0.9346	477500	0.4286
0.9348	477600	0.4994
0.9350	477700	0.515
0.9352	477800	0.2821
0.9354	477900	0.4392
0.9356	478000	0.3645
0.9358	478100	0.4753
0.9360	478200	0.2058
0.9362	478300	0.6372
0.9364	478400	0.3852
0.9366	478500	0.3343
0.9368	478600	0.4757
0.9370	478700	0.2278
0.9371	478800	0.558
0.9373	478900	0.3805
0.9375	479000	0.2577
0.9377	479100	0.572
0.9379	479200	0.2547
0.9381	479300	0.2882
0.9383	479400	0.4115
0.9385	479500	0.6186
0.9387	479600	0.7437
0.9389	479700	0.47
0.9391	479800	0.6397
0.9393	479900	0.4718
0.9395	480000	0.8374
0.9397	480100	0.4704
0.9399	480200	0.5336
0.9401	480300	0.881
0.9403	480400	0.533
0.9405	480500	0.2627
0.9407	480600	0.5115
0.9409	480700	0.3104
0.9411	480800	0.3662
0.9413	480900	0.5074
0.9415	481000	0.4883
0.9416	481100	0.3138
0.9418	481200	0.4162
0.9420	481300	0.7396
0.9422	481400	0.4731
0.9424	481500	0.5091
0.9426	481600	0.5645
0.9428	481700	0.4186
0.9430	481800	0.3508
0.9432	481900	0.3432
0.9434	482000	0.5344
0.9436	482100	0.3951
0.9438	482200	0.4525
0.9440	482300	0.5419
0.9442	482400	0.2866
0.9444	482500	0.3396
0.9446	482600	0.4842
0.9448	482700	0.2872
0.9450	482800	0.6347
0.9452	482900	0.5994
0.9454	483000	0.4243
0.9456	483100	0.2367
0.9458	483200	0.4187
0.9460	483300	0.338
0.9462	483400	0.4273
0.9463	483500	0.4366
0.9465	483600	0.7104
0.9467	483700	0.558
0.9469	483800	0.3544
0.9471	483900	0.6016
0.9473	484000	0.6432
0.9475	484100	0.3605
0.9477	484200	0.4009
0.9479	484300	0.3945
0.9481	484400	0.4941
0.9483	484500	0.4264
0.9485	484600	0.5525
0.9487	484700	0.5157
0.9489	484800	0.5479
0.9491	484900	0.3311
0.9493	485000	0.4652
0.9495	485100	0.3268
0.9497	485200	0.2551
0.9499	485300	0.7131
0.9501	485400	0.1545
0.9503	485500	0.4479
0.9505	485600	0.5279
0.9507	485700	0.647
0.9508	485800	0.6092
0.9510	485900	0.4673
0.9512	486000	0.5326
0.9514	486100	0.3222
0.9516	486200	0.3999
0.9518	486300	0.3467
0.9520	486400	0.5624
0.9522	486500	0.5002
0.9524	486600	0.3063
0.9526	486700	0.3624
0.9528	486800	0.4062
0.9530	486900	0.7078
0.9532	487000	0.5306
0.9534	487100	0.2256
0.9536	487200	0.4881
0.9538	487300	0.4701
0.9540	487400	0.5641
0.9542	487500	0.3832
0.9544	487600	0.4693
0.9546	487700	0.3029
0.9548	487800	0.3395
0.9550	487900	0.7536
0.9552	488000	0.1996
0.9554	488100	0.4883
0.9555	488200	0.6352
0.9557	488300	0.8098
0.9559	488400	0.4542
0.9561	488500	0.5242
0.9563	488600	0.6252
0.9565	488700	0.5076
0.9567	488800	0.6284
0.9569	488900	0.2738
0.9571	489000	0.2661
0.9573	489100	0.4144
0.9575	489200	0.5165
0.9577	489300	0.1962
0.9579	489400	0.2752
0.9581	489500	0.4945
0.9583	489600	0.4698
0.9585	489700	0.4292
0.9587	489800	0.6252
0.9589	489900	0.5178
0.9591	490000	0.3462
0.9593	490100	0.2622
0.9595	490200	0.4657
0.9597	490300	0.4289
0.9599	490400	0.4461
0.9600	490500	0.8697
0.9602	490600	0.6165
0.9604	490700	0.4929
0.9606	490800	0.3413
0.9608	490900	0.4872
0.9610	491000	0.4736
0.9612	491100	0.1794
0.9614	491200	0.7041
0.9616	491300	0.4494
0.9618	491400	0.4179
0.9620	491500	0.2557
0.9622	491600	0.4197
0.9624	491700	0.5246
0.9626	491800	0.5922
0.9628	491900	0.6314
0.9630	492000	0.5771
0.9632	492100	0.36
0.9634	492200	0.3529
0.9636	492300	0.427
0.9638	492400	0.528
0.9640	492500	0.3588
0.9642	492600	0.6069
0.9644	492700	0.3908
0.9645	492800	0.5345
0.9647	492900	0.6541
0.9649	493000	0.4447
0.9651	493100	0.3473
0.9653	493200	0.3605
0.9655	493300	0.5213
0.9657	493400	0.5283
0.9659	493500	0.5645
0.9661	493600	0.5567
0.9663	493700	0.5123
0.9665	493800	0.4996
0.9667	493900	0.4733
0.9669	494000	0.4836
0.9671	494100	0.3959
0.9673	494200	0.2585
0.9675	494300	0.5084
0.9677	494400	0.3413
0.9679	494500	0.4827
0.9681	494600	0.5682
0.9683	494700	0.5238
0.9685	494800	0.4401
0.9687	494900	0.2702
0.9689	495000	0.6563
0.9691	495100	0.6965
0.9692	495200	0.2334
0.9694	495300	0.3933
0.9696	495400	0.472
0.9698	495500	0.3866
0.9700	495600	0.6007
0.9702	495700	0.4242
0.9704	495800	0.4588
0.9706	495900	0.3699
0.9708	496000	0.4209
0.9710	496100	0.5983
0.9712	496200	0.5552
0.9714	496300	0.4933
0.9716	496400	0.2448
0.9718	496500	0.2024
0.9720	496600	0.4709
0.9722	496700	0.4145
0.9724	496800	0.65
0.9726	496900	0.5921
0.9728	497000	0.5812
0.9730	497100	0.4657
0.9732	497200	0.6306
0.9734	497300	0.5856
0.9736	497400	0.5151
0.9737	497500	0.5238
0.9739	497600	0.6003
0.9741	497700	0.5134
0.9743	497800	0.413
0.9745	497900	0.885
0.9747	498000	0.4356
0.9749	498100	0.3875
0.9751	498200	0.4197
0.9753	498300	0.7071
0.9755	498400	0.4413
0.9757	498500	0.5242
0.9759	498600	0.4832
0.9761	498700	0.4749
0.9763	498800	0.4536
0.9765	498900	0.3056
0.9767	499000	0.3277
0.9769	499100	0.2471
0.9771	499200	0.4415
0.9773	499300	0.5647
0.9775	499400	0.4275
0.9777	499500	0.3088
0.9779	499600	0.5621
0.9781	499700	0.3009
0.9783	499800	0.4238
0.9784	499900	0.5066
0.9786	500000	0.2652
0.9788	500100	0.2096
0.9790	500200	0.5
0.9792	500300	0.3968
0.9794	500400	0.3574
0.9796	500500	0.2184
0.9798	500600	0.4168
0.9800	500700	0.6018
0.9802	500800	0.3362
0.9804	500900	0.566
0.9806	501000	0.4603
0.9808	501100	0.5562
0.9810	501200	0.6819
0.9812	501300	0.3093
0.9814	501400	0.4562
0.9816	501500	0.2537
0.9818	501600	0.665
0.9820	501700	0.3832
0.9822	501800	0.6498
0.9824	501900	0.3836
0.9826	502000	0.8001
0.9828	502100	0.2003
0.9829	502200	0.3801
0.9831	502300	0.3715
0.9833	502400	0.3226
0.9835	502500	0.8292
0.9837	502600	0.3651
0.9839	502700	0.537
0.9841	502800	0.3987
0.9843	502900	0.3794
0.9845	503000	0.6914
0.9847	503100	0.5507
0.9849	503200	0.4579
0.9851	503300	0.4184
0.9853	503400	0.4181
0.9855	503500	0.644
0.9857	503600	0.4458
0.9859	503700	0.5145
0.9861	503800	0.4957
0.9863	503900	0.5733
0.9865	504000	0.4556
0.9867	504100	0.3899
0.9869	504200	0.4923
0.9871	504300	0.4849
0.9873	504400	0.3509
0.9874	504500	0.674
0.9876	504600	0.2371
0.9878	504700	0.5729
0.9880	504800	0.4554
0.9882	504900	0.2881
0.9884	505000	0.6204
0.9886	505100	0.7559
0.9888	505200	0.3141
0.9890	505300	0.2824
0.9892	505400	0.5978
0.9894	505500	0.3659
0.9896	505600	0.4224
0.9898	505700	0.3314
0.9900	505800	0.4367
0.9902	505900	0.3334
0.9904	506000	0.5803
0.9906	506100	0.2818
0.9908	506200	0.5703
0.9910	506300	0.4657
0.9912	506400	0.4177
0.9914	506500	0.3394
0.9916	506600	0.5064
0.9918	506700	0.6834
0.9920	506800	0.5492
0.9921	506900	0.4035
0.9923	507000	0.4495
0.9925	507100	0.3237
0.9927	507200	0.6566
0.9929	507300	0.4246
0.9931	507400	0.7875
0.9933	507500	0.5485
0.9935	507600	0.6658
0.9937	507700	0.3354
0.9939	507800	0.4725
0.9941	507900	0.6616
0.9943	508000	0.6485
0.9945	508100	0.4389
0.9947	508200	0.5407
0.9949	508300	0.7002
0.9951	508400	0.7161
0.9953	508500	0.4251
0.9955	508600	0.6348
0.9957	508700	0.2893
0.9959	508800	0.4279
0.9961	508900	0.5075
0.9963	509000	0.519
0.9965	509100	0.3323
0.9966	509200	0.5461
0.9968	509300	0.529
0.9970	509400	0.4357
0.9972	509500	0.2738
0.9974	509600	0.3871
0.9976	509700	0.7447
0.9978	509800	0.3894
0.9980	509900	0.4419
0.9982	510000	0.3943
0.9984	510100	0.3806
0.9986	510200	0.7614
0.9988	510300	0.5159
0.9990	510400	0.5546
0.9992	510500	0.7035
0.9994	510600	0.3879
0.9996	510700	0.7201
0.9998	510800	0.5359
1.0000	510900	0.398

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},
}