all-MiniLM-L6-v7-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v7_balanced_calibrated 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_v7_balanced_calibrated
• 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 = [
    'chocolate cookie',
    'women bathing cover',
    'sports wristbands',
]
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, 0.4979, 0.4782],
#         [0.4979, 1.0000, 0.7929],
#         [0.4782, 0.7929, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v7_balanced_calibrated

• Dataset: pairs_three_scores_v7_balanced_calibrated at 9c7e882
• Size: 8,826,496 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: 5.71 tokens max: 45 tokens	min: 3 tokens mean: 5.78 tokens max: 45 tokens	min: 0.0 mean: 0.52 max: 1.0

• Samples:

  sentence1	sentence2	score
  lamb dog food	frizz control shampoo	0.0
  high fiber muesli	cloth clutch	0.04
  smoked sausage	ready to cook kofta	0.43

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v7_balanced_calibrated

• Dataset: pairs_three_scores_v7_balanced_calibrated at 9c7e882
• Size: 44,355 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: 5.59 tokens max: 44 tokens	min: 3 tokens mean: 5.7 tokens max: 31 tokens	min: 0.0 mean: 0.51 max: 1.0

• Samples:

  sentence1	sentence2	score
  sandwich fries meal	grilled chicken souvlaki wrap	1.0
  deli	juice glass	0.05
  classic coffee shake	basic dress	0.05

• 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
0.0015	100	13.3048
0.0029	200	13.1862
0.0044	300	12.8397
0.0058	400	12.0152
0.0073	500	11.4185
0.0087	600	10.7677
0.0102	700	9.8943
0.0116	800	9.4991
0.0131	900	9.1097
0.0145	1000	8.7566
0.0160	1100	8.5687
0.0174	1200	8.4785
0.0189	1300	8.4378
0.0203	1400	8.3864
0.0218	1500	8.3545
0.0232	1600	8.3495
0.0247	1700	8.3226
0.0261	1800	8.3071
0.0276	1900	8.2657
0.0290	2000	8.2359
0.0305	2100	8.2483
0.0319	2200	8.2237
0.0334	2300	8.1927
0.0348	2400	8.1974
0.0363	2500	8.1804
0.0377	2600	8.1663
0.0392	2700	8.1552
0.0406	2800	8.1536
0.0421	2900	8.132
0.0435	3000	8.1287
0.0450	3100	8.1068
0.0464	3200	8.0878
0.0479	3300	8.0974
0.0493	3400	8.085
0.0508	3500	8.0707
0.0522	3600	8.0684
0.0537	3700	8.0549
0.0551	3800	8.0311
0.0566	3900	8.0207
0.0580	4000	8.0163
0.0595	4100	8.0261
0.0609	4200	8.0119
0.0624	4300	7.9935
0.0638	4400	7.9862
0.0653	4500	7.9841
0.0667	4600	7.973
0.0682	4700	7.9396
0.0696	4800	7.9148
0.0711	4900	7.9454
0.0725	5000	7.9606
0.0740	5100	7.9254
0.0754	5200	7.898
0.0769	5300	7.8979
0.0783	5400	7.8754
0.0798	5500	7.9112
0.0812	5600	7.8664
0.0827	5700	7.8963
0.0841	5800	7.8563
0.0856	5900	7.8445
0.0870	6000	7.857
0.0885	6100	7.8432
0.0899	6200	7.8388
0.0914	6300	7.7983
0.0928	6400	7.8176
0.0943	6500	7.8265
0.0957	6600	7.8054
0.0972	6700	7.8091
0.0986	6800	7.7831
0.1001	6900	7.7593
0.1015	7000	7.8059
0.1030	7100	7.7663
0.1044	7200	7.7572
0.1059	7300	7.7801
0.1073	7400	7.7551
0.1088	7500	7.7223
0.1102	7600	7.758
0.1117	7700	7.7588
0.1131	7800	7.7418
0.1146	7900	7.7174
0.1160	8000	7.6791
0.1175	8100	7.6968
0.1189	8200	7.7013
0.1204	8300	7.6958
0.1218	8400	7.6967
0.1233	8500	7.6606
0.1247	8600	7.6977
0.1262	8700	7.6956
0.1276	8800	7.6707
0.1291	8900	7.6763
0.1305	9000	7.6413
0.1320	9100	7.6582
0.1334	9200	7.641
0.1349	9300	7.6999
0.1363	9400	7.6453
0.1378	9500	7.6351
0.1392	9600	7.64
0.1407	9700	7.6578
0.1421	9800	7.6345
0.1436	9900	7.6143
0.1450	10000	7.6331
0.1465	10100	7.5877
0.1479	10200	7.6273
0.1494	10300	7.5957
0.1508	10400	7.6315
0.1523	10500	7.5612
0.1537	10600	7.6246
0.1552	10700	7.5974
0.1566	10800	7.6075
0.1581	10900	7.5713
0.1595	11000	7.5874
0.1610	11100	7.5549
0.1624	11200	7.5743
0.1639	11300	7.5223
0.1653	11400	7.5496
0.1668	11500	7.5846
0.1682	11600	7.5876
0.1697	11700	7.5735
0.1711	11800	7.5434
0.1726	11900	7.5673
0.1740	12000	7.5181
0.1755	12100	7.5778
0.1769	12200	7.5557
0.1784	12300	7.5137
0.1798	12400	7.546
0.1813	12500	7.5375
0.1827	12600	7.5576
0.1842	12700	7.5075
0.1856	12800	7.5178
0.1871	12900	7.5254
0.1885	13000	7.5349
0.1900	13100	7.5193
0.1914	13200	7.5352
0.1929	13300	7.5146
0.1943	13400	7.5305
0.1958	13500	7.5202
0.1972	13600	7.4845
0.1987	13700	7.4707
0.2001	13800	7.5193
0.2016	13900	7.4866
0.2030	14000	7.4782
0.2045	14100	7.507
0.2059	14200	7.47
0.2074	14300	7.5295
0.2088	14400	7.5049
0.2103	14500	7.4738
0.2117	14600	7.4808
0.2132	14700	7.5044
0.2146	14800	7.4933
0.2161	14900	7.4481
0.2175	15000	7.4323
0.2190	15100	7.4591
0.2204	15200	7.4819
0.2219	15300	7.4255
0.2233	15400	7.4383
0.2248	15500	7.4858
0.2262	15600	7.4464
0.2277	15700	7.4639
0.2291	15800	7.4269
0.2306	15900	7.4219
0.2320	16000	7.4719
0.2335	16100	7.4446
0.2349	16200	7.4658
0.2364	16300	7.4489
0.2378	16400	7.4082
0.2393	16500	7.456
0.2407	16600	7.4113
0.2422	16700	7.4144
0.2436	16800	7.4304
0.2451	16900	7.4192
0.2465	17000	7.4019
0.2480	17100	7.4118
0.2494	17200	7.4348
0.2509	17300	7.4117
0.2523	17400	7.3867
0.2538	17500	7.4006
0.2552	17600	7.4335
0.2567	17700	7.404
0.2581	17800	7.3861
0.2596	17900	7.4109
0.2610	18000	7.417
0.2625	18100	7.3861
0.2639	18200	7.4313
0.2654	18300	7.4198
0.2668	18400	7.4177
0.2683	18500	7.4113
0.2697	18600	7.4214
0.2712	18700	7.3925
0.2726	18800	7.4241
0.2741	18900	7.3627
0.2755	19000	7.3991
0.2770	19100	7.3401
0.2784	19200	7.3592
0.2799	19300	7.3619
0.2813	19400	7.3968
0.2828	19500	7.3659
0.2842	19600	7.3553
0.2857	19700	7.4121
0.2871	19800	7.3858
0.2886	19900	7.4223
0.2900	20000	7.3699
0.2915	20100	7.3452
0.2929	20200	7.3673
0.2944	20300	7.3568
0.2958	20400	7.3753
0.2973	20500	7.375
0.2987	20600	7.3699
0.3002	20700	7.3537
0.3016	20800	7.3739
0.3031	20900	7.3218
0.3045	21000	7.3739
0.3060	21100	7.3781
0.3074	21200	7.3724
0.3089	21300	7.3396
0.3103	21400	7.3074
0.3118	21500	7.3135
0.3132	21600	7.4059
0.3147	21700	7.3887
0.3161	21800	7.2713
0.3176	21900	7.3444
0.3190	22000	7.3375
0.3205	22100	7.3426
0.3219	22200	7.3319
0.3234	22300	7.3323
0.3248	22400	7.3345
0.3263	22500	7.2884
0.3277	22600	7.285
0.3292	22700	7.3242
0.3306	22800	7.3198
0.3321	22900	7.2734
0.3335	23000	7.3444
0.3350	23100	7.3301
0.3364	23200	7.3302
0.3379	23300	7.3194
0.3393	23400	7.3118
0.3408	23500	7.3143
0.3422	23600	7.3177
0.3437	23700	7.3174
0.3451	23800	7.3054
0.3466	23900	7.3186
0.3480	24000	7.3204
0.3495	24100	7.3106
0.3509	24200	7.2729
0.3524	24300	7.2944
0.3538	24400	7.3143
0.3553	24500	7.3126
0.3567	24600	7.3428
0.3582	24700	7.3465
0.3596	24800	7.2775
0.3611	24900	7.3395
0.3625	25000	7.2664
0.3640	25100	7.3029
0.3654	25200	7.2996
0.3669	25300	7.297
0.3683	25400	7.2545
0.3698	25500	7.3155
0.3712	25600	7.3197
0.3727	25700	7.2667
0.3741	25800	7.2578
0.3756	25900	7.2993
0.3770	26000	7.2528
0.3785	26100	7.3429
0.3799	26200	7.3111
0.3814	26300	7.3344
0.3828	26400	7.2869
0.3843	26500	7.2636
0.3857	26600	7.3047
0.3872	26700	7.2681
0.3886	26800	7.297
0.3901	26900	7.2075
0.3915	27000	7.2792
0.3930	27100	7.2952
0.3944	27200	7.3172
0.3959	27300	7.3063
0.3973	27400	7.2786
0.3988	27500	7.2072
0.4002	27600	7.2589
0.4017	27700	7.2975
0.4031	27800	7.2228
0.4046	27900	7.2548
0.4061	28000	7.2572
0.4075	28100	7.2664
0.4090	28200	7.2913
0.4104	28300	7.3064
0.4119	28400	7.2726
0.4133	28500	7.2588
0.4148	28600	7.2715
0.4162	28700	7.275
0.4177	28800	7.2364
0.4191	28900	7.2308
0.4206	29000	7.3067
0.4220	29100	7.2369
0.4235	29200	7.2519
0.4249	29300	7.2358
0.4264	29400	7.244
0.4278	29500	7.2531
0.4293	29600	7.2268
0.4307	29700	7.2785
0.4322	29800	7.2429
0.4336	29900	7.2478
0.4351	30000	7.22
0.4365	30100	7.2125
0.4380	30200	7.2839
0.4394	30300	7.323
0.4409	30400	7.269
0.4423	30500	7.2373
0.4438	30600	7.3115
0.4452	30700	7.2345
0.4467	30800	7.2022
0.4481	30900	7.2235
0.4496	31000	7.207
0.4510	31100	7.2684
0.4525	31200	7.2309
0.4539	31300	7.2201
0.4554	31400	7.2645
0.4568	31500	7.2171
0.4583	31600	7.1958
0.4597	31700	7.2728
0.4612	31800	7.2175
0.4626	31900	7.1995
0.4641	32000	7.1677
0.4655	32100	7.2124
0.4670	32200	7.2163
0.4684	32300	7.1728
0.4699	32400	7.1941
0.4713	32500	7.1826
0.4728	32600	7.2542
0.4742	32700	7.1866
0.4757	32800	7.2511
0.4771	32900	7.2587
0.4786	33000	7.1963
0.4800	33100	7.213
0.4815	33200	7.2072
0.4829	33300	7.3
0.4844	33400	7.1509
0.4858	33500	7.1924
0.4873	33600	7.2083
0.4887	33700	7.2112
0.4902	33800	7.2109
0.4916	33900	7.1624
0.4931	34000	7.1807
0.4945	34100	7.1922
0.4960	34200	7.2215
0.4974	34300	7.2036
0.4989	34400	7.204
0.5003	34500	7.1716
0.5018	34600	7.2463
0.5032	34700	7.2446
0.5047	34800	7.2203
0.5061	34900	7.2153
0.5076	35000	7.153
0.5090	35100	7.2332
0.5105	35200	7.1656
0.5119	35300	7.142
0.5134	35400	7.2018
0.5148	35500	7.177
0.5163	35600	7.1974
0.5177	35700	7.2767
0.5192	35800	7.2503
0.5206	35900	7.1468
0.5221	36000	7.1862
0.5235	36100	7.2403
0.5250	36200	7.2375
0.5264	36300	7.1832
0.5279	36400	7.1365
0.5293	36500	7.2009
0.5308	36600	7.2533
0.5322	36700	7.2221
0.5337	36800	7.2076
0.5351	36900	7.185
0.5366	37000	7.2257
0.5380	37100	7.1446
0.5395	37200	7.2148
0.5409	37300	7.1769
0.5424	37400	7.1636
0.5438	37500	7.2075
0.5453	37600	7.2295
0.5467	37700	7.1181
0.5482	37800	7.1449
0.5496	37900	7.1355
0.5511	38000	7.1549
0.5525	38100	7.1616
0.5540	38200	7.1747
0.5554	38300	7.1871
0.5569	38400	7.1817
0.5583	38500	7.1495
0.5598	38600	7.2552
0.5612	38700	7.1916
0.5627	38800	7.226
0.5641	38900	7.1136
0.5656	39000	7.1555
0.5670	39100	7.1272
0.5685	39200	7.1998
0.5699	39300	7.1242
0.5714	39400	7.2167
0.5728	39500	7.1848
0.5743	39600	7.178
0.5757	39700	7.1347
0.5772	39800	7.1059
0.5786	39900	7.1004
0.5801	40000	7.1096
0.5815	40100	7.1272
0.5830	40200	7.2099
0.5844	40300	7.158
0.5859	40400	7.0955
0.5873	40500	7.1366
0.5888	40600	7.12
0.5902	40700	7.1694
0.5917	40800	7.1576
0.5931	40900	7.2108
0.5946	41000	7.112
0.5960	41100	7.184
0.5975	41200	7.1528
0.5989	41300	7.1737
0.6004	41400	7.2168
0.6018	41500	7.1676
0.6033	41600	7.17
0.6047	41700	7.077
0.6062	41800	7.1684
0.6076	41900	7.1425
0.6091	42000	7.1449
0.6105	42100	7.1325
0.6120	42200	7.195
0.6134	42300	7.159
0.6149	42400	7.179
0.6163	42500	7.1657
0.6178	42600	7.19
0.6192	42700	7.0956
0.6207	42800	7.0952
0.6221	42900	7.1905
0.6236	43000	7.1203
0.6250	43100	7.1293
0.6265	43200	7.1273
0.6279	43300	7.1374
0.6294	43400	7.1003
0.6308	43500	7.1644
0.6323	43600	7.1432
0.6337	43700	7.1237
0.6352	43800	7.1663
0.6366	43900	7.1404
0.6381	44000	7.1664
0.6395	44100	7.1906
0.6410	44200	7.1707
0.6424	44300	7.0727
0.6439	44400	7.1768
0.6453	44500	7.117
0.6468	44600	7.0683
0.6482	44700	7.0952
0.6497	44800	7.1768
0.6511	44900	7.1327
0.6526	45000	7.0887
0.6540	45100	7.1047
0.6555	45200	7.1983
0.6569	45300	7.0902
0.6584	45400	7.1647
0.6598	45500	7.1453
0.6613	45600	7.1043
0.6627	45700	7.0729
0.6642	45800	7.1508
0.6656	45900	7.1688
0.6671	46000	7.1259
0.6685	46100	7.1323
0.6700	46200	7.0916
0.6714	46300	7.1297
0.6729	46400	7.1138
0.6743	46500	7.129
0.6758	46600	7.1228
0.6772	46700	7.0995
0.6787	46800	7.1034
0.6801	46900	7.1085
0.6816	47000	7.1223
0.6830	47100	7.0934
0.6845	47200	7.0865
0.6859	47300	7.076
0.6874	47400	7.1252
0.6888	47500	7.1788
0.6903	47600	7.0807
0.6917	47700	7.1163
0.6932	47800	7.0631
0.6946	47900	7.1842
0.6961	48000	7.1084
0.6975	48100	7.0994
0.6990	48200	7.1163
0.7004	48300	7.0563
0.7019	48400	7.1086
0.7033	48500	7.1233
0.7048	48600	7.0724
0.7062	48700	7.095
0.7077	48800	7.1039
0.7091	48900	7.1138
0.7106	49000	7.1184
0.7120	49100	7.0557
0.7135	49200	7.1065
0.7149	49300	7.1455
0.7164	49400	7.0808
0.7178	49500	7.1734
0.7193	49600	7.1396
0.7207	49700	7.1184
0.7222	49800	7.0714
0.7236	49900	7.1617
0.7251	50000	7.1244
0.7265	50100	7.0367
0.7280	50200	7.1068
0.7294	50300	7.1152
0.7309	50400	7.0782
0.7323	50500	7.0937
0.7338	50600	7.0899
0.7352	50700	7.0212
0.7367	50800	7.0308
0.7381	50900	7.0298
0.7396	51000	7.094
0.7410	51100	7.1962
0.7425	51200	7.0881
0.7439	51300	7.0484
0.7454	51400	7.0536
0.7468	51500	7.1169
0.7483	51600	7.0975
0.7497	51700	7.1155
0.7512	51800	7.0659
0.7526	51900	7.0567
0.7541	52000	7.0942
0.7555	52100	7.1224
0.7570	52200	7.1349
0.7584	52300	7.0874
0.7599	52400	7.0636
0.7613	52500	7.1171
0.7628	52600	7.1359
0.7642	52700	7.1599
0.7657	52800	7.0568
0.7671	52900	7.0948
0.7686	53000	7.0982
0.7700	53100	7.0856
0.7715	53200	7.071
0.7729	53300	7.0562
0.7744	53400	7.066
0.7758	53500	7.119
0.7773	53600	7.1492
0.7787	53700	7.0461
0.7802	53800	7.1003
0.7816	53900	7.0984
0.7831	54000	7.0875
0.7845	54100	7.1238
0.7860	54200	7.0896
0.7874	54300	7.0569
0.7889	54400	7.0994
0.7903	54500	7.146
0.7918	54600	7.0819
0.7932	54700	7.1003
0.7947	54800	7.0744
0.7961	54900	7.1047
0.7976	55000	7.1147
0.7990	55100	7.0318
0.8005	55200	7.0548
0.8019	55300	7.1215
0.8034	55400	7.1124
0.8048	55500	7.1096
0.8063	55600	7.0467
0.8077	55700	7.0454
0.8092	55800	7.0824
0.8107	55900	7.075
0.8121	56000	7.0316
0.8136	56100	7.1231
0.8150	56200	7.0449
0.8165	56300	7.1556
0.8179	56400	7.1036
0.8194	56500	6.9778
0.8208	56600	7.0649
0.8223	56700	7.1124
0.8237	56800	7.0294
0.8252	56900	7.1424
0.8266	57000	7.0891
0.8281	57100	7.0899
0.8295	57200	7.1276
0.8310	57300	7.0621
0.8324	57400	7.0253
0.8339	57500	7.0532
0.8353	57600	7.0171
0.8368	57700	7.0731
0.8382	57800	7.0837
0.8397	57900	7.0778
0.8411	58000	7.0478
0.8426	58100	7.0946
0.8440	58200	7.0772
0.8455	58300	7.0556
0.8469	58400	7.0451
0.8484	58500	7.0708
0.8498	58600	7.0881
0.8513	58700	7.0783
0.8527	58800	7.0632
0.8542	58900	7.0175
0.8556	59000	7.0248
0.8571	59100	7.0781
0.8585	59200	7.0403
0.8600	59300	7.1009
0.8614	59400	7.0367
0.8629	59500	7.0728
0.8643	59600	7.0292
0.8658	59700	7.027
0.8672	59800	7.0737
0.8687	59900	7.0514
0.8701	60000	7.033
0.8716	60100	6.9728
0.8730	60200	7.0672
0.8745	60300	7.1248
0.8759	60400	7.1127
0.8774	60500	7.0061
0.8788	60600	7.0643
0.8803	60700	7.0996
0.8817	60800	7.0991
0.8832	60900	7.05
0.8846	61000	7.0198
0.8861	61100	7.0489
0.8875	61200	7.0778
0.8890	61300	7.1017
0.8904	61400	7.0815
0.8919	61500	7.0565
0.8933	61600	7.0187
0.8948	61700	7.0809
0.8962	61800	7.0219
0.8977	61900	7.0343
0.8991	62000	7.1052
0.9006	62100	7.0448
0.9020	62200	7.0598
0.9035	62300	7.0498
0.9049	62400	7.1148
0.9064	62500	7.048
0.9078	62600	7.1137
0.9093	62700	7.0538
0.9107	62800	7.089
0.9122	62900	7.1247
0.9136	63000	6.9895
0.9151	63100	7.0364
0.9165	63200	7.1219
0.9180	63300	7.0399
0.9194	63400	7.0669
0.9209	63500	7.1429
0.9223	63600	7.1196
0.9238	63700	7.0336
0.9252	63800	7.0792
0.9267	63900	7.0935
0.9281	64000	7.1163
0.9296	64100	7.0483
0.9310	64200	7.0632
0.9325	64300	6.9877
0.9339	64400	6.9545
0.9354	64500	7.047
0.9368	64600	7.0755
0.9383	64700	6.9931
0.9397	64800	7.0
0.9412	64900	7.0293
0.9426	65000	7.0471
0.9441	65100	7.0567
0.9455	65200	7.0853
0.9470	65300	7.0801
0.9484	65400	7.0202
0.9499	65500	7.1004
0.9513	65600	7.1051
0.9528	65700	7.0403
0.9542	65800	7.003
0.9557	65900	7.0495
0.9571	66000	6.9828
0.9586	66100	7.0453
0.9600	66200	7.0196
0.9615	66300	7.1254
0.9629	66400	7.0849
0.9644	66500	7.0223
0.9658	66600	7.1217
0.9673	66700	6.9922
0.9687	66800	7.025
0.9702	66900	7.0705
0.9716	67000	7.0794
0.9731	67100	7.0162
0.9745	67200	7.0855
0.9760	67300	7.0078
0.9774	67400	7.0908
0.9789	67500	7.0663
0.9803	67600	7.0175
0.9818	67700	7.0059
0.9832	67800	7.0673
0.9847	67900	7.0495
0.9861	68000	7.005
0.9876	68100	7.0198
0.9890	68200	7.0515
0.9905	68300	7.0274
0.9919	68400	7.1286
0.9934	68500	7.0913
0.9948	68600	7.0087
0.9963	68700	7.0341
0.9977	68800	7.046
0.9992	68900	7.057

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},
}