all-MiniLM-L6-v12-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v10_synonyms 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_v10_synonyms
• 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 = [
    'knitwear',
    'unisex trousers',
    'daily exfoliating scrub',
]
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, 0.7775, 0.4984],
#         [0.7775, 1.0000, 0.4737],
#         [0.4984, 0.4737, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v10_synonyms

• Dataset: pairs_three_scores_v10_synonyms at 7a03b60
• Size: 16,131,988 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: 5.63 tokens max: 20 tokens	min: 3 tokens mean: 5.75 tokens max: 41 tokens	min: 0.15 mean: 0.36 max: 1.0

• Samples:

  sentence1	sentence2	score
  kango gloves	balance board	0.27
  nylon fanny pack	internal pockets bag	0.33
  marshmallow scent perfume	handmade bowl	0.21

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v10_synonyms

• Dataset: pairs_three_scores_v10_synonyms at 7a03b60
• Size: 81,066 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: 5.56 tokens max: 14 tokens	min: 3 tokens mean: 5.71 tokens max: 22 tokens	min: 0.16 mean: 0.34 max: 1.0

• Samples:

  sentence1	sentence2	score
  tahini brownies	laylo tee	0.25
  vinyl sticker candy	buttercream cupcake	0.3
  relax sofa	stoneware plate	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
0.0008	100	12.0412
0.0016	200	11.9152
0.0024	300	11.912
0.0032	400	11.5195
0.0040	500	11.2838
0.0048	600	11.1474
0.0056	700	10.7648
0.0063	800	10.4413
0.0071	900	10.2946
0.0079	1000	10.0453
0.0087	1100	9.7748
0.0095	1200	9.6514
0.0103	1300	9.4917
0.0111	1400	9.2272
0.0119	1500	9.0495
0.0127	1600	8.9256
0.0135	1700	8.8294
0.0143	1800	8.7685
0.0151	1900	8.7427
0.0159	2000	8.7067
0.0167	2100	8.7053
0.0175	2200	8.6753
0.0182	2300	8.6717
0.0190	2400	8.6575
0.0198	2500	8.6501
0.0206	2600	8.6424
0.0214	2700	8.6203
0.0222	2800	8.6342
0.0230	2900	8.6031
0.0238	3000	8.6121
0.0246	3100	8.5977
0.0254	3200	8.5898
0.0262	3300	8.5821
0.0270	3400	8.5881
0.0278	3500	8.5784
0.0286	3600	8.5604
0.0294	3700	8.5606
0.0302	3800	8.5429
0.0309	3900	8.5491
0.0317	4000	8.5483
0.0325	4100	8.5394
0.0333	4200	8.5343
0.0341	4300	8.5251
0.0349	4400	8.5183
0.0357	4500	8.5069
0.0365	4600	8.5296
0.0373	4700	8.501
0.0381	4800	8.5133
0.0389	4900	8.4931
0.0397	5000	8.4872
0.0405	5100	8.5026
0.0413	5200	8.4917
0.0421	5300	8.4758
0.0428	5400	8.4826
0.0436	5500	8.4639
0.0444	5600	8.4732
0.0452	5700	8.4576
0.0460	5800	8.4761
0.0468	5900	8.4504
0.0476	6000	8.458
0.0484	6100	8.4411
0.0492	6200	8.4336
0.0500	6300	8.4425
0.0508	6400	8.4439
0.0516	6500	8.4314
0.0524	6600	8.426
0.0532	6700	8.4333
0.0540	6800	8.4237
0.0547	6900	8.4138
0.0555	7000	8.404
0.0563	7100	8.4076
0.0571	7200	8.4042
0.0579	7300	8.4052
0.0587	7400	8.4037
0.0595	7500	8.4017
0.0603	7600	8.4103
0.0611	7700	8.3919
0.0619	7800	8.3827
0.0627	7900	8.371
0.0635	8000	8.3792
0.0643	8100	8.3737
0.0651	8200	8.376
0.0659	8300	8.3804
0.0666	8400	8.3679
0.0674	8500	8.3731
0.0682	8600	8.3716
0.0690	8700	8.372
0.0698	8800	8.3806
0.0706	8900	8.3491
0.0714	9000	8.3285
0.0722	9100	8.3454
0.0730	9200	8.3536
0.0738	9300	8.3538
0.0746	9400	8.3495
0.0754	9500	8.3395
0.0762	9600	8.3342
0.0770	9700	8.3125
0.0778	9800	8.3323
0.0786	9900	8.3057
0.0793	10000	8.3212
0.0801	10100	8.3136
0.0809	10200	8.3163
0.0817	10300	8.326
0.0825	10400	8.3099
0.0833	10500	8.3121
0.0841	10600	8.3165
0.0849	10700	8.3076
0.0857	10800	8.298
0.0865	10900	8.2938
0.0873	11000	8.289
0.0881	11100	8.2997
0.0889	11200	8.2932
0.0897	11300	8.2841
0.0905	11400	8.2825
0.0912	11500	8.2785
0.0920	11600	8.3002
0.0928	11700	8.2711
0.0936	11800	8.2854
0.0944	11900	8.2745
0.0952	12000	8.2641
0.0960	12100	8.2712
0.0968	12200	8.2613
0.0976	12300	8.2779
0.0984	12400	8.2499
0.0992	12500	8.2666
0.1000	12600	8.2553
0.1008	12700	8.2421
0.1016	12800	8.2562
0.1024	12900	8.2483
0.1031	13000	8.2657
0.1039	13100	8.2454
0.1047	13200	8.2381
0.1055	13300	8.2406
0.1063	13400	8.229
0.1071	13500	8.2139
0.1079	13600	8.2308
0.1087	13700	8.2442
0.1095	13800	8.2102
0.1103	13900	8.2337
0.1111	14000	8.234
0.1119	14100	8.2024
0.1127	14200	8.2114
0.1135	14300	8.2167
0.1143	14400	8.2168
0.1151	14500	8.2264
0.1158	14600	8.2055
0.1166	14700	8.2172
0.1174	14800	8.1961
0.1182	14900	8.1905
0.1190	15000	8.1855
0.1198	15100	8.1984
0.1206	15200	8.1847
0.1214	15300	8.1916
0.1222	15400	8.1725
0.1230	15500	8.2086
0.1238	15600	8.177
0.1246	15700	8.1659
0.1254	15800	8.1787
0.1262	15900	8.1683
0.1270	16000	8.1752
0.1277	16100	8.1832
0.1285	16200	8.1832
0.1293	16300	8.1786
0.1301	16400	8.1713
0.1309	16500	8.1666
0.1317	16600	8.1555
0.1325	16700	8.1553
0.1333	16800	8.1702
0.1341	16900	8.1586
0.1349	17000	8.1578
0.1357	17100	8.1531
0.1365	17200	8.1681
0.1373	17300	8.1509
0.1381	17400	8.147
0.1389	17500	8.1465
0.1396	17600	8.1658
0.1404	17700	8.1514
0.1412	17800	8.1463
0.1420	17900	8.1372
0.1428	18000	8.1369
0.1436	18100	8.1435
0.1444	18200	8.147
0.1452	18300	8.1396
0.1460	18400	8.1538
0.1468	18500	8.1308
0.1476	18600	8.1696
0.1484	18700	8.1229
0.1492	18800	8.1333
0.1500	18900	8.1217
0.1508	19000	8.1189
0.1515	19100	8.1132
0.1523	19200	8.1085
0.1531	19300	8.141
0.1539	19400	8.1169
0.1547	19500	8.1234
0.1555	19600	8.1328
0.1563	19700	8.1204
0.1571	19800	8.1107
0.1579	19900	8.1383
0.1587	20000	8.1167
0.1595	20100	8.1088
0.1603	20200	8.0967
0.1611	20300	8.1275
0.1619	20400	8.103
0.1627	20500	8.0989
0.1635	20600	8.1116
0.1642	20700	8.0952
0.1650	20800	8.1064
0.1658	20900	8.0833
0.1666	21000	8.0924
0.1674	21100	8.083
0.1682	21200	8.1075
0.1690	21300	8.07
0.1698	21400	8.0769
0.1706	21500	8.1305
0.1714	21600	8.0656
0.1722	21700	8.0887
0.1730	21800	8.0884
0.1738	21900	8.0961
0.1746	22000	8.0807
0.1754	22100	8.0795
0.1761	22200	8.0833
0.1769	22300	8.1031
0.1777	22400	8.0857
0.1785	22500	8.0878
0.1793	22600	8.07
0.1801	22700	8.0943
0.1809	22800	8.0835
0.1817	22900	8.0973
0.1825	23000	8.081
0.1833	23100	8.0924
0.1841	23200	8.0438
0.1849	23300	8.0755
0.1857	23400	8.0749
0.1865	23500	8.0786
0.1873	23600	8.0558
0.1880	23700	8.0627
0.1888	23800	8.0876
0.1896	23900	8.0635
0.1904	24000	8.041
0.1912	24100	8.0657
0.1920	24200	8.0608
0.1928	24300	8.0688
0.1936	24400	8.0401
0.1944	24500	8.0585
0.1952	24600	8.0621
0.1960	24700	8.0194
0.1968	24800	8.0729
0.1976	24900	8.0449
0.1984	25000	8.041
0.1992	25100	8.074
0.1999	25200	8.0483
0.2007	25300	8.0656
0.2015	25400	8.0639
0.2023	25500	8.0359
0.2031	25600	8.019
0.2039	25700	8.0337
0.2047	25800	8.036
0.2055	25900	8.0224
0.2063	26000	8.0444
0.2071	26100	8.0227
0.2079	26200	8.0208
0.2087	26300	8.05
0.2095	26400	8.0272
0.2103	26500	8.022
0.2111	26600	8.0318
0.2119	26700	8.0332
0.2126	26800	8.0434
0.2134	26900	8.0407
0.2142	27000	8.0326
0.2150	27100	8.028
0.2158	27200	8.0233
0.2166	27300	8.0384
0.2174	27400	8.0513
0.2182	27500	8.0096
0.2190	27600	8.0334
0.2198	27700	8.0335
0.2206	27800	8.0297
0.2214	27900	8.0124
0.2222	28000	8.0294
0.2230	28100	8.0197
0.2238	28200	7.9973
0.2245	28300	8.0122
0.2253	28400	8.0034
0.2261	28500	8.0284
0.2269	28600	8.0158
0.2277	28700	8.0077
0.2285	28800	8.0155
0.2293	28900	8.0216
0.2301	29000	8.0141
0.2309	29100	7.9963
0.2317	29200	8.0045
0.2325	29300	8.0118
0.2333	29400	8.0192
0.2341	29500	7.9981
0.2349	29600	7.9893
0.2357	29700	8.0174
0.2364	29800	7.9907
0.2372	29900	8.0144
0.2380	30000	8.0101
0.2388	30100	7.9858
0.2396	30200	8.0121
0.2404	30300	8.0037
0.2412	30400	8.0033
0.2420	30500	7.966
0.2428	30600	7.9766
0.2436	30700	7.9915
0.2444	30800	8.0029
0.2452	30900	8.0012
0.2460	31000	7.9844
0.2468	31100	7.9884
0.2476	31200	7.9929
0.2483	31300	7.9936
0.2491	31400	7.9997
0.2499	31500	7.9811
0.2507	31600	8.0012
0.2515	31700	7.9789
0.2523	31800	8.0087
0.2531	31900	8.0072
0.2539	32000	7.9996
0.2547	32100	7.9918
0.2555	32200	8.0013
0.2563	32300	7.9866
0.2571	32400	7.9679
0.2579	32500	8.0188
0.2587	32600	7.9661
0.2595	32700	7.9891
0.2603	32800	7.9697
0.2610	32900	7.969
0.2618	33000	7.9749
0.2626	33100	7.9636
0.2634	33200	7.9802
0.2642	33300	7.9643
0.2650	33400	7.9989
0.2658	33500	7.9458
0.2666	33600	7.9944
0.2674	33700	7.9794
0.2682	33800	7.9824
0.2690	33900	7.9922
0.2698	34000	7.9699
0.2706	34100	7.9711
0.2714	34200	7.9582
0.2722	34300	7.9877
0.2729	34400	7.9604
0.2737	34500	7.9874
0.2745	34600	7.9601
0.2753	34700	7.9355
0.2761	34800	7.9501
0.2769	34900	7.9548
0.2777	35000	7.9632
0.2785	35100	7.981
0.2793	35200	7.9614
0.2801	35300	7.9746
0.2809	35400	7.938
0.2817	35500	7.9592
0.2825	35600	7.9508
0.2833	35700	7.9587
0.2841	35800	7.9414
0.2848	35900	7.9619
0.2856	36000	7.9494
0.2864	36100	7.9448
0.2872	36200	7.9596
0.2880	36300	7.9503
0.2888	36400	7.9502
0.2896	36500	7.943
0.2904	36600	7.935
0.2912	36700	7.965
0.2920	36800	7.9485
0.2928	36900	7.9289
0.2936	37000	7.9595
0.2944	37100	7.9497
0.2952	37200	7.9302
0.2960	37300	7.9177
0.2968	37400	7.9516
0.2975	37500	7.9546
0.2983	37600	7.9561
0.2991	37700	7.9394
0.2999	37800	7.9266
0.3007	37900	7.9413
0.3015	38000	7.9485
0.3023	38100	7.9366
0.3031	38200	7.9355
0.3039	38300	7.9164
0.3047	38400	7.9553
0.3055	38500	7.958
0.3063	38600	7.9331
0.3071	38700	7.9183
0.3079	38800	7.9185
0.3087	38900	7.9438
0.3094	39000	7.9204
0.3102	39100	7.9175
0.3110	39200	7.9323
0.3118	39300	7.9108
0.3126	39400	7.9405
0.3134	39500	7.9238
0.3142	39600	7.9306
0.3150	39700	7.9372
0.3158	39800	7.948
0.3166	39900	7.9174
0.3174	40000	7.916
0.3182	40100	7.9212
0.3190	40200	7.9407
0.3198	40300	7.9181
0.3206	40400	7.9181
0.3213	40500	7.9285
0.3221	40600	7.9136
0.3229	40700	7.9239
0.3237	40800	7.9119
0.3245	40900	7.9201
0.3253	41000	7.9126
0.3261	41100	7.9269
0.3269	41200	7.8949
0.3277	41300	7.8836
0.3285	41400	7.9099
0.3293	41500	7.9219
0.3301	41600	7.9426
0.3309	41700	7.9163
0.3317	41800	7.9249
0.3325	41900	7.9062
0.3332	42000	7.8736
0.3340	42100	7.9214
0.3348	42200	7.9024
0.3356	42300	7.9086
0.3364	42400	7.9015
0.3372	42500	7.9202
0.3380	42600	7.9097
0.3388	42700	7.9373
0.3396	42800	7.8987
0.3404	42900	7.8992
0.3412	43000	7.8831
0.3420	43100	7.9166
0.3428	43200	7.9293
0.3436	43300	7.9095
0.3444	43400	7.903
0.3452	43500	7.9295
0.3459	43600	7.908
0.3467	43700	7.887
0.3475	43800	7.8854
0.3483	43900	7.9023
0.3491	44000	7.9025
0.3499	44100	7.9328
0.3507	44200	7.8859
0.3515	44300	7.891
0.3523	44400	7.9165
0.3531	44500	7.8875
0.3539	44600	7.8752
0.3547	44700	7.8807
0.3555	44800	7.8818
0.3563	44900	7.8955
0.3571	45000	7.8975
0.3578	45100	7.8736
0.3586	45200	7.8815
0.3594	45300	7.9161
0.3602	45400	7.8515
0.3610	45500	7.9015
0.3618	45600	7.9023
0.3626	45700	7.859
0.3634	45800	7.9132
0.3642	45900	7.9016
0.3650	46000	7.9213
0.3658	46100	7.8946
0.3666	46200	7.8778
0.3674	46300	7.8708
0.3682	46400	7.8756
0.3690	46500	7.9123
0.3697	46600	7.8953
0.3705	46700	7.8767
0.3713	46800	7.8677
0.3721	46900	7.8689
0.3729	47000	7.9171
0.3737	47100	7.91
0.3745	47200	7.88
0.3753	47300	7.891
0.3761	47400	7.8574
0.3769	47500	7.8915
0.3777	47600	7.8857
0.3785	47700	7.9033
0.3793	47800	7.877
0.3801	47900	7.8959
0.3809	48000	7.8763
0.3816	48100	7.8653
0.3824	48200	7.8716
0.3832	48300	7.8871
0.3840	48400	7.8883
0.3848	48500	7.8753
0.3856	48600	7.9032
0.3864	48700	7.8551
0.3872	48800	7.8779
0.3880	48900	7.8767
0.3888	49000	7.8497
0.3896	49100	7.8794
0.3904	49200	7.8867
0.3912	49300	7.8679
0.3920	49400	7.8564
0.3928	49500	7.874
0.3936	49600	7.8734
0.3943	49700	7.8795
0.3951	49800	7.8588
0.3959	49900	7.8713
0.3967	50000	7.8615
0.3975	50100	7.8803
0.3983	50200	7.8909
0.3991	50300	7.8863
0.3999	50400	7.8841
0.4007	50500	7.8682
0.4015	50600	7.8797
0.4023	50700	7.8572
0.4031	50800	7.8712
0.4039	50900	7.8674
0.4047	51000	7.8506
0.4055	51100	7.8768
0.4062	51200	7.8719
0.4070	51300	7.8455
0.4078	51400	7.8829
0.4086	51500	7.8543
0.4094	51600	7.8743
0.4102	51700	7.8779
0.4110	51800	7.8645
0.4118	51900	7.8401
0.4126	52000	7.8621
0.4134	52100	7.8753
0.4142	52200	7.8547
0.4150	52300	7.8518
0.4158	52400	7.8615
0.4166	52500	7.8499
0.4174	52600	7.8632
0.4181	52700	7.8644
0.4189	52800	7.8802
0.4197	52900	7.8653
0.4205	53000	7.8436
0.4213	53100	7.8619
0.4221	53200	7.8601
0.4229	53300	7.8635
0.4237	53400	7.8675
0.4245	53500	7.8669
0.4253	53600	7.8496
0.4261	53700	7.8601
0.4269	53800	7.8567
0.4277	53900	7.829
0.4285	54000	7.828
0.4293	54100	7.8727
0.4300	54200	7.8735
0.4308	54300	7.8582
0.4316	54400	7.8406
0.4324	54500	7.8351
0.4332	54600	7.8549
0.4340	54700	7.8363
0.4348	54800	7.8635
0.4356	54900	7.8572
0.4364	55000	7.8587
0.4372	55100	7.8167
0.4380	55200	7.8116
0.4388	55300	7.8655
0.4396	55400	7.8535
0.4404	55500	7.8363
0.4412	55600	7.8742
0.4420	55700	7.855
0.4427	55800	7.8514
0.4435	55900	7.8316
0.4443	56000	7.8481
0.4451	56100	7.8476
0.4459	56200	7.8584
0.4467	56300	7.8213
0.4475	56400	7.8209
0.4483	56500	7.8181
0.4491	56600	7.8297
0.4499	56700	7.8515
0.4507	56800	7.8609
0.4515	56900	7.8297
0.4523	57000	7.8383
0.4531	57100	7.8139
0.4539	57200	7.856
0.4546	57300	7.8191
0.4554	57400	7.8386
0.4562	57500	7.8752
0.4570	57600	7.8101
0.4578	57700	7.8346
0.4586	57800	7.8217
0.4594	57900	7.8416
0.4602	58000	7.8171
0.4610	58100	7.8451
0.4618	58200	7.8454
0.4626	58300	7.8095
0.4634	58400	7.8377
0.4642	58500	7.8376
0.4650	58600	7.823
0.4658	58700	7.8331
0.4665	58800	7.8253
0.4673	58900	7.8325
0.4681	59000	7.8509
0.4689	59100	7.8452
0.4697	59200	7.8332
0.4705	59300	7.8238
0.4713	59400	7.8026
0.4721	59500	7.8639
0.4729	59600	7.8262
0.4737	59700	7.8494
0.4745	59800	7.8479
0.4753	59900	7.831
0.4761	60000	7.8333
0.4769	60100	7.8325
0.4777	60200	7.8248
0.4784	60300	7.8784
0.4792	60400	7.8093
0.4800	60500	7.8351
0.4808	60600	7.8217
0.4816	60700	7.8132
0.4824	60800	7.8225
0.4832	60900	7.834
0.4840	61000	7.8317
0.4848	61100	7.8747
0.4856	61200	7.8552
0.4864	61300	7.818
0.4872	61400	7.8246
0.4880	61500	7.822
0.4888	61600	7.8202
0.4896	61700	7.8203
0.4904	61800	7.808
0.4911	61900	7.8176
0.4919	62000	7.7943
0.4927	62100	7.8168
0.4935	62200	7.7912
0.4943	62300	7.8415
0.4951	62400	7.826
0.4959	62500	7.8168
0.4967	62600	7.8436
0.4975	62700	7.7826
0.4983	62800	7.8321
0.4991	62900	7.8269
0.4999	63000	7.8432
0.5007	63100	7.8307
0.5015	63200	7.8151
0.5023	63300	7.7998
0.5030	63400	7.8185
0.5038	63500	7.7965
0.5046	63600	7.8193
0.5054	63700	7.8319
0.5062	63800	7.8101
0.5070	63900	7.7838
0.5078	64000	7.828
0.5086	64100	7.8331
0.5094	64200	7.8342
0.5102	64300	7.8022
0.5110	64400	7.7986
0.5118	64500	7.8048
0.5126	64600	7.8123
0.5134	64700	7.799
0.5142	64800	7.8118
0.5149	64900	7.8234
0.5157	65000	7.8083
0.5165	65100	7.8056
0.5173	65200	7.8051
0.5181	65300	7.8097
0.5189	65400	7.8143
0.5197	65500	7.8116
0.5205	65600	7.7758
0.5213	65700	7.7913
0.5221	65800	7.7804
0.5229	65900	7.7906
0.5237	66000	7.7676
0.5245	66100	7.8007
0.5253	66200	7.8194
0.5261	66300	7.8149
0.5269	66400	7.7842
0.5276	66500	7.8083
0.5284	66600	7.8145
0.5292	66700	7.8174
0.5300	66800	7.7821
0.5308	66900	7.795
0.5316	67000	7.8241
0.5324	67100	7.832
0.5332	67200	7.7978
0.5340	67300	7.8049
0.5348	67400	7.8231
0.5356	67500	7.8171
0.5364	67600	7.8007
0.5372	67700	7.8477
0.5380	67800	7.8003
0.5388	67900	7.8196
0.5395	68000	7.8105
0.5403	68100	7.7716
0.5411	68200	7.8121
0.5419	68300	7.7958
0.5427	68400	7.8067
0.5435	68500	7.8335
0.5443	68600	7.8158
0.5451	68700	7.8133
0.5459	68800	7.8423
0.5467	68900	7.8051
0.5475	69000	7.8195
0.5483	69100	7.8095
0.5491	69200	7.7677
0.5499	69300	7.7847
0.5507	69400	7.7981
0.5514	69500	7.7737
0.5522	69600	7.7971
0.5530	69700	7.8085
0.5538	69800	7.7996
0.5546	69900	7.7833
0.5554	70000	7.8204
0.5562	70100	7.7875
0.5570	70200	7.8002
0.5578	70300	7.8105
0.5586	70400	7.8107
0.5594	70500	7.7909
0.5602	70600	7.8094
0.5610	70700	7.7725
0.5618	70800	7.8224
0.5626	70900	7.766
0.5633	71000	7.7958
0.5641	71100	7.7841
0.5649	71200	7.7846
0.5657	71300	7.795
0.5665	71400	7.7668
0.5673	71500	7.7875
0.5681	71600	7.8003
0.5689	71700	7.7688
0.5697	71800	7.751
0.5705	71900	7.773
0.5713	72000	7.7892
0.5721	72100	7.7687
0.5729	72200	7.7745
0.5737	72300	7.7657
0.5745	72400	7.7373
0.5753	72500	7.765
0.5760	72600	7.7766
0.5768	72700	7.785
0.5776	72800	7.7955
0.5784	72900	7.8414
0.5792	73000	7.7838
0.5800	73100	7.8033
0.5808	73200	7.7758
0.5816	73300	7.8067
0.5824	73400	7.7902
0.5832	73500	7.7921
0.5840	73600	7.7989
0.5848	73700	7.8024
0.5856	73800	7.8233
0.5864	73900	7.7966
0.5872	74000	7.7693
0.5879	74100	7.7697
0.5887	74200	7.7514
0.5895	74300	7.8101
0.5903	74400	7.768
0.5911	74500	7.8202
0.5919	74600	7.7555
0.5927	74700	7.8208
0.5935	74800	7.7757
0.5943	74900	7.7755
0.5951	75000	7.7854
0.5959	75100	7.8051
0.5967	75200	7.7653
0.5975	75300	7.8007
0.5983	75400	7.7729
0.5991	75500	7.7658
0.5998	75600	7.7667
0.6006	75700	7.808
0.6014	75800	7.8034
0.6022	75900	7.8004
0.6030	76000	7.7595
0.6038	76100	7.764
0.6046	76200	7.7663
0.6054	76300	7.8129
0.6062	76400	7.788
0.6070	76500	7.7721
0.6078	76600	7.7951
0.6086	76700	7.7497
0.6094	76800	7.7769
0.6102	76900	7.8075
0.6110	77000	7.7576
0.6117	77100	7.7834
0.6125	77200	7.7573
0.6133	77300	7.7652
0.6141	77400	7.7348
0.6149	77500	7.8105
0.6157	77600	7.786
0.6165	77700	7.7999
0.6173	77800	7.7863
0.6181	77900	7.7732
0.6189	78000	7.7531
0.6197	78100	7.7992
0.6205	78200	7.8139
0.6213	78300	7.7678
0.6221	78400	7.7512
0.6229	78500	7.7512
0.6237	78600	7.7516
0.6244	78700	7.7591
0.6252	78800	7.7853
0.6260	78900	7.7598
0.6268	79000	7.7489
0.6276	79100	7.7585
0.6284	79200	7.79
0.6292	79300	7.7485
0.6300	79400	7.8023
0.6308	79500	7.7705
0.6316	79600	7.7609
0.6324	79700	7.7404
0.6332	79800	7.748
0.6340	79900	7.7489
0.6348	80000	7.7646
0.6356	80100	7.7661
0.6363	80200	7.7978
0.6371	80300	7.79
0.6379	80400	7.771
0.6387	80500	7.759
0.6395	80600	7.7393
0.6403	80700	7.7748
0.6411	80800	7.766
0.6419	80900	7.7782
0.6427	81000	7.7686
0.6435	81100	7.7724
0.6443	81200	7.7512
0.6451	81300	7.7616
0.6459	81400	7.7614
0.6467	81500	7.7511
0.6475	81600	7.764
0.6482	81700	7.7391
0.6490	81800	7.7428
0.6498	81900	7.7868
0.6506	82000	7.7309
0.6514	82100	7.7582
0.6522	82200	7.7754
0.6530	82300	7.7282
0.6538	82400	7.7693
0.6546	82500	7.7742
0.6554	82600	7.7859
0.6562	82700	7.7177
0.6570	82800	7.7538
0.6578	82900	7.7574
0.6586	83000	7.7423
0.6594	83100	7.7485
0.6601	83200	7.7748
0.6609	83300	7.7371
0.6617	83400	7.769
0.6625	83500	7.7637
0.6633	83600	7.765
0.6641	83700	7.7525
0.6649	83800	7.738
0.6657	83900	7.783
0.6665	84000	7.7489
0.6673	84100	7.7615
0.6681	84200	7.7318
0.6689	84300	7.7583
0.6697	84400	7.7781
0.6705	84500	7.7194
0.6713	84600	7.7482
0.6721	84700	7.7483
0.6728	84800	7.7635
0.6736	84900	7.739
0.6744	85000	7.7449
0.6752	85100	7.6926
0.6760	85200	7.758
0.6768	85300	7.739
0.6776	85400	7.7419
0.6784	85500	7.7793
0.6792	85600	7.7731
0.6800	85700	7.7676
0.6808	85800	7.741
0.6816	85900	7.7646
0.6824	86000	7.7848
0.6832	86100	7.7405
0.6840	86200	7.749
0.6847	86300	7.7295
0.6855	86400	7.7499
0.6863	86500	7.7653
0.6871	86600	7.7719
0.6879	86700	7.8107
0.6887	86800	7.7414
0.6895	86900	7.7397
0.6903	87000	7.7213
0.6911	87100	7.7619
0.6919	87200	7.7267
0.6927	87300	7.7408
0.6935	87400	7.7421
0.6943	87500	7.7754
0.6951	87600	7.7386
0.6959	87700	7.721
0.6966	87800	7.7403
0.6974	87900	7.771
0.6982	88000	7.7491
0.6990	88100	7.744
0.6998	88200	7.7231
0.7006	88300	7.7498
0.7014	88400	7.7619
0.7022	88500	7.7374
0.7030	88600	7.7649
0.7038	88700	7.7399
0.7046	88800	7.7882
0.7054	88900	7.7816
0.7062	89000	7.7451
0.7070	89100	7.7813
0.7078	89200	7.7419
0.7086	89300	7.7456
0.7093	89400	7.7203
0.7101	89500	7.7378
0.7109	89600	7.7689
0.7117	89700	7.7392
0.7125	89800	7.7071
0.7133	89900	7.7081
0.7141	90000	7.7365
0.7149	90100	7.7483
0.7157	90200	7.7614
0.7165	90300	7.7732
0.7173	90400	7.7589
0.7181	90500	7.7484
0.7189	90600	7.708
0.7197	90700	7.7244
0.7205	90800	7.7543
0.7212	90900	7.7054
0.7220	91000	7.7162
0.7228	91100	7.7454
0.7236	91200	7.7878
0.7244	91300	7.7339
0.7252	91400	7.7792
0.7260	91500	7.7707
0.7268	91600	7.716
0.7276	91700	7.7608
0.7284	91800	7.7055
0.7292	91900	7.7477
0.7300	92000	7.7109
0.7308	92100	7.7544
0.7316	92200	7.7419
0.7324	92300	7.7431
0.7331	92400	7.6993
0.7339	92500	7.7143
0.7347	92600	7.7545
0.7355	92700	7.7326
0.7363	92800	7.741
0.7371	92900	7.7614
0.7379	93000	7.76
0.7387	93100	7.7515
0.7395	93200	7.6917
0.7403	93300	7.7208
0.7411	93400	7.7186
0.7419	93500	7.7356
0.7427	93600	7.7412
0.7435	93700	7.7369
0.7443	93800	7.761
0.7450	93900	7.7277
0.7458	94000	7.7195
0.7466	94100	7.6837
0.7474	94200	7.6995
0.7482	94300	7.7319
0.7490	94400	7.7739
0.7498	94500	7.7449
0.7506	94600	7.7263
0.7514	94700	7.6986
0.7522	94800	7.728
0.7530	94900	7.7952
0.7538	95000	7.7436
0.7546	95100	7.7355
0.7554	95200	7.7532
0.7562	95300	7.7724
0.7570	95400	7.7634
0.7577	95500	7.7302
0.7585	95600	7.7296
0.7593	95700	7.7449
0.7601	95800	7.7524
0.7609	95900	7.7283
0.7617	96000	7.7244
0.7625	96100	7.747
0.7633	96200	7.7524
0.7641	96300	7.7394
0.7649	96400	7.7361
0.7657	96500	7.7341
0.7665	96600	7.7108
0.7673	96700	7.7478
0.7681	96800	7.7656
0.7689	96900	7.7456
0.7696	97000	7.7063
0.7704	97100	7.7138
0.7712	97200	7.7314
0.7720	97300	7.726
0.7728	97400	7.7465
0.7736	97500	7.7501
0.7744	97600	7.7457
0.7752	97700	7.7299
0.7760	97800	7.7463
0.7768	97900	7.7252
0.7776	98000	7.7436
0.7784	98100	7.7624
0.7792	98200	7.7469
0.7800	98300	7.7272
0.7808	98400	7.729
0.7815	98500	7.7571
0.7823	98600	7.7204
0.7831	98700	7.7173
0.7839	98800	7.7226
0.7847	98900	7.6997
0.7855	99000	7.717
0.7863	99100	7.7023
0.7871	99200	7.7006
0.7879	99300	7.7622
0.7887	99400	7.7258
0.7895	99500	7.7504
0.7903	99600	7.7327
0.7911	99700	7.7826
0.7919	99800	7.7066
0.7927	99900	7.7174
0.7934	100000	7.7106
0.7942	100100	7.7423
0.7950	100200	7.7595
0.7958	100300	7.7035
0.7966	100400	7.7308
0.7974	100500	7.7353
0.7982	100600	7.7145
0.7990	100700	7.7311
0.7998	100800	7.7048
0.8006	100900	7.7036
0.8014	101000	7.7387
0.8022	101100	7.7198
0.8030	101200	7.7429
0.8038	101300	7.6884
0.8046	101400	7.7252
0.8054	101500	7.7067
0.8061	101600	7.73
0.8069	101700	7.7027
0.8077	101800	7.7318
0.8085	101900	7.7057
0.8093	102000	7.754
0.8101	102100	7.7112
0.8109	102200	7.7117
0.8117	102300	7.7651
0.8125	102400	7.7167
0.8133	102500	7.67
0.8141	102600	7.7433
0.8149	102700	7.7096
0.8157	102800	7.7173
0.8165	102900	7.7329
0.8173	103000	7.7081
0.8180	103100	7.7031
0.8188	103200	7.7116
0.8196	103300	7.7244
0.8204	103400	7.7479
0.8212	103500	7.7482
0.8220	103600	7.7226
0.8228	103700	7.7198
0.8236	103800	7.7418
0.8244	103900	7.7206
0.8252	104000	7.6748
0.8260	104100	7.726
0.8268	104200	7.7106
0.8276	104300	7.6973
0.8284	104400	7.7458
0.8292	104500	7.7373
0.8299	104600	7.7182
0.8307	104700	7.707
0.8315	104800	7.71
0.8323	104900	7.6899
0.8331	105000	7.6667
0.8339	105100	7.71
0.8347	105200	7.7444
0.8355	105300	7.6934
0.8363	105400	7.7217
0.8371	105500	7.7162
0.8379	105600	7.673
0.8387	105700	7.7248
0.8395	105800	7.7479
0.8403	105900	7.6815
0.8411	106000	7.6878
0.8418	106100	7.7098
0.8426	106200	7.7118
0.8434	106300	7.7066
0.8442	106400	7.6979
0.8450	106500	7.7493
0.8458	106600	7.7283
0.8466	106700	7.746
0.8474	106800	7.6793
0.8482	106900	7.6892
0.8490	107000	7.6969
0.8498	107100	7.7307
0.8506	107200	7.7291
0.8514	107300	7.7283
0.8522	107400	7.7321
0.8530	107500	7.7268
0.8538	107600	7.7407
0.8545	107700	7.7133
0.8553	107800	7.7541
0.8561	107900	7.7013
0.8569	108000	7.7121
0.8577	108100	7.7004
0.8585	108200	7.734
0.8593	108300	7.6979
0.8601	108400	7.675
0.8609	108500	7.718
0.8617	108600	7.7178
0.8625	108700	7.7362
0.8633	108800	7.7027
0.8641	108900	7.7332
0.8649	109000	7.6945
0.8657	109100	7.6932
0.8664	109200	7.7061
0.8672	109300	7.7138
0.8680	109400	7.7057
0.8688	109500	7.7152
0.8696	109600	7.7505
0.8704	109700	7.7545
0.8712	109800	7.7368
0.8720	109900	7.7147
0.8728	110000	7.7154
0.8736	110100	7.6988
0.8744	110200	7.7057
0.8752	110300	7.6855
0.8760	110400	7.6839
0.8768	110500	7.7192
0.8776	110600	7.7253
0.8783	110700	7.7051
0.8791	110800	7.6837
0.8799	110900	7.7374
0.8807	111000	7.7311
0.8815	111100	7.7378
0.8823	111200	7.6895
0.8831	111300	7.7247
0.8839	111400	7.7215
0.8847	111500	7.6748
0.8855	111600	7.708
0.8863	111700	7.7195
0.8871	111800	7.6679
0.8879	111900	7.7038
0.8887	112000	7.6776
0.8895	112100	7.7374
0.8903	112200	7.7286
0.8910	112300	7.712
0.8918	112400	7.6966
0.8926	112500	7.7214
0.8934	112600	7.7212
0.8942	112700	7.7122
0.8950	112800	7.7271
0.8958	112900	7.691
0.8966	113000	7.7237
0.8974	113100	7.6735
0.8982	113200	7.7033
0.8990	113300	7.7326
0.8998	113400	7.6882
0.9006	113500	7.7046
0.9014	113600	7.7118
0.9022	113700	7.7158
0.9029	113800	7.7286
0.9037	113900	7.6703
0.9045	114000	7.7134
0.9053	114100	7.7285
0.9061	114200	7.7386
0.9069	114300	7.7152
0.9077	114400	7.6893
0.9085	114500	7.7343
0.9093	114600	7.7187
0.9101	114700	7.7263
0.9109	114800	7.6965
0.9117	114900	7.7039
0.9125	115000	7.6704
0.9133	115100	7.6937
0.9141	115200	7.6965
0.9148	115300	7.7149
0.9156	115400	7.6896
0.9164	115500	7.7276
0.9172	115600	7.7305
0.9180	115700	7.6934
0.9188	115800	7.7237
0.9196	115900	7.6887
0.9204	116000	7.7331
0.9212	116100	7.6533
0.9220	116200	7.7115
0.9228	116300	7.7417
0.9236	116400	7.7217
0.9244	116500	7.7225
0.9252	116600	7.6883
0.9260	116700	7.7073
0.9267	116800	7.698
0.9275	116900	7.7024
0.9283	117000	7.6976
0.9291	117100	7.6934
0.9299	117200	7.6732
0.9307	117300	7.6981
0.9315	117400	7.7606
0.9323	117500	7.7274
0.9331	117600	7.7134
0.9339	117700	7.6873
0.9347	117800	7.7084
0.9355	117900	7.7014
0.9363	118000	7.7204
0.9371	118100	7.6777
0.9379	118200	7.6858
0.9387	118300	7.6906
0.9394	118400	7.6936
0.9402	118500	7.6827
0.9410	118600	7.6914
0.9418	118700	7.6868
0.9426	118800	7.6998
0.9434	118900	7.6739
0.9442	119000	7.7324
0.9450	119100	7.7352
0.9458	119200	7.6911
0.9466	119300	7.7013
0.9474	119400	7.7063
0.9482	119500	7.7036
0.9490	119600	7.7127
0.9498	119700	7.7237
0.9506	119800	7.6743
0.9513	119900	7.7109
0.9521	120000	7.7011
0.9529	120100	7.75
0.9537	120200	7.7269
0.9545	120300	7.7101
0.9553	120400	7.7317
0.9561	120500	7.7198
0.9569	120600	7.6811
0.9577	120700	7.7046
0.9585	120800	7.6942
0.9593	120900	7.7118
0.9601	121000	7.6967
0.9609	121100	7.7331
0.9617	121200	7.7024
0.9625	121300	7.6961
0.9632	121400	7.6887
0.9640	121500	7.7019
0.9648	121600	7.6886
0.9656	121700	7.7069
0.9664	121800	7.6981
0.9672	121900	7.6676
0.9680	122000	7.6765
0.9688	122100	7.6878
0.9696	122200	7.6992
0.9704	122300	7.6754
0.9712	122400	7.6856
0.9720	122500	7.7118
0.9728	122600	7.7434
0.9736	122700	7.6584
0.9744	122800	7.716
0.9751	122900	7.6941
0.9759	123000	7.7396
0.9767	123100	7.7097
0.9775	123200	7.6739
0.9783	123300	7.6959
0.9791	123400	7.704
0.9799	123500	7.6598
0.9807	123600	7.6704
0.9815	123700	7.7039
0.9823	123800	7.672
0.9831	123900	7.6978
0.9839	124000	7.6927
0.9847	124100	7.6665
0.9855	124200	7.7026
0.9863	124300	7.6866
0.9871	124400	7.6796
0.9878	124500	7.7315
0.9886	124600	7.7352
0.9894	124700	7.7342
0.9902	124800	7.7109
0.9910	124900	7.6762
0.9918	125000	7.6896
0.9926	125100	7.6893
0.9934	125200	7.6874
0.9942	125300	7.7031
0.9950	125400	7.7119
0.9958	125500	7.6758
0.9966	125600	7.7484
0.9974	125700	7.6668
0.9982	125800	7.672
0.9990	125900	7.7099
0.9997	126000	7.7058

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},
}