all-MiniLM-L6-v13-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v11_tag_sim 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_v11_tag_sim
• 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 = [
    'relaxed fit swim shorts',
    'elasticated edges swimsuit',
    'mustard square cushion',
]
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, 0.8868, 0.6624],
#         [0.8868, 1.0000, 0.6654],
#         [0.6624, 0.6654, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v11_tag_sim

• Dataset: pairs_three_scores_v11_tag_sim at e98a5bf
• Size: 8,407,159 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: 5.71 tokens max: 45 tokens	min: 3 tokens mean: 5.94 tokens max: 84 tokens	min: 0.15 mean: 0.36 max: 0.96

• Samples:

  sentence1	sentence2	score
  chicken mushroom pasta	rosemary essential hair oil	0.19
  deli	mozzarella pacman	0.25
  tea tree oil face cream	all skin types cream	0.33

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v11_tag_sim

• Dataset: pairs_three_scores_v11_tag_sim at e98a5bf
• Size: 42,248 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: 5.69 tokens max: 115 tokens	min: 3 tokens mean: 5.91 tokens max: 65 tokens	min: 0.14 mean: 0.38 max: 0.93

• Samples:

  sentence1	sentence2	score
  comeback sauce sandwiches	lemon dill sandwich	0.82
  crossfit tiers storage rack	garage gear parallel	0.78
  shake	toast with balsamic dressing	0.23

• 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
0.0015	100	11.8209
0.0030	200	11.5402
0.0046	300	11.2817
0.0061	400	11.1501
0.0076	500	10.5829
0.0091	600	10.0617
0.0107	700	9.6697
0.0122	800	9.3381
0.0137	900	8.9682
0.0152	1000	8.7555
0.0167	1100	8.6119
0.0183	1200	8.5628
0.0198	1300	8.5158
0.0213	1400	8.4803
0.0228	1500	8.4599
0.0244	1600	8.4506
0.0259	1700	8.4444
0.0274	1800	8.4166
0.0289	1900	8.4118
0.0305	2000	8.3848
0.0320	2100	8.3781
0.0335	2200	8.3782
0.0350	2300	8.3495
0.0365	2400	8.3462
0.0381	2500	8.3582
0.0396	2600	8.3337
0.0411	2700	8.3263
0.0426	2800	8.3261
0.0442	2900	8.2994
0.0457	3000	8.3027
0.0472	3100	8.3071
0.0487	3200	8.3062
0.0502	3300	8.2753
0.0518	3400	8.2743
0.0533	3500	8.2805
0.0548	3600	8.2679
0.0563	3700	8.2735
0.0579	3800	8.2669
0.0594	3900	8.2665
0.0609	4000	8.2463
0.0624	4100	8.2464
0.0639	4200	8.2505
0.0655	4300	8.2347
0.0670	4400	8.2356
0.0685	4500	8.2143
0.0700	4600	8.2157
0.0716	4700	8.2123
0.0731	4800	8.2186
0.0746	4900	8.2071
0.0761	5000	8.2004
0.0776	5100	8.2007
0.0792	5200	8.2099
0.0807	5300	8.1938
0.0822	5400	8.1945
0.0837	5500	8.1857
0.0853	5600	8.1857
0.0868	5700	8.183
0.0883	5800	8.1942
0.0898	5900	8.1603
0.0914	6000	8.1564
0.0929	6100	8.1644
0.0944	6200	8.1707
0.0959	6300	8.1625
0.0974	6400	8.1428
0.0990	6500	8.1556
0.1005	6600	8.1423
0.1020	6700	8.1434
0.1035	6800	8.14
0.1051	6900	8.15
0.1066	7000	8.1369
0.1081	7100	8.1349
0.1096	7200	8.1414
0.1111	7300	8.1175
0.1127	7400	8.1144
0.1142	7500	8.1202
0.1157	7600	8.0978
0.1172	7700	8.1213
0.1188	7800	8.0999
0.1203	7900	8.1001
0.1218	8000	8.0883
0.1233	8100	8.1111
0.1248	8200	8.1003
0.1264	8300	8.0971
0.1279	8400	8.1177
0.1294	8500	8.099
0.1309	8600	8.1015
0.1325	8700	8.1006
0.1340	8800	8.0826
0.1355	8900	8.0896
0.1370	9000	8.072
0.1385	9100	8.0749
0.1401	9200	8.0864
0.1416	9300	8.0913
0.1431	9400	8.0794
0.1446	9500	8.0693
0.1462	9600	8.0665
0.1477	9700	8.0698
0.1492	9800	8.0788
0.1507	9900	8.062
0.1523	10000	8.0552
0.1538	10100	8.0699
0.1553	10200	8.0528
0.1568	10300	8.0469
0.1583	10400	8.0657
0.1599	10500	8.0533
0.1614	10600	8.0503
0.1629	10700	8.0665
0.1644	10800	8.0383
0.1660	10900	8.0477
0.1675	11000	8.0487
0.1690	11100	8.0564
0.1705	11200	8.0657
0.1720	11300	8.0477
0.1736	11400	8.0444
0.1751	11500	8.0469
0.1766	11600	8.0384
0.1781	11700	8.0414
0.1797	11800	8.0446
0.1812	11900	8.0492
0.1827	12000	8.0391
0.1842	12100	8.0234
0.1857	12200	8.0256
0.1873	12300	8.0346
0.1888	12400	8.0245
0.1903	12500	8.0185
0.1918	12600	8.0225
0.1934	12700	8.0267
0.1949	12800	8.0468
0.1964	12900	8.0195
0.1979	13000	8.0293
0.1994	13100	8.0132
0.2010	13200	8.029
0.2025	13300	8.0177
0.2040	13400	7.9961
0.2055	13500	8.0149
0.2071	13600	8.0102
0.2086	13700	8.0201
0.2101	13800	8.0256
0.2116	13900	8.0067
0.2132	14000	8.0105
0.2147	14100	8.0077
0.2162	14200	8.0151
0.2177	14300	8.0208
0.2192	14400	7.9954
0.2208	14500	8.0184
0.2223	14600	7.9915
0.2238	14700	8.0013
0.2253	14800	8.0177
0.2269	14900	7.9963
0.2284	15000	8.0014
0.2299	15100	8.0038
0.2314	15200	7.9831
0.2329	15300	7.9983
0.2345	15400	7.9953
0.2360	15500	7.9829
0.2375	15600	7.9888
0.2390	15700	7.9763
0.2406	15800	7.9822
0.2421	15900	7.9795
0.2436	16000	7.9858
0.2451	16100	7.9737
0.2466	16200	7.9821
0.2482	16300	7.9793
0.2497	16400	7.9683
0.2512	16500	7.9785
0.2527	16600	7.9766
0.2543	16700	7.979
0.2558	16800	7.977
0.2573	16900	7.9742
0.2588	17000	7.9824
0.2603	17100	7.96
0.2619	17200	7.9828
0.2634	17300	7.9696
0.2649	17400	7.979
0.2664	17500	7.9837
0.2680	17600	7.955
0.2695	17700	7.9561
0.2710	17800	7.9899
0.2725	17900	7.9699
0.2741	18000	7.9849
0.2756	18100	7.9622
0.2771	18200	7.9561
0.2786	18300	7.976
0.2801	18400	7.9805
0.2817	18500	7.9639
0.2832	18600	7.9533
0.2847	18700	7.972
0.2862	18800	7.9847
0.2878	18900	7.9502
0.2893	19000	7.9681
0.2908	19100	7.9574
0.2923	19200	7.9697
0.2938	19300	7.9639
0.2954	19400	7.955
0.2969	19500	7.9647
0.2984	19600	7.9565
0.2999	19700	7.9494
0.3015	19800	7.9708
0.3030	19900	7.9599
0.3045	20000	7.9781
0.3060	20100	7.9363
0.3075	20200	7.9599
0.3091	20300	7.9311
0.3106	20400	7.9446
0.3121	20500	7.9482
0.3136	20600	7.9529
0.3152	20700	7.9624
0.3167	20800	7.9534
0.3182	20900	7.9588
0.3197	21000	7.9606
0.3212	21100	7.9268
0.3228	21200	7.9501
0.3243	21300	7.9346
0.3258	21400	7.9411
0.3273	21500	7.9331
0.3289	21600	7.9612
0.3304	21700	7.9609
0.3319	21800	7.9322
0.3334	21900	7.9416
0.3350	22000	7.9288
0.3365	22100	7.9436
0.3380	22200	7.9382
0.3395	22300	7.9259
0.3410	22400	7.9265
0.3426	22500	7.9275
0.3441	22600	7.9568
0.3456	22700	7.9347
0.3471	22800	7.9205
0.3487	22900	7.9319
0.3502	23000	7.9266
0.3517	23100	7.9435
0.3532	23200	7.9404
0.3547	23300	7.9327
0.3563	23400	7.9312
0.3578	23500	7.93
0.3593	23600	7.916
0.3608	23700	7.9342
0.3624	23800	7.9371
0.3639	23900	7.917
0.3654	24000	7.9196
0.3669	24100	7.934
0.3684	24200	7.929
0.3700	24300	7.9386
0.3715	24400	7.9194
0.3730	24500	7.9228
0.3745	24600	7.9261
0.3761	24700	7.9218
0.3776	24800	7.9048
0.3791	24900	7.9264
0.3806	25000	7.9198
0.3822	25100	7.9206
0.3837	25200	7.9159
0.3852	25300	7.9106
0.3867	25400	7.905
0.3882	25500	7.9215
0.3898	25600	7.9186
0.3913	25700	7.9055
0.3928	25800	7.9032
0.3943	25900	7.9094
0.3959	26000	7.8977
0.3974	26100	7.9013
0.3989	26200	7.918
0.4004	26300	7.9182
0.4019	26400	7.9105
0.4035	26500	7.9071
0.4050	26600	7.9253
0.4065	26700	7.9091
0.4080	26800	7.9196
0.4096	26900	7.9094
0.4111	27000	7.9229
0.4126	27100	7.911
0.4141	27200	7.8899
0.4156	27300	7.9316
0.4172	27400	7.8894
0.4187	27500	7.9143
0.4202	27600	7.9046
0.4217	27700	7.8977
0.4233	27800	7.8756
0.4248	27900	7.8881
0.4263	28000	7.9026
0.4278	28100	7.9071
0.4293	28200	7.9115
0.4309	28300	7.9058
0.4324	28400	7.889
0.4339	28500	7.8942
0.4354	28600	7.8969
0.4370	28700	7.9029
0.4385	28800	7.8911
0.4400	28900	7.8799
0.4415	29000	7.8743
0.4431	29100	7.9117
0.4446	29200	7.8922
0.4461	29300	7.9221
0.4476	29400	7.8975
0.4491	29500	7.9151
0.4507	29600	7.8861
0.4522	29700	7.9109
0.4537	29800	7.8892
0.4552	29900	7.9072
0.4568	30000	7.9004
0.4583	30100	7.8736
0.4598	30200	7.9009
0.4613	30300	7.9058
0.4628	30400	7.8926
0.4644	30500	7.9111
0.4659	30600	7.8922
0.4674	30700	7.9212
0.4689	30800	7.8591
0.4705	30900	7.8885
0.4720	31000	7.9038
0.4735	31100	7.8983
0.4750	31200	7.8894
0.4765	31300	7.8918
0.4781	31400	7.8758
0.4796	31500	7.8818
0.4811	31600	7.8897
0.4826	31700	7.8722
0.4842	31800	7.8683
0.4857	31900	7.8811
0.4872	32000	7.8735
0.4887	32100	7.8972
0.4902	32200	7.8855
0.4918	32300	7.8977
0.4933	32400	7.8635
0.4948	32500	7.8849
0.4963	32600	7.8745
0.4979	32700	7.8924
0.4994	32800	7.8666
0.5009	32900	7.8872
0.5024	33000	7.8965
0.5040	33100	7.8705
0.5055	33200	7.8926
0.5070	33300	7.8697
0.5085	33400	7.8752
0.5100	33500	7.8949
0.5116	33600	7.8844
0.5131	33700	7.8678
0.5146	33800	7.8807
0.5161	33900	7.8904
0.5177	34000	7.8595
0.5192	34100	7.8743
0.5207	34200	7.8716
0.5222	34300	7.8908
0.5237	34400	7.8586
0.5253	34500	7.8698
0.5268	34600	7.871
0.5283	34700	7.8758
0.5298	34800	7.8698
0.5314	34900	7.8578
0.5329	35000	7.8447
0.5344	35100	7.8611
0.5359	35200	7.8727
0.5374	35300	7.8655
0.5390	35400	7.8786
0.5405	35500	7.8706
0.5420	35600	7.8736
0.5435	35700	7.8741
0.5451	35800	7.8801
0.5466	35900	7.8552
0.5481	36000	7.891
0.5496	36100	7.8654
0.5511	36200	7.8689
0.5527	36300	7.869
0.5542	36400	7.8677
0.5557	36500	7.8475
0.5572	36600	7.8691
0.5588	36700	7.8662
0.5603	36800	7.8852
0.5618	36900	7.8632
0.5633	37000	7.8513
0.5649	37100	7.8691
0.5664	37200	7.8513
0.5679	37300	7.8642
0.5694	37400	7.8767
0.5709	37500	7.8693
0.5725	37600	7.8807
0.5740	37700	7.8741
0.5755	37800	7.8708
0.5770	37900	7.8696
0.5786	38000	7.8642
0.5801	38100	7.8688
0.5816	38200	7.8445
0.5831	38300	7.8474
0.5846	38400	7.8608
0.5862	38500	7.846
0.5877	38600	7.8701
0.5892	38700	7.8543
0.5907	38800	7.8704
0.5923	38900	7.8611
0.5938	39000	7.8677
0.5953	39100	7.8625
0.5968	39200	7.8809
0.5983	39300	7.8587
0.5999	39400	7.8566
0.6014	39500	7.8658
0.6029	39600	7.8513
0.6044	39700	7.8685
0.6060	39800	7.8476
0.6075	39900	7.8375
0.6090	40000	7.8707
0.6105	40100	7.8599
0.6120	40200	7.8602
0.6136	40300	7.8509
0.6151	40400	7.8491
0.6166	40500	7.841
0.6181	40600	7.8454
0.6197	40700	7.8492
0.6212	40800	7.8725
0.6227	40900	7.8411
0.6242	41000	7.8496
0.6258	41100	7.8304
0.6273	41200	7.8273
0.6288	41300	7.862
0.6303	41400	7.854
0.6318	41500	7.8462
0.6334	41600	7.8418
0.6349	41700	7.8423
0.6364	41800	7.8522
0.6379	41900	7.8574
0.6395	42000	7.8348
0.6410	42100	7.8371
0.6425	42200	7.8462
0.6440	42300	7.8367
0.6455	42400	7.8649
0.6471	42500	7.8708
0.6486	42600	7.834
0.6501	42700	7.8318
0.6516	42800	7.8604
0.6532	42900	7.8496
0.6547	43000	7.827
0.6562	43100	7.8456
0.6577	43200	7.849
0.6592	43300	7.8772
0.6608	43400	7.8538
0.6623	43500	7.8617
0.6638	43600	7.8309
0.6653	43700	7.8405
0.6669	43800	7.8367
0.6684	43900	7.8552
0.6699	44000	7.8456
0.6714	44100	7.8434
0.6729	44200	7.8215
0.6745	44300	7.8504
0.6760	44400	7.8153
0.6775	44500	7.8521
0.6790	44600	7.8265
0.6806	44700	7.8568
0.6821	44800	7.8373
0.6836	44900	7.8438
0.6851	45000	7.8583
0.6867	45100	7.847
0.6882	45200	7.8383
0.6897	45300	7.838
0.6912	45400	7.8262
0.6927	45500	7.832
0.6943	45600	7.8331
0.6958	45700	7.8472
0.6973	45800	7.838
0.6988	45900	7.8563
0.7004	46000	7.8461
0.7019	46100	7.8381
0.7034	46200	7.8566
0.7049	46300	7.8464
0.7064	46400	7.837
0.7080	46500	7.8358
0.7095	46600	7.8627
0.7110	46700	7.8511
0.7125	46800	7.8442
0.7141	46900	7.8467
0.7156	47000	7.8388
0.7171	47100	7.8385
0.7186	47200	7.851
0.7201	47300	7.8466
0.7217	47400	7.8353
0.7232	47500	7.8536
0.7247	47600	7.8335
0.7262	47700	7.8312
0.7278	47800	7.8338
0.7293	47900	7.8291
0.7308	48000	7.8339
0.7323	48100	7.8368
0.7338	48200	7.8303
0.7354	48300	7.8457
0.7369	48400	7.8312
0.7384	48500	7.8442
0.7399	48600	7.8415
0.7415	48700	7.8326
0.7430	48800	7.83
0.7445	48900	7.8398
0.7460	49000	7.8305
0.7476	49100	7.835
0.7491	49200	7.8421
0.7506	49300	7.8342
0.7521	49400	7.846
0.7536	49500	7.8187
0.7552	49600	7.8314
0.7567	49700	7.8289
0.7582	49800	7.8421
0.7597	49900	7.8559
0.7613	50000	7.8445
0.7628	50100	7.8115
0.7643	50200	7.8541
0.7658	50300	7.8359
0.7673	50400	7.8239
0.7689	50500	7.834
0.7704	50600	7.8407
0.7719	50700	7.8369
0.7734	50800	7.8588
0.7750	50900	7.8307
0.7765	51000	7.8117
0.7780	51100	7.8262
0.7795	51200	7.8324
0.7810	51300	7.8271
0.7826	51400	7.8221
0.7841	51500	7.828
0.7856	51600	7.8217
0.7871	51700	7.8404
0.7887	51800	7.8268
0.7902	51900	7.8256
0.7917	52000	7.8258
0.7932	52100	7.8308
0.7948	52200	7.8252
0.7963	52300	7.8276
0.7978	52400	7.8101
0.7993	52500	7.8217
0.8008	52600	7.8282
0.8024	52700	7.8613
0.8039	52800	7.8352
0.8054	52900	7.8258
0.8069	53000	7.8166
0.8085	53100	7.8245
0.8100	53200	7.8186
0.8115	53300	7.8166
0.8130	53400	7.816
0.8145	53500	7.8353
0.8161	53600	7.8194
0.8176	53700	7.8204
0.8191	53800	7.8354
0.8206	53900	7.8261
0.8222	54000	7.8463
0.8237	54100	7.8254
0.8252	54200	7.818
0.8267	54300	7.8266
0.8282	54400	7.8093
0.8298	54500	7.8297
0.8313	54600	7.8457
0.8328	54700	7.8311
0.8343	54800	7.8281
0.8359	54900	7.8158
0.8374	55000	7.8196
0.8389	55100	7.843
0.8404	55200	7.8168
0.8419	55300	7.8125
0.8435	55400	7.8077
0.8450	55500	7.8112
0.8465	55600	7.8165
0.8480	55700	7.8116
0.8496	55800	7.7858
0.8511	55900	7.8216
0.8526	56000	7.8326
0.8541	56100	7.8207
0.8557	56200	7.8246
0.8572	56300	7.8004
0.8587	56400	7.8195
0.8602	56500	7.8212
0.8617	56600	7.8016
0.8633	56700	7.8264
0.8648	56800	7.7963
0.8663	56900	7.801
0.8678	57000	7.8315
0.8694	57100	7.8263
0.8709	57200	7.7979
0.8724	57300	7.8204
0.8739	57400	7.8276
0.8754	57500	7.8276
0.8770	57600	7.7986
0.8785	57700	7.795
0.8800	57800	7.8201
0.8815	57900	7.8109
0.8831	58000	7.8204
0.8846	58100	7.8294
0.8861	58200	7.8154
0.8876	58300	7.7995
0.8891	58400	7.8059
0.8907	58500	7.826
0.8922	58600	7.8412
0.8937	58700	7.8326
0.8952	58800	7.8078
0.8968	58900	7.8314
0.8983	59000	7.7992
0.8998	59100	7.8209
0.9013	59200	7.8388
0.9028	59300	7.7981
0.9044	59400	7.8047
0.9059	59500	7.8209
0.9074	59600	7.8173
0.9089	59700	7.8073
0.9105	59800	7.8105
0.9120	59900	7.8047
0.9135	60000	7.8104
0.9150	60100	7.8217
0.9166	60200	7.8212
0.9181	60300	7.7984
0.9196	60400	7.8127
0.9211	60500	7.8227
0.9226	60600	7.8057
0.9242	60700	7.8092
0.9257	60800	7.8461
0.9272	60900	7.8068
0.9287	61000	7.8208
0.9303	61100	7.8149
0.9318	61200	7.8076
0.9333	61300	7.8143
0.9348	61400	7.8119
0.9363	61500	7.7992
0.9379	61600	7.8107
0.9394	61700	7.8068
0.9409	61800	7.8168
0.9424	61900	7.8278
0.9440	62000	7.8177
0.9455	62100	7.8153
0.9470	62200	7.8252
0.9485	62300	7.8217
0.9500	62400	7.8236
0.9516	62500	7.8171
0.9531	62600	7.8158
0.9546	62700	7.8186
0.9561	62800	7.834
0.9577	62900	7.788
0.9592	63000	7.7916
0.9607	63100	7.8135
0.9622	63200	7.814
0.9637	63300	7.8263
0.9653	63400	7.8155
0.9668	63500	7.8185
0.9683	63600	7.8054
0.9698	63700	7.8109
0.9714	63800	7.8055
0.9729	63900	7.8135
0.9744	64000	7.8247
0.9759	64100	7.8158
0.9775	64200	7.8103
0.9790	64300	7.8152
0.9805	64400	7.8255
0.9820	64500	7.8087
0.9835	64600	7.8028
0.9851	64700	7.7851
0.9866	64800	7.8105
0.9881	64900	7.8106
0.9896	65000	7.8212
0.9912	65100	7.8047
0.9927	65200	7.8143
0.9942	65300	7.8055
0.9957	65400	7.8047
0.9972	65500	7.8096
0.9988	65600	7.8203

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},
}