Remonatef/all-MiniLM-L6-v17-pair_score

all-MiniLM-L6-v8-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 = [
    'deluxe mug for morning coffee',
    'polyfibre scarf',
    'cheddar cheese burrito',
]
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: 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: 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
0.0014	100	11.4553
0.0028	200	11.5147
0.0042	300	11.1304
0.0056	400	10.7925
0.0070	500	10.4493
0.0084	600	10.2631
0.0098	700	9.987
0.0112	800	9.8477
0.0126	900	9.6295
0.0140	1000	9.3638
0.0153	1100	9.1913
0.0167	1200	8.9688
0.0181	1300	8.808
0.0195	1400	8.6993
0.0209	1500	8.6078
0.0223	1600	8.5739
0.0237	1700	8.5575
0.0251	1800	8.5173
0.0265	1900	8.4983
0.0279	2000	8.4662
0.0293	2100	8.4408
0.0307	2200	8.4136
0.0321	2300	8.4002
0.0335	2400	8.3883
0.0349	2500	8.3785
0.0363	2600	8.3458
0.0377	2700	8.3617
0.0391	2800	8.3338
0.0405	2900	8.3281
0.0419	3000	8.3043
0.0433	3100	8.3087
0.0447	3200	8.2913
0.0460	3300	8.2854
0.0474	3400	8.2408
0.0488	3500	8.2628
0.0502	3600	8.2401
0.0516	3700	8.2538
0.0530	3800	8.2103
0.0544	3900	8.2221
0.0558	4000	8.2248
0.0572	4100	8.2045
0.0586	4200	8.2008
0.0600	4300	8.196
0.0614	4400	8.1757
0.0628	4500	8.1845
0.0642	4600	8.1714
0.0656	4700	8.1745
0.0670	4800	8.1702
0.0684	4900	8.1767
0.0698	5000	8.1379
0.0712	5100	8.1473
0.0726	5200	8.1443
0.0740	5300	8.1173
0.0754	5400	8.121
0.0767	5500	8.136
0.0781	5600	8.1246
0.0795	5700	8.0983
0.0809	5800	8.1023
0.0823	5900	8.1013
0.0837	6000	8.0657
0.0851	6100	8.0998
0.0865	6200	8.0585
0.0879	6300	8.1082
0.0893	6400	8.0652
0.0907	6500	8.0808
0.0921	6600	8.0756
0.0935	6700	8.0279
0.0949	6800	8.0659
0.0963	6900	8.0428
0.0977	7000	8.0363
0.0991	7100	8.0343
0.1005	7200	8.0488
0.1019	7300	8.0225
0.1033	7400	8.0203
0.1047	7500	8.0248
0.1061	7600	7.9882
0.1074	7700	7.9956
0.1088	7800	8.0338
0.1102	7900	7.9827
0.1116	8000	7.9849
0.1130	8100	8.0072
0.1144	8200	7.9708
0.1158	8300	7.9786
0.1172	8400	7.9983
0.1186	8500	7.9762
0.1200	8600	7.9955
0.1214	8700	7.9969
0.1228	8800	7.9913
0.1242	8900	7.9512
0.1256	9000	7.9672
0.1270	9100	7.9853
0.1284	9200	7.9626
0.1298	9300	7.9767
0.1312	9400	7.9404
0.1326	9500	7.9076
0.1340	9600	7.968
0.1354	9700	7.9432
0.1367	9800	7.9255
0.1381	9900	7.9095
0.1395	10000	7.9337
0.1409	10100	7.9464
0.1423	10200	7.9218
0.1437	10300	7.9102
0.1451	10400	7.9379
0.1465	10500	7.8907
0.1479	10600	7.8968
0.1493	10700	7.9193
0.1507	10800	7.9327
0.1521	10900	7.896
0.1535	11000	7.9228
0.1549	11100	7.9253
0.1563	11200	7.8825
0.1577	11300	7.8812
0.1591	11400	7.8883
0.1605	11500	7.8721
0.1619	11600	7.9218
0.1633	11700	7.8893
0.1647	11800	7.8961
0.1661	11900	7.8647
0.1674	12000	7.89
0.1688	12100	7.8422
0.1702	12200	7.9348
0.1716	12300	7.8808
0.1730	12400	7.8788
0.1744	12500	7.8794
0.1758	12600	7.848
0.1772	12700	7.8279
0.1786	12800	7.8655
0.1800	12900	7.8612
0.1814	13000	7.828
0.1828	13100	7.8419
0.1842	13200	7.8574
0.1856	13300	7.8688
0.1870	13400	7.8408
0.1884	13500	7.8172
0.1898	13600	7.8579
0.1912	13700	7.8392
0.1926	13800	7.849
0.1940	13900	7.8485
0.1954	14000	7.861
0.1968	14100	7.8257
0.1981	14200	7.8647
0.1995	14300	7.857
0.2009	14400	7.8031
0.2023	14500	7.8498
0.2037	14600	7.8175
0.2051	14700	7.8474
0.2065	14800	7.8158
0.2079	14900	7.7777
0.2093	15000	7.8362
0.2107	15100	7.8387
0.2121	15200	7.8225
0.2135	15300	7.8627
0.2149	15400	7.8543
0.2163	15500	7.8096
0.2177	15600	7.8201
0.2191	15700	7.8178
0.2205	15800	7.8138
0.2219	15900	7.8384
0.2233	16000	7.7811
0.2247	16100	7.82
0.2261	16200	7.7731
0.2275	16300	7.8508
0.2288	16400	7.8087
0.2302	16500	7.7959
0.2316	16600	7.7857
0.2330	16700	7.7946
0.2344	16800	7.7884
0.2358	16900	7.8226
0.2372	17000	7.7811
0.2386	17100	7.778
0.2400	17200	7.7825
0.2414	17300	7.782
0.2428	17400	7.8164
0.2442	17500	7.7514
0.2456	17600	7.7744
0.2470	17700	7.7974
0.2484	17800	7.7913
0.2498	17900	7.757
0.2512	18000	7.7724
0.2526	18100	7.7772
0.2540	18200	7.7723
0.2554	18300	7.753
0.2568	18400	7.8055
0.2581	18500	7.7878
0.2595	18600	7.7822
0.2609	18700	7.7923
0.2623	18800	7.8378
0.2637	18900	7.8226
0.2651	19000	7.8015
0.2665	19100	7.7355
0.2679	19200	7.789
0.2693	19300	7.7473
0.2707	19400	7.7521
0.2721	19500	7.7867
0.2735	19600	7.7597
0.2749	19700	7.7506
0.2763	19800	7.732
0.2777	19900	7.7288
0.2791	20000	7.7317
0.2805	20100	7.7495
0.2819	20200	7.7236
0.2833	20300	7.7489
0.2847	20400	7.7592
0.2861	20500	7.7455
0.2875	20600	7.7623
0.2888	20700	7.7774
0.2902	20800	7.7485
0.2916	20900	7.7043
0.2930	21000	7.8039
0.2944	21100	7.7383
0.2958	21200	7.759
0.2972	21300	7.7362
0.2986	21400	7.7788
0.3000	21500	7.7244
0.3014	21600	7.72
0.3028	21700	7.7453
0.3042	21800	7.729
0.3056	21900	7.7735
0.3070	22000	7.7185
0.3084	22100	7.7641
0.3098	22200	7.7293
0.3112	22300	7.7401
0.3126	22400	7.725
0.3140	22500	7.7315
0.3154	22600	7.716
0.3168	22700	7.7576
0.3182	22800	7.7088
0.3195	22900	7.7428
0.3209	23000	7.7266
0.3223	23100	7.7246
0.3237	23200	7.7084
0.3251	23300	7.7094
0.3265	23400	7.7081
0.3279	23500	7.7472
0.3293	23600	7.7581
0.3307	23700	7.7264
0.3321	23800	7.7262
0.3335	23900	7.7252
0.3349	24000	7.7219
0.3363	24100	7.706
0.3377	24200	7.7372
0.3391	24300	7.6965
0.3405	24400	7.6865
0.3419	24500	7.6798
0.3433	24600	7.6962
0.3447	24700	7.701
0.3461	24800	7.6722
0.3475	24900	7.7453
0.3489	25000	7.6463
0.3502	25100	7.7256
0.3516	25200	7.693
0.3530	25300	7.7306
0.3544	25400	7.7037
0.3558	25500	7.6733
0.3572	25600	7.7202
0.3586	25700	7.6866
0.3600	25800	7.715
0.3614	25900	7.6925
0.3628	26000	7.6961
0.3642	26100	7.6752
0.3656	26200	7.7377
0.3670	26300	7.6744
0.3684	26400	7.6698
0.3698	26500	7.6931
0.3712	26600	7.6789
0.3726	26700	7.6736
0.3740	26800	7.6918
0.3754	26900	7.7129
0.3768	27000	7.7179
0.3782	27100	7.6747
0.3795	27200	7.6809
0.3809	27300	7.6803
0.3823	27400	7.6777
0.3837	27500	7.6702
0.3851	27600	7.7005
0.3865	27700	7.6671
0.3879	27800	7.6873
0.3893	27900	7.6919
0.3907	28000	7.6987
0.3921	28100	7.6641
0.3935	28200	7.6449
0.3949	28300	7.6715
0.3963	28400	7.6672
0.3977	28500	7.6796
0.3991	28600	7.7085
0.4005	28700	7.6557
0.4019	28800	7.6592
0.4033	28900	7.6695
0.4047	29000	7.6734
0.4061	29100	7.6499
0.4075	29200	7.6472
0.4089	29300	7.6705
0.4102	29400	7.6856
0.4116	29500	7.6474
0.4130	29600	7.6581
0.4144	29700	7.6699
0.4158	29800	7.6693
0.4172	29900	7.6716
0.4186	30000	7.6594
0.4200	30100	7.6391
0.4214	30200	7.6758
0.4228	30300	7.652
0.4242	30400	7.6312
0.4256	30500	7.6538
0.4270	30600	7.6959
0.4284	30700	7.7324
0.4298	30800	7.6529
0.4312	30900	7.6528
0.4326	31000	7.7036
0.4340	31100	7.6794
0.4354	31200	7.6603
0.4368	31300	7.6372
0.4382	31400	7.6427
0.4396	31500	7.6852
0.4409	31600	7.6987
0.4423	31700	7.6385
0.4437	31800	7.701
0.4451	31900	7.6702
0.4465	32000	7.6551
0.4479	32100	7.6464
0.4493	32200	7.667
0.4507	32300	7.628
0.4521	32400	7.7012
0.4535	32500	7.6333
0.4549	32600	7.6707
0.4563	32700	7.6304
0.4577	32800	7.6719
0.4591	32900	7.6744
0.4605	33000	7.7102
0.4619	33100	7.6918
0.4633	33200	7.7018
0.4647	33300	7.6131
0.4661	33400	7.6476
0.4675	33500	7.6594
0.4689	33600	7.6301
0.4703	33700	7.6134
0.4716	33800	7.7383
0.4730	33900	7.6253
0.4744	34000	7.662
0.4758	34100	7.6341
0.4772	34200	7.6622
0.4786	34300	7.6429
0.4800	34400	7.6777
0.4814	34500	7.6089
0.4828	34600	7.6382
0.4842	34700	7.6324
0.4856	34800	7.6176
0.4870	34900	7.624
0.4884	35000	7.6163
0.4898	35100	7.6503
0.4912	35200	7.6609
0.4926	35300	7.6587
0.4940	35400	7.5999
0.4954	35500	7.586
0.4968	35600	7.6585
0.4982	35700	7.7349
0.4996	35800	7.642
0.5009	35900	7.646
0.5023	36000	7.5942
0.5037	36100	7.6477
0.5051	36200	7.6259
0.5065	36300	7.5926
0.5079	36400	7.6166
0.5093	36500	7.6323
0.5107	36600	7.6324
0.5121	36700	7.6411
0.5135	36800	7.6343
0.5149	36900	7.6313
0.5163	37000	7.6187
0.5177	37100	7.6545
0.5191	37200	7.6555
0.5205	37300	7.6984
0.5219	37400	7.6638
0.5233	37500	7.6093
0.5247	37600	7.5925
0.5261	37700	7.6281
0.5275	37800	7.6349
0.5289	37900	7.6152
0.5303	38000	7.6531
0.5316	38100	7.6078
0.5330	38200	7.6775
0.5344	38300	7.6268
0.5358	38400	7.641
0.5372	38500	7.6721
0.5386	38600	7.6069
0.5400	38700	7.6174
0.5414	38800	7.6407
0.5428	38900	7.6226
0.5442	39000	7.5843
0.5456	39100	7.6588
0.5470	39200	7.6405
0.5484	39300	7.5908
0.5498	39400	7.6203
0.5512	39500	7.608
0.5526	39600	7.6177
0.5540	39700	7.606
0.5554	39800	7.7102
0.5568	39900	7.6252
0.5582	40000	7.6235
0.5596	40100	7.6325
0.5610	40200	7.6146
0.5623	40300	7.6386
0.5637	40400	7.6189
0.5651	40500	7.638
0.5665	40600	7.5859
0.5679	40700	7.5737
0.5693	40800	7.6331
0.5707	40900	7.6265
0.5721	41000	7.6475
0.5735	41100	7.5966
0.5749	41200	7.6331
0.5763	41300	7.5655
0.5777	41400	7.6727
0.5791	41500	7.5972
0.5805	41600	7.5911
0.5819	41700	7.6734
0.5833	41800	7.6528
0.5847	41900	7.6063
0.5861	42000	7.6496
0.5875	42100	7.6225
0.5889	42200	7.6863
0.5903	42300	7.6145
0.5916	42400	7.6072
0.5930	42500	7.625
0.5944	42600	7.6087
0.5958	42700	7.6622
0.5972	42800	7.5619
0.5986	42900	7.6563
0.6000	43000	7.5958
0.6014	43100	7.6107
0.6028	43200	7.6208
0.6042	43300	7.5973
0.6056	43400	7.5928
0.6070	43500	7.637
0.6084	43600	7.5659
0.6098	43700	7.5921
0.6112	43800	7.5961
0.6126	43900	7.5614
0.6140	44000	7.6366
0.6154	44100	7.5947
0.6168	44200	7.5976
0.6182	44300	7.6406
0.6196	44400	7.585
0.6210	44500	7.5722
0.6223	44600	7.6193
0.6237	44700	7.6249
0.6251	44800	7.6208
0.6265	44900	7.6293
0.6279	45000	7.6023
0.6293	45100	7.5996
0.6307	45200	7.5553
0.6321	45300	7.5996
0.6335	45400	7.5994
0.6349	45500	7.6691
0.6363	45600	7.6051
0.6377	45700	7.6589
0.6391	45800	7.6217
0.6405	45900	7.6053
0.6419	46000	7.6082
0.6433	46100	7.5913
0.6447	46200	7.5742
0.6461	46300	7.597
0.6475	46400	7.5759
0.6489	46500	7.5964
0.6503	46600	7.6719
0.6517	46700	7.605
0.6530	46800	7.5705
0.6544	46900	7.6292
0.6558	47000	7.5978
0.6572	47100	7.5525
0.6586	47200	7.5838
0.6600	47300	7.5672
0.6614	47400	7.6041
0.6628	47500	7.6255
0.6642	47600	7.5415
0.6656	47700	7.61
0.6670	47800	7.573
0.6684	47900	7.6413
0.6698	48000	7.6277
0.6712	48100	7.5903
0.6726	48200	7.6542
0.6740	48300	7.5772
0.6754	48400	7.5991
0.6768	48500	7.5853
0.6782	48600	7.5909
0.6796	48700	7.5912
0.6810	48800	7.6052
0.6824	48900	7.632
0.6837	49000	7.5851
0.6851	49100	7.6688
0.6865	49200	7.6091
0.6879	49300	7.5745
0.6893	49400	7.5833
0.6907	49500	7.5777
0.6921	49600	7.5637
0.6935	49700	7.5622
0.6949	49800	7.5633
0.6963	49900	7.6023
0.6977	50000	7.6103
0.6991	50100	7.547
0.7005	50200	7.5907
0.7019	50300	7.5882
0.7033	50400	7.5875
0.7047	50500	7.5909
0.7061	50600	7.6021
0.7075	50700	7.549
0.7089	50800	7.6511
0.7103	50900	7.6606
0.7117	51000	7.5967
0.7130	51100	7.5722
0.7144	51200	7.6129
0.7158	51300	7.5736
0.7172	51400	7.5799
0.7186	51500	7.6209
0.7200	51600	7.595
0.7214	51700	7.5484
0.7228	51800	7.5999
0.7242	51900	7.5638
0.7256	52000	7.5654
0.7270	52100	7.6303
0.7284	52200	7.5485
0.7298	52300	7.676
0.7312	52400	7.6376
0.7326	52500	7.557
0.7340	52600	7.5631
0.7354	52700	7.6637
0.7368	52800	7.588
0.7382	52900	7.5771
0.7396	53000	7.5766
0.7410	53100	7.5731
0.7424	53200	7.508
0.7437	53300	7.6023
0.7451	53400	7.5796
0.7465	53500	7.5593
0.7479	53600	7.5516
0.7493	53700	7.5973
0.7507	53800	7.5868
0.7521	53900	7.623
0.7535	54000	7.5972
0.7549	54100	7.6304
0.7563	54200	7.5927
0.7577	54300	7.5351
0.7591	54400	7.5732
0.7605	54500	7.6676
0.7619	54600	7.6103
0.7633	54700	7.5572
0.7647	54800	7.574
0.7661	54900	7.555
0.7675	55000	7.6347
0.7689	55100	7.5827
0.7703	55200	7.678
0.7717	55300	7.5577
0.7731	55400	7.5606
0.7744	55500	7.5284
0.7758	55600	7.5561
0.7772	55700	7.6569
0.7786	55800	7.5604
0.7800	55900	7.6444
0.7814	56000	7.602
0.7828	56100	7.5532
0.7842	56200	7.5524
0.7856	56300	7.654
0.7870	56400	7.5799
0.7884	56500	7.5609
0.7898	56600	7.5625
0.7912	56700	7.571
0.7926	56800	7.5126
0.7940	56900	7.5644
0.7954	57000	7.5508
0.7968	57100	7.5183
0.7982	57200	7.5749
0.7996	57300	7.5339
0.8010	57400	7.5739
0.8024	57500	7.5492
0.8038	57600	7.5781
0.8051	57700	7.5753
0.8065	57800	7.5485
0.8079	57900	7.5608
0.8093	58000	7.5515
0.8107	58100	7.6011
0.8121	58200	7.6072
0.8135	58300	7.5615
0.8149	58400	7.5583
0.8163	58500	7.5423
0.8177	58600	7.5852
0.8191	58700	7.5612
0.8205	58800	7.5808
0.8219	58900	7.5888
0.8233	59000	7.6449
0.8247	59100	7.6599
0.8261	59200	7.573
0.8275	59300	7.5533
0.8289	59400	7.5423
0.8303	59500	7.5879
0.8317	59600	7.5699
0.8331	59700	7.5792
0.8344	59800	7.5552
0.8358	59900	7.5982
0.8372	60000	7.5984
0.8386	60100	7.5383
0.8400	60200	7.5518
0.8414	60300	7.5587
0.8428	60400	7.5152
0.8442	60500	7.5945
0.8456	60600	7.5674
0.8470	60700	7.5527
0.8484	60800	7.5941
0.8498	60900	7.5964
0.8512	61000	7.5625
0.8526	61100	7.5526
0.8540	61200	7.5592
0.8554	61300	7.5593
0.8568	61400	7.5392
0.8582	61500	7.641
0.8596	61600	7.6258
0.8610	61700	7.6588
0.8624	61800	7.5707
0.8638	61900	7.5171
0.8651	62000	7.6107
0.8665	62100	7.6272
0.8679	62200	7.5549
0.8693	62300	7.5535
0.8707	62400	7.6454
0.8721	62500	7.5498
0.8735	62600	7.5898
0.8749	62700	7.5461
0.8763	62800	7.5611
0.8777	62900	7.6068
0.8791	63000	7.6001
0.8805	63100	7.5407
0.8819	63200	7.5961
0.8833	63300	7.5839
0.8847	63400	7.5426
0.8861	63500	7.6011
0.8875	63600	7.5708
0.8889	63700	7.5964
0.8903	63800	7.5704
0.8917	63900	7.5372
0.8931	64000	7.5835
0.8945	64100	7.5483
0.8958	64200	7.544
0.8972	64300	7.5677
0.8986	64400	7.5636
0.9000	64500	7.5914
0.9014	64600	7.5789
0.9028	64700	7.5666
0.9042	64800	7.5866
0.9056	64900	7.6195
0.9070	65000	7.5388
0.9084	65100	7.5821
0.9098	65200	7.6767
0.9112	65300	7.6625
0.9126	65400	7.5812
0.9140	65500	7.5026
0.9154	65600	7.5524
0.9168	65700	7.5851
0.9182	65800	7.5762
0.9196	65900	7.5466
0.9210	66000	7.6039
0.9224	66100	7.6041
0.9238	66200	7.5805
0.9252	66300	7.6334
0.9265	66400	7.5348
0.9279	66500	7.6065
0.9293	66600	7.5003
0.9307	66700	7.5512
0.9321	66800	7.5404
0.9335	66900	7.6176
0.9349	67000	7.5634
0.9363	67100	7.5786
0.9377	67200	7.6327
0.9391	67300	7.5532
0.9405	67400	7.5362
0.9419	67500	7.5844
0.9433	67600	7.5632
0.9447	67700	7.553
0.9461	67800	7.5422
0.9475	67900	7.5483
0.9489	68000	7.5477
0.9503	68100	7.5423
0.9517	68200	7.5656
0.9531	68300	7.5573
0.9545	68400	7.525
0.9558	68500	7.55
0.9572	68600	7.5341
0.9586	68700	7.5318
0.9600	68800	7.5691
0.9614	68900	7.5793
0.9628	69000	7.5615
0.9642	69100	7.5348
0.9656	69200	7.5384
0.9670	69300	7.5392
0.9684	69400	7.5909
0.9698	69500	7.5587
0.9712	69600	7.5447
0.9726	69700	7.5731
0.9740	69800	7.5767
0.9754	69900	7.6208
0.9768	70000	7.5414
0.9782	70100	7.6061
0.9796	70200	7.6285
0.9810	70300	7.5533
0.9824	70400	7.5552
0.9838	70500	7.5479
0.9852	70600	7.571
0.9865	70700	7.6259
0.9879	70800	7.6366
0.9893	70900	7.5615
0.9907	71000	7.612
0.9921	71100	7.5309
0.9935	71200	7.5122
0.9949	71300	7.5692
0.9963	71400	7.6198
0.9977	71500	7.527
0.9991	71600	7.5496

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},
}