all-MiniLM-L6-v11-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v9 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_v9
• 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 = [
    'vanilla hair perfume',
    'soup bowl',
    'home accessory',
]
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, 0.4112, 0.6046],
#         [0.4112, 1.0000, 0.7030],
#         [0.6046, 0.7030, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v9

• Dataset: pairs_three_scores_v9 at b566d18
• Size: 16,129,188 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: 5.62 tokens max: 12 tokens	min: 3 tokens mean: 5.73 tokens max: 41 tokens	min: 0.16 mean: 0.35 max: 1.0

• Samples:

  sentence1	sentence2	score
  warmth poncho	paraben free shower gel	0.19
  concert ear plugs	wood handle pizza cutter	0.22
  coconut oil tanning oil	aromatherapy body cream	0.38

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v9

• Dataset: pairs_three_scores_v9 at b566d18
• Size: 81,052 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: 5.67 tokens max: 15 tokens	min: 3 tokens mean: 5.66 tokens max: 21 tokens	min: 0.14 mean: 0.36 max: 1.0

• Samples:

  sentence1	sentence2	score
  genuphil	unisex shoes	0.26
  ribbed round collar sweatshirt	cuffs hoodie	1.0
  vanilla sauce shake	snacks	0.27

• 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
0.0008	100	12.0571
0.0016	200	11.8936
0.0024	300	11.8073
0.0032	400	11.4103
0.0040	500	11.2388
0.0048	600	11.1116
0.0056	700	10.8225
0.0063	800	10.5745
0.0071	900	10.154
0.0079	1000	9.969
0.0087	1100	9.8383
0.0095	1200	9.6264
0.0103	1300	9.4763
0.0111	1400	9.2263
0.0119	1500	9.0704
0.0127	1600	8.9056
0.0135	1700	8.8125
0.0143	1800	8.7812
0.0151	1900	8.7363
0.0159	2000	8.7182
0.0167	2100	8.6884
0.0175	2200	8.6968
0.0183	2300	8.6768
0.0190	2400	8.6585
0.0198	2500	8.6481
0.0206	2600	8.6425
0.0214	2700	8.6291
0.0222	2800	8.6181
0.0230	2900	8.606
0.0238	3000	8.6161
0.0246	3100	8.5945
0.0254	3200	8.5882
0.0262	3300	8.5835
0.0270	3400	8.5796
0.0278	3500	8.5748
0.0286	3600	8.5799
0.0294	3700	8.5635
0.0302	3800	8.5539
0.0309	3900	8.5536
0.0317	4000	8.5514
0.0325	4100	8.5423
0.0333	4200	8.5307
0.0341	4300	8.5334
0.0349	4400	8.5257
0.0357	4500	8.5252
0.0365	4600	8.5114
0.0373	4700	8.511
0.0381	4800	8.5103
0.0389	4900	8.4919
0.0397	5000	8.4947
0.0405	5100	8.493
0.0413	5200	8.4885
0.0421	5300	8.485
0.0429	5400	8.4746
0.0436	5500	8.4784
0.0444	5600	8.4756
0.0452	5700	8.476
0.0460	5800	8.4522
0.0468	5900	8.4492
0.0476	6000	8.4661
0.0484	6100	8.4458
0.0492	6200	8.4523
0.0500	6300	8.4325
0.0508	6400	8.4276
0.0516	6500	8.4357
0.0524	6600	8.4363
0.0532	6700	8.4382
0.0540	6800	8.4203
0.0548	6900	8.4337
0.0556	7000	8.4132
0.0563	7100	8.4204
0.0571	7200	8.3942
0.0579	7300	8.3997
0.0587	7400	8.4087
0.0595	7500	8.3958
0.0603	7600	8.3935
0.0611	7700	8.4017
0.0619	7800	8.4057
0.0627	7900	8.3924
0.0635	8000	8.3859
0.0643	8100	8.3814
0.0651	8200	8.3903
0.0659	8300	8.3601
0.0667	8400	8.3755
0.0675	8500	8.3735
0.0682	8600	8.3516
0.0690	8700	8.3581
0.0698	8800	8.3449
0.0706	8900	8.3512
0.0714	9000	8.361
0.0722	9100	8.3473
0.0730	9200	8.3574
0.0738	9300	8.3456
0.0746	9400	8.3339
0.0754	9500	8.3606
0.0762	9600	8.3426
0.0770	9700	8.3563
0.0778	9800	8.335
0.0786	9900	8.3257
0.0794	10000	8.3156
0.0802	10100	8.3185
0.0809	10200	8.3096
0.0817	10300	8.3275
0.0825	10400	8.2933
0.0833	10500	8.3171
0.0841	10600	8.3246
0.0849	10700	8.2964
0.0857	10800	8.2994
0.0865	10900	8.2931
0.0873	11000	8.2976
0.0881	11100	8.267
0.0889	11200	8.2888
0.0897	11300	8.294
0.0905	11400	8.2958
0.0913	11500	8.2724
0.0921	11600	8.2746
0.0928	11700	8.2743
0.0936	11800	8.2725
0.0944	11900	8.2683
0.0952	12000	8.2714
0.0960	12100	8.2713
0.0968	12200	8.2599
0.0976	12300	8.2755
0.0984	12400	8.2744
0.0992	12500	8.2579
0.1000	12600	8.2467
0.1008	12700	8.2504
0.1016	12800	8.2431
0.1024	12900	8.2456
0.1032	13000	8.2398
0.1040	13100	8.2449
0.1048	13200	8.2443
0.1055	13300	8.249
0.1063	13400	8.2428
0.1071	13500	8.2298
0.1079	13600	8.2326
0.1087	13700	8.233
0.1095	13800	8.2269
0.1103	13900	8.2386
0.1111	14000	8.227
0.1119	14100	8.2247
0.1127	14200	8.2155
0.1135	14300	8.2188
0.1143	14400	8.2127
0.1151	14500	8.209
0.1159	14600	8.2137
0.1167	14700	8.2068
0.1175	14800	8.1809
0.1182	14900	8.2048
0.1190	15000	8.2068
0.1198	15100	8.1905
0.1206	15200	8.2222
0.1214	15300	8.1931
0.1222	15400	8.178
0.1230	15500	8.2043
0.1238	15600	8.1827
0.1246	15700	8.1759
0.1254	15800	8.1776
0.1262	15900	8.1764
0.1270	16000	8.1762
0.1278	16100	8.1623
0.1286	16200	8.1721
0.1294	16300	8.1665
0.1301	16400	8.1663
0.1309	16500	8.1846
0.1317	16600	8.1678
0.1325	16700	8.1656
0.1333	16800	8.1833
0.1341	16900	8.1681
0.1349	17000	8.1544
0.1357	17100	8.1718
0.1365	17200	8.1771
0.1373	17300	8.1496
0.1381	17400	8.1459
0.1389	17500	8.1436
0.1397	17600	8.1541
0.1405	17700	8.1644
0.1413	17800	8.141
0.1421	17900	8.1576
0.1428	18000	8.1331
0.1436	18100	8.1244
0.1444	18200	8.1358
0.1452	18300	8.1306
0.1460	18400	8.1223
0.1468	18500	8.1164
0.1476	18600	8.1501
0.1484	18700	8.142
0.1492	18800	8.1193
0.1500	18900	8.1347
0.1508	19000	8.1151
0.1516	19100	8.1384
0.1524	19200	8.1304
0.1532	19300	8.1371
0.1540	19400	8.1136
0.1547	19500	8.1089
0.1555	19600	8.1061
0.1563	19700	8.1096
0.1571	19800	8.1018
0.1579	19900	8.1221
0.1587	20000	8.1215
0.1595	20100	8.123
0.1603	20200	8.1271
0.1611	20300	8.1161
0.1619	20400	8.104
0.1627	20500	8.0977
0.1635	20600	8.0869
0.1643	20700	8.1191
0.1651	20800	8.088
0.1659	20900	8.1011
0.1667	21000	8.0908
0.1674	21100	8.0835
0.1682	21200	8.0927
0.1690	21300	8.0872
0.1698	21400	8.0886
0.1706	21500	8.0878
0.1714	21600	8.0971
0.1722	21700	8.1051
0.1730	21800	8.1007
0.1738	21900	8.0791
0.1746	22000	8.1008
0.1754	22100	8.0822
0.1762	22200	8.0925
0.1770	22300	8.0912
0.1778	22400	8.0766
0.1786	22500	8.0709
0.1794	22600	8.0566
0.1801	22700	8.0865
0.1809	22800	8.0596
0.1817	22900	8.0591
0.1825	23000	8.067
0.1833	23100	8.0577
0.1841	23200	8.0716
0.1849	23300	8.0657
0.1857	23400	8.0805
0.1865	23500	8.0639
0.1873	23600	8.0751
0.1881	23700	8.0466
0.1889	23800	8.0438
0.1897	23900	8.0744
0.1905	24000	8.0597
0.1913	24100	8.0522
0.1920	24200	8.029
0.1928	24300	8.0615
0.1936	24400	8.0486
0.1944	24500	8.0434
0.1952	24600	8.0659
0.1960	24700	8.0452
0.1968	24800	8.0455
0.1976	24900	8.0533
0.1984	25000	8.0484
0.1992	25100	8.067
0.2000	25200	8.0463
0.2008	25300	8.0726
0.2016	25400	8.0357
0.2024	25500	8.0332
0.2032	25600	8.0261
0.2040	25700	8.0379
0.2047	25800	8.034
0.2055	25900	8.0385
0.2063	26000	8.0583
0.2071	26100	8.0263
0.2079	26200	8.0378
0.2087	26300	8.0358
0.2095	26400	8.0506
0.2103	26500	8.0428
0.2111	26600	8.0147
0.2119	26700	8.0268
0.2127	26800	8.0316
0.2135	26900	8.0318
0.2143	27000	8.0322
0.2151	27100	8.036
0.2159	27200	8.0463
0.2166	27300	8.0247
0.2174	27400	8.0172
0.2182	27500	8.0444
0.2190	27600	8.0258
0.2198	27700	8.0078
0.2206	27800	8.0172
0.2214	27900	8.0096
0.2222	28000	8.0176
0.2230	28100	8.043
0.2238	28200	8.0148
0.2246	28300	8.0201
0.2254	28400	8.0153
0.2262	28500	8.0029
0.2270	28600	8.0177
0.2278	28700	7.9915
0.2286	28800	8.0029
0.2293	28900	8.0194
0.2301	29000	7.9943
0.2309	29100	8.0225
0.2317	29200	8.0087
0.2325	29300	7.9943
0.2333	29400	7.9821
0.2341	29500	8.0337
0.2349	29600	7.9904
0.2357	29700	8.0029
0.2365	29800	8.0132
0.2373	29900	8.0133
0.2381	30000	8.0109
0.2389	30100	8.0007
0.2397	30200	7.9951
0.2405	30300	8.0092
0.2413	30400	7.9876
0.2420	30500	7.974
0.2428	30600	8.0293
0.2436	30700	8.0168
0.2444	30800	8.0134
0.2452	30900	7.9936
0.2460	31000	7.9884
0.2468	31100	8.0183
0.2476	31200	7.9687
0.2484	31300	7.9874
0.2492	31400	7.9994
0.2500	31500	8.0076
0.2508	31600	7.9906
0.2516	31700	7.9987
0.2524	31800	7.9599
0.2532	31900	7.9957
0.2539	32000	7.9948
0.2547	32100	7.985
0.2555	32200	8.0045
0.2563	32300	7.9805
0.2571	32400	7.9843
0.2579	32500	7.9826
0.2587	32600	7.9999
0.2595	32700	7.9855
0.2603	32800	7.9767
0.2611	32900	7.9793
0.2619	33000	7.9961
0.2627	33100	7.9766
0.2635	33200	7.9618
0.2643	33300	7.951
0.2651	33400	7.9468
0.2659	33500	7.9869
0.2666	33600	7.9575
0.2674	33700	7.9773
0.2682	33800	7.9753
0.2690	33900	7.935
0.2698	34000	7.9692
0.2706	34100	7.965
0.2714	34200	7.9761
0.2722	34300	8.0068
0.2730	34400	7.9536
0.2738	34500	7.9541
0.2746	34600	7.962
0.2754	34700	7.9495
0.2762	34800	7.9683
0.2770	34900	7.9584
0.2778	35000	7.9716
0.2785	35100	7.9519
0.2793	35200	7.9529
0.2801	35300	7.9413
0.2809	35400	7.9636
0.2817	35500	7.9426
0.2825	35600	7.9692
0.2833	35700	7.9426
0.2841	35800	7.935
0.2849	35900	7.9374
0.2857	36000	7.9531
0.2865	36100	7.9026
0.2873	36200	7.9394
0.2881	36300	7.9636
0.2889	36400	7.9517
0.2897	36500	7.9726
0.2905	36600	7.9631
0.2912	36700	7.9693
0.2920	36800	7.9425
0.2928	36900	7.9484
0.2936	37000	7.9596
0.2944	37100	7.9672
0.2952	37200	7.9653
0.2960	37300	7.9428
0.2968	37400	7.9487
0.2976	37500	7.9445
0.2984	37600	7.9382
0.2992	37700	7.9222
0.3000	37800	7.9331
0.3008	37900	7.9419
0.3016	38000	7.9458
0.3024	38100	7.9164
0.3032	38200	7.9503
0.3039	38300	7.9397
0.3047	38400	7.9297
0.3055	38500	7.9413
0.3063	38600	7.9428
0.3071	38700	7.9539
0.3079	38800	7.9257
0.3087	38900	7.9333
0.3095	39000	7.9469
0.3103	39100	7.955
0.3111	39200	7.9186
0.3119	39300	7.9632
0.3127	39400	7.9334
0.3135	39500	7.9175
0.3143	39600	7.9461
0.3151	39700	7.9151
0.3158	39800	7.9528
0.3166	39900	7.9169
0.3174	40000	7.9113
0.3182	40100	7.9366
0.3190	40200	7.9159
0.3198	40300	7.9217
0.3206	40400	7.9045
0.3214	40500	7.9366
0.3222	40600	7.9116
0.3230	40700	7.9137
0.3238	40800	7.9387
0.3246	40900	7.9331
0.3254	41000	7.9558
0.3262	41100	7.9365
0.3270	41200	7.9175
0.3278	41300	7.9329
0.3285	41400	7.9237
0.3293	41500	7.9016
0.3301	41600	7.9156
0.3309	41700	7.9239
0.3317	41800	7.9125
0.3325	41900	7.9353
0.3333	42000	7.8883
0.3341	42100	7.9012
0.3349	42200	7.8779
0.3357	42300	7.881
0.3365	42400	7.8885
0.3373	42500	7.8855
0.3381	42600	7.9205
0.3389	42700	7.9214
0.3397	42800	7.9223
0.3404	42900	7.8759
0.3412	43000	7.8805
0.3420	43100	7.9208
0.3428	43200	7.8863
0.3436	43300	7.8829
0.3444	43400	7.9344
0.3452	43500	7.9121
0.3460	43600	7.9014
0.3468	43700	7.9155
0.3476	43800	7.8697
0.3484	43900	7.9239
0.3492	44000	7.8936
0.3500	44100	7.884
0.3508	44200	7.8932
0.3516	44300	7.8956
0.3524	44400	7.9098
0.3531	44500	7.9522
0.3539	44600	7.918
0.3547	44700	7.8953
0.3555	44800	7.8702
0.3563	44900	7.8849
0.3571	45000	7.8968
0.3579	45100	7.9054
0.3587	45200	7.8979
0.3595	45300	7.887
0.3603	45400	7.9034
0.3611	45500	7.907
0.3619	45600	7.8722
0.3627	45700	7.8959
0.3635	45800	7.8751
0.3643	45900	7.886
0.3651	46000	7.8726
0.3658	46100	7.8798
0.3666	46200	7.9157
0.3674	46300	7.8851
0.3682	46400	7.8991
0.3690	46500	7.8911
0.3698	46600	7.881
0.3706	46700	7.8913
0.3714	46800	7.9111
0.3722	46900	7.9139
0.3730	47000	7.8595
0.3738	47100	7.8925
0.3746	47200	7.9022
0.3754	47300	7.8725
0.3762	47400	7.8861
0.3770	47500	7.8775
0.3777	47600	7.8922
0.3785	47700	7.8804
0.3793	47800	7.8762
0.3801	47900	7.9114
0.3809	48000	7.8826
0.3817	48100	7.8857
0.3825	48200	7.891
0.3833	48300	7.8671
0.3841	48400	7.9003
0.3849	48500	7.8653
0.3857	48600	7.8554
0.3865	48700	7.8738
0.3873	48800	7.8421
0.3881	48900	7.8719
0.3889	49000	7.8765
0.3897	49100	7.8666
0.3904	49200	7.8836
0.3912	49300	7.8824
0.3920	49400	7.8807
0.3928	49500	7.8924
0.3936	49600	7.8641
0.3944	49700	7.8644
0.3952	49800	7.9068
0.3960	49900	7.8805
0.3968	50000	7.8713
0.3976	50100	7.835
0.3984	50200	7.8765
0.3992	50300	7.8671
0.4000	50400	7.8644
0.4008	50500	7.8531
0.4016	50600	7.8603
0.4023	50700	7.873
0.4031	50800	7.8211
0.4039	50900	7.8875
0.4047	51000	7.8361
0.4055	51100	7.846
0.4063	51200	7.8665
0.4071	51300	7.8654
0.4079	51400	7.871
0.4087	51500	7.8837
0.4095	51600	7.8653
0.4103	51700	7.8692
0.4111	51800	7.8727
0.4119	51900	7.8494
0.4127	52000	7.864
0.4135	52100	7.8321
0.4143	52200	7.8817
0.4150	52300	7.8643
0.4158	52400	7.8742
0.4166	52500	7.8269
0.4174	52600	7.8703
0.4182	52700	7.8418
0.4190	52800	7.8645
0.4198	52900	7.8913
0.4206	53000	7.8711
0.4214	53100	7.8614
0.4222	53200	7.8542
0.4230	53300	7.8609
0.4238	53400	7.8436
0.4246	53500	7.8384
0.4254	53600	7.8505
0.4262	53700	7.8446
0.4270	53800	7.8647
0.4277	53900	7.8698
0.4285	54000	7.8662
0.4293	54100	7.8487
0.4301	54200	7.8446
0.4309	54300	7.8413
0.4317	54400	7.8485
0.4325	54500	7.8481
0.4333	54600	7.8446
0.4341	54700	7.847
0.4349	54800	7.8648
0.4357	54900	7.8568
0.4365	55000	7.8572
0.4373	55100	7.8201
0.4381	55200	7.8743
0.4389	55300	7.8584
0.4396	55400	7.8556
0.4404	55500	7.8377
0.4412	55600	7.8395
0.4420	55700	7.8151
0.4428	55800	7.8701
0.4436	55900	7.8195
0.4444	56000	7.8359
0.4452	56100	7.802
0.4460	56200	7.8598
0.4468	56300	7.811
0.4476	56400	7.8316
0.4484	56500	7.8364
0.4492	56600	7.8345
0.4500	56700	7.8643
0.4508	56800	7.8588
0.4516	56900	7.8429
0.4523	57000	7.8163
0.4531	57100	7.8507
0.4539	57200	7.8508
0.4547	57300	7.8474
0.4555	57400	7.8376
0.4563	57500	7.8592
0.4571	57600	7.8193
0.4579	57700	7.8459
0.4587	57800	7.8394
0.4595	57900	7.8519
0.4603	58000	7.8297
0.4611	58100	7.8396
0.4619	58200	7.8112
0.4627	58300	7.8486
0.4635	58400	7.8347
0.4642	58500	7.8188
0.4650	58600	7.8357
0.4658	58700	7.8081
0.4666	58800	7.8215
0.4674	58900	7.8503
0.4682	59000	7.8115
0.4690	59100	7.8347
0.4698	59200	7.8164
0.4706	59300	7.8217
0.4714	59400	7.8241
0.4722	59500	7.8531
0.4730	59600	7.8324
0.4738	59700	7.8145
0.4746	59800	7.8476
0.4754	59900	7.8152
0.4762	60000	7.8189
0.4769	60100	7.837
0.4777	60200	7.8571
0.4785	60300	7.8238
0.4793	60400	7.7942
0.4801	60500	7.8173
0.4809	60600	7.8186
0.4817	60700	7.8126
0.4825	60800	7.825
0.4833	60900	7.8299
0.4841	61000	7.8519
0.4849	61100	7.8689
0.4857	61200	7.8178
0.4865	61300	7.8121
0.4873	61400	7.8131
0.4881	61500	7.8413
0.4889	61600	7.8433
0.4896	61700	7.8375
0.4904	61800	7.8078
0.4912	61900	7.8312
0.4920	62000	7.8159
0.4928	62100	7.8169
0.4936	62200	7.7726
0.4944	62300	7.8022
0.4952	62400	7.8344
0.4960	62500	7.859
0.4968	62600	7.8218
0.4976	62700	7.8391
0.4984	62800	7.8261
0.4992	62900	7.8323
0.5000	63000	7.7875
0.5008	63100	7.7741
0.5015	63200	7.8069
0.5023	63300	7.8076
0.5031	63400	7.8038
0.5039	63500	7.8486
0.5047	63600	7.8278
0.5055	63700	7.8126
0.5063	63800	7.8137
0.5071	63900	7.8078
0.5079	64000	7.8305
0.5087	64100	7.7989
0.5095	64200	7.8163
0.5103	64300	7.8128
0.5111	64400	7.7948
0.5119	64500	7.8028
0.5127	64600	7.8121
0.5135	64700	7.8053
0.5142	64800	7.815
0.5150	64900	7.8244
0.5158	65000	7.8276
0.5166	65100	7.796
0.5174	65200	7.8108
0.5182	65300	7.8166
0.5190	65400	7.8152
0.5198	65500	7.8633
0.5206	65600	7.783
0.5214	65700	7.7833
0.5222	65800	7.8244
0.5230	65900	7.8006
0.5238	66000	7.8124
0.5246	66100	7.7986
0.5254	66200	7.8133
0.5261	66300	7.8178
0.5269	66400	7.7955
0.5277	66500	7.7917
0.5285	66600	7.7886
0.5293	66700	7.794
0.5301	66800	7.8144
0.5309	66900	7.7854
0.5317	67000	7.8071
0.5325	67100	7.827
0.5333	67200	7.8037
0.5341	67300	7.8292
0.5349	67400	7.8169
0.5357	67500	7.8021
0.5365	67600	7.7747
0.5373	67700	7.8087
0.5381	67800	7.7942
0.5388	67900	7.8302
0.5396	68000	7.7977
0.5404	68100	7.8037
0.5412	68200	7.8149
0.5420	68300	7.8062
0.5428	68400	7.7885
0.5436	68500	7.7884
0.5444	68600	7.8039
0.5452	68700	7.7627
0.5460	68800	7.8333
0.5468	68900	7.8053
0.5476	69000	7.7688
0.5484	69100	7.7829
0.5492	69200	7.7843
0.5500	69300	7.802
0.5507	69400	7.8292
0.5515	69500	7.8138
0.5523	69600	7.7905
0.5531	69700	7.824
0.5539	69800	7.7783
0.5547	69900	7.8024
0.5555	70000	7.7807
0.5563	70100	7.7772
0.5571	70200	7.7863
0.5579	70300	7.7998
0.5587	70400	7.7856
0.5595	70500	7.7606
0.5603	70600	7.7987
0.5611	70700	7.7853
0.5619	70800	7.7884
0.5627	70900	7.7602
0.5634	71000	7.7772
0.5642	71100	7.7539
0.5650	71200	7.7724
0.5658	71300	7.7803
0.5666	71400	7.7986
0.5674	71500	7.7866
0.5682	71600	7.8035
0.5690	71700	7.8079
0.5698	71800	7.7923
0.5706	71900	7.7759
0.5714	72000	7.7848
0.5722	72100	7.7979
0.5730	72200	7.7862
0.5738	72300	7.7896
0.5746	72400	7.757
0.5754	72500	7.7763
0.5761	72600	7.7988
0.5769	72700	7.7997
0.5777	72800	7.737
0.5785	72900	7.7566
0.5793	73000	7.7913
0.5801	73100	7.8101
0.5809	73200	7.8247
0.5817	73300	7.7959
0.5825	73400	7.7512
0.5833	73500	7.7952
0.5841	73600	7.7806
0.5849	73700	7.7492
0.5857	73800	7.7714
0.5865	73900	7.7809
0.5873	74000	7.7698
0.5880	74100	7.7788
0.5888	74200	7.8036
0.5896	74300	7.77
0.5904	74400	7.7614
0.5912	74500	7.7626
0.5920	74600	7.8025
0.5928	74700	7.8055
0.5936	74800	7.7715
0.5944	74900	7.7786
0.5952	75000	7.7386
0.5960	75100	7.7807
0.5968	75200	7.7871
0.5976	75300	7.7905
0.5984	75400	7.79
0.5992	75500	7.7719
0.6000	75600	7.7581
0.6007	75700	7.7619
0.6015	75800	7.8176
0.6023	75900	7.7459
0.6031	76000	7.7442
0.6039	76100	7.7827
0.6047	76200	7.745
0.6055	76300	7.7466
0.6063	76400	7.7689
0.6071	76500	7.7913
0.6079	76600	7.7981
0.6087	76700	7.7484
0.6095	76800	7.7786
0.6103	76900	7.7808
0.6111	77000	7.7762
0.6119	77100	7.7662
0.6126	77200	7.7814
0.6134	77300	7.7712
0.6142	77400	7.7619
0.6150	77500	7.751
0.6158	77600	7.759
0.6166	77700	7.793
0.6174	77800	7.7561
0.6182	77900	7.7942
0.6190	78000	7.7757
0.6198	78100	7.7635
0.6206	78200	7.7829
0.6214	78300	7.7624
0.6222	78400	7.7786
0.6230	78500	7.7773
0.6238	78600	7.7637
0.6246	78700	7.774
0.6253	78800	7.7452
0.6261	78900	7.7391
0.6269	79000	7.807
0.6277	79100	7.7618
0.6285	79200	7.7735
0.6293	79300	7.8033
0.6301	79400	7.7517
0.6309	79500	7.7263
0.6317	79600	7.7884
0.6325	79700	7.7401
0.6333	79800	7.7499
0.6341	79900	7.7994
0.6349	80000	7.7616
0.6357	80100	7.7527
0.6365	80200	7.7651
0.6373	80300	7.7944
0.6380	80400	7.761
0.6388	80500	7.7546
0.6396	80600	7.7555
0.6404	80700	7.7601
0.6412	80800	7.7656
0.6420	80900	7.7681
0.6428	81000	7.7618
0.6436	81100	7.7523
0.6444	81200	7.7482
0.6452	81300	7.738
0.6460	81400	7.7705
0.6468	81500	7.7567
0.6476	81600	7.7263
0.6484	81700	7.7656
0.6492	81800	7.7492
0.6499	81900	7.7643
0.6507	82000	7.7697
0.6515	82100	7.7898
0.6523	82200	7.7474
0.6531	82300	7.765
0.6539	82400	7.7493
0.6547	82500	7.7186
0.6555	82600	7.7751
0.6563	82700	7.7584
0.6571	82800	7.725
0.6579	82900	7.7482
0.6587	83000	7.7703
0.6595	83100	7.8157
0.6603	83200	7.7594
0.6611	83300	7.755
0.6619	83400	7.7403
0.6626	83500	7.7531
0.6634	83600	7.7466
0.6642	83700	7.7645
0.6650	83800	7.7265
0.6658	83900	7.7419
0.6666	84000	7.7565
0.6674	84100	7.7604
0.6682	84200	7.7965
0.6690	84300	7.7233
0.6698	84400	7.7228
0.6706	84500	7.7756
0.6714	84600	7.739
0.6722	84700	7.7439
0.6730	84800	7.7333
0.6738	84900	7.7324
0.6745	85000	7.7553
0.6753	85100	7.7355
0.6761	85200	7.7462
0.6769	85300	7.7894
0.6777	85400	7.7553
0.6785	85500	7.7171
0.6793	85600	7.7608
0.6801	85700	7.7437
0.6809	85800	7.7567
0.6817	85900	7.7391
0.6825	86000	7.7263
0.6833	86100	7.7565
0.6841	86200	7.7873
0.6849	86300	7.7522
0.6857	86400	7.7391
0.6865	86500	7.8187
0.6872	86600	7.7231
0.6880	86700	7.7677
0.6888	86800	7.7376
0.6896	86900	7.7464
0.6904	87000	7.7548
0.6912	87100	7.7433
0.6920	87200	7.762
0.6928	87300	7.7735
0.6936	87400	7.7268
0.6944	87500	7.7826
0.6952	87600	7.7548
0.6960	87700	7.7438
0.6968	87800	7.7642
0.6976	87900	7.7662
0.6984	88000	7.749
0.6992	88100	7.7252
0.6999	88200	7.7467
0.7007	88300	7.7366
0.7015	88400	7.7542
0.7023	88500	7.7649
0.7031	88600	7.7338
0.7039	88700	7.7264
0.7047	88800	7.7229
0.7055	88900	7.7511
0.7063	89000	7.7641
0.7071	89100	7.7461
0.7079	89200	7.7402
0.7087	89300	7.7558
0.7095	89400	7.7222
0.7103	89500	7.7489
0.7111	89600	7.7097
0.7118	89700	7.7535
0.7126	89800	7.7049
0.7134	89900	7.7168
0.7142	90000	7.7702
0.7150	90100	7.7659
0.7158	90200	7.7147
0.7166	90300	7.7281
0.7174	90400	7.7067
0.7182	90500	7.7369
0.7190	90600	7.761
0.7198	90700	7.7218
0.7206	90800	7.7625
0.7214	90900	7.7258
0.7222	91000	7.7782
0.7230	91100	7.7302
0.7238	91200	7.7343
0.7245	91300	7.7384
0.7253	91400	7.7583
0.7261	91500	7.7248
0.7269	91600	7.7312
0.7277	91700	7.7476
0.7285	91800	7.7212
0.7293	91900	7.7823
0.7301	92000	7.7211
0.7309	92100	7.7505
0.7317	92200	7.7494
0.7325	92300	7.7565
0.7333	92400	7.7311
0.7341	92500	7.7563
0.7349	92600	7.7294
0.7357	92700	7.7313
0.7364	92800	7.7366
0.7372	92900	7.754
0.7380	93000	7.7368
0.7388	93100	7.7108
0.7396	93200	7.7149
0.7404	93300	7.7395
0.7412	93400	7.7078
0.7420	93500	7.7508
0.7428	93600	7.744
0.7436	93700	7.7103
0.7444	93800	7.696
0.7452	93900	7.777
0.7460	94000	7.7409
0.7468	94100	7.7116
0.7476	94200	7.7163
0.7484	94300	7.7435
0.7491	94400	7.7199
0.7499	94500	7.6969
0.7507	94600	7.7359
0.7515	94700	7.7256
0.7523	94800	7.7651
0.7531	94900	7.7584
0.7539	95000	7.7042
0.7547	95100	7.7672
0.7555	95200	7.7523
0.7563	95300	7.7483
0.7571	95400	7.7278
0.7579	95500	7.6938
0.7587	95600	7.7303
0.7595	95700	7.7241
0.7603	95800	7.7088
0.7611	95900	7.7295
0.7618	96000	7.7236
0.7626	96100	7.7194
0.7634	96200	7.7435
0.7642	96300	7.7305
0.7650	96400	7.7401
0.7658	96500	7.7202
0.7666	96600	7.7153
0.7674	96700	7.6997
0.7682	96800	7.7401
0.7690	96900	7.7211
0.7698	97000	7.7502
0.7706	97100	7.7497
0.7714	97200	7.7604
0.7722	97300	7.7206
0.7730	97400	7.7096
0.7737	97500	7.7296
0.7745	97600	7.7173
0.7753	97700	7.7311
0.7761	97800	7.7351
0.7769	97900	7.7613
0.7777	98000	7.6853
0.7785	98100	7.7264
0.7793	98200	7.742
0.7801	98300	7.7311
0.7809	98400	7.7176
0.7817	98500	7.7883
0.7825	98600	7.709
0.7833	98700	7.7046
0.7841	98800	7.7098
0.7849	98900	7.7763
0.7857	99000	7.7084
0.7864	99100	7.7412
0.7872	99200	7.7477
0.7880	99300	7.7184
0.7888	99400	7.7347
0.7896	99500	7.7394
0.7904	99600	7.7199
0.7912	99700	7.7151
0.7920	99800	7.7274
0.7928	99900	7.6888
0.7936	100000	7.725
0.7944	100100	7.7009
0.7952	100200	7.7246
0.7960	100300	7.7188
0.7968	100400	7.7341
0.7976	100500	7.7318
0.7983	100600	7.6957
0.7991	100700	7.7267
0.7999	100800	7.7679
0.8007	100900	7.7271
0.8015	101000	7.7217
0.8023	101100	7.7253
0.8031	101200	7.7329
0.8039	101300	7.6941
0.8047	101400	7.7323
0.8055	101500	7.6976
0.8063	101600	7.7439
0.8071	101700	7.7623
0.8079	101800	7.729
0.8087	101900	7.6938
0.8095	102000	7.6783
0.8103	102100	7.7248
0.8110	102200	7.7036
0.8118	102300	7.768
0.8126	102400	7.7526
0.8134	102500	7.7281
0.8142	102600	7.7057
0.8150	102700	7.7184
0.8158	102800	7.7045
0.8166	102900	7.7093
0.8174	103000	7.7216
0.8182	103100	7.7283
0.8190	103200	7.7214
0.8198	103300	7.6943
0.8206	103400	7.6937
0.8214	103500	7.7123
0.8222	103600	7.706
0.8230	103700	7.6929
0.8237	103800	7.7503
0.8245	103900	7.6824
0.8253	104000	7.7889
0.8261	104100	7.7266
0.8269	104200	7.7
0.8277	104300	7.7261
0.8285	104400	7.7088
0.8293	104500	7.7035
0.8301	104600	7.7058
0.8309	104700	7.7463
0.8317	104800	7.7048
0.8325	104900	7.7301
0.8333	105000	7.7147
0.8341	105100	7.6955
0.8349	105200	7.7118
0.8356	105300	7.7108
0.8364	105400	7.6946
0.8372	105500	7.7186
0.8380	105600	7.6818
0.8388	105700	7.7563
0.8396	105800	7.7027
0.8404	105900	7.7339
0.8412	106000	7.7373
0.8420	106100	7.7244
0.8428	106200	7.7042
0.8436	106300	7.7341
0.8444	106400	7.7367
0.8452	106500	7.7172
0.8460	106600	7.7426
0.8468	106700	7.696
0.8476	106800	7.6818
0.8483	106900	7.7041
0.8491	107000	7.7221
0.8499	107100	7.6901
0.8507	107200	7.7343
0.8515	107300	7.7109
0.8523	107400	7.7084
0.8531	107500	7.6836
0.8539	107600	7.7377
0.8547	107700	7.6956
0.8555	107800	7.675
0.8563	107900	7.7321
0.8571	108000	7.7514
0.8579	108100	7.7446
0.8587	108200	7.7156
0.8595	108300	7.7188
0.8602	108400	7.689
0.8610	108500	7.7278
0.8618	108600	7.712
0.8626	108700	7.736
0.8634	108800	7.7417
0.8642	108900	7.7039
0.8650	109000	7.7193
0.8658	109100	7.7213
0.8666	109200	7.7153
0.8674	109300	7.7459
0.8682	109400	7.6906
0.8690	109500	7.7042
0.8698	109600	7.7097
0.8706	109700	7.7423
0.8714	109800	7.6876
0.8722	109900	7.716
0.8729	110000	7.6976
0.8737	110100	7.6601
0.8745	110200	7.7405
0.8753	110300	7.7046
0.8761	110400	7.6847
0.8769	110500	7.7363
0.8777	110600	7.733
0.8785	110700	7.6918
0.8793	110800	7.714
0.8801	110900	7.733
0.8809	111000	7.7292
0.8817	111100	7.7081
0.8825	111200	7.7203
0.8833	111300	7.7239
0.8841	111400	7.718
0.8849	111500	7.7051
0.8856	111600	7.6943
0.8864	111700	7.7002
0.8872	111800	7.7352
0.8880	111900	7.7299
0.8888	112000	7.7282
0.8896	112100	7.7045
0.8904	112200	7.6851
0.8912	112300	7.6894
0.8920	112400	7.7602
0.8928	112500	7.7152
0.8936	112600	7.6842
0.8944	112700	7.6943
0.8952	112800	7.6727
0.8960	112900	7.712
0.8968	113000	7.7092
0.8975	113100	7.6826
0.8983	113200	7.7176
0.8991	113300	7.68
0.8999	113400	7.7299
0.9007	113500	7.6977
0.9015	113600	7.7029
0.9023	113700	7.7294
0.9031	113800	7.6958
0.9039	113900	7.7444
0.9047	114000	7.7007
0.9055	114100	7.7493
0.9063	114200	7.6909
0.9071	114300	7.7131
0.9079	114400	7.6643
0.9087	114500	7.7092
0.9095	114600	7.6754
0.9102	114700	7.7094
0.9110	114800	7.716
0.9118	114900	7.6793
0.9126	115000	7.7112
0.9134	115100	7.7104
0.9142	115200	7.6768
0.9150	115300	7.6843
0.9158	115400	7.7062
0.9166	115500	7.7014
0.9174	115600	7.7026
0.9182	115700	7.6843
0.9190	115800	7.6891
0.9198	115900	7.7344
0.9206	116000	7.694
0.9214	116100	7.7584
0.9221	116200	7.6932
0.9229	116300	7.6908
0.9237	116400	7.7406
0.9245	116500	7.674
0.9253	116600	7.7146
0.9261	116700	7.6996
0.9269	116800	7.6695
0.9277	116900	7.6783
0.9285	117000	7.7497
0.9293	117100	7.7069
0.9301	117200	7.6609
0.9309	117300	7.6881
0.9317	117400	7.7238
0.9325	117500	7.7049
0.9333	117600	7.7181
0.9341	117700	7.7412
0.9348	117800	7.6789
0.9356	117900	7.72
0.9364	118000	7.7105
0.9372	118100	7.7394
0.9380	118200	7.7004
0.9388	118300	7.6771
0.9396	118400	7.71
0.9404	118500	7.753
0.9412	118600	7.7365
0.9420	118700	7.7401
0.9428	118800	7.7054
0.9436	118900	7.6886
0.9444	119000	7.6996
0.9452	119100	7.6824
0.9460	119200	7.7129
0.9468	119300	7.6946
0.9475	119400	7.7069
0.9483	119500	7.7098
0.9491	119600	7.7241
0.9499	119700	7.7222
0.9507	119800	7.7286
0.9515	119900	7.7165
0.9523	120000	7.7206
0.9531	120100	7.7114
0.9539	120200	7.6897
0.9547	120300	7.6895
0.9555	120400	7.7139
0.9563	120500	7.6983
0.9571	120600	7.6662
0.9579	120700	7.6931
0.9587	120800	7.6913
0.9594	120900	7.7001
0.9602	121000	7.6926
0.9610	121100	7.7116
0.9618	121200	7.6727
0.9626	121300	7.6788
0.9634	121400	7.7195
0.9642	121500	7.7806
0.9650	121600	7.6785
0.9658	121700	7.7084
0.9666	121800	7.6979
0.9674	121900	7.7208
0.9682	122000	7.686
0.9690	122100	7.6887
0.9698	122200	7.7139
0.9706	122300	7.7221
0.9714	122400	7.7109
0.9721	122500	7.669
0.9729	122600	7.6576
0.9737	122700	7.7048
0.9745	122800	7.6844
0.9753	122900	7.7081
0.9761	123000	7.7326
0.9769	123100	7.7075
0.9777	123200	7.7402
0.9785	123300	7.7331
0.9793	123400	7.6837
0.9801	123500	7.6931
0.9809	123600	7.6739
0.9817	123700	7.6916
0.9825	123800	7.6714
0.9833	123900	7.6778
0.9840	124000	7.695
0.9848	124100	7.7051
0.9856	124200	7.7207
0.9864	124300	7.675
0.9872	124400	7.7243
0.9880	124500	7.6943
0.9888	124600	7.6948
0.9896	124700	7.7449
0.9904	124800	7.6688
0.9912	124900	7.7113
0.9920	125000	7.7101
0.9928	125100	7.7033
0.9936	125200	7.6743
0.9944	125300	7.7035
0.9952	125400	7.7285
0.9960	125500	7.6847
0.9967	125600	7.6844
0.9975	125700	7.7296
0.9983	125800	7.7482
0.9991	125900	7.6953
0.9999	126000	7.7326

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},
}