all-MiniLM-L6-v13-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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 tokens
• Similarity Function: Cosine Similarity
• 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}) with Transformer model: 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 = [
    'smart toothbrush',
    'onions vine leaves',
    'crispy cheese sauce casserole',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

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: 2
• 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: 2
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• dispatch_batches: None
• split_batches: 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss
0.8232	61100	2.2627
0.8246	61200	1.8503
0.8259	61300	2.0076
0.8273	61400	1.7956
0.8286	61500	1.5268
0.8300	61600	1.8155
0.8313	61700	2.1089
0.8327	61800	2.4272
0.8340	61900	1.9374
0.8354	62000	1.6402
0.8367	62100	2.4922
0.8381	62200	1.9729
0.8394	62300	1.5534
0.8408	62400	1.7918
0.8421	62500	2.2717
0.8434	62600	2.2199
0.8448	62700	1.7964
0.8461	62800	2.2251
0.8475	62900	2.0824
0.8488	63000	1.647
0.8502	63100	1.5672
0.8515	63200	1.7727
0.8529	63300	1.7529
0.8542	63400	1.3972
0.8556	63500	1.8951
0.8569	63600	1.7989
0.8583	63700	1.5449
0.8596	63800	1.9917
0.8610	63900	1.8591
0.8623	64000	1.9657
0.8637	64100	2.2015
0.8650	64200	1.8189
0.8664	64300	1.9765
0.8677	64400	1.8208
0.8690	64500	2.007
0.8704	64600	2.181
0.8717	64700	2.2569
0.8731	64800	1.6881
0.8744	64900	1.7391
0.8758	65000	2.0425
0.8771	65100	1.7074
0.8785	65200	1.9264
0.8798	65300	1.6291
0.8812	65400	1.7177
0.8825	65500	1.5505
0.8839	65600	2.1976
0.8852	65700	1.7166
0.8866	65800	1.623
0.8879	65900	1.8934
0.8893	66000	1.5433
0.8906	66100	2.303
0.8920	66200	2.0442
0.8933	66300	1.9883
0.8946	66400	1.7443
0.8960	66500	1.8812
0.8973	66600	1.872
0.8987	66700	1.826
0.9000	66800	1.9124
0.9014	66900	2.1901
0.9027	67000	1.8261
0.9041	67100	1.8076
0.9054	67200	1.9869
0.9068	67300	1.7586
0.9081	67400	1.6167
0.9095	67500	2.0103
0.9108	67600	1.9229
0.9122	67700	1.7532
0.9135	67800	1.8408
0.9149	67900	1.4797
0.9162	68000	1.818
0.9176	68100	1.6391
0.9189	68200	1.6242
0.9202	68300	1.639
0.9216	68400	2.0135
0.9229	68500	1.8024
0.9243	68600	1.8188
0.9256	68700	1.556
0.9270	68800	1.7777
0.9283	68900	1.6406
0.9297	69000	1.5881
0.9310	69100	2.0322
0.9324	69200	1.8145
0.9337	69300	2.0887
0.9351	69400	1.5552
0.9364	69500	1.7682
0.9378	69600	2.1938
0.9391	69700	2.1021
0.9405	69800	1.6815
0.9418	69900	1.6488
0.9432	70000	1.9412
0.9445	70100	1.765
0.9458	70200	2.0429
0.9472	70300	1.9302
0.9485	70400	2.0909
0.9499	70500	1.6209
0.9512	70600	2.203
0.9526	70700	1.9052
0.9539	70800	2.2339
0.9553	70900	1.8504
0.9566	71000	1.9318
0.9580	71100	1.5013
0.9593	71200	2.0928
0.9607	71300	1.8393
0.9620	71400	1.9516
0.9634	71500	1.8203
0.9647	71600	1.9596
0.9661	71700	2.0126
0.9674	71800	1.5654
0.9688	71900	1.7494
0.9701	72000	1.675
0.9714	72100	1.9596
0.9728	72200	1.8531
0.9741	72300	1.695
0.9755	72400	1.98
0.9768	72500	1.6654
0.9782	72600	1.4514
0.9795	72700	1.669
0.9809	72800	1.5103
0.9822	72900	1.5932
0.9836	73000	1.9951
0.9849	73100	1.6629
0.9863	73200	1.6346
0.9876	73300	1.7458
0.9890	73400	1.5405
0.9903	73500	2.2183
0.9917	73600	2.4572
0.9930	73700	1.6371
0.9944	73800	1.9842
0.9957	73900	1.642
0.9970	74000	1.8484
0.9984	74100	1.6463
0.9997	74200	1.7123
1.0011	74300	1.4431
1.0024	74400	2.0678
1.0038	74500	1.5143
1.0051	74600	1.6055
1.0065	74700	1.5292
1.0078	74800	2.052
1.0092	74900	1.9049
1.0105	75000	1.6666
1.0119	75100	1.7374
1.0132	75200	1.5201
1.0146	75300	1.6994
1.0159	75400	1.8111
1.0173	75500	1.9701
1.0186	75600	1.7418
1.0200	75700	1.4604
1.0213	75800	1.8545
1.0226	75900	1.487
1.0240	76000	1.9216
1.0253	76100	1.2685
1.0267	76200	1.6035
1.0280	76300	1.5329
1.0294	76400	1.7169
1.0307	76500	1.4756
1.0321	76600	1.4021
1.0334	76700	1.7533
1.0348	76800	2.3071
1.0361	76900	1.8261
1.0375	77000	2.1211
1.0388	77100	1.9237
1.0402	77200	1.7846
1.0415	77300	1.5664
1.0429	77400	1.8463
1.0442	77500	1.7455
1.0456	77600	1.7717
1.0469	77700	1.6028
1.0482	77800	2.3449
1.0496	77900	1.7559
1.0509	78000	2.3763
1.0523	78100	1.844
1.0536	78200	1.5563
1.0550	78300	1.7808
1.0563	78400	2.0689
1.0577	78500	1.3285
1.0590	78600	1.5348
1.0604	78700	2.4918
1.0617	78800	2.2498
1.0631	78900	1.8905
1.0644	79000	1.8463
1.0658	79100	1.7168
1.0671	79200	2.215
1.0685	79300	1.5194
1.0698	79400	1.6528
1.0712	79500	1.7271
1.0725	79600	1.8336
1.0738	79700	1.6057
1.0752	79800	1.6951
1.0765	79900	1.811
1.0779	80000	1.8606
1.0792	80100	1.6004
1.0806	80200	1.9454
1.0819	80300	1.9395
1.0833	80400	1.5483
1.0846	80500	1.6592
1.0860	80600	1.7823
1.0873	80700	1.6464
1.0887	80800	1.7621
1.0900	80900	1.9007
1.0914	81000	1.817
1.0927	81100	1.8079
1.0941	81200	1.793
1.0954	81300	1.775
1.0968	81400	1.8482
1.0981	81500	2.1591
1.0994	81600	1.8745
1.1008	81700	1.5664
1.1021	81800	2.0571
1.1035	81900	1.5686
1.1048	82000	1.847
1.1062	82100	1.6045
1.1075	82200	1.2121
1.1089	82300	1.5535
1.1102	82400	1.7324
1.1116	82500	1.5164
1.1129	82600	1.6282
1.1143	82700	1.8102
1.1156	82800	1.39
1.1170	82900	1.8485
1.1183	83000	1.977
1.1197	83100	1.6974
1.1210	83200	2.0346
1.1224	83300	1.418
1.1237	83400	2.2979
1.1250	83500	2.3943
1.1264	83600	1.651
1.1277	83700	1.6725
1.1291	83800	1.6154
1.1304	83900	1.6627
1.1318	84000	1.8559
1.1331	84100	1.7952
1.1345	84200	1.7902
1.1358	84300	1.9019
1.1372	84400	1.4513
1.1385	84500	1.7438
1.1399	84600	1.5009
1.1412	84700	1.6993
1.1426	84800	1.6195
1.1439	84900	1.4334
1.1453	85000	1.5223
1.1466	85100	1.6166
1.1480	85200	1.8966
1.1493	85300	1.7093
1.1506	85400	1.3838
1.1520	85500	1.7472
1.1533	85600	1.4164
1.1547	85700	1.233
1.1560	85800	1.4688
1.1574	85900	1.4373
1.1587	86000	1.491
1.1601	86100	2.102
1.1614	86200	2.1561
1.1628	86300	1.4177
1.1641	86400	1.5393
1.1655	86500	1.6477
1.1668	86600	2.3109
1.1682	86700	1.5485
1.1695	86800	1.5293
1.1709	86900	1.6376
1.1722	87000	1.5661
1.1736	87100	1.6482
1.1749	87200	1.7779
1.1762	87300	1.3775
1.1776	87400	1.6072
1.1789	87500	1.3095
1.1803	87600	1.4503
1.1816	87700	1.4568
1.1830	87800	1.4942
1.1843	87900	1.5583
1.1857	88000	1.7898
1.1870	88100	1.7546
1.1884	88200	1.205
1.1897	88300	1.9065
1.1911	88400	2.0353
1.1924	88500	1.7578
1.1938	88600	1.8053
1.1951	88700	1.3341
1.1965	88800	2.0699
1.1978	88900	1.8514
1.1992	89000	1.9375
1.2005	89100	1.845
1.2018	89200	1.3934
1.2032	89300	1.4777
1.2045	89400	1.5636
1.2059	89500	1.7731
1.2072	89600	1.4624
1.2086	89700	1.7582
1.2099	89800	1.4571
1.2113	89900	1.6627
1.2126	90000	1.3795
1.2140	90100	2.2098
1.2153	90200	1.417
1.2167	90300	1.3832
1.2180	90400	1.7651
1.2194	90500	1.8122
1.2207	90600	1.5503
1.2221	90700	2.2202
1.2234	90800	1.593
1.2248	90900	1.5671
1.2261	91000	1.6143
1.2274	91100	1.9637
1.2288	91200	1.4438
1.2301	91300	1.9687
1.2315	91400	1.7887
1.2328	91500	1.7756
1.2342	91600	1.4491
1.2355	91700	2.2564
1.2369	91800	1.4821
1.2382	91900	1.5253
1.2396	92000	1.5747
1.2409	92100	1.1671
1.2423	92200	1.9347
1.2436	92300	1.6319
1.2450	92400	2.3654
1.2463	92500	1.537
1.2477	92600	1.5141
1.2490	92700	1.9275
1.2504	92800	1.8062
1.2517	92900	1.7132
1.2530	93000	2.4315
1.2544	93100	1.1016
1.2557	93200	1.6248
1.2571	93300	2.2185
1.2584	93400	1.4869
1.2598	93500	1.7578
1.2611	93600	1.3692
1.2625	93700	2.2538
1.2638	93800	1.4158
1.2652	93900	1.4309
1.2665	94000	2.036
1.2679	94100	1.5315
1.2692	94200	1.2562
1.2706	94300	1.4589
1.2719	94400	1.4579
1.2733	94500	1.3806
1.2746	94600	1.4328
1.2760	94700	1.3881
1.2773	94800	1.6977
1.2786	94900	1.9541
1.2800	95000	1.8359
1.2813	95100	1.4229
1.2827	95200	1.3777
1.2840	95300	1.486
1.2854	95400	1.5093
1.2867	95500	1.6792
1.2881	95600	2.0964
1.2894	95700	1.9592
1.2908	95800	1.8839
1.2921	95900	1.8193
1.2935	96000	1.2074
1.2948	96100	1.5
1.2962	96200	1.6936
1.2975	96300	1.2643
1.2989	96400	1.7983
1.3002	96500	1.9845
1.3016	96600	1.97
1.3029	96700	1.824
1.3042	96800	1.8034
1.3056	96900	1.6887
1.3069	97000	1.9653
1.3083	97100	2.0337
1.3096	97200	1.9934
1.3110	97300	1.5434
1.3123	97400	1.8976
1.3137	97500	1.6114
1.3150	97600	1.7799
1.3164	97700	2.1148
1.3177	97800	1.6252
1.3191	97900	2.1435
1.3204	98000	1.7719
1.3218	98100	1.8351
1.3231	98200	1.3329
1.3245	98300	1.9484
1.3258	98400	1.9758
1.3272	98500	1.2146
1.3285	98600	1.4158
1.3298	98700	1.6679
1.3312	98800	1.9363
1.3325	98900	1.4793
1.3339	99000	1.257
1.3352	99100	1.9477
1.3366	99200	1.603
1.3379	99300	1.4738
1.3393	99400	1.6832
1.3406	99500	1.6934
1.3420	99600	1.715
1.3433	99700	1.4162
1.3447	99800	1.7815
1.3460	99900	1.9255
1.3474	100000	1.5564
1.3487	100100	1.7694
1.3501	100200	1.7545
1.3514	100300	1.3728
1.3528	100400	1.5254
1.3541	100500	1.7833
1.3554	100600	1.7485
1.3568	100700	1.8016
1.3581	100800	1.7602
1.3595	100900	2.0944
1.3608	101000	1.6225
1.3622	101100	1.8505
1.3635	101200	1.5885
1.3649	101300	1.6147
1.3662	101400	1.6244
1.3676	101500	1.9271
1.3689	101600	1.4003
1.3703	101700	1.9319
1.3716	101800	1.4809
1.3730	101900	1.4683
1.3743	102000	1.8048
1.3757	102100	1.658
1.3770	102200	1.4604
1.3784	102300	1.6056
1.3797	102400	1.4837
1.3810	102500	1.7507
1.3824	102600	1.4528
1.3837	102700	1.7623
1.3851	102800	1.6916
1.3864	102900	1.0608
1.3878	103000	1.2387
1.3891	103100	1.3267
1.3905	103200	1.7035
1.3918	103300	1.9545
1.3932	103400	1.4143
1.3945	103500	1.9986
1.3959	103600	1.5485
1.3972	103700	1.6946
1.3986	103800	1.4163
1.3999	103900	1.7001
1.4013	104000	1.8313
1.4026	104100	1.6345
1.4040	104200	2.0902
1.4053	104300	1.6568
1.4066	104400	2.1615
1.4080	104500	2.0037
1.4093	104600	1.702
1.4107	104700	1.5521
1.4120	104800	1.5274
1.4134	104900	1.431
1.4147	105000	1.7616
1.4161	105100	1.6825
1.4174	105200	1.6137
1.4188	105300	1.8515
1.4201	105400	1.7499
1.4215	105500	1.8541
1.4228	105600	1.7024
1.4242	105700	1.545
1.4255	105800	1.7382
1.4269	105900	1.7512
1.4282	106000	2.0386
1.4296	106100	1.9658
1.4309	106200	2.0754
1.4322	106300	1.2682
1.4336	106400	1.7468
1.4349	106500	1.5854
1.4363	106600	1.4202
1.4376	106700	1.3942
1.4390	106800	1.7737
1.4403	106900	1.2561
1.4417	107000	1.9416
1.4430	107100	1.9931
1.4444	107200	1.7395
1.4457	107300	1.6517
1.4471	107400	1.1001
1.4484	107500	1.9577
1.4498	107600	1.7326
1.4511	107700	1.8625
1.4525	107800	1.713
1.4538	107900	1.5344
1.4552	108000	1.6243
1.4565	108100	1.4919
1.4578	108200	1.5006
1.4592	108300	1.0809
1.4605	108400	2.1561
1.4619	108500	1.4558
1.4632	108600	1.5179
1.4646	108700	1.3773
1.4659	108800	1.474
1.4673	108900	1.9409
1.4686	109000	1.7273
1.4700	109100	1.5621
1.4713	109200	1.2836
1.4727	109300	1.5104
1.4740	109400	1.2378
1.4754	109500	1.6953
1.4767	109600	1.9938
1.4781	109700	1.4626
1.4794	109800	1.709
1.4808	109900	1.6221
1.4821	110000	1.9676
1.4834	110100	1.6273
1.4848	110200	1.2981
1.4861	110300	1.541
1.4875	110400	1.4703
1.4888	110500	1.8536
1.4902	110600	1.7281
1.4915	110700	1.8766
1.4929	110800	1.6528
1.4942	110900	1.218
1.4956	111000	1.2898
1.4969	111100	1.3452
1.4983	111200	1.8229
1.4996	111300	1.1862
1.5010	111400	1.6804
1.5023	111500	1.6748
1.5037	111600	1.6363
1.5050	111700	1.5167
1.5064	111800	2.2198
1.5077	111900	1.0652
1.5090	112000	1.5825
1.5104	112100	2.1573
1.5117	112200	1.3099
1.5131	112300	1.7038
1.5144	112400	1.4865
1.5158	112500	2.0853
1.5171	112600	1.7619
1.5185	112700	1.8743
1.5198	112800	1.8953
1.5212	112900	1.5148
1.5225	113000	1.6521
1.5239	113100	2.0287
1.5252	113200	1.8012
1.5266	113300	1.1247
1.5279	113400	1.7724
1.5293	113500	2.1853
1.5306	113600	1.2853
1.5320	113700	1.352
1.5333	113800	1.9003
1.5346	113900	1.6962
1.5360	114000	1.3286
1.5373	114100	1.5009
1.5387	114200	1.8231
1.5400	114300	1.6319
1.5414	114400	1.5033
1.5427	114500	1.4697
1.5441	114600	1.5468
1.5454	114700	1.7599
1.5468	114800	1.5572
1.5481	114900	1.6253
1.5495	115000	1.7229
1.5508	115100	1.3799
1.5522	115200	1.5286
1.5535	115300	1.3338
1.5549	115400	1.4199
1.5562	115500	1.4384
1.5576	115600	1.7255
1.5589	115700	1.5644
1.5602	115800	1.5696
1.5616	115900	1.9268
1.5629	116000	1.5231
1.5643	116100	1.6066
1.5656	116200	1.6264
1.5670	116300	1.3553
1.5683	116400	1.7547
1.5697	116500	2.0021
1.5710	116600	1.4245
1.5724	116700	2.0397
1.5737	116800	1.7958
1.5751	116900	2.1313
1.5764	117000	1.6239
1.5778	117100	1.858
1.5791	117200	1.5547
1.5805	117300	1.235
1.5818	117400	1.3374
1.5832	117500	1.4145
1.5845	117600	1.8562
1.5858	117700	1.6566
1.5872	117800	1.4169
1.5885	117900	1.7327
1.5899	118000	1.5307
1.5912	118100	1.7976
1.5926	118200	1.2057
1.5939	118300	1.3177
1.5953	118400	1.6554
1.5966	118500	1.7058
1.5980	118600	1.3839
1.5993	118700	1.2199
1.6007	118800	1.1836
1.6020	118900	1.6226
1.6034	119000	1.9552
1.6047	119100	1.2005
1.6061	119200	1.5903
1.6074	119300	1.5047
1.6088	119400	1.499
1.6101	119500	1.1262
1.6114	119600	2.2492
1.6128	119700	1.2046
1.6141	119800	1.9648
1.6155	119900	1.7029
1.6168	120000	1.7808
1.6182	120100	1.787
1.6195	120200	1.6982
1.6209	120300	1.5131
1.6222	120400	1.7229
1.6236	120500	1.3556
1.6249	120600	1.9729
1.6263	120700	1.5959
1.6276	120800	1.4928
1.6290	120900	1.6249
1.6303	121000	1.4164
1.6317	121100	2.0941
1.6330	121200	1.3584
1.6344	121300	1.8783
1.6357	121400	1.3435
1.6370	121500	1.3914
1.6384	121600	1.7009
1.6397	121700	1.1749
1.6411	121800	1.6401
1.6424	121900	1.893
1.6438	122000	1.305
1.6451	122100	1.3063
1.6465	122200	1.5201
1.6478	122300	1.2591
1.6492	122400	1.7967
1.6505	122500	1.4299
1.6519	122600	1.5752
1.6532	122700	1.5112
1.6546	122800	1.8106
1.6559	122900	1.3184
1.6573	123000	1.3979
1.6586	123100	1.1882
1.6600	123200	1.4188
1.6613	123300	1.897
1.6626	123400	1.5941
1.6640	123500	1.9992
1.6653	123600	1.2469
1.6667	123700	1.4211
1.6680	123800	1.7398
1.6694	123900	1.7558
1.6707	124000	1.2737
1.6721	124100	1.6168
1.6734	124200	1.6744
1.6748	124300	1.7027
1.6761	124400	1.5966
1.6775	124500	1.5876
1.6788	124600	1.5608
1.6802	124700	2.1446
1.6815	124800	1.7975
1.6829	124900	1.9436
1.6842	125000	1.942
1.6856	125100	1.4679
1.6869	125200	1.6186
1.6882	125300	1.7944
1.6896	125400	1.4543
1.6909	125500	1.4701
1.6923	125600	1.82
1.6936	125700	1.325
1.6950	125800	1.4055
1.6963	125900	1.7347
1.6977	126000	1.5435
1.6990	126100	1.6918
1.7004	126200	1.5132
1.7017	126300	1.7676
1.7031	126400	1.4455
1.7044	126500	1.7463
1.7058	126600	1.7647
1.7071	126700	1.2679
1.7085	126800	1.6775
1.7098	126900	1.7353
1.7112	127000	1.4454
1.7125	127100	1.3769
1.7138	127200	1.6437
1.7152	127300	1.5347
1.7165	127400	1.4954
1.7179	127500	1.6035
1.7192	127600	1.4155
1.7206	127700	1.5114
1.7219	127800	1.0086
1.7233	127900	1.6472
1.7246	128000	1.3034
1.7260	128100	1.2263
1.7273	128200	1.2132
1.7287	128300	1.7553
1.7300	128400	1.6663
1.7314	128500	1.7534
1.7327	128600	1.4902
1.7341	128700	1.5908
1.7354	128800	1.5938
1.7368	128900	1.3085
1.7381	129000	1.9479
1.7394	129100	1.3384
1.7408	129200	1.8235
1.7421	129300	1.1016
1.7435	129400	1.5203
1.7448	129500	1.9095
1.7462	129600	1.6981
1.7475	129700	1.7581
1.7489	129800	1.4284
1.7502	129900	1.505
1.7516	130000	1.9087
1.7529	130100	1.5041
1.7543	130200	1.6688
1.7556	130300	1.7098
1.7570	130400	1.8812
1.7583	130500	1.7743
1.7597	130600	1.7902
1.7610	130700	1.834
1.7624	130800	1.8141
1.7637	130900	1.5811
1.7650	131000	1.6987
1.7664	131100	1.7954
1.7677	131200	1.4612
1.7691	131300	1.5317
1.7704	131400	1.3477
1.7718	131500	1.7828
1.7731	131600	2.1168
1.7745	131700	1.5251
1.7758	131800	1.3935
1.7772	131900	1.4564
1.7785	132000	1.7692
1.7799	132100	1.7792
1.7812	132200	1.8703
1.7826	132300	1.4434
1.7839	132400	1.6243
1.7853	132500	1.7519
1.7866	132600	1.8167
1.7880	132700	1.5469
1.7893	132800	1.6512
1.7906	132900	1.3017
1.7920	133000	1.3424
1.7933	133100	1.4329
1.7947	133200	1.1791
1.7960	133300	1.5516
1.7974	133400	1.4913
1.7987	133500	1.4469
1.8001	133600	1.177
1.8014	133700	1.3115
1.8028	133800	1.7379
1.8041	133900	1.3329
1.8055	134000	1.6283
1.8068	134100	1.5019
1.8082	134200	1.5125
1.8095	134300	1.45
1.8109	134400	1.3488
1.8122	134500	1.2128
1.8136	134600	1.2604
1.8149	134700	1.4723
1.8162	134800	1.4218
1.8176	134900	1.2657
1.8189	135000	2.0891
1.8203	135100	1.4758
1.8216	135200	1.2031
1.8230	135300	1.5003
1.8243	135400	1.1243
1.8257	135500	1.6347
1.8270	135600	1.3884
1.8284	135700	1.4571
1.8297	135800	1.5888
1.8311	135900	1.8263
1.8324	136000	1.884
1.8338	136100	1.0704
1.8351	136200	1.5063
1.8365	136300	1.3883
1.8378	136400	1.6448
1.8392	136500	1.6968
1.8405	136600	1.4655
1.8418	136700	2.1945
1.8432	136800	1.5535
1.8445	136900	1.8415
1.8459	137000	1.5415
1.8472	137100	1.5739
1.8486	137200	1.6237
1.8499	137300	1.8467
1.8513	137400	1.5384
1.8526	137500	2.0643
1.8540	137600	1.5304
1.8553	137700	1.3931
1.8567	137800	1.7091
1.8580	137900	1.7951
1.8594	138000	1.4045
1.8607	138100	1.5107
1.8621	138200	1.504
1.8634	138300	1.8333
1.8648	138400	1.388
1.8661	138500	1.6747
1.8674	138600	1.5811
1.8688	138700	0.9687
1.8701	138800	1.8287
1.8715	138900	1.4925
1.8728	139000	2.0032
1.8742	139100	1.749
1.8755	139200	1.2697
1.8769	139300	1.6545
1.8782	139400	1.3993
1.8796	139500	1.2389
1.8809	139600	1.2592
1.8823	139700	1.3851
1.8836	139800	1.5201
1.8850	139900	1.5212
1.8863	140000	1.3385
1.8877	140100	1.3909
1.8890	140200	1.7753
1.8904	140300	1.3581
1.8917	140400	1.7883
1.8930	140500	1.5795
1.8944	140600	2.0231
1.8957	140700	1.6205
1.8971	140800	1.7681
1.8984	140900	1.9825
1.8998	141000	1.8362
1.9011	141100	1.2596
1.9025	141200	1.8202
1.9038	141300	1.5923
1.9052	141400	1.6088
1.9065	141500	1.8636
1.9079	141600	1.3539
1.9092	141700	1.8269
1.9106	141800	1.4569
1.9119	141900	1.3619
1.9133	142000	1.6444
1.9146	142100	1.1433
1.9160	142200	1.7109
1.9173	142300	1.5552
1.9186	142400	1.6076
1.9200	142500	1.8098
1.9213	142600	1.6098
1.9227	142700	1.3428
1.9240	142800	1.8416
1.9254	142900	1.7212
1.9267	143000	1.8468
1.9281	143100	1.5409
1.9294	143200	1.6295
1.9308	143300	1.8112
1.9321	143400	1.3063
1.9335	143500	1.5782
1.9348	143600	1.5314
1.9362	143700	1.2084
1.9375	143800	1.6423
1.9389	143900	1.2447
1.9402	144000	1.0976
1.9416	144100	1.0734
1.9429	144200	1.8122
1.9442	144300	1.5745
1.9456	144400	1.8577
1.9469	144500	2.041
1.9483	144600	1.4208
1.9496	144700	1.243
1.9510	144800	1.6781
1.9523	144900	1.6176
1.9537	145000	1.2095
1.9550	145100	1.2454
1.9564	145200	1.6285
1.9577	145300	1.737
1.9591	145400	1.1004
1.9604	145500	1.3967
1.9618	145600	1.8645
1.9631	145700	1.3151
1.9645	145800	2.1533
1.9658	145900	1.7052
1.9672	146000	1.5864
1.9685	146100	1.1257
1.9698	146200	1.5899
1.9712	146300	1.4375
1.9725	146400	1.5404
1.9739	146500	1.3839
1.9752	146600	1.326
1.9766	146700	1.5772
1.9779	146800	1.7628
1.9793	146900	1.8017
1.9806	147000	1.3599
1.9820	147100	1.1819
1.9833	147200	1.4646
1.9847	147300	1.8529
1.9860	147400	1.4933
1.9874	147500	1.4262
1.9887	147600	1.247
1.9901	147700	1.5074
1.9914	147800	1.5928
1.9928	147900	1.8633
1.9941	148000	1.4895
1.9954	148100	1.6311
1.9968	148200	1.7141
1.9981	148300	1.3199
1.9995	148400	1.2443

Framework Versions

• Python: 3.8.10
• Sentence Transformers: 3.1.1
• Transformers: 4.45.2
• PyTorch: 2.4.1+cu118
• Accelerate: 1.0.1
• Datasets: 3.0.1
• Tokenizers: 0.20.3

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},
}