pairs_with_scores_sampled_category_v25.1

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 = [
    'nightshirt',
    'transmissionsystemblobcorewindowsnetimageslarge6143417e77f63a4025280c65951e9758ejpg',
    'cuffed jacket',
]
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
0.0015	100	11.8602
0.0029	200	11.7216
0.0044	300	11.6593
0.0058	400	11.2427
0.0073	500	10.9864
0.0087	600	10.4159
0.0102	700	10.1391
0.0116	800	9.7647
0.0131	900	9.4895
0.0145	1000	9.1788
0.0160	1100	8.9537
0.0175	1200	8.8094
0.0189	1300	8.6597
0.0204	1400	8.6046
0.0218	1500	8.5694
0.0233	1600	8.5332
0.0247	1700	8.5136
0.0262	1800	8.5075
0.0276	1900	8.4926
0.0291	2000	8.481
0.0305	2100	8.4637
0.0320	2200	8.4412
0.0335	2300	8.4357
0.0349	2400	8.4283
0.0364	2500	8.3974
0.0378	2600	8.4075
0.0393	2700	8.3904
0.0407	2800	8.4059
0.0422	2900	8.3853
0.0436	3000	8.3607
0.0451	3100	8.357
0.0465	3200	8.3447
0.0480	3300	8.3308
0.0495	3400	8.3278
0.0509	3500	8.305
0.0524	3600	8.2994
0.0538	3700	8.2947
0.0553	3800	8.2944
0.0567	3900	8.3156
0.0582	4000	8.2708
0.0596	4100	8.2858
0.0611	4200	8.261
0.0625	4300	8.2635
0.0640	4400	8.2564
0.0655	4500	8.2542
0.0669	4600	8.2483
0.0684	4700	8.2497
0.0698	4800	8.2368
0.0713	4900	8.2278
0.0727	5000	8.2014
0.0742	5100	8.2033
0.0756	5200	8.214
0.0771	5300	8.1914
0.0786	5400	8.1918
0.0800	5500	8.1882
0.0815	5600	8.2037
0.0829	5700	8.1668
0.0844	5800	8.1869
0.0858	5900	8.1763
0.0873	6000	8.1653
0.0887	6100	8.1595
0.0902	6200	8.1446
0.0916	6300	8.1601
0.0931	6400	8.1325
0.0946	6500	8.1373
0.0960	6600	8.1387
0.0975	6700	8.131
0.0989	6800	8.1227
0.1004	6900	8.1347
0.1018	7000	8.1263
0.1033	7100	8.1041
0.1047	7200	8.1196
0.1062	7300	8.0965
0.1076	7400	8.105
0.1091	7500	8.084
0.1106	7600	8.0841
0.1120	7700	8.0686
0.1135	7800	8.0898
0.1149	7900	8.1081
0.1164	8000	8.098
0.1178	8100	8.0614
0.1193	8200	8.0525
0.1207	8300	8.0432
0.1222	8400	8.0527
0.1236	8500	8.0269
0.1251	8600	8.0581
0.1266	8700	8.0562
0.1280	8800	8.0189
0.1295	8900	8.0266
0.1309	9000	8.0053
0.1324	9100	8.0308
0.1338	9200	7.9927
0.1353	9300	8.0196
0.1367	9400	8.0113
0.1382	9500	7.9962
0.1396	9600	8.0227
0.1411	9700	8.0201
0.1426	9800	7.9938
0.1440	9900	7.9907
0.1455	10000	7.9705
0.1469	10100	7.9978
0.1484	10200	7.9897
0.1498	10300	7.984
0.1513	10400	7.9899
0.1527	10500	7.9589
0.1542	10600	7.9623
0.1556	10700	7.9792
0.1571	10800	7.9819
0.1586	10900	7.9463
0.1600	11000	7.9572
0.1615	11100	7.9844
0.1629	11200	7.9502
0.1644	11300	7.9678
0.1658	11400	7.941
0.1673	11500	7.9533
0.1687	11600	7.9356
0.1702	11700	7.9397
0.1716	11800	7.951
0.1731	11900	7.928
0.1746	12000	7.9394
0.1760	12100	7.9486
0.1775	12200	7.9371
0.1789	12300	7.9381
0.1804	12400	7.9412
0.1818	12500	7.9484
0.1833	12600	7.913
0.1847	12700	7.9049
0.1862	12800	7.902
0.1876	12900	7.9318
0.1891	13000	7.9247
0.1906	13100	7.9385
0.1920	13200	7.9145
0.1935	13300	7.9085
0.1949	13400	7.9047
0.1964	13500	7.9235
0.1978	13600	7.8917
0.1993	13700	7.8821
0.2007	13800	7.9088
0.2022	13900	7.9222
0.2036	14000	7.9097
0.2051	14100	7.9239
0.2066	14200	7.9257
0.2080	14300	7.8609
0.2095	14400	7.8979
0.2109	14500	7.8715
0.2124	14600	7.8858
0.2138	14700	7.8801
0.2153	14800	7.8843
0.2167	14900	7.8803
0.2182	15000	7.87
0.2196	15100	7.8729
0.2211	15200	7.8776
0.2226	15300	7.8641
0.2240	15400	7.8444
0.2255	15500	7.8474
0.2269	15600	7.8427
0.2284	15700	7.8283
0.2298	15800	7.8693
0.2313	15900	7.8275
0.2327	16000	7.8454
0.2342	16100	7.8655
0.2357	16200	7.8437
0.2371	16300	7.8574
0.2386	16400	7.8375
0.2400	16500	7.8213
0.2415	16600	7.8416
0.2429	16700	7.8572
0.2444	16800	7.8189
0.2458	16900	7.8553
0.2473	17000	7.8437
0.2487	17100	7.8429
0.2502	17200	7.8307
0.2517	17300	7.8619
0.2531	17400	7.8341
0.2546	17500	7.8194
0.2560	17600	7.8229
0.2575	17700	7.8316
0.2589	17800	7.8226
0.2604	17900	7.8359
0.2618	18000	7.8097
0.2633	18100	7.8206
0.2647	18200	7.8225
0.2662	18300	7.842
0.2677	18400	7.812
0.2691	18500	7.832
0.2706	18600	7.7932
0.2720	18700	7.8192
0.2735	18800	7.7994
0.2749	18900	7.8377
0.2764	19000	7.7911
0.2778	19100	7.8073
0.2793	19200	7.8066
0.2807	19300	7.8112
0.2822	19400	7.7903
0.2837	19500	7.8024
0.2851	19600	7.8045
0.2866	19700	7.7898
0.2880	19800	7.8178
0.2895	19900	7.7921
0.2909	20000	7.804
0.2924	20100	7.8012
0.2938	20200	7.7657
0.2953	20300	7.7882
0.2967	20400	7.7769
0.2982	20500	7.7674
0.2997	20600	7.824
0.3011	20700	7.7837
0.3026	20800	7.7727
0.3040	20900	7.7851
0.3055	21000	7.7821
0.3069	21100	7.7811
0.3084	21200	7.7844
0.3098	21300	7.7764
0.3113	21400	7.7723
0.3127	21500	7.7761
0.3142	21600	7.7901
0.3157	21700	7.7512
0.3171	21800	7.7804
0.3186	21900	7.7995
0.3200	22000	7.758
0.3215	22100	7.7482
0.3229	22200	7.7581
0.3244	22300	7.784
0.3258	22400	7.7666
0.3273	22500	7.7252
0.3287	22600	7.7722
0.3302	22700	7.752
0.3317	22800	7.7552
0.3331	22900	7.7523
0.3346	23000	7.7415
0.3360	23100	7.7278
0.3375	23200	7.7799
0.3389	23300	7.7619
0.3404	23400	7.7518
0.3418	23500	7.7593
0.3433	23600	7.7667
0.3447	23700	7.7765
0.3462	23800	7.7532
0.3477	23900	7.7316
0.3491	24000	7.7692
0.3506	24100	7.761
0.3520	24200	7.7848
0.3535	24300	7.7424
0.3549	24400	7.7288
0.3564	24500	7.7187
0.3578	24600	7.7355
0.3593	24700	7.7431
0.3607	24800	7.7402
0.3622	24900	7.7403
0.3637	25000	7.741
0.3651	25100	7.7246
0.3666	25200	7.7434
0.3680	25300	7.7243
0.3695	25400	7.725
0.3709	25500	7.7558
0.3724	25600	7.7186
0.3738	25700	7.7164
0.3753	25800	7.7185
0.3767	25900	7.7509
0.3782	26000	7.7382
0.3797	26100	7.7353
0.3811	26200	7.7349
0.3826	26300	7.7423
0.3840	26400	7.7139
0.3855	26500	7.7368
0.3869	26600	7.71
0.3884	26700	7.7289
0.3898	26800	7.718
0.3913	26900	7.6944
0.3928	27000	7.7078
0.3942	27100	7.6891
0.3957	27200	7.6911
0.3971	27300	7.6984
0.3986	27400	7.7028
0.4000	27500	7.7264
0.4015	27600	7.6954
0.4029	27700	7.7205
0.4044	27800	7.7098
0.4058	27900	7.6819
0.4073	28000	7.7044
0.4088	28100	7.737
0.4102	28200	7.7023
0.4117	28300	7.7074
0.4131	28400	7.7069
0.4146	28500	7.6934
0.4160	28600	7.7025
0.4175	28700	7.6982
0.4189	28800	7.6765
0.4204	28900	7.6995
0.4218	29000	7.6893
0.4233	29100	7.6871
0.4248	29200	7.6998
0.4262	29300	7.715
0.4277	29400	7.6918
0.4291	29500	7.7161
0.4306	29600	7.6882
0.4320	29700	7.6933
0.4335	29800	7.7069
0.4349	29900	7.6688
0.4364	30000	7.7008
0.4378	30100	7.7052
0.4393	30200	7.6717
0.4408	30300	7.658
0.4422	30400	7.6657
0.4437	30500	7.705
0.4451	30600	7.6998
0.4466	30700	7.6554
0.4480	30800	7.6635
0.4495	30900	7.6691
0.4509	31000	7.6684
0.4524	31100	7.6752
0.4538	31200	7.6819
0.4553	31300	7.6552
0.4568	31400	7.653
0.4582	31500	7.6837
0.4597	31600	7.7052
0.4611	31700	7.6829
0.4626	31800	7.673
0.4640	31900	7.663
0.4655	32000	7.6856
0.4669	32100	7.6509
0.4684	32200	7.6927
0.4698	32300	7.6733
0.4713	32400	7.6683
0.4728	32500	7.6534
0.4742	32600	7.6824
0.4757	32700	7.6764
0.4771	32800	7.6644
0.4786	32900	7.6558
0.4800	33000	7.6549
0.4815	33100	7.6619
0.4829	33200	7.6637
0.4844	33300	7.6555
0.4858	33400	7.6713
0.4873	33500	7.664
0.4888	33600	7.6656
0.4902	33700	7.6753
0.4917	33800	7.6734
0.4931	33900	7.6821
0.4946	34000	7.6878
0.4960	34100	7.7055
0.4975	34200	7.6692
0.4989	34300	7.6319
0.5004	34400	7.6731
0.5018	34500	7.6711
0.5033	34600	7.6613
0.5048	34700	7.6558
0.5062	34800	7.6425
0.5077	34900	7.6678
0.5091	35000	7.6879
0.5106	35100	7.6903
0.5120	35200	7.6729
0.5135	35300	7.6648
0.5149	35400	7.6755
0.5164	35500	7.664
0.5178	35600	7.6395
0.5193	35700	7.6526
0.5208	35800	7.6476
0.5222	35900	7.6749
0.5237	36000	7.6631
0.5251	36100	7.6203
0.5266	36200	7.6308
0.5280	36300	7.6642
0.5295	36400	7.635
0.5309	36500	7.6743
0.5324	36600	7.6552
0.5338	36700	7.6723
0.5353	36800	7.6467
0.5368	36900	7.6547
0.5382	37000	7.6143
0.5397	37100	7.6579
0.5411	37200	7.6442
0.5426	37300	7.646
0.5440	37400	7.612
0.5455	37500	7.6048
0.5469	37600	7.6505
0.5484	37700	7.6281
0.5499	37800	7.6104
0.5513	37900	7.6369
0.5528	38000	7.656
0.5542	38100	7.6551
0.5557	38200	7.5997
0.5571	38300	7.6406
0.5586	38400	7.6538
0.5600	38500	7.6134
0.5615	38600	7.625
0.5629	38700	7.6422
0.5644	38800	7.632
0.5659	38900	7.63
0.5673	39000	7.6069
0.5688	39100	7.6307
0.5702	39200	7.6382
0.5717	39300	7.6192
0.5731	39400	7.6329
0.5746	39500	7.6294
0.5760	39600	7.6376
0.5775	39700	7.5998
0.5789	39800	7.6327
0.5804	39900	7.6354
0.5819	40000	7.6837
0.5833	40100	7.629
0.5848	40200	7.61
0.5862	40300	7.6484
0.5877	40400	7.6285
0.5891	40500	7.6222
0.5906	40600	7.5971
0.5920	40700	7.6186
0.5935	40800	7.5981
0.5949	40900	7.6311
0.5964	41000	7.6138
0.5979	41100	7.5906
0.5993	41200	7.6435
0.6008	41300	7.6084
0.6022	41400	7.5943
0.6037	41500	7.6376
0.6051	41600	7.6174
0.6066	41700	7.6027
0.6080	41800	7.6181
0.6095	41900	7.5849
0.6109	42000	7.5979
0.6124	42100	7.6031
0.6139	42200	7.6162
0.6153	42300	7.5856
0.6168	42400	7.6027
0.6182	42500	7.6012
0.6197	42600	7.6118
0.6211	42700	7.5993
0.6226	42800	7.5932
0.6240	42900	7.6122
0.6255	43000	7.583
0.6269	43100	7.5756
0.6284	43200	7.5786
0.6299	43300	7.6117
0.6313	43400	7.5862
0.6328	43500	7.6137
0.6342	43600	7.6618
0.6357	43700	7.6173
0.6371	43800	7.5769
0.6386	43900	7.5763
0.6400	44000	7.5893
0.6415	44100	7.6219
0.6429	44200	7.6047
0.6444	44300	7.6096
0.6459	44400	7.559
0.6473	44500	7.6262
0.6488	44600	7.5978
0.6502	44700	7.5784
0.6517	44800	7.604
0.6531	44900	7.5889
0.6546	45000	7.6344
0.6560	45100	7.576
0.6575	45200	7.6283
0.6589	45300	7.5998
0.6604	45400	7.571
0.6619	45500	7.6018
0.6633	45600	7.5657
0.6648	45700	7.594
0.6662	45800	7.6216
0.6677	45900	7.5748
0.6691	46000	7.632
0.6706	46100	7.6235
0.6720	46200	7.613
0.6735	46300	7.6356
0.6749	46400	7.5962
0.6764	46500	7.6147
0.6779	46600	7.6005
0.6793	46700	7.6105
0.6808	46800	7.6253
0.6822	46900	7.5691
0.6837	47000	7.5765
0.6851	47100	7.5955
0.6866	47200	7.6008
0.6880	47300	7.5861
0.6895	47400	7.5986
0.6909	47500	7.5651
0.6924	47600	7.5944
0.6939	47700	7.5776
0.6953	47800	7.5993
0.6968	47900	7.6055
0.6982	48000	7.6045
0.6997	48100	7.5867
0.7011	48200	7.5839
0.7026	48300	7.6065
0.7040	48400	7.578
0.7055	48500	7.5889
0.7070	48600	7.5872
0.7084	48700	7.604
0.7099	48800	7.5963
0.7113	48900	7.5951
0.7128	49000	7.5475
0.7142	49100	7.5636
0.7157	49200	7.5871
0.7171	49300	7.5919
0.7186	49400	7.5933
0.7200	49500	7.5829
0.7215	49600	7.5916
0.7230	49700	7.594
0.7244	49800	7.6107
0.7259	49900	7.5942
0.7273	50000	7.5985
0.7288	50100	7.5877
0.7302	50200	7.5676
0.7317	50300	7.6106
0.7331	50400	7.5795
0.7346	50500	7.5802
0.7360	50600	7.6148
0.7375	50700	7.5986
0.7390	50800	7.6037
0.7404	50900	7.6099
0.7419	51000	7.5655
0.7433	51100	7.5681
0.7448	51200	7.5756
0.7462	51300	7.5865
0.7477	51400	7.5289
0.7491	51500	7.559
0.7506	51600	7.5807
0.7520	51700	7.6295
0.7535	51800	7.5576
0.7550	51900	7.5506
0.7564	52000	7.5683
0.7579	52100	7.5839
0.7593	52200	7.5811
0.7608	52300	7.5813
0.7622	52400	7.5665
0.7637	52500	7.5707
0.7651	52600	7.5912
0.7666	52700	7.577
0.7680	52800	7.5317
0.7695	52900	7.5919
0.7710	53000	7.554
0.7724	53100	7.6078
0.7739	53200	7.5386
0.7753	53300	7.5686
0.7768	53400	7.5793
0.7782	53500	7.5721
0.7797	53600	7.5385
0.7811	53700	7.5955
0.7826	53800	7.5843
0.7840	53900	7.5854
0.7855	54000	7.5418
0.7870	54100	7.5546
0.7884	54200	7.5476
0.7899	54300	7.5445
0.7913	54400	7.5509
0.7928	54500	7.5683
0.7942	54600	7.5608
0.7957	54700	7.5546
0.7971	54800	7.5501
0.7986	54900	7.5611
0.8000	55000	7.5574
0.8015	55100	7.5608
0.8030	55200	7.5148
0.8044	55300	7.5546
0.8059	55400	7.6024
0.8073	55500	7.5553
0.8088	55600	7.5889
0.8102	55700	7.5914
0.8117	55800	7.5508
0.8131	55900	7.5768
0.8146	56000	7.5507
0.8160	56100	7.5478
0.8175	56200	7.5717
0.8190	56300	7.5889
0.8204	56400	7.5992
0.8219	56500	7.5502
0.8233	56600	7.5449
0.8248	56700	7.5299
0.8262	56800	7.5695
0.8277	56900	7.5512
0.8291	57000	7.5541
0.8306	57100	7.5615
0.8320	57200	7.4957
0.8335	57300	7.5347
0.8350	57400	7.5837
0.8364	57500	7.5441
0.8379	57600	7.5536
0.8393	57700	7.5935
0.8408	57800	7.5702
0.8422	57900	7.5797
0.8437	58000	7.5749
0.8451	58100	7.5805
0.8466	58200	7.563
0.8480	58300	7.5978
0.8495	58400	7.5548
0.8510	58500	7.5726
0.8524	58600	7.5703
0.8539	58700	7.5534
0.8553	58800	7.5141
0.8568	58900	7.5804
0.8582	59000	7.593
0.8597	59100	7.5755
0.8611	59200	7.551
0.8626	59300	7.5507
0.8641	59400	7.5729
0.8655	59500	7.561
0.8670	59600	7.5672
0.8684	59700	7.5319
0.8699	59800	7.5108
0.8713	59900	7.5568
0.8728	60000	7.5188
0.8742	60100	7.5544
0.8757	60200	7.5459
0.8771	60300	7.5412
0.8786	60400	7.5335
0.8801	60500	7.5408
0.8815	60600	7.5704
0.8830	60700	7.5393
0.8844	60800	7.5455
0.8859	60900	7.5546
0.8873	61000	7.5681
0.8888	61100	7.5528
0.8902	61200	7.5816
0.8917	61300	7.5712
0.8931	61400	7.5562
0.8946	61500	7.5257
0.8961	61600	7.5358
0.8975	61700	7.5591
0.8990	61800	7.5432
0.9004	61900	7.516
0.9019	62000	7.553
0.9033	62100	7.5509
0.9048	62200	7.5174
0.9062	62300	7.5811
0.9077	62400	7.5467
0.9091	62500	7.5149
0.9106	62600	7.5709
0.9121	62700	7.5227
0.9135	62800	7.5552
0.9150	62900	7.5362
0.9164	63000	7.5828
0.9179	63100	7.545
0.9193	63200	7.5135
0.9208	63300	7.5505
0.9222	63400	7.5479
0.9237	63500	7.5511
0.9251	63600	7.5632
0.9266	63700	7.5675
0.9281	63800	7.5714
0.9295	63900	7.5368
0.9310	64000	7.5039
0.9324	64100	7.5821
0.9339	64200	7.5618
0.9353	64300	7.5293
0.9368	64400	7.559
0.9382	64500	7.5266
0.9397	64600	7.5697
0.9411	64700	7.5148
0.9426	64800	7.5597
0.9441	64900	7.5181
0.9455	65000	7.5382
0.9470	65100	7.5164
0.9484	65200	7.5812
0.9499	65300	7.5613
0.9513	65400	7.5138
0.9528	65500	7.5606
0.9542	65600	7.5332
0.9557	65700	7.5441
0.9571	65800	7.5422
0.9586	65900	7.5548
0.9601	66000	7.5772
0.9615	66100	7.5536
0.9630	66200	7.5574
0.9644	66300	7.5567
0.9659	66400	7.5331
0.9673	66500	7.5313
0.9688	66600	7.5109
0.9702	66700	7.5411
0.9717	66800	7.5744
0.9731	66900	7.5378
0.9746	67000	7.529
0.9761	67100	7.5418
0.9775	67200	7.5516
0.9790	67300	7.5621
0.9804	67400	7.5186
0.9819	67500	7.5614
0.9833	67600	7.538
0.9848	67700	7.5508
0.9862	67800	7.589
0.9877	67900	7.5203
0.9891	68000	7.536
0.9906	68100	7.5473
0.9921	68200	7.5972
0.9935	68300	7.5323
0.9950	68400	7.5456
0.9964	68500	7.5457
0.9979	68600	7.5337
0.9993	68700	7.5216

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},
}