all-MiniLM-L6-v17-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v13_synonyms_added 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_v13_synonyms_added
• 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 = [
    'kite',
    'ramadan kaftan clutch',
    'side pocket boardshorts',
]
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, 0.6999, 0.6212],
#         [0.6999, 1.0000, 0.7124],
#         [0.6212, 0.7124, 1.0000]])

Training Details

Training Dataset

pairs_three_scores_v13_synonyms_added

• Dataset: pairs_three_scores_v13_synonyms_added at 10e49f8
• Size: 9,229,520 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: 5.65 tokens max: 18 tokens	min: 3 tokens mean: 5.69 tokens max: 16 tokens	min: 0.15 mean: 0.42 max: 1.0

• Samples:

  sentence1	sentence2	score
  kettlebell	bag	0.22
  mixed berry milk shake	elasticized waistband shorts	0.21
  raw linden honey	refresher sponge	0.22

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

pairs_three_scores_v13_synonyms_added

• Dataset: pairs_three_scores_v13_synonyms_added at 10e49f8
• Size: 46,380 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: 5.69 tokens max: 115 tokens	min: 3 tokens mean: 5.77 tokens max: 115 tokens	min: 0.15 mean: 0.42 max: 1.0

• Samples:

  sentence1	sentence2	score
  bag	nude rocks	0.24
  semi natural necklace	21 kt plated necklace	1.0
  eco friendly coasters	measuring cup	0.23

• 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	Validation Loss
0.0014	100	11.7561	-
0.0028	200	11.739	-
0.0042	300	11.2175	-
0.0055	400	11.0759	-
0.0069	500	10.7749	10.9497
0.0083	600	10.4026	-
0.0097	700	10.2194	-
0.0111	800	9.834	-
0.0125	900	9.6126	-
0.0139	1000	9.3563	9.3834
0.0153	1100	9.0716	-
0.0166	1200	8.9245	-
0.0180	1300	8.7384	-
0.0194	1400	8.6381	-
0.0208	1500	8.6089	8.5228
0.0222	1600	8.5817	-
0.0236	1700	8.5418	-
0.0250	1800	8.532	-
0.0264	1900	8.5107	-
0.0277	2000	8.4917	8.4366
0.0291	2100	8.485	-
0.0305	2200	8.4826	-
0.0319	2300	8.4512	-
0.0333	2400	8.4694	-
0.0347	2500	8.4485	8.3778
0.0361	2600	8.4293	-
0.0374	2700	8.4222	-
0.0388	2800	8.4031	-
0.0402	2900	8.3947	-
0.0416	3000	8.3912	8.3335
0.0430	3100	8.3913	-
0.0444	3200	8.3822	-
0.0458	3300	8.3552	-
0.0472	3400	8.3759	-
0.0485	3500	8.3632	8.2942
0.0499	3600	8.3495	-
0.0513	3700	8.3385	-
0.0527	3800	8.3346	-
0.0541	3900	8.3249	-
0.0555	4000	8.3033	8.2534
0.0569	4100	8.3141	-
0.0582	4200	8.3015	-
0.0596	4300	8.2982	-
0.0610	4400	8.3006	-
0.0624	4500	8.2972	8.2175
0.0638	4600	8.2757	-
0.0652	4700	8.2765	-
0.0666	4800	8.2668	-
0.0680	4900	8.2472	-
0.0693	5000	8.2605	8.1990
0.0707	5100	8.2481	-
0.0721	5200	8.2598	-
0.0735	5300	8.2403	-
0.0749	5400	8.2388	-
0.0763	5500	8.2074	8.1497
0.0777	5600	8.2236	-
0.0791	5700	8.2204	-
0.0804	5800	8.2086	-
0.0818	5900	8.208	-
0.0832	6000	8.1991	8.1357
0.0846	6100	8.2064	-
0.0860	6200	8.1969	-
0.0874	6300	8.1795	-
0.0888	6400	8.1846	-
0.0901	6500	8.188	8.1128
0.0915	6600	8.1902	-
0.0929	6700	8.1624	-
0.0943	6800	8.1527	-
0.0957	6900	8.1589	-
0.0971	7000	8.1624	8.0843
0.0985	7100	8.1705	-
0.0999	7200	8.1362	-
0.1012	7300	8.1419	-
0.1026	7400	8.1564	-
0.1040	7500	8.1422	8.0581
0.1054	7600	8.1214	-
0.1068	7700	8.1369	-
0.1082	7800	8.1024	-
0.1096	7900	8.0974	-
0.1109	8000	8.1316	8.0378
0.1123	8100	8.1185	-
0.1137	8200	8.1148	-
0.1151	8300	8.1015	-
0.1165	8400	8.0851	-
0.1179	8500	8.0881	8.0091
0.1193	8600	8.0734	-
0.1207	8700	8.0644	-
0.1220	8800	8.0802	-
0.1234	8900	8.0827	-
0.1248	9000	8.0934	8.0049
0.1262	9100	8.0544	-
0.1276	9200	8.0828	-
0.1290	9300	8.0844	-
0.1304	9400	8.0598	-
0.1318	9500	8.0575	7.9784
0.1331	9600	8.0476	-
0.1345	9700	8.0617	-
0.1359	9800	8.0632	-
0.1373	9900	8.0398	-
0.1387	10000	8.0455	7.9625
0.1401	10100	8.0441	-
0.1415	10200	8.0462	-
0.1428	10300	8.0429	-
0.1442	10400	8.0332	-
0.1456	10500	8.0087	7.9579
0.1470	10600	8.0374	-
0.1484	10700	8.0243	-
0.1498	10800	8.0445	-
0.1512	10900	8.0155	-
0.1526	11000	8.0161	7.9321
0.1539	11100	8.0092	-
0.1553	11200	8.0041	-
0.1567	11300	8.0165	-
0.1581	11400	8.005	-
0.1595	11500	7.9992	7.9243
0.1609	11600	8.0109	-
0.1623	11700	8.0096	-
0.1636	11800	8.0176	-
0.1650	11900	7.9965	-
0.1664	12000	8.0159	7.9092
0.1678	12100	7.9865	-
0.1692	12200	7.9742	-
0.1706	12300	7.9757	-
0.1720	12400	7.9852	-
0.1734	12500	8.0068	7.8931
0.1747	12600	7.9616	-
0.1761	12700	7.9889	-
0.1775	12800	7.9795	-
0.1789	12900	7.9657	-
0.1803	13000	7.952	7.8785
0.1817	13100	7.9534	-
0.1831	13200	7.9212	-
0.1845	13300	7.9479	-
0.1858	13400	7.9433	-
0.1872	13500	7.9599	7.8757
0.1886	13600	7.9751	-
0.1900	13700	7.9564	-
0.1914	13800	7.9642	-
0.1928	13900	7.9511	-
0.1942	14000	7.9458	7.8580
0.1955	14100	7.9625	-
0.1969	14200	7.9728	-
0.1983	14300	7.9235	-
0.1997	14400	7.9658	-
0.2011	14500	7.9567	7.8480
0.2025	14600	7.9214	-
0.2039	14700	7.8983	-
0.2053	14800	7.9334	-
0.2066	14900	7.9345	-
0.2080	15000	7.9245	7.8334
0.2094	15100	7.9144	-
0.2108	15200	7.9375	-
0.2122	15300	7.9058	-
0.2136	15400	7.9365	-
0.2150	15500	7.9101	7.8291
0.2163	15600	7.9001	-
0.2177	15700	7.8906	-
0.2191	15800	7.9103	-
0.2205	15900	7.8899	-
0.2219	16000	7.8874	7.8157
0.2233	16100	7.9011	-
0.2247	16200	7.92	-
0.2261	16300	7.8933	-
0.2274	16400	7.886	-
0.2288	16500	7.8959	7.8097
0.2302	16600	7.8623	-
0.2316	16700	7.8703	-
0.2330	16800	7.8934	-
0.2344	16900	7.8651	-
0.2358	17000	7.91	7.8047
0.2372	17100	7.8794	-
0.2385	17200	7.8794	-
0.2399	17300	7.8723	-
0.2413	17400	7.9007	-
0.2427	17500	7.8568	7.7977
0.2441	17600	7.8855	-
0.2455	17700	7.8687	-
0.2469	17800	7.8708	-
0.2482	17900	7.8533	-
0.2496	18000	7.87	7.8019
0.2510	18100	7.8364	-
0.2524	18200	7.8901	-
0.2538	18300	7.8782	-
0.2552	18400	7.8817	-
0.2566	18500	7.8794	7.7774
0.2580	18600	7.9031	-
0.2593	18700	7.8897	-
0.2607	18800	7.8741	-
0.2621	18900	7.8774	-
0.2635	19000	7.8771	7.7696
0.2649	19100	7.839	-
0.2663	19200	7.8786	-
0.2677	19300	7.866	-
0.2690	19400	7.868	-
0.2704	19500	7.8804	7.7672
0.2718	19600	7.8398	-
0.2732	19700	7.8662	-
0.2746	19800	7.8341	-
0.2760	19900	7.86	-
0.2774	20000	7.8325	7.7518
0.2788	20100	7.7957	-
0.2801	20200	7.8478	-
0.2815	20300	7.8601	-
0.2829	20400	7.8395	-
0.2843	20500	7.8414	7.7452
0.2857	20600	7.8332	-
0.2871	20700	7.862	-
0.2885	20800	7.8007	-
0.2899	20900	7.8249	-
0.2912	21000	7.8237	7.7456
0.2926	21100	7.8616	-
0.2940	21200	7.865	-
0.2954	21300	7.8226	-
0.2968	21400	7.8245	-
0.2982	21500	7.809	7.7333
0.2996	21600	7.8026	-
0.3009	21700	7.8169	-
0.3023	21800	7.8201	-
0.3037	21900	7.8057	-
0.3051	22000	7.8237	7.7258
0.3065	22100	7.82	-
0.3079	22200	7.819	-
0.3093	22300	7.7972	-
0.3107	22400	7.8141	-
0.3120	22500	7.8135	7.7245
0.3134	22600	7.7951	-
0.3148	22700	7.8051	-
0.3162	22800	7.7968	-
0.3176	22900	7.8256	-
0.3190	23000	7.8407	7.7135
0.3204	23100	7.8241	-
0.3217	23200	7.8195	-
0.3231	23300	7.7964	-
0.3245	23400	7.8166	-
0.3259	23500	7.821	7.6989
0.3273	23600	7.8125	-
0.3287	23700	7.7913	-
0.3301	23800	7.7958	-
0.3315	23900	7.7988	-
0.3328	24000	7.8148	7.7022
0.3342	24100	7.7964	-
0.3356	24200	7.7924	-
0.3370	24300	7.7783	-
0.3384	24400	7.8008	-
0.3398	24500	7.7745	7.6911
0.3412	24600	7.8002	-
0.3426	24700	7.7984	-
0.3439	24800	7.8212	-
0.3453	24900	7.7789	-
0.3467	25000	7.7609	7.6880
0.3481	25100	7.792	-
0.3495	25200	7.8064	-
0.3509	25300	7.7851	-
0.3523	25400	7.784	-
0.3536	25500	7.7905	7.6772
0.3550	25600	7.8252	-
0.3564	25700	7.766	-
0.3578	25800	7.7424	-
0.3592	25900	7.779	-
0.3606	26000	7.7701	7.6759
0.3620	26100	7.774	-
0.3634	26200	7.7752	-
0.3647	26300	7.7928	-
0.3661	26400	7.7525	-
0.3675	26500	7.7783	7.6744
0.3689	26600	7.7618	-
0.3703	26700	7.8067	-
0.3717	26800	7.7771	-
0.3731	26900	7.7936	-
0.3744	27000	7.7499	7.6710
0.3758	27100	7.7629	-
0.3772	27200	7.7843	-
0.3786	27300	7.7735	-
0.3800	27400	7.7662	-
0.3814	27500	7.7453	7.6658
0.3828	27600	7.7417	-
0.3842	27700	7.7793	-
0.3855	27800	7.7535	-
0.3869	27900	7.7695	-
0.3883	28000	7.758	7.6481
0.3897	28100	7.7391	-
0.3911	28200	7.7447	-
0.3925	28300	7.7691	-
0.3939	28400	7.7555	-
0.3953	28500	7.752	7.6460
0.3966	28600	7.7272	-
0.3980	28700	7.7464	-
0.3994	28800	7.7415	-
0.4008	28900	7.7616	-
0.4022	29000	7.7661	7.6477
0.4036	29100	7.7352	-
0.4050	29200	7.7438	-
0.4063	29300	7.7468	-
0.4077	29400	7.768	-
0.4091	29500	7.7581	7.6392
0.4105	29600	7.7374	-
0.4119	29700	7.7307	-
0.4133	29800	7.7292	-
0.4147	29900	7.7543	-
0.4161	30000	7.7435	7.6337
0.4174	30100	7.751	-
0.4188	30200	7.7264	-
0.4202	30300	7.7366	-
0.4216	30400	7.7137	-
0.4230	30500	7.7625	7.6239
0.4244	30600	7.7006	-
0.4258	30700	7.7571	-
0.4271	30800	7.722	-
0.4285	30900	7.7209	-
0.4299	31000	7.7159	7.6189
0.4313	31100	7.7058	-
0.4327	31200	7.7407	-
0.4341	31300	7.7093	-
0.4355	31400	7.7172	-
0.4369	31500	7.7532	7.6187
0.4382	31600	7.7254	-
0.4396	31700	7.716	-
0.4410	31800	7.7231	-
0.4424	31900	7.7272	-
0.4438	32000	7.7214	7.6153
0.4452	32100	7.7325	-
0.4466	32200	7.7268	-
0.4480	32300	7.6801	-
0.4493	32400	7.7209	-
0.4507	32500	7.6958	7.6057
0.4521	32600	7.6903	-
0.4535	32700	7.7379	-
0.4549	32800	7.7245	-
0.4563	32900	7.7506	-
0.4577	33000	7.7095	7.6051
0.4590	33100	7.7148	-
0.4604	33200	7.7182	-
0.4618	33300	7.7307	-
0.4632	33400	7.7381	-
0.4646	33500	7.7214	7.6028
0.4660	33600	7.6882	-
0.4674	33700	7.6864	-
0.4688	33800	7.6718	-
0.4701	33900	7.7201	-
0.4715	34000	7.7173	7.6092
0.4729	34100	7.6805	-
0.4743	34200	7.7264	-
0.4757	34300	7.7013	-
0.4771	34400	7.7074	-
0.4785	34500	7.7044	7.6044
0.4798	34600	7.742	-
0.4812	34700	7.7104	-
0.4826	34800	7.7004	-
0.4840	34900	7.7175	-
0.4854	35000	7.687	7.5947
0.4868	35100	7.7024	-
0.4882	35200	7.6666	-
0.4896	35300	7.6869	-
0.4909	35400	7.7147	-
0.4923	35500	7.7281	7.5804
0.4937	35600	7.6852	-
0.4951	35700	7.6735	-
0.4965	35800	7.7043	-
0.4979	35900	7.6884	-
0.4993	36000	7.7233	7.5851
0.5007	36100	7.6914	-
0.5020	36200	7.7083	-
0.5034	36300	7.6876	-
0.5048	36400	7.6909	-
0.5062	36500	7.679	7.5862
0.5076	36600	7.6884	-
0.5090	36700	7.6697	-
0.5104	36800	7.6625	-
0.5117	36900	7.6881	-
0.5131	37000	7.6859	7.5844
0.5145	37100	7.6624	-
0.5159	37200	7.6932	-
0.5173	37300	7.6851	-
0.5187	37400	7.6941	-
0.5201	37500	7.6473	7.5810
0.5215	37600	7.6619	-
0.5228	37700	7.6789	-
0.5242	37800	7.6842	-
0.5256	37900	7.6686	-
0.5270	38000	7.6677	7.5784
0.5284	38100	7.7113	-
0.5298	38200	7.6863	-
0.5312	38300	7.664	-
0.5325	38400	7.6928	-
0.5339	38500	7.685	7.5819
0.5353	38600	7.6507	-
0.5367	38700	7.6848	-
0.5381	38800	7.6435	-
0.5395	38900	7.6421	-
0.5409	39000	7.6883	7.5664
0.5423	39100	7.6907	-
0.5436	39200	7.6919	-
0.5450	39300	7.6956	-
0.5464	39400	7.6592	-
0.5478	39500	7.6488	7.5738
0.5492	39600	7.6918	-
0.5506	39700	7.6725	-
0.5520	39800	7.6804	-
0.5534	39900	7.6598	-
0.5547	40000	7.6888	7.5581
0.5561	40100	7.6732	-
0.5575	40200	7.7042	-
0.5589	40300	7.6626	-
0.5603	40400	7.7271	-
0.5617	40500	7.6753	7.5562
0.5631	40600	7.6521	-
0.5644	40700	7.667	-
0.5658	40800	7.6823	-
0.5672	40900	7.6635	-
0.5686	41000	7.6609	7.5553
0.5700	41100	7.6609	-
0.5714	41200	7.6712	-
0.5728	41300	7.6687	-
0.5742	41400	7.7182	-
0.5755	41500	7.6335	7.5660
0.5769	41600	7.6791	-
0.5783	41700	7.6509	-
0.5797	41800	7.6497	-
0.5811	41900	7.6514	-
0.5825	42000	7.6288	7.5552
0.5839	42100	7.6699	-
0.5852	42200	7.6824	-
0.5866	42300	7.68	-
0.5880	42400	7.661	-
0.5894	42500	7.6573	7.5487
0.5908	42600	7.6702	-
0.5922	42700	7.6573	-
0.5936	42800	7.6546	-
0.5950	42900	7.6424	-
0.5963	43000	7.6721	7.5504
0.5977	43100	7.6713	-
0.5991	43200	7.6695	-
0.6005	43300	7.6817	-
0.6019	43400	7.6484	-
0.6033	43500	7.6062	7.5481
0.6047	43600	7.6397	-
0.6061	43700	7.6555	-
0.6074	43800	7.6546	-
0.6088	43900	7.6781	-
0.6102	44000	7.6284	7.5399
0.6116	44100	7.666	-
0.6130	44200	7.6597	-
0.6144	44300	7.6651	-
0.6158	44400	7.6475	-
0.6171	44500	7.6565	7.5369
0.6185	44600	7.6336	-
0.6199	44700	7.6421	-
0.6213	44800	7.646	-
0.6227	44900	7.6319	-
0.6241	45000	7.664	7.5368
0.6255	45100	7.6515	-
0.6269	45200	7.6525	-
0.6282	45300	7.6534	-
0.6296	45400	7.655	-
0.6310	45500	7.6712	7.5278
0.6324	45600	7.6342	-
0.6338	45700	7.6077	-
0.6352	45800	7.6476	-
0.6366	45900	7.6412	-
0.6379	46000	7.6546	7.5331
0.6393	46100	7.6378	-
0.6407	46200	7.6572	-
0.6421	46300	7.6284	-
0.6435	46400	7.625	-
0.6449	46500	7.6526	7.5338
0.6463	46600	7.6172	-
0.6477	46700	7.6136	-
0.6490	46800	7.6428	-
0.6504	46900	7.6277	-
0.6518	47000	7.6903	7.5272
0.6532	47100	7.6313	-
0.6546	47200	7.6214	-
0.6560	47300	7.6044	-
0.6574	47400	7.6098	-
0.6588	47500	7.6477	7.5203
0.6601	47600	7.6454	-
0.6615	47700	7.6199	-
0.6629	47800	7.6119	-
0.6643	47900	7.6241	-
0.6657	48000	7.6414	7.5189
0.6671	48100	7.6629	-
0.6685	48200	7.6777	-
0.6698	48300	7.6217	-
0.6712	48400	7.6097	-
0.6726	48500	7.6449	7.5183
0.6740	48600	7.6131	-
0.6754	48700	7.622	-
0.6768	48800	7.6373	-
0.6782	48900	7.6193	-
0.6796	49000	7.6119	7.5209
0.6809	49100	7.6261	-
0.6823	49200	7.626	-
0.6837	49300	7.6232	-
0.6851	49400	7.5951	-
0.6865	49500	7.6368	7.5136
0.6879	49600	7.6641	-
0.6893	49700	7.6046	-
0.6906	49800	7.5923	-
0.6920	49900	7.6119	-
0.6934	50000	7.6301	7.5130
0.6948	50100	7.6288	-
0.6962	50200	7.6338	-
0.6976	50300	7.6137	-
0.6990	50400	7.6473	-
0.7004	50500	7.589	7.5153
0.7017	50600	7.6076	-
0.7031	50700	7.5906	-
0.7045	50800	7.6102	-
0.7059	50900	7.6463	-
0.7073	51000	7.6695	7.5098
0.7087	51100	7.5947	-
0.7101	51200	7.6097	-
0.7115	51300	7.6397	-
0.7128	51400	7.6072	-
0.7142	51500	7.6112	7.5103
0.7156	51600	7.639	-
0.7170	51700	7.6188	-
0.7184	51800	7.6198	-
0.7198	51900	7.6229	-
0.7212	52000	7.6323	7.5050
0.7225	52100	7.6275	-
0.7239	52200	7.6012	-
0.7253	52300	7.6187	-
0.7267	52400	7.6191	-
0.7281	52500	7.6232	7.5109
0.7295	52600	7.6199	-
0.7309	52700	7.5819	-
0.7323	52800	7.6474	-
0.7336	52900	7.6124	-
0.7350	53000	7.622	7.5000
0.7364	53100	7.6184	-
0.7378	53200	7.5761	-
0.7392	53300	7.5943	-
0.7406	53400	7.6209	-
0.7420	53500	7.6065	7.5055
0.7434	53600	7.6065	-
0.7447	53700	7.6285	-
0.7461	53800	7.641	-
0.7475	53900	7.633	-
0.7489	54000	7.6184	7.4995
0.7503	54100	7.6198	-
0.7517	54200	7.6239	-
0.7531	54300	7.6087	-
0.7544	54400	7.6112	-
0.7558	54500	7.6372	7.4957
0.7572	54600	7.5938	-
0.7586	54700	7.6091	-
0.7600	54800	7.622	-
0.7614	54900	7.6052	-
0.7628	55000	7.5775	7.4967
0.7642	55100	7.6484	-
0.7655	55200	7.5911	-
0.7669	55300	7.5966	-
0.7683	55400	7.5708	-
0.7697	55500	7.5905	7.4959
0.7711	55600	7.5858	-
0.7725	55700	7.6255	-
0.7739	55800	7.6169	-
0.7752	55900	7.6159	-
0.7766	56000	7.584	7.4929
0.7780	56100	7.6364	-
0.7794	56200	7.558	-
0.7808	56300	7.6095	-
0.7822	56400	7.6049	-
0.7836	56500	7.6079	7.4934
0.7850	56600	7.584	-
0.7863	56700	7.5543	-
0.7877	56800	7.5971	-
0.7891	56900	7.6395	-
0.7905	57000	7.6006	7.4900
0.7919	57100	7.6199	-
0.7933	57200	7.5938	-
0.7947	57300	7.602	-
0.7961	57400	7.6317	-
0.7974	57500	7.6125	7.4891
0.7988	57600	7.6031	-
0.8002	57700	7.6153	-
0.8016	57800	7.6141	-
0.8030	57900	7.5877	-
0.8044	58000	7.6051	7.4896
0.8058	58100	7.6065	-
0.8071	58200	7.5677	-
0.8085	58300	7.6035	-
0.8099	58400	7.6071	-
0.8113	58500	7.6214	7.4800
0.8127	58600	7.5914	-
0.8141	58700	7.6038	-
0.8155	58800	7.6206	-
0.8169	58900	7.6222	-
0.8182	59000	7.6128	7.4801
0.8196	59100	7.6109	-
0.8210	59200	7.5591	-
0.8224	59300	7.5794	-
0.8238	59400	7.6161	-
0.8252	59500	7.5689	7.4824
0.8266	59600	7.6009	-
0.8279	59700	7.6121	-
0.8293	59800	7.5872	-
0.8307	59900	7.6111	-
0.8321	60000	7.5339	7.4813
0.8335	60100	7.5739	-
0.8349	60200	7.5565	-
0.8363	60300	7.5637	-
0.8377	60400	7.5997	-
0.8390	60500	7.592	7.4829
0.8404	60600	7.6004	-
0.8418	60700	7.6007	-
0.8432	60800	7.602	-
0.8446	60900	7.5755	-
0.8460	61000	7.5771	7.4795
0.8474	61100	7.6143	-
0.8488	61200	7.6088	-
0.8501	61300	7.5555	-
0.8515	61400	7.5841	-
0.8529	61500	7.5979	7.4762
0.8543	61600	7.6403	-
0.8557	61700	7.5607	-
0.8571	61800	7.6151	-
0.8585	61900	7.6179	-
0.8598	62000	7.6152	7.4767
0.8612	62100	7.598	-
0.8626	62200	7.6013	-
0.8640	62300	7.5577	-
0.8654	62400	7.6108	-
0.8668	62500	7.5869	7.4716
0.8682	62600	7.559	-
0.8696	62700	7.5963	-
0.8709	62800	7.5884	-
0.8723	62900	7.5922	-
0.8737	63000	7.5915	7.4683
0.8751	63100	7.5473	-
0.8765	63200	7.5829	-
0.8779	63300	7.6122	-
0.8793	63400	7.5863	-
0.8806	63500	7.5764	7.4707
0.8820	63600	7.6258	-
0.8834	63700	7.5862	-
0.8848	63800	7.5977	-
0.8862	63900	7.5708	-
0.8876	64000	7.6024	7.4675
0.8890	64100	7.5625	-
0.8904	64200	7.5474	-
0.8917	64300	7.5978	-
0.8931	64400	7.5505	-
0.8945	64500	7.5741	7.4678
0.8959	64600	7.5763	-
0.8973	64700	7.5528	-
0.8987	64800	7.5787	-
0.9001	64900	7.5631	-
0.9015	65000	7.582	7.4724
0.9028	65100	7.5931	-
0.9042	65200	7.5977	-
0.9056	65300	7.572	-
0.9070	65400	7.6331	-
0.9084	65500	7.5503	7.4660
0.9098	65600	7.5987	-
0.9112	65700	7.611	-
0.9125	65800	7.563	-
0.9139	65900	7.5699	-
0.9153	66000	7.5942	7.4677
0.9167	66100	7.6119	-
0.9181	66200	7.5873	-
0.9195	66300	7.6036	-
0.9209	66400	7.5827	-
0.9223	66500	7.6103	7.4649
0.9236	66600	7.604	-
0.9250	66700	7.6129	-
0.9264	66800	7.5668	-
0.9278	66900	7.5699	-
0.9292	67000	7.6045	7.4626
0.9306	67100	7.5973	-
0.9320	67200	7.5951	-
0.9333	67300	7.5635	-
0.9347	67400	7.5915	-
0.9361	67500	7.5577	7.4619
0.9375	67600	7.5921	-
0.9389	67700	7.5888	-
0.9403	67800	7.5838	-
0.9417	67900	7.5648	-
0.9431	68000	7.5537	7.4616
0.9444	68100	7.5809	-
0.9458	68200	7.5882	-
0.9472	68300	7.5372	-
0.9486	68400	7.584	-
0.9500	68500	7.5821	7.4607
0.9514	68600	7.5663	-
0.9528	68700	7.5734	-
0.9542	68800	7.6026	-
0.9555	68900	7.5928	-
0.9569	69000	7.5415	7.4615
0.9583	69100	7.5785	-
0.9597	69200	7.5925	-
0.9611	69300	7.5922	-
0.9625	69400	7.5559	-
0.9639	69500	7.5759	7.4594
0.9652	69600	7.5753	-
0.9666	69700	7.6039	-
0.9680	69800	7.5791	-
0.9694	69900	7.5905	-
0.9708	70000	7.57	7.4592
0.9722	70100	7.5804	-
0.9736	70200	7.5709	-
0.9750	70300	7.582	-
0.9763	70400	7.6233	-
0.9777	70500	7.556	7.4582
0.9791	70600	7.6028	-
0.9805	70700	7.6149	-
0.9819	70800	7.5763	-
0.9833	70900	7.5904	-
0.9847	71000	7.5607	7.4590
0.9860	71100	7.5826	-
0.9874	71200	7.5704	-
0.9888	71300	7.5656	-
0.9902	71400	7.5879	-
0.9916	71500	7.5943	7.4583
0.9930	71600	7.5359	-
0.9944	71700	7.6152	-
0.9958	71800	7.5791	-
0.9971	71900	7.5845	-
0.9985	72000	7.5487	7.4580
0.9999	72100	7.6124	-

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},
}