all-MiniLM-L6-v45-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v38 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_v38
• 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 = [
    'outdoor sports smart watch',
    'wigglers category tags wigglers organic compost fertilizers wigglers keywords wigglers attrs brand growpro generic name wigglers weight 250 gr color description revolutionize your egyptian garden with the power of wigglers these mighty earthworms are nature s ultimate soil warriors tirelessly working to aerate fertilize and enrich your soil. specially selected for egypt s climate our wigglers are the perfect companions for organic gardening enthusiasts. whether you re a seasoned gardener or just starting out these hardworking worms will enhance soil fertility promote healthier plants and increase yields. elevate your gardening experience and harness the incredible benefits of wigglers for a greener more vibrant garden in egypt. get your wigglers today and watch your garden thrive',
    'turkish category tags turkish turkish turkish turkish turkish keywords turkish turkish turkish turkish turkish',
]
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, -0.1168, -0.1112],
#         [-0.1168,  1.0000,  0.1334],
#         [-0.1112,  0.1334,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v38

• Dataset: pairs_with_scores_v38 at 5e4a543
• Size: 10,827,162 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: 4.84 tokens max: 18 tokens	min: 6 tokens mean: 56.82 tokens max: 256 tokens	min: 0.0 mean: 0.05 max: 1.0

• Samples:

  sentence1	sentence2	score
  creamy sauce chicken	2 solution category hair loss hair loss tags hair regrowth spray spray keywords hair regrowth spray spray	0.0
  calamyl moisturizing crem	round gold chain category tags metal chain round keywords chain round attrs gender women brand trio generic name features round chain types of styles casual material metal color gold	0.0
  shank	coconut scent category tags customizable personalized coconut scent peony keywords coconut scent peony description 8.5 diameter color and scent customized upon request.	0.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_with_scores_v38

• Dataset: pairs_with_scores_v38 at 5e4a543
• Size: 54,408 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: 4.92 tokens max: 19 tokens	min: 6 tokens mean: 58.2 tokens max: 235 tokens	min: 0.0 mean: 0.04 max: 1.0

• Samples:

  sentence1	sentence2	score
  multicolor	leather in black category tags keywords attrs gender women brand stache generic name size s material leather color black	0.0
  alkapress	valley - 26 cm category tags valley keywords valley description valley s unique use of geometric patterns pays homage to tunisia s rich heritage. tu-va 6100126	0.0
  phone accessory	savannah category tags savannah keywords savannah attrs gender women brand minimal generic name product name savannah size one size types of styles casual bohemian everyday wear neckline v-neck sleeve style short sleeve fit loose fit season spring summer	0.0

• 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
0.0012	100	3.0011
0.0024	200	3.1188
0.0035	300	2.702
0.0047	400	2.1866
0.0059	500	1.8666
0.0071	600	2.0708
0.0083	700	1.912
0.0095	800	1.8157
0.0106	900	1.456
0.0118	1000	1.1928
0.0130	1100	1.5215
0.0142	1200	1.4088
0.0154	1300	1.2589
0.0166	1400	1.2721
0.0177	1500	1.2735
0.0189	1600	1.2677
0.0201	1700	1.0044
0.0213	1800	1.1296
0.0225	1900	1.0031
0.0236	2000	0.8479
0.0248	2100	0.9297
0.0260	2200	0.9659
0.0272	2300	0.8802
0.0284	2400	0.7423
0.0296	2500	0.7238
0.0307	2600	0.7042
0.0319	2700	0.8845
0.0331	2800	0.7968
0.0343	2900	0.7393
0.0355	3000	0.6384
0.0366	3100	0.9247
0.0378	3200	0.6522
0.0390	3300	0.6111
0.0402	3400	0.7083
0.0414	3500	0.6053
0.0426	3600	0.7644
0.0437	3700	0.6411
0.0449	3800	0.5584
0.0461	3900	0.5369
0.0473	4000	0.6116
0.0485	4100	0.463
0.0497	4200	0.5766
0.0508	4300	0.547
0.0520	4400	0.5447
0.0532	4500	0.5169
0.0544	4600	0.4696
0.0556	4700	0.6726
0.0567	4800	0.554
0.0579	4900	0.5802
0.0591	5000	0.6521
0.0603	5100	0.54
0.0615	5200	0.6098
0.0627	5300	0.5981
0.0638	5400	0.7111
0.0650	5500	0.5905
0.0662	5600	0.5065
0.0674	5700	0.6835
0.0686	5800	0.7086
0.0697	5900	0.5259
0.0709	6000	0.6127
0.0721	6100	0.507
0.0733	6200	0.6596
0.0745	6300	0.4578
0.0757	6400	0.5081
0.0768	6500	0.5813
0.0780	6600	0.5689
0.0792	6700	0.5149
0.0804	6800	0.8857
0.0816	6900	0.6218
0.0828	7000	0.3192
0.0839	7100	0.5446
0.0851	7200	0.4598
0.0863	7300	0.5047
0.0875	7400	0.3884
0.0887	7500	0.447
0.0898	7600	0.4975
0.0910	7700	0.4983
0.0922	7800	0.6884
0.0934	7900	0.7074
0.0946	8000	0.6115
0.0958	8100	0.4229
0.0969	8200	0.5483
0.0981	8300	0.4274
0.0993	8400	0.2982
0.1005	8500	0.4978
0.1017	8600	0.4267
0.1029	8700	0.5728
0.1040	8800	0.524
0.1052	8900	0.4712
0.1064	9000	0.523
0.1076	9100	0.4475
0.1088	9200	0.46
0.1099	9300	0.5011
0.1111	9400	0.4889
0.1123	9500	0.3932
0.1135	9600	0.5747
0.1147	9700	0.3885
0.1159	9800	0.5188
0.1170	9900	0.4613
0.1182	10000	0.417
0.1194	10100	0.5523
0.1206	10200	0.4751
0.1218	10300	0.4184
0.1229	10400	0.4386
0.1241	10500	0.4688
0.1253	10600	0.4059
0.1265	10700	0.5529
0.1277	10800	0.6302
0.1289	10900	0.566
0.1300	11000	0.4066
0.1312	11100	0.3974
0.1324	11200	0.4391
0.1336	11300	0.2897
0.1348	11400	0.5067
0.1360	11500	0.5282
0.1371	11600	0.4356
0.1383	11700	0.396
0.1395	11800	0.4778
0.1407	11900	0.1936
0.1419	12000	0.3093
0.1430	12100	0.5292
0.1442	12200	0.3002
0.1454	12300	0.5085
0.1466	12400	0.4501
0.1478	12500	0.2488
0.1490	12600	0.3276
0.1501	12700	0.4537
0.1513	12800	0.5538
0.1525	12900	0.3487
0.1537	13000	0.3601
0.1549	13100	0.2983
0.1561	13200	0.4569
0.1572	13300	0.2914
0.1584	13400	0.5063
0.1596	13500	0.4396
0.1608	13600	0.3497
0.1620	13700	0.4536
0.1631	13800	0.5392
0.1643	13900	0.3739
0.1655	14000	0.3998
0.1667	14100	0.4318
0.1679	14200	0.3659
0.1691	14300	0.4774
0.1702	14400	0.3459
0.1714	14500	0.3431
0.1726	14600	0.4075
0.1738	14700	0.4312
0.1750	14800	0.4297
0.1761	14900	0.4807
0.1773	15000	0.3426
0.1785	15100	0.3523
0.1797	15200	0.472
0.1809	15300	0.434
0.1821	15400	0.528
0.1832	15500	0.4272
0.1844	15600	0.4504
0.1856	15700	0.4886
0.1868	15800	0.3516
0.1880	15900	0.3879
0.1892	16000	0.2654
0.1903	16100	0.3661
0.1915	16200	0.3489
0.1927	16300	0.3325
0.1939	16400	0.3594
0.1951	16500	0.3784
0.1962	16600	0.5795
0.1974	16700	0.2197
0.1986	16800	0.3513
0.1998	16900	0.4946
0.2010	17000	0.2278
0.2022	17100	0.3707
0.2033	17200	0.5117
0.2045	17300	0.5504
0.2057	17400	0.4665
0.2069	17500	0.4916
0.2081	17600	0.4502
0.2092	17700	0.4014
0.2104	17800	0.2362
0.2116	17900	0.3995
0.2128	18000	0.372
0.2140	18100	0.3913
0.2152	18200	0.2522
0.2163	18300	0.2747
0.2175	18400	0.3137
0.2187	18500	0.2479
0.2199	18600	0.3771
0.2211	18700	0.2902
0.2223	18800	0.2752
0.2234	18900	0.3635
0.2246	19000	0.4402
0.2258	19100	0.3342
0.2270	19200	0.3303
0.2282	19300	0.3801
0.2293	19400	0.4835
0.2305	19500	0.4257
0.2317	19600	0.2798
0.2329	19700	0.321
0.2341	19800	0.2779
0.2353	19900	0.3611
0.2364	20000	0.3353
0.2376	20100	0.2631
0.2388	20200	0.2941
0.2400	20300	0.2123
0.2412	20400	0.2888
0.2424	20500	0.2814
0.2435	20600	0.4901
0.2447	20700	0.2923
0.2459	20800	0.3386
0.2471	20900	0.2815
0.2483	21000	0.3529
0.2494	21100	0.2674
0.2506	21200	0.3017
0.2518	21300	0.2603
0.2530	21400	0.2724
0.2542	21500	0.2933
0.2554	21600	0.3194
0.2565	21700	0.3594
0.2577	21800	0.2353
0.2589	21900	0.1686
0.2601	22000	0.5729
0.2613	22100	0.2403
0.2624	22200	0.477
0.2636	22300	0.2741
0.2648	22400	0.3584
0.2660	22500	0.34
0.2672	22600	0.142
0.2684	22700	0.5215
0.2695	22800	0.3599
0.2707	22900	0.392
0.2719	23000	0.21
0.2731	23100	0.3272
0.2743	23200	0.1939
0.2755	23300	0.2996
0.2766	23400	0.4124
0.2778	23500	0.2191
0.2790	23600	0.4189
0.2802	23700	0.3127
0.2814	23800	0.2836
0.2825	23900	0.4377
0.2837	24000	0.2477
0.2849	24100	0.1823
0.2861	24200	0.3345
0.2873	24300	0.1592
0.2885	24400	0.2826
0.2896	24500	0.2746
0.2908	24600	0.3893
0.2920	24700	0.2831
0.2932	24800	0.2058
0.2944	24900	0.3126
0.2956	25000	0.4332
0.2967	25100	0.3453
0.2979	25200	0.2358
0.2991	25300	0.3359
0.3003	25400	0.2262
0.3015	25500	0.2517
0.3026	25600	0.3285
0.3038	25700	0.2966
0.3050	25800	0.2261
0.3062	25900	0.2621
0.3074	26000	0.447
0.3086	26100	0.1679
0.3097	26200	0.2305
0.3109	26300	0.3093
0.3121	26400	0.3461
0.3133	26500	0.1874
0.3145	26600	0.2953
0.3156	26700	0.2159
0.3168	26800	0.3724
0.3180	26900	0.3694
0.3192	27000	0.2765
0.3204	27100	0.3718
0.3216	27200	0.2275
0.3227	27300	0.3712
0.3239	27400	0.3034
0.3251	27500	0.2761
0.3263	27600	0.3387
0.3275	27700	0.2386
0.3287	27800	0.2951
0.3298	27900	0.2373
0.3310	28000	0.3166
0.3322	28100	0.1861
0.3334	28200	0.3138
0.3346	28300	0.2721
0.3357	28400	0.2558
0.3369	28500	0.4647
0.3381	28600	0.3267
0.3393	28700	0.186
0.3405	28800	0.2337
0.3417	28900	0.2898
0.3428	29000	0.3932
0.3440	29100	0.3455
0.3452	29200	0.3812
0.3464	29300	0.2193
0.3476	29400	0.4008
0.3487	29500	0.5107
0.3499	29600	0.2428
0.3511	29700	0.183
0.3523	29800	0.2731
0.3535	29900	0.4061
0.3547	30000	0.2645
0.3558	30100	0.1469
0.3570	30200	0.1441
0.3582	30300	0.4598
0.3594	30400	0.3069
0.3606	30500	0.2
0.3618	30600	0.318
0.3629	30700	0.483
0.3641	30800	0.3724
0.3653	30900	0.4162
0.3665	31000	0.2893
0.3677	31100	0.1603
0.3688	31200	0.2551
0.3700	31300	0.2852
0.3712	31400	0.2831
0.3724	31500	0.241
0.3736	31600	0.4407
0.3748	31700	0.3294
0.3759	31800	0.2951
0.3771	31900	0.4059
0.3783	32000	0.2387
0.3795	32100	0.2159
0.3807	32200	0.196
0.3819	32300	0.3167
0.3830	32400	0.31
0.3842	32500	0.2916
0.3854	32600	0.4266
0.3866	32700	0.3467
0.3878	32800	0.264
0.3889	32900	0.3363
0.3901	33000	0.2973
0.3913	33100	0.2986
0.3925	33200	0.1551
0.3937	33300	0.3737
0.3949	33400	0.2519
0.3960	33500	0.1205
0.3972	33600	0.3429
0.3984	33700	0.3489
0.3996	33800	0.267
0.4008	33900	0.2295
0.4019	34000	0.498
0.4031	34100	0.2181
0.4043	34200	0.3637
0.4055	34300	0.2737
0.4067	34400	0.237
0.4079	34500	0.4576
0.4090	34600	0.2861
0.4102	34700	0.2962
0.4114	34800	0.3223
0.4126	34900	0.1787
0.4138	35000	0.1651
0.4150	35100	0.218
0.4161	35200	0.3494
0.4173	35300	0.254
0.4185	35400	0.2484
0.4197	35500	0.2111
0.4209	35600	0.2182
0.4220	35700	0.2826
0.4232	35800	0.3862
0.4244	35900	0.1778
0.4256	36000	0.2026
0.4268	36100	0.4062
0.4280	36200	0.3377
0.4291	36300	0.2501
0.4303	36400	0.1971
0.4315	36500	0.1965
0.4327	36600	0.2112
0.4339	36700	0.2779
0.4350	36800	0.2446
0.4362	36900	0.1647
0.4374	37000	0.372
0.4386	37100	0.2256
0.4398	37200	0.4294
0.4410	37300	0.2305
0.4421	37400	0.2338
0.4433	37500	0.1425
0.4445	37600	0.27
0.4457	37700	0.3507
0.4469	37800	0.3602
0.4481	37900	0.208
0.4492	38000	0.5506
0.4504	38100	0.3372
0.4516	38200	0.2552
0.4528	38300	0.2641
0.4540	38400	0.2489
0.4551	38500	0.2349
0.4563	38600	0.4253
0.4575	38700	0.1115
0.4587	38800	0.2437
0.4599	38900	0.2427
0.4611	39000	0.2807
0.4622	39100	0.1583
0.4634	39200	0.3696
0.4646	39300	0.2216
0.4658	39400	0.2269
0.4670	39500	0.2348
0.4682	39600	0.1744
0.4693	39700	0.4657
0.4705	39800	0.2744
0.4717	39900	0.2182
0.4729	40000	0.3068
0.4741	40100	0.2823
0.4752	40200	0.2098
0.4764	40300	0.14
0.4776	40400	0.2795
0.4788	40500	0.2503
0.4800	40600	0.2208
0.4812	40700	0.281
0.4823	40800	0.322
0.4835	40900	0.1852
0.4847	41000	0.2546
0.4859	41100	0.2212
0.4871	41200	0.2098
0.4882	41300	0.1822
0.4894	41400	0.1093
0.4906	41500	0.2268
0.4918	41600	0.2133
0.4930	41700	0.254
0.4942	41800	0.184
0.4953	41900	0.1988
0.4965	42000	0.1867
0.4977	42100	0.1983
0.4989	42200	0.4042
0.5001	42300	0.4507
0.5013	42400	0.2423
0.5024	42500	0.1334
0.5036	42600	0.2268
0.5048	42700	0.3753
0.5060	42800	0.2982
0.5072	42900	0.2205
0.5083	43000	0.2951
0.5095	43100	0.2851
0.5107	43200	0.1809
0.5119	43300	0.3159
0.5131	43400	0.382
0.5143	43500	0.2359
0.5154	43600	0.1513
0.5166	43700	0.1668
0.5178	43800	0.2322
0.5190	43900	0.2437
0.5202	44000	0.2542
0.5214	44100	0.2593
0.5225	44200	0.1744
0.5237	44300	0.2984
0.5249	44400	0.1511
0.5261	44500	0.2455
0.5273	44600	0.1389
0.5284	44700	0.3415
0.5296	44800	0.3254
0.5308	44900	0.2966
0.5320	45000	0.2549
0.5332	45100	0.2043
0.5344	45200	0.3562
0.5355	45300	0.325
0.5367	45400	0.3129
0.5379	45500	0.2292
0.5391	45600	0.4046
0.5403	45700	0.2194
0.5414	45800	0.2
0.5426	45900	0.148
0.5438	46000	0.2381
0.5450	46100	0.2145
0.5462	46200	0.2321
0.5474	46300	0.3046
0.5485	46400	0.2048
0.5497	46500	0.1872
0.5509	46600	0.1826
0.5521	46700	0.2892
0.5533	46800	0.2199
0.5545	46900	0.1905
0.5556	47000	0.1966
0.5568	47100	0.281
0.5580	47200	0.3232
0.5592	47300	0.302
0.5604	47400	0.1269
0.5615	47500	0.0806
0.5627	47600	0.3116
0.5639	47700	0.1909
0.5651	47800	0.11
0.5663	47900	0.301
0.5675	48000	0.1455
0.5686	48100	0.2442
0.5698	48200	0.1955
0.5710	48300	0.3293
0.5722	48400	0.1447
0.5734	48500	0.3026
0.5745	48600	0.2611
0.5757	48700	0.1316
0.5769	48800	0.3313
0.5781	48900	0.2435
0.5793	49000	0.2051
0.5805	49100	0.281
0.5816	49200	0.4651
0.5828	49300	0.2014
0.5840	49400	0.2743
0.5852	49500	0.1366
0.5864	49600	0.1223
0.5876	49700	0.218
0.5887	49800	0.2868
0.5899	49900	0.1618
0.5911	50000	0.2116
0.5923	50100	0.2716
0.5935	50200	0.1612
0.5946	50300	0.1549
0.5958	50400	0.218
0.5970	50500	0.106
0.5982	50600	0.3294
0.5994	50700	0.1903
0.6006	50800	0.3658
0.6017	50900	0.2213
0.6029	51000	0.1229
0.6041	51100	0.289
0.6053	51200	0.3822
0.6065	51300	0.2053
0.6077	51400	0.1599
0.6088	51500	0.1261
0.6100	51600	0.1338
0.6112	51700	0.1417
0.6124	51800	0.1983
0.6136	51900	0.3362
0.6147	52000	0.1495
0.6159	52100	0.1899
0.6171	52200	0.246
0.6183	52300	0.319
0.6195	52400	0.2951
0.6207	52500	0.1243
0.6218	52600	0.2563
0.6230	52700	0.191
0.6242	52800	0.3106
0.6254	52900	0.1707
0.6266	53000	0.2719
0.6277	53100	0.1056
0.6289	53200	0.2603
0.6301	53300	0.2132
0.6313	53400	0.2362
0.6325	53500	0.1517
0.6337	53600	0.1552
0.6348	53700	0.1852
0.6360	53800	0.2365
0.6372	53900	0.1801
0.6384	54000	0.2784
0.6396	54100	0.3607
0.6408	54200	0.2457
0.6419	54300	0.2772
0.6431	54400	0.2288
0.6443	54500	0.3408
0.6455	54600	0.2904
0.6467	54700	0.1665
0.6478	54800	0.1763
0.6490	54900	0.1696
0.6502	55000	0.2586
0.6514	55100	0.1744
0.6526	55200	0.185
0.6538	55300	0.2609
0.6549	55400	0.3522
0.6561	55500	0.1749
0.6573	55600	0.1988
0.6585	55700	0.1897
0.6597	55800	0.2397
0.6609	55900	0.1677
0.6620	56000	0.4117
0.6632	56100	0.2489
0.6644	56200	0.1876
0.6656	56300	0.1634
0.6668	56400	0.2486
0.6679	56500	0.3521
0.6691	56600	0.1474
0.6703	56700	0.1088
0.6715	56800	0.3521
0.6727	56900	0.2327
0.6739	57000	0.1259
0.6750	57100	0.2464
0.6762	57200	0.1698
0.6774	57300	0.292
0.6786	57400	0.1067
0.6798	57500	0.1909
0.6809	57600	0.1196
0.6821	57700	0.3523
0.6833	57800	0.1899
0.6845	57900	0.3315
0.6857	58000	0.36
0.6869	58100	0.1868
0.6880	58200	0.0783
0.6892	58300	0.203
0.6904	58400	0.2928
0.6916	58500	0.1506
0.6928	58600	0.244
0.6940	58700	0.2145
0.6951	58800	0.1517
0.6963	58900	0.1806
0.6975	59000	0.349
0.6987	59100	0.1427
0.6999	59200	0.1945
0.7010	59300	0.1912
0.7022	59400	0.1737
0.7034	59500	0.1589
0.7046	59600	0.1207
0.7058	59700	0.219
0.7070	59800	0.1421
0.7081	59900	0.1325
0.7093	60000	0.2163
0.7105	60100	0.1793
0.7117	60200	0.1418
0.7129	60300	0.1328
0.7140	60400	0.1868
0.7152	60500	0.2235
0.7164	60600	0.1998
0.7176	60700	0.3268
0.7188	60800	0.2645
0.7200	60900	0.251
0.7211	61000	0.2678
0.7223	61100	0.2007
0.7235	61200	0.2702
0.7247	61300	0.2013
0.7259	61400	0.2137
0.7271	61500	0.1684
0.7282	61600	0.2005
0.7294	61700	0.1853
0.7306	61800	0.1019
0.7318	61900	0.2857
0.7330	62000	0.2217
0.7341	62100	0.229
0.7353	62200	0.1762
0.7365	62300	0.147
0.7377	62400	0.2027
0.7389	62500	0.1486
0.7401	62600	0.0796
0.7412	62700	0.2477
0.7424	62800	0.169
0.7436	62900	0.2577
0.7448	63000	0.2607
0.7460	63100	0.0863
0.7472	63200	0.1393
0.7483	63300	0.1486
0.7495	63400	0.1343
0.7507	63500	0.1787
0.7519	63600	0.1812
0.7531	63700	0.2089
0.7542	63800	0.2912
0.7554	63900	0.1511
0.7566	64000	0.2044
0.7578	64100	0.3588
0.7590	64200	0.1315
0.7602	64300	0.1951
0.7613	64400	0.1738
0.7625	64500	0.3529
0.7637	64600	0.3025
0.7649	64700	0.1893
0.7661	64800	0.3588
0.7672	64900	0.2323
0.7684	65000	0.2435
0.7696	65100	0.1503
0.7708	65200	0.2285
0.7720	65300	0.1856
0.7732	65400	0.1878
0.7743	65500	0.2569
0.7755	65600	0.1553
0.7767	65700	0.1378
0.7779	65800	0.1398
0.7791	65900	0.2696
0.7803	66000	0.1928
0.7814	66100	0.1289
0.7826	66200	0.1539
0.7838	66300	0.3213
0.7850	66400	0.1173
0.7862	66500	0.1969
0.7873	66600	0.1642
0.7885	66700	0.2291
0.7897	66800	0.2609
0.7909	66900	0.2279
0.7921	67000	0.1902
0.7933	67100	0.1036
0.7944	67200	0.1954
0.7956	67300	0.1375
0.7968	67400	0.2393
0.7980	67500	0.2051
0.7992	67600	0.186
0.8003	67700	0.1368
0.8015	67800	0.1505
0.8027	67900	0.113
0.8039	68000	0.1533
0.8051	68100	0.1741
0.8063	68200	0.1154
0.8074	68300	0.2375
0.8086	68400	0.2681
0.8098	68500	0.2329
0.8110	68600	0.1549
0.8122	68700	0.1407
0.8134	68800	0.1875
0.8145	68900	0.1684
0.8157	69000	0.327
0.8169	69100	0.161
0.8181	69200	0.2245
0.8193	69300	0.0945
0.8204	69400	0.1376
0.8216	69500	0.1955
0.8228	69600	0.1514
0.8240	69700	0.2525
0.8252	69800	0.1432
0.8264	69900	0.1585
0.8275	70000	0.2364
0.8287	70100	0.1341
0.8299	70200	0.0829
0.8311	70300	0.0944
0.8323	70400	0.2952
0.8335	70500	0.3315
0.8346	70600	0.2225
0.8358	70700	0.1873
0.8370	70800	0.164
0.8382	70900	0.1399
0.8394	71000	0.2327
0.8405	71100	0.1962
0.8417	71200	0.2469
0.8429	71300	0.2247
0.8441	71400	0.1333
0.8453	71500	0.1753
0.8465	71600	0.1417
0.8476	71700	0.0978
0.8488	71800	0.1675
0.8500	71900	0.2479
0.8512	72000	0.2256
0.8524	72100	0.1176
0.8535	72200	0.2608
0.8547	72300	0.1199
0.8559	72400	0.2638
0.8571	72500	0.2186
0.8583	72600	0.1652
0.8595	72700	0.1627
0.8606	72800	0.2129
0.8618	72900	0.1206
0.8630	73000	0.1989
0.8642	73100	0.1513
0.8654	73200	0.1579
0.8666	73300	0.2043
0.8677	73400	0.1531
0.8689	73500	0.1164
0.8701	73600	0.1754
0.8713	73700	0.3191
0.8725	73800	0.2397
0.8736	73900	0.0874
0.8748	74000	0.2364
0.8760	74100	0.145
0.8772	74200	0.1775
0.8784	74300	0.1724
0.8796	74400	0.1303
0.8807	74500	0.1858
0.8819	74600	0.2444
0.8831	74700	0.0803
0.8843	74800	0.1852
0.8855	74900	0.1755
0.8867	75000	0.1407
0.8878	75100	0.1773
0.8890	75200	0.2912
0.8902	75300	0.1203
0.8914	75400	0.2338
0.8926	75500	0.1733
0.8937	75600	0.1118
0.8949	75700	0.1831
0.8961	75800	0.4156
0.8973	75900	0.1494
0.8985	76000	0.072
0.8997	76100	0.1744
0.9008	76200	0.1091
0.9020	76300	0.1464
0.9032	76400	0.2111
0.9044	76500	0.0763
0.9056	76600	0.1468
0.9067	76700	0.1483
0.9079	76800	0.1197
0.9091	76900	0.2614
0.9103	77000	0.1826
0.9115	77100	0.2556
0.9127	77200	0.2355
0.9138	77300	0.1621
0.9150	77400	0.1812
0.9162	77500	0.08
0.9174	77600	0.0916
0.9186	77700	0.2734
0.9198	77800	0.1764
0.9209	77900	0.1261
0.9221	78000	0.1266
0.9233	78100	0.2578
0.9245	78200	0.147
0.9257	78300	0.0892
0.9268	78400	0.2436
0.9280	78500	0.3233
0.9292	78600	0.2142
0.9304	78700	0.2231
0.9316	78800	0.1546
0.9328	78900	0.1716
0.9339	79000	0.1514
0.9351	79100	0.064
0.9363	79200	0.1428
0.9375	79300	0.2453
0.9387	79400	0.348
0.9398	79500	0.2739
0.9410	79600	0.2446
0.9422	79700	0.1081
0.9434	79800	0.3078
0.9446	79900	0.1948
0.9458	80000	0.1562
0.9469	80100	0.2414
0.9481	80200	0.1235
0.9493	80300	0.164
0.9505	80400	0.2325
0.9517	80500	0.126
0.9529	80600	0.1135
0.9540	80700	0.1889
0.9552	80800	0.2255
0.9564	80900	0.1105
0.9576	81000	0.1364
0.9588	81100	0.2261
0.9599	81200	0.2825
0.9611	81300	0.1119
0.9623	81400	0.1864
0.9635	81500	0.2259
0.9647	81600	0.1556
0.9659	81700	0.1305
0.9670	81800	0.2178
0.9682	81900	0.1686
0.9694	82000	0.2118
0.9706	82100	0.197
0.9718	82200	0.174
0.9730	82300	0.1995
0.9741	82400	0.1058
0.9753	82500	0.2344
0.9765	82600	0.1284
0.9777	82700	0.0896
0.9789	82800	0.2184
0.9800	82900	0.2321
0.9812	83000	0.1135
0.9824	83100	0.1824
0.9836	83200	0.0695
0.9848	83300	0.1236
0.9860	83400	0.1259
0.9871	83500	0.0869
0.9883	83600	0.1957
0.9895	83700	0.2565
0.9907	83800	0.1731
0.9919	83900	0.1427
0.9930	84000	0.1762
0.9942	84100	0.1108
0.9954	84200	0.1748
0.9966	84300	0.0978
0.9978	84400	0.1419
0.9990	84500	0.1937

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},
}