all-MiniLM-L6-v14-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v13_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_three_scores_v13_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 = [
    'Even applicationLiquid Primer',
    'Portable beach stand',
    'Bowl',
]
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, 0.7720, 0.7641],
#         [0.7720, 1.0000, 0.9039],
#         [0.7641, 0.9039, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v13_description

• Dataset: pairs_three_scores_v13_description at 6fd8086
• Size: 10,001,819 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: 5.97 tokens max: 43 tokens	min: 3 tokens mean: 6.17 tokens max: 69 tokens	min: 0.13 mean: 0.25 max: 0.8

• Samples:

  sentence1	sentence2	score
  Adult Cat Treats	sweet chili vegan nugget	0.28
  Brick Sweater	Chestnut Brown hair dye	0.18
  Sweetal	PVC tote bag	0.22

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v13_description

• Dataset: pairs_three_scores_v13_description at 6fd8086
• Size: 50,261 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: 5.82 tokens max: 54 tokens	min: 3 tokens mean: 6.47 tokens max: 67 tokens	min: 0.14 mean: 0.25 max: 0.83

• Samples:

  sentence1	sentence2	score
  Buff Foundation	nursing product	0.27
  Elastic waist Pants	Crisp rim bowl	0.28
  Appetizers	comfortable Jumpsuit	0.2

• 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
0.0013	100	11.9475
0.0026	200	11.5542
0.0038	300	11.4709
0.0051	400	11.061
0.0064	500	10.8765
0.0077	600	10.7174
0.0090	700	10.4134
0.0102	800	10.2001
0.0115	900	10.0598
0.0128	1000	9.8019
0.0141	1100	9.6144
0.0154	1200	9.3509
0.0166	1300	9.1212
0.0179	1400	8.9316
0.0192	1500	8.8345
0.0205	1600	8.791
0.0218	1700	8.7675
0.0230	1800	8.7487
0.0243	1900	8.7465
0.0256	2000	8.7353
0.0269	2100	8.7231
0.0282	2200	8.7079
0.0294	2300	8.6999
0.0307	2400	8.7062
0.0320	2500	8.7044
0.0333	2600	8.6868
0.0346	2700	8.6834
0.0358	2800	8.6796
0.0371	2900	8.6736
0.0384	3000	8.6677
0.0397	3100	8.653
0.0410	3200	8.6472
0.0422	3300	8.6597
0.0435	3400	8.646
0.0448	3500	8.6523
0.0461	3600	8.6513
0.0474	3700	8.639
0.0486	3800	8.6269
0.0499	3900	8.6201
0.0512	4000	8.634
0.0525	4100	8.6203
0.0537	4200	8.6243
0.0550	4300	8.6289
0.0563	4400	8.6065
0.0576	4500	8.6068
0.0589	4600	8.6026
0.0601	4700	8.6067
0.0614	4800	8.6048
0.0627	4900	8.6078
0.0640	5000	8.6006
0.0653	5100	8.6056
0.0665	5200	8.5972
0.0678	5300	8.5999
0.0691	5400	8.5856
0.0704	5500	8.59
0.0717	5600	8.5799
0.0729	5700	8.5922
0.0742	5800	8.573
0.0755	5900	8.5764
0.0768	6000	8.5729
0.0781	6100	8.5816
0.0793	6200	8.5763
0.0806	6300	8.5784
0.0819	6400	8.5798
0.0832	6500	8.5775
0.0845	6600	8.5698
0.0857	6700	8.5695
0.0870	6800	8.5661
0.0883	6900	8.5594
0.0896	7000	8.5523
0.0909	7100	8.5615
0.0921	7200	8.5565
0.0934	7300	8.5522
0.0947	7400	8.5463
0.0960	7500	8.5433
0.0973	7600	8.5307
0.0985	7700	8.5448
0.0998	7800	8.5462
0.1011	7900	8.529
0.1024	8000	8.5377
0.1037	8100	8.5306
0.1049	8200	8.5407
0.1062	8300	8.5382
0.1075	8400	8.5281
0.1088	8500	8.5358
0.1101	8600	8.528
0.1113	8700	8.5216
0.1126	8800	8.5264
0.1139	8900	8.5178
0.1152	9000	8.525
0.1165	9100	8.5221
0.1177	9200	8.5134
0.1190	9300	8.5212
0.1203	9400	8.5197
0.1216	9500	8.5189
0.1229	9600	8.5091
0.1241	9700	8.5085
0.1254	9800	8.5176
0.1267	9900	8.5143
0.1280	10000	8.5011
0.1293	10100	8.4946
0.1305	10200	8.504
0.1318	10300	8.5046
0.1331	10400	8.5074
0.1344	10500	8.504
0.1357	10600	8.5057
0.1369	10700	8.5027
0.1382	10800	8.5046
0.1395	10900	8.4947
0.1408	11000	8.4928
0.1421	11100	8.5046
0.1433	11200	8.4979
0.1446	11300	8.4974
0.1459	11400	8.49
0.1472	11500	8.4924
0.1485	11600	8.4981
0.1497	11700	8.4821
0.1510	11800	8.4827
0.1523	11900	8.4849
0.1536	12000	8.4816
0.1549	12100	8.4959
0.1561	12200	8.4887
0.1574	12300	8.4904
0.1587	12400	8.4805
0.1600	12500	8.4821
0.1612	12600	8.4896
0.1625	12700	8.4888
0.1638	12800	8.4816
0.1651	12900	8.4784
0.1664	13000	8.4832
0.1676	13100	8.4832
0.1689	13200	8.4731
0.1702	13300	8.4835
0.1715	13400	8.4808
0.1728	13500	8.4773
0.1740	13600	8.4734
0.1753	13700	8.4732
0.1766	13800	8.4758
0.1779	13900	8.4675
0.1792	14000	8.466
0.1804	14100	8.4649
0.1817	14200	8.467
0.1830	14300	8.4811
0.1843	14400	8.4761
0.1856	14500	8.4584
0.1868	14600	8.4674
0.1881	14700	8.477
0.1894	14800	8.4639
0.1907	14900	8.4527
0.1920	15000	8.4657
0.1932	15100	8.4592
0.1945	15200	8.4663
0.1958	15300	8.4699
0.1971	15400	8.4646
0.1984	15500	8.4676
0.1996	15600	8.4546
0.2009	15700	8.4575
0.2022	15800	8.4541
0.2035	15900	8.4627
0.2048	16000	8.4648
0.2060	16100	8.4605
0.2073	16200	8.4563
0.2086	16300	8.456
0.2099	16400	8.4513
0.2112	16500	8.4614
0.2124	16600	8.4591
0.2137	16700	8.4533
0.2150	16800	8.4507
0.2163	16900	8.4543
0.2176	17000	8.4539
0.2188	17100	8.4433
0.2201	17200	8.4406
0.2214	17300	8.4449
0.2227	17400	8.4532
0.2240	17500	8.4473
0.2252	17600	8.4399
0.2265	17700	8.4442
0.2278	17800	8.4449
0.2291	17900	8.4461
0.2304	18000	8.4434
0.2316	18100	8.4497
0.2329	18200	8.4506
0.2342	18300	8.4465
0.2355	18400	8.4278
0.2368	18500	8.4296
0.2380	18600	8.4554
0.2393	18700	8.4302
0.2406	18800	8.4376
0.2419	18900	8.4393
0.2432	19000	8.4395
0.2444	19100	8.4318
0.2457	19200	8.4434
0.2470	19300	8.4383
0.2483	19400	8.4345
0.2496	19500	8.4236
0.2508	19600	8.4413
0.2521	19700	8.4338
0.2534	19800	8.4194
0.2547	19900	8.434
0.2560	20000	8.4358
0.2572	20100	8.4433
0.2585	20200	8.4302
0.2598	20300	8.4224
0.2611	20400	8.4419
0.2623	20500	8.4315
0.2636	20600	8.4218
0.2649	20700	8.4276
0.2662	20800	8.4278
0.2675	20900	8.4339
0.2687	21000	8.4391
0.2700	21100	8.4306
0.2713	21200	8.4192
0.2726	21300	8.4265
0.2739	21400	8.435
0.2751	21500	8.4226
0.2764	21600	8.4146
0.2777	21700	8.428
0.2790	21800	8.4157
0.2803	21900	8.412
0.2815	22000	8.408
0.2828	22100	8.4233
0.2841	22200	8.433
0.2854	22300	8.4141
0.2867	22400	8.4068
0.2879	22500	8.4272
0.2892	22600	8.4193
0.2905	22700	8.4171
0.2918	22800	8.4209
0.2931	22900	8.4049
0.2943	23000	8.4204
0.2956	23100	8.4178
0.2969	23200	8.4095
0.2982	23300	8.4213
0.2995	23400	8.4162
0.3007	23500	8.4164
0.3020	23600	8.4157
0.3033	23700	8.4194
0.3046	23800	8.4173
0.3059	23900	8.4237
0.3071	24000	8.4244
0.3084	24100	8.4147
0.3097	24200	8.4045
0.3110	24300	8.4109
0.3123	24400	8.4162
0.3135	24500	8.4225
0.3148	24600	8.4152
0.3161	24700	8.3963
0.3174	24800	8.4144
0.3187	24900	8.4172
0.3199	25000	8.4095
0.3212	25100	8.4031
0.3225	25200	8.408
0.3238	25300	8.4049
0.3251	25400	8.405
0.3263	25500	8.3955
0.3276	25600	8.3845
0.3289	25700	8.4132
0.3302	25800	8.4106
0.3315	25900	8.4189
0.3327	26000	8.3942
0.3340	26100	8.4062
0.3353	26200	8.4118
0.3366	26300	8.4032
0.3379	26400	8.4077
0.3391	26500	8.4188
0.3404	26600	8.3865
0.3417	26700	8.4043
0.3430	26800	8.4053
0.3443	26900	8.3966
0.3455	27000	8.3957
0.3468	27100	8.4032
0.3481	27200	8.3814
0.3494	27300	8.3974
0.3507	27400	8.4064
0.3519	27500	8.4001
0.3532	27600	8.402
0.3545	27700	8.41
0.3558	27800	8.4052
0.3571	27900	8.4021
0.3583	28000	8.3969
0.3596	28100	8.4142
0.3609	28200	8.3894
0.3622	28300	8.3988
0.3635	28400	8.3861
0.3647	28500	8.379
0.3660	28600	8.3919
0.3673	28700	8.3976
0.3686	28800	8.4002
0.3698	28900	8.3957
0.3711	29000	8.401
0.3724	29100	8.3846
0.3737	29200	8.3951
0.3750	29300	8.3855
0.3762	29400	8.3968
0.3775	29500	8.3826
0.3788	29600	8.397
0.3801	29700	8.4039
0.3814	29800	8.3793
0.3826	29900	8.3853
0.3839	30000	8.3851
0.3852	30100	8.3874
0.3865	30200	8.3851
0.3878	30300	8.3776
0.3890	30400	8.3846
0.3903	30500	8.3822
0.3916	30600	8.392
0.3929	30700	8.4014
0.3942	30800	8.3892
0.3954	30900	8.3892
0.3967	31000	8.3866
0.3980	31100	8.3837
0.3993	31200	8.3856
0.4006	31300	8.3851
0.4018	31400	8.3755
0.4031	31500	8.398
0.4044	31600	8.3769
0.4057	31700	8.3926
0.4070	31800	8.3806
0.4082	31900	8.3855
0.4095	32000	8.3667
0.4108	32100	8.3754
0.4121	32200	8.3874
0.4134	32300	8.3905
0.4146	32400	8.3952
0.4159	32500	8.3759
0.4172	32600	8.3883
0.4185	32700	8.3896
0.4198	32800	8.3859
0.4210	32900	8.3765
0.4223	33000	8.3805
0.4236	33100	8.3729
0.4249	33200	8.3609
0.4262	33300	8.3731
0.4274	33400	8.3693
0.4287	33500	8.3731
0.4300	33600	8.3693
0.4313	33700	8.3735
0.4326	33800	8.377
0.4338	33900	8.3792
0.4351	34000	8.3764
0.4364	34100	8.3774
0.4377	34200	8.3728
0.4390	34300	8.371
0.4402	34400	8.3791
0.4415	34500	8.365
0.4428	34600	8.3781
0.4441	34700	8.3574
0.4454	34800	8.3798
0.4466	34900	8.3865
0.4479	35000	8.3734
0.4492	35100	8.3859
0.4505	35200	8.3743
0.4518	35300	8.3741
0.4530	35400	8.3654
0.4543	35500	8.3836
0.4556	35600	8.3703
0.4569	35700	8.3699
0.4582	35800	8.3658
0.4594	35900	8.3768
0.4607	36000	8.3637
0.4620	36100	8.39
0.4633	36200	8.3744
0.4646	36300	8.3674
0.4658	36400	8.3797
0.4671	36500	8.3827
0.4684	36600	8.372
0.4697	36700	8.3645
0.4709	36800	8.3655
0.4722	36900	8.3846
0.4735	37000	8.3646
0.4748	37100	8.3624
0.4761	37200	8.3639
0.4773	37300	8.3636
0.4786	37400	8.3491
0.4799	37500	8.3738
0.4812	37600	8.3637
0.4825	37700	8.3645
0.4837	37800	8.37
0.4850	37900	8.3699
0.4863	38000	8.3609
0.4876	38100	8.3783
0.4889	38200	8.3613
0.4901	38300	8.3745
0.4914	38400	8.3503
0.4927	38500	8.3747
0.4940	38600	8.3635
0.4953	38700	8.3608
0.4965	38800	8.3675
0.4978	38900	8.368
0.4991	39000	8.3706
0.5004	39100	8.3716
0.5017	39200	8.3744
0.5029	39300	8.3659
0.5042	39400	8.3687
0.5055	39500	8.3637
0.5068	39600	8.3479
0.5081	39700	8.3429
0.5093	39800	8.3607
0.5106	39900	8.3534
0.5119	40000	8.3465
0.5132	40100	8.372
0.5145	40200	8.3547
0.5157	40300	8.3565
0.5170	40400	8.369
0.5183	40500	8.374
0.5196	40600	8.3595
0.5209	40700	8.357
0.5221	40800	8.3545
0.5234	40900	8.3541
0.5247	41000	8.3595
0.5260	41100	8.3504
0.5273	41200	8.3667
0.5285	41300	8.3542
0.5298	41400	8.3665
0.5311	41500	8.36
0.5324	41600	8.3554
0.5337	41700	8.3564
0.5349	41800	8.368
0.5362	41900	8.3634
0.5375	42000	8.3513
0.5388	42100	8.3544
0.5401	42200	8.3532
0.5413	42300	8.3576
0.5426	42400	8.3578
0.5439	42500	8.3596
0.5452	42600	8.3542
0.5465	42700	8.354
0.5477	42800	8.3606
0.5490	42900	8.3611
0.5503	43000	8.3708
0.5516	43100	8.3627
0.5529	43200	8.3451
0.5541	43300	8.361
0.5554	43400	8.3499
0.5567	43500	8.3559
0.5580	43600	8.3356
0.5593	43700	8.3467
0.5605	43800	8.3648
0.5618	43900	8.3523
0.5631	44000	8.3599
0.5644	44100	8.3687
0.5657	44200	8.347
0.5669	44300	8.3365
0.5682	44400	8.348
0.5695	44500	8.3631
0.5708	44600	8.3609
0.5721	44700	8.368
0.5733	44800	8.374
0.5746	44900	8.349
0.5759	45000	8.3493
0.5772	45100	8.3568
0.5784	45200	8.3294
0.5797	45300	8.337
0.5810	45400	8.3545
0.5823	45500	8.3512
0.5836	45600	8.3419
0.5848	45700	8.3411
0.5861	45800	8.3509
0.5874	45900	8.3465
0.5887	46000	8.3489
0.5900	46100	8.3555
0.5912	46200	8.3506
0.5925	46300	8.3492
0.5938	46400	8.3493
0.5951	46500	8.3494
0.5964	46600	8.3591
0.5976	46700	8.3357
0.5989	46800	8.3337
0.6002	46900	8.3414
0.6015	47000	8.3598
0.6028	47100	8.3433
0.6040	47200	8.3296
0.6053	47300	8.3354
0.6066	47400	8.3515
0.6079	47500	8.3472
0.6092	47600	8.3374
0.6104	47700	8.3516
0.6117	47800	8.3549
0.6130	47900	8.3436
0.6143	48000	8.3295
0.6156	48100	8.3592
0.6168	48200	8.3374
0.6181	48300	8.3328
0.6194	48400	8.33
0.6207	48500	8.3433
0.6220	48600	8.347
0.6232	48700	8.3492
0.6245	48800	8.3485
0.6258	48900	8.344
0.6271	49000	8.357
0.6284	49100	8.3444
0.6296	49200	8.3464
0.6309	49300	8.345
0.6322	49400	8.3462
0.6335	49500	8.3451
0.6348	49600	8.3402
0.6360	49700	8.3375
0.6373	49800	8.343
0.6386	49900	8.3463
0.6399	50000	8.3352
0.6412	50100	8.3317
0.6424	50200	8.3414
0.6437	50300	8.326
0.6450	50400	8.3281
0.6463	50500	8.3354
0.6476	50600	8.3411
0.6488	50700	8.3384
0.6501	50800	8.3415
0.6514	50900	8.3672
0.6527	51000	8.3371
0.6540	51100	8.3431
0.6552	51200	8.3471
0.6565	51300	8.3292
0.6578	51400	8.3398
0.6591	51500	8.3333
0.6604	51600	8.3412
0.6616	51700	8.3256
0.6629	51800	8.3417
0.6642	51900	8.335
0.6655	52000	8.3431
0.6668	52100	8.3214
0.6680	52200	8.3327
0.6693	52300	8.3311
0.6706	52400	8.3515
0.6719	52500	8.3409
0.6732	52600	8.3295
0.6744	52700	8.3242
0.6757	52800	8.3459
0.6770	52900	8.3088
0.6783	53000	8.3454
0.6795	53100	8.3336
0.6808	53200	8.3534
0.6821	53300	8.3277
0.6834	53400	8.3534
0.6847	53500	8.3399
0.6859	53600	8.3332
0.6872	53700	8.3269
0.6885	53800	8.3339
0.6898	53900	8.339
0.6911	54000	8.3452
0.6923	54100	8.324
0.6936	54200	8.3305
0.6949	54300	8.3359
0.6962	54400	8.3267
0.6975	54500	8.3221
0.6987	54600	8.3295
0.7000	54700	8.3459
0.7013	54800	8.3446
0.7026	54900	8.3235
0.7039	55000	8.3393
0.7051	55100	8.3359
0.7064	55200	8.3209
0.7077	55300	8.3377
0.7090	55400	8.3277
0.7103	55500	8.3298
0.7115	55600	8.3279
0.7128	55700	8.3207
0.7141	55800	8.3202
0.7154	55900	8.3339
0.7167	56000	8.329
0.7179	56100	8.3409
0.7192	56200	8.3398
0.7205	56300	8.3331
0.7218	56400	8.3327
0.7231	56500	8.3228
0.7243	56600	8.3246
0.7256	56700	8.3395
0.7269	56800	8.3438
0.7282	56900	8.3258
0.7295	57000	8.3256
0.7307	57100	8.3336
0.7320	57200	8.341
0.7333	57300	8.3229
0.7346	57400	8.3364
0.7359	57500	8.3219
0.7371	57600	8.3247
0.7384	57700	8.3254
0.7397	57800	8.3319
0.7410	57900	8.3202
0.7423	58000	8.327
0.7435	58100	8.3228
0.7448	58200	8.3472
0.7461	58300	8.3413
0.7474	58400	8.3173
0.7487	58500	8.3264
0.7499	58600	8.3166
0.7512	58700	8.3209
0.7525	58800	8.3184
0.7538	58900	8.3357
0.7551	59000	8.3249
0.7563	59100	8.3251
0.7576	59200	8.3215
0.7589	59300	8.3323
0.7602	59400	8.3552
0.7615	59500	8.3237
0.7627	59600	8.3355
0.7640	59700	8.328
0.7653	59800	8.324
0.7666	59900	8.3117
0.7679	60000	8.3367
0.7691	60100	8.3214
0.7704	60200	8.3084
0.7717	60300	8.3249
0.7730	60400	8.3238
0.7743	60500	8.3251
0.7755	60600	8.3328
0.7768	60700	8.3344
0.7781	60800	8.3186
0.7794	60900	8.3177
0.7807	61000	8.3032
0.7819	61100	8.3274
0.7832	61200	8.3101
0.7845	61300	8.3196
0.7858	61400	8.3467
0.7870	61500	8.3203
0.7883	61600	8.3033
0.7896	61700	8.3259
0.7909	61800	8.3348
0.7922	61900	8.3174
0.7934	62000	8.343
0.7947	62100	8.3223
0.7960	62200	8.3161
0.7973	62300	8.3138
0.7986	62400	8.3144
0.7998	62500	8.3111
0.8011	62600	8.3178
0.8024	62700	8.3169
0.8037	62800	8.328
0.8050	62900	8.314
0.8062	63000	8.3264
0.8075	63100	8.3135
0.8088	63200	8.3158
0.8101	63300	8.3081
0.8114	63400	8.3235
0.8126	63500	8.321
0.8139	63600	8.3307
0.8152	63700	8.3335
0.8165	63800	8.3139
0.8178	63900	8.315
0.8190	64000	8.3172
0.8203	64100	8.3265
0.8216	64200	8.322
0.8229	64300	8.3278
0.8242	64400	8.3116
0.8254	64500	8.3248
0.8267	64600	8.3241
0.8280	64700	8.3269
0.8293	64800	8.3154
0.8306	64900	8.3174
0.8318	65000	8.3154
0.8331	65100	8.3184
0.8344	65200	8.323
0.8357	65300	8.3243
0.8370	65400	8.3127
0.8382	65500	8.3186
0.8395	65600	8.3142
0.8408	65700	8.3161
0.8421	65800	8.3199
0.8434	65900	8.3289
0.8446	66000	8.3174
0.8459	66100	8.3215
0.8472	66200	8.3187
0.8485	66300	8.3367
0.8498	66400	8.3151
0.8510	66500	8.32
0.8523	66600	8.3233
0.8536	66700	8.3116
0.8549	66800	8.3262
0.8562	66900	8.3162
0.8574	67000	8.3153
0.8587	67100	8.2974
0.8600	67200	8.3354
0.8613	67300	8.3185
0.8626	67400	8.3173
0.8638	67500	8.3274
0.8651	67600	8.3203
0.8664	67700	8.3123
0.8677	67800	8.3221
0.8690	67900	8.3101
0.8702	68000	8.3304
0.8715	68100	8.3146
0.8728	68200	8.3216
0.8741	68300	8.3168
0.8754	68400	8.2954
0.8766	68500	8.311
0.8779	68600	8.3275
0.8792	68700	8.3215
0.8805	68800	8.3222
0.8818	68900	8.3125
0.8830	69000	8.3228
0.8843	69100	8.3251
0.8856	69200	8.317
0.8869	69300	8.3041
0.8881	69400	8.3273
0.8894	69500	8.3254
0.8907	69600	8.3222
0.8920	69700	8.311
0.8933	69800	8.2815
0.8945	69900	8.3134
0.8958	70000	8.3259
0.8971	70100	8.3067
0.8984	70200	8.3008
0.8997	70300	8.3187
0.9009	70400	8.3242
0.9022	70500	8.3078
0.9035	70600	8.3089
0.9048	70700	8.3238
0.9061	70800	8.3225
0.9073	70900	8.305
0.9086	71000	8.3014
0.9099	71100	8.3057
0.9112	71200	8.3147
0.9125	71300	8.3201
0.9137	71400	8.3095
0.9150	71500	8.3133
0.9163	71600	8.3021
0.9176	71700	8.3053
0.9189	71800	8.3112
0.9201	71900	8.3074
0.9214	72000	8.3105
0.9227	72100	8.3145
0.9240	72200	8.3248
0.9253	72300	8.3199
0.9265	72400	8.3199
0.9278	72500	8.3221
0.9291	72600	8.3113
0.9304	72700	8.3212
0.9317	72800	8.309
0.9329	72900	8.3186
0.9342	73000	8.3038
0.9355	73100	8.3173
0.9368	73200	8.317
0.9381	73300	8.3313
0.9393	73400	8.3018
0.9406	73500	8.3118
0.9419	73600	8.3089
0.9432	73700	8.3304
0.9445	73800	8.3074
0.9457	73900	8.3007
0.9470	74000	8.3059
0.9483	74100	8.3043
0.9496	74200	8.3115
0.9509	74300	8.3278
0.9521	74400	8.3231
0.9534	74500	8.3109
0.9547	74600	8.3235
0.9560	74700	8.3196
0.9573	74800	8.3113
0.9585	74900	8.3197
0.9598	75000	8.3143
0.9611	75100	8.3121
0.9624	75200	8.2992
0.9637	75300	8.2954
0.9649	75400	8.3133
0.9662	75500	8.3099
0.9675	75600	8.3236
0.9688	75700	8.3101
0.9701	75800	8.3256
0.9713	75900	8.3041
0.9726	76000	8.3035
0.9739	76100	8.312
0.9752	76200	8.3112
0.9765	76300	8.3044
0.9777	76400	8.3135
0.9790	76500	8.3116
0.9803	76600	8.3006
0.9816	76700	8.3068
0.9829	76800	8.3023
0.9841	76900	8.31
0.9854	77000	8.3129
0.9867	77100	8.3197
0.9880	77200	8.3105
0.9893	77300	8.3196
0.9905	77400	8.3169
0.9918	77500	8.3168
0.9931	77600	8.3241
0.9944	77700	8.3144
0.9956	77800	8.2999
0.9969	77900	8.3206
0.9982	78000	8.3046
0.9995	78100	8.306

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.5.1+cu121
• 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},
}