all-MiniLM-L6-v9-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v8 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_three_scores_v8
• 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 = [
    'pasabah',
    'thermos mug',
    'sports tracksuit',
]
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, 0.8317, 0.6751],
#         [0.8317, 1.0000, 0.7012],
#         [0.6751, 0.7012, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v8

• Dataset: pairs_three_scores_v8 at 7e8a1e6
• Size: 9,164,180 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: 5.6 tokens max: 20 tokens	min: 3 tokens mean: 5.79 tokens max: 24 tokens	min: 0.15 mean: 0.43 max: 1.0

• Samples:

  sentence1	sentence2	score
  booster face cleanser	pizza cutter	0.24
  line sinker	accessories	1.0
  tricovel	cot bed mattress protector	0.28

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v8

• Dataset: pairs_three_scores_v8 at 7e8a1e6
• Size: 46,052 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: 5.66 tokens max: 21 tokens	min: 3 tokens mean: 5.6 tokens max: 41 tokens	min: 0.15 mean: 0.42 max: 1.0

• Samples:

  sentence1	sentence2	score
  printed set	crushed outfit	1.0
  value	eva cosmetics serum	0.23
  zino shakes	candy	0.27

• 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
0.0014	100	12.0868
0.0028	200	11.6909
0.0042	300	11.6708
0.0056	400	11.0891
0.0070	500	10.6572
0.0084	600	10.3743
0.0098	700	10.1343
0.0112	800	9.8599
0.0126	900	9.6081
0.0140	1000	9.279
0.0154	1100	9.0853
0.0168	1200	8.8411
0.0182	1300	8.7139
0.0196	1400	8.6466
0.0210	1500	8.5972
0.0223	1600	8.5773
0.0237	1700	8.5516
0.0251	1800	8.5211
0.0265	1900	8.5185
0.0279	2000	8.5054
0.0293	2100	8.4975
0.0307	2200	8.4673
0.0321	2300	8.4779
0.0335	2400	8.4543
0.0349	2500	8.4363
0.0363	2600	8.4421
0.0377	2700	8.4267
0.0391	2800	8.4111
0.0405	2900	8.4245
0.0419	3000	8.3958
0.0433	3100	8.3894
0.0447	3200	8.3711
0.0461	3300	8.3785
0.0475	3400	8.3831
0.0489	3500	8.3727
0.0503	3600	8.3673
0.0517	3700	8.3408
0.0531	3800	8.3389
0.0545	3900	8.3482
0.0559	4000	8.3351
0.0573	4100	8.3255
0.0587	4200	8.3111
0.0601	4300	8.3122
0.0615	4400	8.3078
0.0629	4500	8.2959
0.0642	4600	8.2769
0.0656	4700	8.3087
0.0670	4800	8.2688
0.0684	4900	8.265
0.0698	5000	8.2562
0.0712	5100	8.2535
0.0726	5200	8.2526
0.0740	5300	8.2508
0.0754	5400	8.2453
0.0768	5500	8.2459
0.0782	5600	8.2298
0.0796	5700	8.2516
0.0810	5800	8.2284
0.0824	5900	8.2286
0.0838	6000	8.2158
0.0852	6100	8.2069
0.0866	6200	8.2051
0.0880	6300	8.1962
0.0894	6400	8.1916
0.0908	6500	8.2049
0.0922	6600	8.1833
0.0936	6700	8.173
0.0950	6800	8.1915
0.0964	6900	8.1757
0.0978	7000	8.163
0.0992	7100	8.1686
0.1006	7200	8.1532
0.1020	7300	8.1675
0.1034	7400	8.1389
0.1048	7500	8.131
0.1062	7600	8.1373
0.1075	7700	8.1451
0.1089	7800	8.1322
0.1103	7900	8.1343
0.1117	8000	8.121
0.1131	8100	8.1268
0.1145	8200	8.1238
0.1159	8300	8.1031
0.1173	8400	8.1116
0.1187	8500	8.1188
0.1201	8600	8.1112
0.1215	8700	8.087
0.1229	8800	8.0927
0.1243	8900	8.094
0.1257	9000	8.0809
0.1271	9100	8.0611
0.1285	9200	8.0846
0.1299	9300	8.0797
0.1313	9400	8.0445
0.1327	9500	8.073
0.1341	9600	8.0916
0.1355	9700	8.0523
0.1369	9800	8.0561
0.1383	9900	8.0524
0.1397	10000	8.0444
0.1411	10100	8.0722
0.1425	10200	8.0399
0.1439	10300	8.0502
0.1453	10400	8.0529
0.1467	10500	8.0426
0.1481	10600	8.0253
0.1494	10700	8.0427
0.1508	10800	8.0155
0.1522	10900	8.01
0.1536	11000	8.0176
0.1550	11100	8.0369
0.1564	11200	8.0222
0.1578	11300	8.0243
0.1592	11400	8.0045
0.1606	11500	7.9829
0.1620	11600	8.0131
0.1634	11700	8.0041
0.1648	11800	8.0254
0.1662	11900	8.0208
0.1676	12000	7.9967
0.1690	12100	7.9783
0.1704	12200	7.98
0.1718	12300	7.9696
0.1732	12400	7.9868
0.1746	12500	8.0012
0.1760	12600	7.9694
0.1774	12700	7.9781
0.1788	12800	7.9777
0.1802	12900	7.9891
0.1816	13000	7.9699
0.1830	13100	7.9706
0.1844	13200	7.9755
0.1858	13300	7.9648
0.1872	13400	7.9665
0.1886	13500	7.9624
0.1900	13600	7.9794
0.1914	13700	7.9621
0.1927	13800	7.948
0.1941	13900	7.9598
0.1955	14000	7.9402
0.1969	14100	7.9515
0.1983	14200	7.961
0.1997	14300	7.9214
0.2011	14400	7.9587
0.2025	14500	7.9519
0.2039	14600	7.9504
0.2053	14700	7.9676
0.2067	14800	7.9341
0.2081	14900	7.957
0.2095	15000	7.9331
0.2109	15100	7.9692
0.2123	15200	7.9489
0.2137	15300	7.9541
0.2151	15400	7.9416
0.2165	15500	7.9215
0.2179	15600	7.9275
0.2193	15700	7.9034
0.2207	15800	7.8911
0.2221	15900	7.9397
0.2235	16000	7.9283
0.2249	16100	7.9132
0.2263	16200	7.9
0.2277	16300	7.8765
0.2291	16400	7.9209
0.2305	16500	7.9016
0.2319	16600	7.894
0.2333	16700	7.9451
0.2346	16800	7.8843
0.2360	16900	7.8795
0.2374	17000	7.9126
0.2388	17100	7.9154
0.2402	17200	7.9338
0.2416	17300	7.9
0.2430	17400	7.8878
0.2444	17500	7.8784
0.2458	17600	7.8853
0.2472	17700	7.8855
0.2486	17800	7.9002
0.2500	17900	7.8711
0.2514	18000	7.8943
0.2528	18100	7.8591
0.2542	18200	7.8622
0.2556	18300	7.8705
0.2570	18400	7.8734
0.2584	18500	7.8603
0.2598	18600	7.8778
0.2612	18700	7.8524
0.2626	18800	7.8577
0.2640	18900	7.8777
0.2654	19000	7.8728
0.2668	19100	7.8567
0.2682	19200	7.8359
0.2696	19300	7.8707
0.2710	19400	7.8708
0.2724	19500	7.8435
0.2738	19600	7.8486
0.2752	19700	7.8577
0.2766	19800	7.8559
0.2779	19900	7.8602
0.2793	20000	7.8401
0.2807	20100	7.8515
0.2821	20200	7.8539
0.2835	20300	7.8699
0.2849	20400	7.8434
0.2863	20500	7.8412
0.2877	20600	7.8419
0.2891	20700	7.8397
0.2905	20800	7.8539
0.2919	20900	7.8482
0.2933	21000	7.8632
0.2947	21100	7.8482
0.2961	21200	7.8394
0.2975	21300	7.8587
0.2989	21400	7.8625
0.3003	21500	7.8516
0.3017	21600	7.8321
0.3031	21700	7.8306
0.3045	21800	7.8226
0.3059	21900	7.8306
0.3073	22000	7.8271
0.3087	22100	7.8257
0.3101	22200	7.8387
0.3115	22300	7.8185
0.3129	22400	7.8575
0.3143	22500	7.8248
0.3157	22600	7.8203
0.3171	22700	7.8059
0.3185	22800	7.8356
0.3199	22900	7.8619
0.3212	23000	7.8178
0.3226	23100	7.816
0.3240	23200	7.8296
0.3254	23300	7.8028
0.3268	23400	7.8112
0.3282	23500	7.8059
0.3296	23600	7.8179
0.3310	23700	7.7965
0.3324	23800	7.8181
0.3338	23900	7.8142
0.3352	24000	7.7948
0.3366	24100	7.7777
0.3380	24200	7.8166
0.3394	24300	7.8028
0.3408	24400	7.828
0.3422	24500	7.8129
0.3436	24600	7.7927
0.3450	24700	7.805
0.3464	24800	7.8153
0.3478	24900	7.7955
0.3492	25000	7.8043
0.3506	25100	7.7807
0.3520	25200	7.8078
0.3534	25300	7.7599
0.3548	25400	7.7659
0.3562	25500	7.818
0.3576	25600	7.7496
0.3590	25700	7.7957
0.3604	25800	7.7679
0.3618	25900	7.8055
0.3631	26000	7.7885
0.3645	26100	7.7795
0.3659	26200	7.7752
0.3673	26300	7.7882
0.3687	26400	7.7951
0.3701	26500	7.7913
0.3715	26600	7.8002
0.3729	26700	7.7393
0.3743	26800	7.7809
0.3757	26900	7.7339
0.3771	27000	7.778
0.3785	27100	7.7895
0.3799	27200	7.8127
0.3813	27300	7.7827
0.3827	27400	7.7493
0.3841	27500	7.7709
0.3855	27600	7.7423
0.3869	27700	7.8034
0.3883	27800	7.759
0.3897	27900	7.7835
0.3911	28000	7.7631
0.3925	28100	7.7889
0.3939	28200	7.7357
0.3953	28300	7.7858
0.3967	28400	7.8136
0.3981	28500	7.7568
0.3995	28600	7.753
0.4009	28700	7.7624
0.4023	28800	7.765
0.4037	28900	7.7551
0.4051	29000	7.7631
0.4064	29100	7.7445
0.4078	29200	7.7821
0.4092	29300	7.7269
0.4106	29400	7.7565
0.4120	29500	7.7447
0.4134	29600	7.7304
0.4148	29700	7.7389
0.4162	29800	7.7275
0.4176	29900	7.7383
0.4190	30000	7.7789
0.4204	30100	7.7663
0.4218	30200	7.7539
0.4232	30300	7.7569
0.4246	30400	7.7637
0.4260	30500	7.7446
0.4274	30600	7.7284
0.4288	30700	7.7419
0.4302	30800	7.7533
0.4316	30900	7.7624
0.4330	31000	7.7265
0.4344	31100	7.7562
0.4358	31200	7.7201
0.4372	31300	7.7427
0.4386	31400	7.7415
0.4400	31500	7.7672
0.4414	31600	7.7433
0.4428	31700	7.7678
0.4442	31800	7.7108
0.4456	31900	7.7638
0.4470	32000	7.7389
0.4483	32100	7.7439
0.4497	32200	7.7312
0.4511	32300	7.7271
0.4525	32400	7.7388
0.4539	32500	7.7487
0.4553	32600	7.7087
0.4567	32700	7.7529
0.4581	32800	7.7288
0.4595	32900	7.7476
0.4609	33000	7.717
0.4623	33100	7.762
0.4637	33200	7.7271
0.4651	33300	7.7478
0.4665	33400	7.7026
0.4679	33500	7.7697
0.4693	33600	7.6938
0.4707	33700	7.7347
0.4721	33800	7.7068
0.4735	33900	7.711
0.4749	34000	7.7346
0.4763	34100	7.7116
0.4777	34200	7.7029
0.4791	34300	7.7197
0.4805	34400	7.7398
0.4819	34500	7.7208
0.4833	34600	7.6952
0.4847	34700	7.6922
0.4861	34800	7.6887
0.4875	34900	7.7389
0.4889	35000	7.7247
0.4903	35100	7.7315
0.4916	35200	7.6813
0.4930	35300	7.7163
0.4944	35400	7.7209
0.4958	35500	7.6907
0.4972	35600	7.666
0.4986	35700	7.703
0.5000	35800	7.7209
0.5014	35900	7.6848
0.5028	36000	7.7093
0.5042	36100	7.7143
0.5056	36200	7.6982
0.5070	36300	7.701
0.5084	36400	7.6692
0.5098	36500	7.7381
0.5112	36600	7.7162
0.5126	36700	7.7257
0.5140	36800	7.6956
0.5154	36900	7.726
0.5168	37000	7.7005
0.5182	37100	7.6989
0.5196	37200	7.6922
0.5210	37300	7.6886
0.5224	37400	7.7063
0.5238	37500	7.7059
0.5252	37600	7.6855
0.5266	37700	7.7311
0.5280	37800	7.6952
0.5294	37900	7.7072
0.5308	38000	7.6702
0.5322	38100	7.6954
0.5335	38200	7.675
0.5349	38300	7.6638
0.5363	38400	7.7127
0.5377	38500	7.6803
0.5391	38600	7.7213
0.5405	38700	7.6807
0.5419	38800	7.6737
0.5433	38900	7.7128
0.5447	39000	7.6819
0.5461	39100	7.6947
0.5475	39200	7.6457
0.5489	39300	7.654
0.5503	39400	7.6518
0.5517	39500	7.7081
0.5531	39600	7.6922
0.5545	39700	7.6965
0.5559	39800	7.6782
0.5573	39900	7.6472
0.5587	40000	7.7049
0.5601	40100	7.6999
0.5615	40200	7.6978
0.5629	40300	7.6853
0.5643	40400	7.6937
0.5657	40500	7.6953
0.5671	40600	7.6697
0.5685	40700	7.6675
0.5699	40800	7.6498
0.5713	40900	7.703
0.5727	41000	7.6775
0.5741	41100	7.6664
0.5755	41200	7.6843
0.5768	41300	7.6783
0.5782	41400	7.6657
0.5796	41500	7.6741
0.5810	41600	7.6617
0.5824	41700	7.654
0.5838	41800	7.6979
0.5852	41900	7.6644
0.5866	42000	7.6663
0.5880	42100	7.7044
0.5894	42200	7.6678
0.5908	42300	7.6679
0.5922	42400	7.6679
0.5936	42500	7.6712
0.5950	42600	7.702
0.5964	42700	7.6401
0.5978	42800	7.6613
0.5992	42900	7.6868
0.6006	43000	7.6424
0.6020	43100	7.6654
0.6034	43200	7.6769
0.6048	43300	7.6645
0.6062	43400	7.6889
0.6076	43500	7.6552
0.6090	43600	7.67
0.6104	43700	7.6811
0.6118	43800	7.6618
0.6132	43900	7.6628
0.6146	44000	7.6413
0.6160	44100	7.6378
0.6174	44200	7.6836
0.6187	44300	7.6842
0.6201	44400	7.6445
0.6215	44500	7.6639
0.6229	44600	7.636
0.6243	44700	7.6571
0.6257	44800	7.662
0.6271	44900	7.6481
0.6285	45000	7.6761
0.6299	45100	7.6551
0.6313	45200	7.6471
0.6327	45300	7.65
0.6341	45400	7.6231
0.6355	45500	7.6314
0.6369	45600	7.6243
0.6383	45700	7.6414
0.6397	45800	7.6451
0.6411	45900	7.6482
0.6425	46000	7.6597
0.6439	46100	7.6402
0.6453	46200	7.6414
0.6467	46300	7.6425
0.6481	46400	7.6182
0.6495	46500	7.6251
0.6509	46600	7.6422
0.6523	46700	7.6152
0.6537	46800	7.6418
0.6551	46900	7.6781
0.6565	47000	7.6551
0.6579	47100	7.6306
0.6593	47200	7.6366
0.6607	47300	7.6708
0.6620	47400	7.6668
0.6634	47500	7.6296
0.6648	47600	7.6555
0.6662	47700	7.6232
0.6676	47800	7.6476
0.6690	47900	7.6504
0.6704	48000	7.6564
0.6718	48100	7.6696
0.6732	48200	7.6486
0.6746	48300	7.6278
0.6760	48400	7.6414
0.6774	48500	7.6713
0.6788	48600	7.6578
0.6802	48700	7.5976
0.6816	48800	7.6387
0.6830	48900	7.6214
0.6844	49000	7.6243
0.6858	49100	7.6437
0.6872	49200	7.6052
0.6886	49300	7.6088
0.6900	49400	7.6297
0.6914	49500	7.6474
0.6928	49600	7.6433
0.6942	49700	7.6289
0.6956	49800	7.6657
0.6970	49900	7.6593
0.6984	50000	7.6708
0.6998	50100	7.6413
0.7012	50200	7.6112
0.7026	50300	7.6106
0.7039	50400	7.6576
0.7053	50500	7.6476
0.7067	50600	7.6078
0.7081	50700	7.5909
0.7095	50800	7.6175
0.7109	50900	7.6501
0.7123	51000	7.623
0.7137	51100	7.6103
0.7151	51200	7.65
0.7165	51300	7.6565
0.7179	51400	7.6364
0.7193	51500	7.6286
0.7207	51600	7.6663
0.7221	51700	7.6359
0.7235	51800	7.6285
0.7249	51900	7.6467
0.7263	52000	7.6214
0.7277	52100	7.6249
0.7291	52200	7.5814
0.7305	52300	7.615
0.7319	52400	7.6581
0.7333	52500	7.6419
0.7347	52600	7.6426
0.7361	52700	7.6306
0.7375	52800	7.58
0.7389	52900	7.5902
0.7403	53000	7.6334
0.7417	53100	7.6168
0.7431	53200	7.6451
0.7445	53300	7.6189
0.7459	53400	7.6671
0.7472	53500	7.6401
0.7486	53600	7.6363
0.7500	53700	7.6032
0.7514	53800	7.6506
0.7528	53900	7.6238
0.7542	54000	7.5901
0.7556	54100	7.6239
0.7570	54200	7.6114
0.7584	54300	7.6005
0.7598	54400	7.6137
0.7612	54500	7.6069
0.7626	54600	7.6223
0.7640	54700	7.6301
0.7654	54800	7.628
0.7668	54900	7.6296
0.7682	55000	7.605
0.7696	55100	7.6194
0.7710	55200	7.6252
0.7724	55300	7.6269
0.7738	55400	7.5882
0.7752	55500	7.5711
0.7766	55600	7.6398
0.7780	55700	7.6142
0.7794	55800	7.5884
0.7808	55900	7.6556
0.7822	56000	7.6153
0.7836	56100	7.6223
0.7850	56200	7.6424
0.7864	56300	7.6269
0.7878	56400	7.612
0.7892	56500	7.5898
0.7905	56600	7.6565
0.7919	56700	7.5972
0.7933	56800	7.6461
0.7947	56900	7.6026
0.7961	57000	7.6218
0.7975	57100	7.6082
0.7989	57200	7.6322
0.8003	57300	7.6439
0.8017	57400	7.6399
0.8031	57500	7.5862
0.8045	57600	7.5764
0.8059	57700	7.5985
0.8073	57800	7.6166
0.8087	57900	7.6592
0.8101	58000	7.6213
0.8115	58100	7.5822
0.8129	58200	7.6558
0.8143	58300	7.6409
0.8157	58400	7.5881
0.8171	58500	7.6038
0.8185	58600	7.6504
0.8199	58700	7.5968
0.8213	58800	7.594
0.8227	58900	7.6114
0.8241	59000	7.6423
0.8255	59100	7.6116
0.8269	59200	7.6188
0.8283	59300	7.5876
0.8297	59400	7.5823
0.8311	59500	7.6267
0.8324	59600	7.653
0.8338	59700	7.6051
0.8352	59800	7.6293
0.8366	59900	7.6038
0.8380	60000	7.6025
0.8394	60100	7.6169
0.8408	60200	7.619
0.8422	60300	7.6105
0.8436	60400	7.5876
0.8450	60500	7.5915
0.8464	60600	7.6217
0.8478	60700	7.5864
0.8492	60800	7.6194
0.8506	60900	7.5685
0.8520	61000	7.6145
0.8534	61100	7.6252
0.8548	61200	7.6284
0.8562	61300	7.631
0.8576	61400	7.6127
0.8590	61500	7.6132
0.8604	61600	7.6115
0.8618	61700	7.6493
0.8632	61800	7.6306
0.8646	61900	7.5841
0.8660	62000	7.6069
0.8674	62100	7.5825
0.8688	62200	7.5968
0.8702	62300	7.6097
0.8716	62400	7.5914
0.8730	62500	7.6144
0.8744	62600	7.6123
0.8757	62700	7.5844
0.8771	62800	7.573
0.8785	62900	7.5754
0.8799	63000	7.59
0.8813	63100	7.5754
0.8827	63200	7.5935
0.8841	63300	7.6287
0.8855	63400	7.5785
0.8869	63500	7.6004
0.8883	63600	7.5884
0.8897	63700	7.5901
0.8911	63800	7.5923
0.8925	63900	7.5834
0.8939	64000	7.6133
0.8953	64100	7.5938
0.8967	64200	7.6232
0.8981	64300	7.5682
0.8995	64400	7.618
0.9009	64500	7.596
0.9023	64600	7.5645
0.9037	64700	7.6386
0.9051	64800	7.5777
0.9065	64900	7.5788
0.9079	65000	7.5889
0.9093	65100	7.5699
0.9107	65200	7.5495
0.9121	65300	7.5881
0.9135	65400	7.5911
0.9149	65500	7.6214
0.9163	65600	7.5886
0.9176	65700	7.5784
0.9190	65800	7.5975
0.9204	65900	7.591
0.9218	66000	7.5844
0.9232	66100	7.5797
0.9246	66200	7.5775
0.9260	66300	7.574
0.9274	66400	7.5608
0.9288	66500	7.6209
0.9302	66600	7.5795
0.9316	66700	7.6324
0.9330	66800	7.5482
0.9344	66900	7.5494
0.9358	67000	7.5864
0.9372	67100	7.6184
0.9386	67200	7.6167
0.9400	67300	7.5876
0.9414	67400	7.5567
0.9428	67500	7.5763
0.9442	67600	7.5748
0.9456	67700	7.572
0.9470	67800	7.617
0.9484	67900	7.571
0.9498	68000	7.5916
0.9512	68100	7.5612
0.9526	68200	7.6116
0.9540	68300	7.5878
0.9554	68400	7.6086
0.9568	68500	7.6044
0.9582	68600	7.6018
0.9596	68700	7.5985
0.9609	68800	7.6214
0.9623	68900	7.568
0.9637	69000	7.5951
0.9651	69100	7.572
0.9665	69200	7.5724
0.9679	69300	7.5617
0.9693	69400	7.6132
0.9707	69500	7.5599
0.9721	69600	7.583
0.9735	69700	7.5867
0.9749	69800	7.606
0.9763	69900	7.5613
0.9777	70000	7.5896
0.9791	70100	7.5707
0.9805	70200	7.575
0.9819	70300	7.61
0.9833	70400	7.5958
0.9847	70500	7.617
0.9861	70600	7.5813
0.9875	70700	7.5614
0.9889	70800	7.5873
0.9903	70900	7.577
0.9917	71000	7.5563
0.9931	71100	7.6124
0.9945	71200	7.5421
0.9959	71300	7.572
0.9973	71400	7.5634
0.9987	71500	7.5796

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.5.1+cu121
• 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},
}