all-MiniLM-L6-v46-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v39 dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • pairs_with_scores_v39
• 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 = [
    'novomix flexpen',
    'roll roasted baby potato house salad roll cheddar roll served with roasted baby potato and house salad.',
    'metal stand 2.4 meters - 1 metal stand brand artshop generic name tree measurements 2.4 meters components stand purpose decoration features stability material metal color green occasion christmas',
]
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, -0.1810, -0.2092],
#         [-0.1810,  1.0000, -0.0018],
#         [-0.2092, -0.0018,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v39

• Dataset: pairs_with_scores_v39 at 7497594
• Size: 11,487,261 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: 4.89 tokens max: 16 tokens	min: 3 tokens mean: 59.57 tokens max: 256 tokens	min: 0.0 mean: 0.13 max: 1.0

• Samples:

  sentence1	sentence2	score
  oil therapy	pink beige crochet knitting gender women brand ebra generic name types of styles casual color pink beige	0.0
  instant repair	red christmas 6 pieces per box christmas brand art shop generic name components 6 pieces shape round purpose decoration color red occasion christmas electronics spec 6 pieces	0.0
  fabric	doughnut white chocolate restaurants desserts sweet doughnut white chocolate doughnut	0.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_with_scores_v39

• Dataset: pairs_with_scores_v39 at 7497594
• Size: 57,725 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: 4.86 tokens max: 15 tokens	min: 3 tokens mean: 60.27 tokens max: 251 tokens	min: 0.0 mean: 0.15 max: 1.0

• Samples:

  sentence1	sentence2	score
  beaded	korean bbq chicken restaurants asian meat and poultry chicken bbq chicken korean chicken	0.0
  handcrafted	cover - 1 cover dust protection cover with storage pouch cover for 1 heavy duty cover outdoor cover waterproof cover for 1 heavy duty cover outdoor cover waterproof cover this cover ensures your stays protected against bad weather dust and unwanted attention. sold with a storage pouch. this cover ensures your stays protected against bad weather dust and unwanted attention. sold with a storage pouch.not suitable for transport on a carrier.	0.0
  entremet	nabulseya soft shallal cheese kunafa honey syrup kunafa cheese kunafa nabulseya soft kunafa - ghee - shallal cheese - honey syrup.	1.0

• Loss: CoSENTLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0011	100	7.781
0.0022	200	7.6977
0.0033	300	7.8146
0.0045	400	7.4676
0.0056	500	7.4344
0.0067	600	7.3267
0.0078	700	7.1855
0.0089	800	7.1101
0.0100	900	7.0273
0.0111	1000	7.0256
0.0123	1100	6.8403
0.0134	1200	6.83
0.0145	1300	6.7047
0.0156	1400	6.7801
0.0167	1500	6.8393
0.0178	1600	6.7527
0.0189	1700	6.5327
0.0201	1800	6.3824
0.0212	1900	6.5516
0.0223	2000	6.3956
0.0234	2100	6.4506
0.0245	2200	6.3552
0.0256	2300	6.2621
0.0267	2400	6.2312
0.0279	2500	6.1267
0.0290	2600	5.9464
0.0301	2700	6.0353
0.0312	2800	5.925
0.0323	2900	5.9721
0.0334	3000	5.9019
0.0345	3100	5.9031
0.0357	3200	5.7872
0.0368	3300	5.8287
0.0379	3400	5.7435
0.0390	3500	5.6909
0.0401	3600	5.6887
0.0412	3700	5.7179
0.0423	3800	5.5674
0.0435	3900	5.4861
0.0446	4000	5.5088
0.0457	4100	5.6294
0.0468	4200	5.5495
0.0479	4300	5.3843
0.0490	4400	5.6037
0.0501	4500	5.5812
0.0513	4600	5.3833
0.0524	4700	5.4256
0.0535	4800	5.4692
0.0546	4900	5.3605
0.0557	5000	5.4164
0.0568	5100	5.3128
0.0579	5200	5.3191
0.0591	5300	5.2231
0.0602	5400	5.4908
0.0613	5500	5.2385
0.0624	5600	5.1819
0.0635	5700	5.1822
0.0646	5800	5.1557
0.0657	5900	5.2426
0.0669	6000	5.2496
0.0680	6100	5.1473
0.0691	6200	5.0006
0.0702	6300	5.1531
0.0713	6400	5.0564
0.0724	6500	5.1469
0.0735	6600	5.1241
0.0747	6700	4.889
0.0758	6800	5.1057
0.0769	6900	4.9187
0.0780	7000	5.0095
0.0791	7100	4.7445
0.0802	7200	5.0233
0.0813	7300	4.9246
0.0825	7400	4.8501
0.0836	7500	4.9916
0.0847	7600	4.9908
0.0858	7700	4.8067
0.0869	7800	4.9323
0.0880	7900	4.9526
0.0891	8000	4.771
0.0903	8100	4.8832
0.0914	8200	4.6787
0.0925	8300	4.8584
0.0936	8400	4.7421
0.0947	8500	4.7825
0.0958	8600	4.7741
0.0969	8700	4.756
0.0981	8800	4.8269
0.0992	8900	4.7103
0.1003	9000	4.8136
0.1014	9100	4.6953
0.1025	9200	4.6109
0.1036	9300	4.7606
0.1047	9400	4.611
0.1059	9500	4.5573
0.1070	9600	4.6853
0.1081	9700	4.557
0.1092	9800	4.6714
0.1103	9900	4.5931
0.1114	10000	4.7099
0.1125	10100	4.6946
0.1137	10200	4.5909
0.1148	10300	4.5929
0.1159	10400	4.6968
0.1170	10500	4.4228
0.1181	10600	4.4819
0.1192	10700	4.6047
0.1203	10800	4.5854
0.1215	10900	4.3537
0.1226	11000	4.3952
0.1237	11100	4.5584
0.1248	11200	4.4845
0.1259	11300	4.4464
0.1270	11400	4.4853
0.1281	11500	4.4629
0.1293	11600	4.4021
0.1304	11700	4.5114
0.1315	11800	4.2865
0.1326	11900	4.3262
0.1337	12000	4.4959
0.1348	12100	4.2781
0.1359	12200	4.4563
0.1371	12300	4.271
0.1382	12400	4.4458
0.1393	12500	4.3367
0.1404	12600	4.2028
0.1415	12700	4.1754
0.1426	12800	4.5272
0.1437	12900	4.1957
0.1449	13000	4.3109
0.1460	13100	4.2773
0.1471	13200	4.2371
0.1482	13300	4.1962
0.1493	13400	4.1562
0.1504	13500	4.4308
0.1515	13600	4.3178
0.1527	13700	4.2735
0.1538	13800	4.2122
0.1549	13900	4.139
0.1560	14000	4.4304
0.1571	14100	4.2245
0.1582	14200	4.231
0.1593	14300	4.298
0.1605	14400	4.189
0.1616	14500	4.1365
0.1627	14600	4.013
0.1638	14700	4.1823
0.1649	14800	3.9866
0.1660	14900	3.9731
0.1671	15000	3.899
0.1683	15100	4.4284
0.1694	15200	4.1157
0.1705	15300	4.1108
0.1716	15400	4.049
0.1727	15500	4.197
0.1738	15600	3.9035
0.1749	15700	4.206
0.1761	15800	4.1319
0.1772	15900	4.2188
0.1783	16000	4.0189
0.1794	16100	4.0194
0.1805	16200	3.9852
0.1816	16300	4.08
0.1827	16400	4.0028
0.1839	16500	3.9497
0.1850	16600	3.9631
0.1861	16700	3.8714
0.1872	16800	3.9307
0.1883	16900	4.0415
0.1894	17000	4.2202
0.1905	17100	3.9339
0.1917	17200	4.1461
0.1928	17300	4.0017
0.1939	17400	4.2757
0.1950	17500	3.9857
0.1961	17600	3.9057
0.1972	17700	3.8719
0.1983	17800	4.0742
0.1995	17900	4.1678
0.2006	18000	3.9832
0.2017	18100	4.1081
0.2028	18200	3.7065
0.2039	18300	3.8002
0.2050	18400	3.848
0.2061	18500	3.9369
0.2073	18600	3.9646
0.2084	18700	4.1001
0.2095	18800	3.9613
0.2106	18900	3.6784
0.2117	19000	3.892
0.2128	19100	3.7462
0.2139	19200	3.9293
0.2151	19300	4.1326
0.2162	19400	3.7621
0.2173	19500	3.5261
0.2184	19600	3.8535
0.2195	19700	3.9802
0.2206	19800	3.8718
0.2217	19900	3.7482
0.2229	20000	3.7934
0.2240	20100	3.5943
0.2251	20200	4.1763
0.2262	20300	3.5294
0.2273	20400	3.6091
0.2284	20500	4.0409
0.2295	20600	3.5869
0.2307	20700	3.5304
0.2318	20800	3.7357
0.2329	20900	4.0062
0.2340	21000	3.6469
0.2351	21100	3.5325
0.2362	21200	3.9055
0.2373	21300	3.6513
0.2385	21400	3.8208
0.2396	21500	3.9353
0.2407	21600	3.5271
0.2418	21700	3.563
0.2429	21800	3.681
0.2440	21900	3.8594
0.2451	22000	3.9684
0.2463	22100	3.7434
0.2474	22200	3.6236
0.2485	22300	3.6629
0.2496	22400	3.6444
0.2507	22500	3.5604
0.2518	22600	3.7704
0.2529	22700	3.7022
0.2541	22800	3.8572
0.2552	22900	3.7028
0.2563	23000	3.6059
0.2574	23100	3.9444
0.2585	23200	3.8939
0.2596	23300	3.5191
0.2607	23400	3.7512
0.2619	23500	3.4612
0.2630	23600	3.8199
0.2641	23700	3.5164
0.2652	23800	3.7952
0.2663	23900	3.6319
0.2674	24000	3.5752
0.2685	24100	3.6386
0.2697	24200	3.6126
0.2708	24300	3.4635
0.2719	24400	3.9634
0.2730	24500	3.62
0.2741	24600	3.5796
0.2752	24700	3.4796
0.2763	24800	3.6596
0.2775	24900	3.4343
0.2786	25000	3.7906
0.2797	25100	3.584
0.2808	25200	3.6996
0.2819	25300	3.3773
0.2830	25400	3.6989
0.2841	25500	3.6713
0.2853	25600	3.6557
0.2864	25700	3.6278
0.2875	25800	3.3894
0.2886	25900	3.4738
0.2897	26000	3.4902
0.2908	26100	3.5088
0.2919	26200	3.3813
0.2931	26300	3.3372
0.2942	26400	3.735
0.2953	26500	3.4846
0.2964	26600	3.7902
0.2975	26700	3.5292
0.2986	26800	3.7249
0.2997	26900	3.4924
0.3009	27000	3.4777
0.3020	27100	3.3972
0.3031	27200	3.6039
0.3042	27300	3.5797
0.3053	27400	3.3834
0.3064	27500	3.5819
0.3075	27600	3.4984
0.3087	27700	3.6684
0.3098	27800	3.3041
0.3109	27900	3.5252
0.3120	28000	3.4671
0.3131	28100	3.7028
0.3142	28200	3.2945
0.3153	28300	3.3255
0.3165	28400	3.3833
0.3176	28500	3.4168
0.3187	28600	3.6709
0.3198	28700	3.4312
0.3209	28800	3.7334
0.3220	28900	3.5456
0.3231	29000	3.5013
0.3243	29100	3.2595
0.3254	29200	3.2261
0.3265	29300	3.7388
0.3276	29400	3.3458
0.3287	29500	3.6001
0.3298	29600	3.3244
0.3309	29700	3.3093
0.3321	29800	3.4269
0.3332	29900	3.575
0.3343	30000	3.5406
0.3354	30100	3.426
0.3365	30200	3.6019
0.3376	30300	3.4974
0.3387	30400	3.2452
0.3399	30500	3.2673
0.3410	30600	3.6226
0.3421	30700	3.6291
0.3432	30800	3.089
0.3443	30900	3.4612
0.3454	31000	3.1337
0.3465	31100	3.0619
0.3477	31200	3.2744
0.3488	31300	3.4046
0.3499	31400	3.3423
0.3510	31500	3.8694
0.3521	31600	3.4827
0.3532	31700	3.1727
0.3543	31800	3.093
0.3555	31900	3.4245
0.3566	32000	3.3751
0.3577	32100	3.3841
0.3588	32200	3.1227
0.3599	32300	3.5656
0.3610	32400	3.1675
0.3621	32500	3.4382
0.3633	32600	3.1922
0.3644	32700	3.5881
0.3655	32800	3.1469
0.3666	32900	3.2861
0.3677	33000	3.5547
0.3688	33100	3.2019
0.3699	33200	3.3915
0.3711	33300	3.2242
0.3722	33400	2.8817
0.3733	33500	2.9474
0.3744	33600	3.3955
0.3755	33700	3.4472
0.3766	33800	3.4152
0.3777	33900	3.2953
0.3789	34000	3.5369
0.3800	34100	3.2048
0.3811	34200	3.4401
0.3822	34300	3.4823
0.3833	34400	3.1931
0.3844	34500	3.2406
0.3855	34600	3.4288
0.3867	34700	3.1184
0.3878	34800	3.2587
0.3889	34900	3.4785
0.3900	35000	3.1433
0.3911	35100	3.3927
0.3922	35200	2.9461
0.3933	35300	3.4004
0.3945	35400	3.348
0.3956	35500	3.2556
0.3967	35600	3.3638
0.3978	35700	3.1183
0.3989	35800	2.9134
0.4000	35900	3.188
0.4011	36000	3.349
0.4023	36100	3.1895
0.4034	36200	3.1663
0.4045	36300	3.06
0.4056	36400	3.344
0.4067	36500	3.3145
0.4078	36600	3.2479
0.4089	36700	3.0955
0.4101	36800	3.0943
0.4112	36900	3.331
0.4123	37000	3.0724
0.4134	37100	3.1087
0.4145	37200	3.2367
0.4156	37300	3.061
0.4167	37400	3.2694
0.4179	37500	2.9672
0.4190	37600	2.9936
0.4201	37700	3.2728
0.4212	37800	3.1532
0.4223	37900	2.8813
0.4234	38000	3.1064
0.4245	38100	3.2095
0.4257	38200	3.3292
0.4268	38300	2.7734
0.4279	38400	3.2193
0.4290	38500	3.3198
0.4301	38600	3.108
0.4312	38700	3.2684
0.4323	38800	3.4744
0.4335	38900	3.321
0.4346	39000	3.0532
0.4357	39100	3.3345
0.4368	39200	3.3756
0.4379	39300	2.9148
0.4390	39400	3.0617
0.4401	39500	3.1388
0.4413	39600	3.0605
0.4424	39700	3.0019
0.4435	39800	2.9789
0.4446	39900	3.1358
0.4457	40000	3.2883
0.4468	40100	2.9311
0.4479	40200	3.0822
0.4491	40300	2.9454
0.4502	40400	2.9287
0.4513	40500	2.7007
0.4524	40600	3.3075
0.4535	40700	2.9108
0.4546	40800	3.3308
0.4557	40900	3.0218
0.4568	41000	2.7262
0.4580	41100	2.8638
0.4591	41200	2.861
0.4602	41300	3.1541
0.4613	41400	3.1804
0.4624	41500	3.0013
0.4635	41600	3.0353
0.4646	41700	2.8252
0.4658	41800	3.2673
0.4669	41900	3.163
0.4680	42000	2.8744
0.4691	42100	2.8989
0.4702	42200	3.02
0.4713	42300	3.3095
0.4724	42400	3.3481
0.4736	42500	2.992
0.4747	42600	3.057
0.4758	42700	2.9483
0.4769	42800	2.9682
0.4780	42900	2.8527
0.4791	43000	3.0596
0.4802	43100	2.9866
0.4814	43200	3.0778
0.4825	43300	3.0389
0.4836	43400	2.6923
0.4847	43500	2.6553
0.4858	43600	3.1671
0.4869	43700	3.0429
0.4880	43800	2.7542
0.4892	43900	3.0521
0.4903	44000	3.0838
0.4914	44100	2.8597
0.4925	44200	3.352
0.4936	44300	2.7871
0.4947	44400	2.8919
0.4958	44500	2.7729
0.4970	44600	3.0161
0.4981	44700	3.1166
0.4992	44800	3.1102
0.5003	44900	3.1297
0.5014	45000	2.8511
0.5025	45100	2.9846
0.5036	45200	3.0894
0.5048	45300	3.0553
0.5059	45400	3.3906
0.5070	45500	3.217
0.5081	45600	2.9356
0.5092	45700	2.6007
0.5103	45800	3.0349
0.5114	45900	2.7931
0.5126	46000	2.7037
0.5137	46100	2.9981
0.5148	46200	2.9933
0.5159	46300	2.9637
0.5170	46400	3.2177
0.5181	46500	3.0208
0.5192	46600	2.7417
0.5204	46700	2.8955
0.5215	46800	3.3061
0.5226	46900	3.0689
0.5237	47000	3.2537
0.5248	47100	2.7195
0.5259	47200	2.9922
0.5270	47300	2.7818
0.5282	47400	2.6848
0.5293	47500	2.7592
0.5304	47600	2.846
0.5315	47700	3.0123
0.5326	47800	2.812
0.5337	47900	2.9033
0.5348	48000	3.2094
0.5360	48100	2.7067
0.5371	48200	3.0005
0.5382	48300	2.9653
0.5393	48400	2.8663
0.5404	48500	3.0767
0.5415	48600	2.9052
0.5426	48700	3.222
0.5438	48800	2.9333
0.5449	48900	2.8302
0.5460	49000	3.1831
0.5471	49100	2.6548
0.5482	49200	3.0421
0.5493	49300	2.7913
0.5504	49400	2.7212
0.5516	49500	2.8636
0.5527	49600	2.7652
0.5538	49700	2.7511
0.5549	49800	3.121
0.5560	49900	2.7596
0.5571	50000	2.9957
0.5582	50100	2.8845
0.5594	50200	3.0774
0.5605	50300	2.6694
0.5616	50400	2.955
0.5627	50500	2.7277
0.5638	50600	2.8498
0.5649	50700	2.9883
0.5660	50800	2.6582
0.5672	50900	3.0527
0.5683	51000	3.0214
0.5694	51100	2.8653
0.5705	51200	2.8046
0.5716	51300	2.8311
0.5727	51400	2.763
0.5738	51500	2.7166
0.5750	51600	3.2317
0.5761	51700	2.6479
0.5772	51800	3.0303
0.5783	51900	2.6713
0.5794	52000	2.6773
0.5805	52100	2.9558
0.5816	52200	2.7725
0.5828	52300	2.8697
0.5839	52400	2.8884
0.5850	52500	2.9832
0.5861	52600	2.8777
0.5872	52700	2.9665
0.5883	52800	2.8847
0.5894	52900	2.8856
0.5906	53000	2.6081
0.5917	53100	3.0658
0.5928	53200	2.4448
0.5939	53300	2.8358
0.5950	53400	2.6821
0.5961	53500	2.8038
0.5972	53600	2.605
0.5984	53700	2.6228
0.5995	53800	2.678
0.6006	53900	2.979
0.6017	54000	2.7621
0.6028	54100	2.9125
0.6039	54200	2.5993
0.6050	54300	2.9332
0.6062	54400	2.9868
0.6073	54500	2.8581
0.6084	54600	3.0002
0.6095	54700	2.7088
0.6106	54800	2.8871
0.6117	54900	2.9107
0.6128	55000	2.9346
0.6140	55100	3.1101
0.6151	55200	2.6433
0.6162	55300	2.7572
0.6173	55400	2.4793
0.6184	55500	2.7714
0.6195	55600	2.6838
0.6206	55700	3.0335
0.6218	55800	2.7824
0.6229	55900	2.7294
0.6240	56000	2.5556
0.6251	56100	2.7591
0.6262	56200	2.7347
0.6273	56300	2.6867
0.6284	56400	2.6531
0.6296	56500	2.385
0.6307	56600	2.8569
0.6318	56700	2.4496
0.6329	56800	2.8848
0.6340	56900	3.073
0.6351	57000	2.9489
0.6362	57100	2.7335
0.6374	57200	2.8648
0.6385	57300	2.6287
0.6396	57400	3.0466
0.6407	57500	2.9157
0.6418	57600	2.4994
0.6429	57700	3.0576
0.6440	57800	2.629
0.6452	57900	2.6633
0.6463	58000	2.6127
0.6474	58100	2.7356
0.6485	58200	2.9599
0.6496	58300	2.7278
0.6507	58400	2.8117
0.6518	58500	2.6333
0.6530	58600	2.5245
0.6541	58700	2.6356
0.6552	58800	2.541
0.6563	58900	2.7453
0.6574	59000	2.7478
0.6585	59100	2.8445
0.6596	59200	2.3727
0.6608	59300	2.7217
0.6619	59400	2.5786
0.6630	59500	2.7439
0.6641	59600	2.4819
0.6652	59700	2.7137
0.6663	59800	2.7881
0.6674	59900	2.537
0.6686	60000	2.9142
0.6697	60100	2.4558
0.6708	60200	2.7024
0.6719	60300	2.9162
0.6730	60400	2.6689
0.6741	60500	2.3225
0.6752	60600	2.53
0.6764	60700	2.5516
0.6775	60800	2.7432
0.6786	60900	2.5637
0.6797	61000	2.5396
0.6808	61100	2.8075
0.6819	61200	2.4293
0.6830	61300	2.7045
0.6842	61400	2.6755
0.6853	61500	2.5829
0.6864	61600	2.6338
0.6875	61700	2.5192
0.6886	61800	2.6971
0.6897	61900	2.5544
0.6908	62000	2.6042
0.6920	62100	2.5646
0.6931	62200	2.9341
0.6942	62300	2.6771
0.6953	62400	2.6982
0.6964	62500	2.5825
0.6975	62600	2.5255
0.6986	62700	2.9016
0.6998	62800	2.645
0.7009	62900	2.8009
0.7020	63000	2.4597
0.7031	63100	2.779
0.7042	63200	2.669
0.7053	63300	2.4737
0.7064	63400	2.5867
0.7076	63500	2.4753
0.7087	63600	2.6584
0.7098	63700	2.857
0.7109	63800	2.6794
0.7120	63900	3.0755
0.7131	64000	2.6695
0.7142	64100	2.3964
0.7154	64200	2.64
0.7165	64300	2.788
0.7176	64400	2.711
0.7187	64500	2.4543
0.7198	64600	2.7556
0.7209	64700	2.6188
0.7220	64800	2.5484
0.7232	64900	2.6427
0.7243	65000	2.7341
0.7254	65100	2.8827
0.7265	65200	2.5771
0.7276	65300	2.53
0.7287	65400	2.4843
0.7298	65500	2.8183
0.7310	65600	2.7308
0.7321	65700	2.6206
0.7332	65800	2.8627
0.7343	65900	2.4606
0.7354	66000	2.5487
0.7365	66100	2.9358
0.7376	66200	2.4098
0.7388	66300	2.5057
0.7399	66400	2.7309
0.7410	66500	2.4718
0.7421	66600	2.6132
0.7432	66700	2.3843
0.7443	66800	2.44
0.7454	66900	2.6312
0.7466	67000	2.5121
0.7477	67100	2.1577
0.7488	67200	2.6088
0.7499	67300	2.6139
0.7510	67400	2.723
0.7521	67500	2.7125
0.7532	67600	2.6453
0.7544	67700	2.5741
0.7555	67800	2.1855
0.7566	67900	2.6724
0.7577	68000	2.4742
0.7588	68100	2.9868
0.7599	68200	2.5431
0.7610	68300	2.7198
0.7622	68400	2.815
0.7633	68500	2.7539
0.7644	68600	2.5769
0.7655	68700	2.6334
0.7666	68800	2.7169
0.7677	68900	2.5289
0.7688	69000	2.5482
0.7700	69100	2.5316
0.7711	69200	2.5067
0.7722	69300	2.7919
0.7733	69400	2.4646
0.7744	69500	2.4914
0.7755	69600	2.5082
0.7766	69700	2.5477
0.7778	69800	2.3765
0.7789	69900	2.7202
0.7800	70000	2.5833
0.7811	70100	2.4363
0.7822	70200	2.9144
0.7833	70300	2.6464
0.7844	70400	2.4045
0.7856	70500	2.2249
0.7867	70600	2.7861
0.7878	70700	2.5609
0.7889	70800	2.6787
0.7900	70900	2.6362
0.7911	71000	2.3908
0.7922	71100	2.5075
0.7934	71200	2.2672
0.7945	71300	2.6078
0.7956	71400	2.6091
0.7967	71500	2.4387
0.7978	71600	2.7142
0.7989	71700	2.6693
0.8000	71800	2.2282
0.8012	71900	2.7182
0.8023	72000	2.4427
0.8034	72100	2.7168
0.8045	72200	2.3587
0.8056	72300	2.3488
0.8067	72400	2.5575
0.8078	72500	2.6438
0.8090	72600	2.6303
0.8101	72700	2.2755
0.8112	72800	2.9162
0.8123	72900	2.8419
0.8134	73000	2.8453
0.8145	73100	2.8078
0.8156	73200	2.6746
0.8168	73300	2.3452
0.8179	73400	2.5047
0.8190	73500	2.4881
0.8201	73600	2.4959
0.8212	73700	2.5962
0.8223	73800	2.3182
0.8234	73900	2.692
0.8246	74000	2.6732
0.8257	74100	2.5427
0.8268	74200	2.8532
0.8279	74300	2.5634
0.8290	74400	2.6332
0.8301	74500	2.6033
0.8312	74600	2.4092
0.8324	74700	2.5701
0.8335	74800	2.3081
0.8346	74900	2.5152
0.8357	75000	2.535
0.8368	75100	2.4122
0.8379	75200	2.5668
0.8390	75300	2.7135
0.8402	75400	2.5792
0.8413	75500	2.5207
0.8424	75600	2.9513
0.8435	75700	2.5084
0.8446	75800	2.5127
0.8457	75900	2.3821
0.8468	76000	2.4856
0.8480	76100	2.6037
0.8491	76200	2.3668
0.8502	76300	2.3263
0.8513	76400	2.6755
0.8524	76500	2.5847
0.8535	76600	2.1144
0.8546	76700	2.3284
0.8558	76800	2.1945
0.8569	76900	2.347
0.8580	77000	2.6759
0.8591	77100	2.4855
0.8602	77200	2.3587
0.8613	77300	2.3677
0.8624	77400	2.5622
0.8636	77500	2.1484
0.8647	77600	2.4992
0.8658	77700	2.2722
0.8669	77800	2.4102
0.8680	77900	2.3872
0.8691	78000	2.6522
0.8702	78100	2.5756
0.8714	78200	2.3486
0.8725	78300	2.4247
0.8736	78400	2.8043
0.8747	78500	2.1276
0.8758	78600	2.6145
0.8769	78700	2.1282
0.8780	78800	2.5882
0.8792	78900	2.6405
0.8803	79000	2.2386
0.8814	79100	2.6346
0.8825	79200	2.5904
0.8836	79300	2.4596
0.8847	79400	2.1917
0.8858	79500	2.3351
0.8870	79600	2.1016
0.8881	79700	2.46
0.8892	79800	2.3291
0.8903	79900	2.7271
0.8914	80000	2.612
0.8925	80100	2.1448
0.8936	80200	2.6311
0.8948	80300	2.5768
0.8959	80400	2.5495
0.8970	80500	2.5793
0.8981	80600	2.5327
0.8992	80700	2.3167
0.9003	80800	2.2797
0.9014	80900	2.3442
0.9026	81000	2.3866
0.9037	81100	2.3717
0.9048	81200	2.236
0.9059	81300	2.2512
0.9070	81400	2.554
0.9081	81500	2.4142
0.9092	81600	2.2029
0.9104	81700	2.7294
0.9115	81800	2.331
0.9126	81900	2.5096
0.9137	82000	2.1889
0.9148	82100	2.7556
0.9159	82200	2.7346
0.9170	82300	2.3659
0.9182	82400	2.3576
0.9193	82500	2.4588
0.9204	82600	2.4287
0.9215	82700	2.3407
0.9226	82800	2.2271
0.9237	82900	2.3587
0.9248	83000	2.6926
0.9260	83100	2.606
0.9271	83200	2.6432
0.9282	83300	2.5754
0.9293	83400	2.2363
0.9304	83500	2.5354
0.9315	83600	2.2057
0.9326	83700	2.1881
0.9338	83800	2.3975
0.9349	83900	2.6035
0.9360	84000	2.4348
0.9371	84100	2.4094
0.9382	84200	2.4179
0.9393	84300	2.0758
0.9404	84400	2.3564
0.9416	84500	2.5612
0.9427	84600	2.4769
0.9438	84700	2.2501
0.9449	84800	2.4321
0.9460	84900	2.6939
0.9471	85000	2.7534
0.9482	85100	2.4501
0.9494	85200	2.6138
0.9505	85300	2.2162
0.9516	85400	2.4273
0.9527	85500	2.5488
0.9538	85600	2.8395
0.9549	85700	2.405
0.9560	85800	2.3363
0.9572	85900	2.6963
0.9583	86000	2.805
0.9594	86100	2.4963
0.9605	86200	2.1018
0.9616	86300	2.3119
0.9627	86400	2.739
0.9638	86500	2.5531
0.9650	86600	2.6202
0.9661	86700	2.2476
0.9672	86800	2.4419
0.9683	86900	2.6504
0.9694	87000	2.0924
0.9705	87100	2.3009
0.9716	87200	2.5534
0.9728	87300	2.4352
0.9739	87400	2.3606
0.9750	87500	2.317
0.9761	87600	2.4355
0.9772	87700	2.2195
0.9783	87800	2.1766
0.9794	87900	2.7233
0.9806	88000	2.1094
0.9817	88100	2.4423
0.9828	88200	2.5551
0.9839	88300	2.5164
0.9850	88400	2.3041
0.9861	88500	2.3134
0.9872	88600	2.6084
0.9884	88700	2.3939
0.9895	88800	2.341
0.9906	88900	2.3269
0.9917	89000	2.0977
0.9928	89100	2.2958
0.9939	89200	2.3969
0.9950	89300	2.6141
0.9962	89400	2.3172
0.9973	89500	2.5162
0.9984	89600	2.4896
0.9995	89700	2.7332

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.21.4

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}