seongil-dn/gte-noneg-bs512-lr5e-5-1000

SentenceTransformer based on Alibaba-NLP/gte-multilingual-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-multilingual-base. It maps sentences & paragraphs to a 768-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: Alibaba-NLP/gte-multilingual-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

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': 512, 'do_lower_case': False}) with Transformer model: NewModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("seongil-dn/gte-noneg-bs512-lr5e-5-1000")
# Run inference
sentences = [
    'LPGA 투어에서 고진영이 컷 탈락을 기록한 건 얼마나 돼',
    '여자골프 세계랭킹 1위 고진영(26)이 미국여자프로골프(LPGA) 투어 드라이브온 챔피언십(총상금 150만 달러)에서 컷 탈락했다. 고진영은 6일(한국시간) 미국 플로리다주 오칼라의 골든 오칼라 골프 클럽(파72ㆍ6,526야드)에서 열린 대회 2라운드에서 버디와 보기 하나씩을 묶어 이븐파 72타를 쳤다. 1라운드 3오버파 75타로 공동 86위에 그쳤던 고진영은 이틀간 합계 3오버파 147타로 공동 72위에 머물러 컷을 통과하지 못했다. 컷은 2오버파 146타였다. 고진영이 LPGA 투어 대회에서 컷 탈락한 건 세 번째다. 앞서 2017년 3월 ANA 인스피레이션, 2018년 8월 브리티시여자오픈에서 컷을 통과하지 못했다. 그리고 2년 7개월 만에 또 한 번 컷 탈락이 기록됐다. 이날 2라운드는 10번 홀에서 시작, 15번 홀(파3) 버디를 잡아냈으나 17번 홀(파4) 보기를 써내 전반 타수를 줄이지 못했고, 후반엔 9개 홀 모두 파를 기록했다. 그는 이날 페어웨이는 한 번밖에 놓치지 않았으나 그린을 6차례 놓치고 퍼트 수가 30개에 달했다. 리더보드 맨 위엔 10언더파 134타의 제니퍼 컵초, 오스틴 언스트(이상 미국)가 이름을 올린 가운데 데일리 베스트인 7언더파를 몰아친 카를로타 시간다(스페인ㆍ8언더파 136타)가 두 타 차로 추격했다. 한국 선수 중에는 허미정(32)이 3언더파 141타, 공동 11위로 가장 좋은 성적을 냈다. 세계랭킹 2위 김세영(28)은 공동 17위(2언더파 142타), 전인지(27)는 공동 24위(1언더파 143타)에 자리했다. 정은(25)은 5타, 박성현(28)은 한 타를 잃고 공동 58위(2오버파 146타)에 올라 가까스로 컷을 통과했다.',
    '1회용품 함께 줄이기 계획\nⅠ. 추진 배경\n□ (그간 추진 경과) ‘자원의 절약 및 재활용 촉진에 관한 법률’에 따라 1회용품 사용억제 제도 운영(1994~, 18개품목-18개업종)\no (성과) 「재활용 폐기물 관리 종합대책」(2018.5)을 수립하고 1회용컵, 비닐봉투 사용저감을 집중 추진하여 일정 감축성과 창출\n* 커피전문점 매장 내 1회용컵 75% 감소, 제과점 1회용 비닐봉투 84% 감소 등\no (한계) 그러나 국민이 체감할 변화는 아직 미흡하며, 비 규제 품목(빨대 등) 및 유형(배달 등)에 대한 관리 강화 요구 증가\n□ (해외 동향) 세계 각 국은 1회용품 사용을 저감하기 위한 중장기 로드맵을 발표하고, 국가별로 다양한 규제방안 도입\n* EU는 1회용 플라스틱 10대 품목 선정, 품목별 시장출시 금지 등 규제방안 마련\n** 미국 일부 州, 캐나다, 프랑스, 케냐, 칠레 등 1회용 비닐봉투 등 사용금지 도입',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• warmup_steps: 100
• bf16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• 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: 5e-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: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 100
• 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: True
• fp16: False
• 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: True
• 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0011	1	0.4348
0.0021	2	0.4712
0.0032	3	0.4947
0.0042	4	0.4267
0.0053	5	0.4421
0.0064	6	0.4834
0.0074	7	0.4726
0.0085	8	0.4524
0.0096	9	0.4645
0.0106	10	0.4654
0.0117	11	0.4574
0.0127	12	0.5019
0.0138	13	0.4481
0.0149	14	0.423
0.0159	15	0.4694
0.0170	16	0.4316
0.0180	17	0.4372
0.0191	18	0.4623
0.0202	19	0.4222
0.0212	20	0.4494
0.0223	21	0.3932
0.0234	22	0.3924
0.0244	23	0.3869
0.0255	24	0.4064
0.0265	25	0.3945
0.0276	26	0.382
0.0287	27	0.3684
0.0297	28	0.3881
0.0308	29	0.3784
0.0318	30	0.3715
0.0329	31	0.34
0.0340	32	0.3421
0.0350	33	0.3678
0.0361	34	0.3489
0.0372	35	0.3112
0.0382	36	0.3137
0.0393	37	0.2928
0.0403	38	0.3053
0.0414	39	0.2838
0.0425	40	0.2638
0.0435	41	0.2827
0.0446	42	0.2372
0.0456	43	0.2635
0.0467	44	0.2749
0.0478	45	0.2381
0.0488	46	0.2113
0.0499	47	0.1914
0.0510	48	0.1944
0.0520	49	0.1863
0.0531	50	0.191
0.0541	51	0.1547
0.0552	52	0.1854
0.0563	53	0.1587
0.0573	54	0.1555
0.0584	55	0.1563
0.0594	56	0.1711
0.0605	57	0.1432
0.0616	58	0.1263
0.0626	59	0.1247
0.0637	60	0.1369
0.0648	61	0.1305
0.0658	62	0.1022
0.0669	63	0.1191
0.0679	64	0.1083
0.0690	65	0.0936
0.0701	66	0.0988
0.0711	67	0.0942
0.0722	68	0.107
0.0732	69	0.0823
0.0743	70	0.0886
0.0754	71	0.1055
0.0764	72	0.1013
0.0775	73	0.0807
0.0786	74	0.0776
0.0796	75	0.0737
0.0807	76	0.0916
0.0817	77	0.0654
0.0828	78	0.0904
0.0839	79	0.0954
0.0849	80	0.0697
0.0860	81	0.0751
0.0870	82	0.0886
0.0881	83	0.0752
0.0892	84	0.0806
0.0902	85	0.0807
0.0913	86	0.0842
0.0924	87	0.0821
0.0934	88	0.0723
0.0945	89	0.0797
0.0955	90	0.0797
0.0966	91	0.0832
0.0977	92	0.0713
0.0987	93	0.0681
0.0998	94	0.0825
0.1008	95	0.0838
0.1019	96	0.0746
0.1030	97	0.0792
0.1040	98	0.0692
0.1051	99	0.0705
0.1062	100	0.0666
0.1072	101	0.0692
0.1083	102	0.0675
0.1093	103	0.0734
0.1104	104	0.072
0.1115	105	0.0565
0.1125	106	0.0663
0.1136	107	0.0789
0.1146	108	0.0605
0.1157	109	0.0671
0.1168	110	0.083
0.1178	111	0.071
0.1189	112	0.0759
0.1200	113	0.0604
0.1210	114	0.0682
0.1221	115	0.0531
0.1231	116	0.0779
0.1242	117	0.0646
0.1253	118	0.0621
0.1263	119	0.081
0.1274	120	0.0688
0.1285	121	0.055
0.1295	122	0.0513
0.1306	123	0.063
0.1316	124	0.0634
0.1327	125	0.075
0.1338	126	0.062
0.1348	127	0.0821
0.1359	128	0.0565
0.1369	129	0.0492
0.1380	130	0.0762
0.1391	131	0.0735
0.1401	132	0.069
0.1412	133	0.0619
0.1423	134	0.0789
0.1433	135	0.0621
0.1444	136	0.0568
0.1454	137	0.0717
0.1465	138	0.0764
0.1476	139	0.0502
0.1486	140	0.0626
0.1497	141	0.0615
0.1507	142	0.0555
0.1518	143	0.0674
0.1529	144	0.0635
0.1539	145	0.0553
0.1550	146	0.0525
0.1561	147	0.055
0.1571	148	0.0665
0.1582	149	0.0703
0.1592	150	0.0657
0.1603	151	0.0612
0.1614	152	0.0671
0.1624	153	0.059
0.1635	154	0.0636
0.1645	155	0.0753
0.1656	156	0.0931
0.1667	157	0.0531
0.1677	158	0.0558
0.1688	159	0.0599
0.1699	160	0.0501
0.1709	161	0.051
0.1720	162	0.0697
0.1730	163	0.074
0.1741	164	0.0607
0.1752	165	0.0611
0.1762	166	0.059
0.1773	167	0.073
0.1783	168	0.0541
0.1794	169	0.0576
0.1805	170	0.0656
0.1815	171	0.0499
0.1826	172	0.055
0.1837	173	0.0646
0.1847	174	0.0747
0.1858	175	0.0558
0.1868	176	0.0537
0.1879	177	0.0574
0.1890	178	0.061
0.1900	179	0.0743
0.1911	180	0.0553
0.1921	181	0.0603
0.1932	182	0.0613
0.1943	183	0.0557
0.1953	184	0.0629
0.1964	185	0.0524
0.1975	186	0.0533
0.1985	187	0.0624
0.1996	188	0.0566
0.2006	189	0.0446
0.2017	190	0.0578
0.2028	191	0.0487
0.2038	192	0.066
0.2049	193	0.0618
0.2059	194	0.0591
0.2070	195	0.0553
0.2081	196	0.052
0.2091	197	0.0451
0.2102	198	0.0633
0.2113	199	0.0658
0.2123	200	0.0623
0.2134	201	0.0593
0.2144	202	0.0491
0.2155	203	0.0526
0.2166	204	0.057
0.2176	205	0.0631
0.2187	206	0.0809
0.2197	207	0.063
0.2208	208	0.0571
0.2219	209	0.054
0.2229	210	0.0607
0.2240	211	0.056
0.2251	212	0.06
0.2261	213	0.0597
0.2272	214	0.0538
0.2282	215	0.0584
0.2293	216	0.0473
0.2304	217	0.052
0.2314	218	0.06
0.2325	219	0.0566
0.2335	220	0.0559
0.2346	221	0.0536
0.2357	222	0.0634
0.2367	223	0.0637
0.2378	224	0.056
0.2389	225	0.0504
0.2399	226	0.0371
0.2410	227	0.0678
0.2420	228	0.0569
0.2431	229	0.0551
0.2442	230	0.0486
0.2452	231	0.0536
0.2463	232	0.0615
0.2473	233	0.0535
0.2484	234	0.0502
0.2495	235	0.0571
0.2505	236	0.0593
0.2516	237	0.0557
0.2527	238	0.0671
0.2537	239	0.0609
0.2548	240	0.0667
0.2558	241	0.064
0.2569	242	0.0503
0.2580	243	0.0461
0.2590	244	0.059
0.2601	245	0.0594
0.2611	246	0.0577
0.2622	247	0.0664
0.2633	248	0.0736
0.2643	249	0.0506
0.2654	250	0.0611
0.2665	251	0.0657
0.2675	252	0.0543
0.2686	253	0.0595
0.2696	254	0.0531
0.2707	255	0.0552
0.2718	256	0.061
0.2728	257	0.0456
0.2739	258	0.0498
0.2749	259	0.0567
0.2760	260	0.0444
0.2771	261	0.0567
0.2781	262	0.0524
0.2792	263	0.0518
0.2803	264	0.0664
0.2813	265	0.0537
0.2824	266	0.0537
0.2834	267	0.0558
0.2845	268	0.0501
0.2856	269	0.0558
0.2866	270	0.0411
0.2877	271	0.0432
0.2887	272	0.0535
0.2898	273	0.0511
0.2909	274	0.0469
0.2919	275	0.0587
0.2930	276	0.052
0.2941	277	0.0594
0.2951	278	0.0651
0.2962	279	0.0486
0.2972	280	0.0602
0.2983	281	0.0567
0.2994	282	0.0547
0.3004	283	0.0669
0.3015	284	0.0543
0.3025	285	0.0616
0.3036	286	0.0532
0.3047	287	0.0689
0.3057	288	0.0461
0.3068	289	0.0516
0.3079	290	0.0496
0.3089	291	0.0581
0.3100	292	0.0446
0.3110	293	0.048
0.3121	294	0.0442
0.3132	295	0.0504
0.3142	296	0.0531
0.3153	297	0.0681
0.3163	298	0.0458
0.3174	299	0.0584
0.3185	300	0.064
0.3195	301	0.0595
0.3206	302	0.0604
0.3217	303	0.0621
0.3227	304	0.0466
0.3238	305	0.0545
0.3248	306	0.0523
0.3259	307	0.0496
0.3270	308	0.0468
0.3280	309	0.0649
0.3291	310	0.056
0.3301	311	0.0539
0.3312	312	0.0497
0.3323	313	0.0517
0.3333	314	0.0511
0.3344	315	0.0511
0.3355	316	0.0518
0.3365	317	0.0508
0.3376	318	0.0579
0.3386	319	0.0463
0.3397	320	0.046
0.3408	321	0.0461
0.3418	322	0.0469
0.3429	323	0.0399
0.3439	324	0.0516
0.3450	325	0.0551
0.3461	326	0.0497
0.3471	327	0.0455
0.3482	328	0.0534
0.3493	329	0.0437
0.3503	330	0.0542
0.3514	331	0.0462
0.3524	332	0.0429
0.3535	333	0.0542
0.3546	334	0.0452
0.3556	335	0.0569
0.3567	336	0.0495
0.3577	337	0.0443
0.3588	338	0.0543
0.3599	339	0.0671
0.3609	340	0.054
0.3620	341	0.0596
0.3631	342	0.0468
0.3641	343	0.0644
0.3652	344	0.044
0.3662	345	0.0477
0.3673	346	0.0403
0.3684	347	0.0553
0.3694	348	0.0533
0.3705	349	0.0447
0.3715	350	0.0527
0.3726	351	0.0465
0.3737	352	0.0518
0.3747	353	0.0345
0.3758	354	0.0515
0.3769	355	0.0438
0.3779	356	0.0489
0.3790	357	0.046
0.3800	358	0.0621
0.3811	359	0.0667
0.3822	360	0.0489
0.3832	361	0.0555
0.3843	362	0.0445
0.3854	363	0.0492
0.3864	364	0.0562
0.3875	365	0.0484
0.3885	366	0.0582
0.3896	367	0.0551
0.3907	368	0.0512
0.3917	369	0.0486
0.3928	370	0.0537
0.3938	371	0.0499
0.3949	372	0.0651
0.3960	373	0.0531
0.3970	374	0.0743
0.3981	375	0.052
0.3992	376	0.0476
0.4002	377	0.0572
0.4013	378	0.0555
0.4023	379	0.0569
0.4034	380	0.052
0.4045	381	0.0524
0.4055	382	0.0726
0.4066	383	0.0456
0.4076	384	0.0531
0.4087	385	0.0474
0.4098	386	0.0485
0.4108	387	0.0459
0.4119	388	0.0474
0.4130	389	0.0541
0.4140	390	0.0452
0.4151	391	0.0362
0.4161	392	0.0407
0.4172	393	0.0449
0.4183	394	0.0444
0.4193	395	0.0469
0.4204	396	0.0493
0.4214	397	0.0437
0.4225	398	0.0551
0.4236	399	0.0412
0.4246	400	0.0401
0.4257	401	0.0488
0.4268	402	0.0506
0.4278	403	0.0458
0.4289	404	0.0436
0.4299	405	0.0574
0.4310	406	0.0516
0.4321	407	0.0599
0.4331	408	0.0476
0.4342	409	0.0462
0.4352	410	0.0502
0.4363	411	0.0448
0.4374	412	0.0461
0.4384	413	0.035
0.4395	414	0.0451
0.4406	415	0.0456
0.4416	416	0.0399
0.4427	417	0.0602
0.4437	418	0.0588
0.4448	419	0.0675
0.4459	420	0.0628
0.4469	421	0.0498
0.4480	422	0.0413
0.4490	423	0.0437
0.4501	424	0.0514
0.4512	425	0.0586
0.4522	426	0.0596
0.4533	427	0.0368
0.4544	428	0.0448
0.4554	429	0.056
0.4565	430	0.0415
0.4575	431	0.0448
0.4586	432	0.055
0.4597	433	0.0442
0.4607	434	0.0462
0.4618	435	0.0479
0.4628	436	0.0507
0.4639	437	0.049
0.4650	438	0.0626
0.4660	439	0.0375
0.4671	440	0.0541
0.4682	441	0.0579
0.4692	442	0.0642
0.4703	443	0.0471
0.4713	444	0.0559
0.4724	445	0.0508
0.4735	446	0.0696
0.4745	447	0.056
0.4756	448	0.0649
0.4766	449	0.0641
0.4777	450	0.0547
0.4788	451	0.0509
0.4798	452	0.0544
0.4809	453	0.0487
0.4820	454	0.0639
0.4830	455	0.047
0.4841	456	0.0513
0.4851	457	0.0451
0.4862	458	0.0567
0.4873	459	0.0541
0.4883	460	0.0475
0.4894	461	0.0445
0.4904	462	0.0597
0.4915	463	0.0434
0.4926	464	0.0468
0.4936	465	0.0449
0.4947	466	0.0422
0.4958	467	0.0504
0.4968	468	0.0565
0.4979	469	0.0611
0.4989	470	0.044
0.5	471	0.0543
0.5011	472	0.0424
0.5021	473	0.0443
0.5032	474	0.0367
0.5042	475	0.0427
0.5053	476	0.0431
0.5064	477	0.063
0.5074	478	0.0421
0.5085	479	0.0367
0.5096	480	0.0456
0.5106	481	0.0586
0.5117	482	0.0747
0.5127	483	0.05
0.5138	484	0.0509
0.5149	485	0.054
0.5159	486	0.0531
0.5170	487	0.0458
0.5180	488	0.0522
0.5191	489	0.0406
0.5202	490	0.0529
0.5212	491	0.0602
0.5223	492	0.0469
0.5234	493	0.0602
0.5244	494	0.0506
0.5255	495	0.0522
0.5265	496	0.0433
0.5276	497	0.0531
0.5287	498	0.0453
0.5297	499	0.0416
0.5308	500	0.0366
0.5318	501	0.0483
0.5329	502	0.0453
0.5340	503	0.0495
0.5350	504	0.0522
0.5361	505	0.0476
0.5372	506	0.0416
0.5382	507	0.0497
0.5393	508	0.0431
0.5403	509	0.0494
0.5414	510	0.041
0.5425	511	0.0412
0.5435	512	0.0399
0.5446	513	0.0478
0.5456	514	0.061
0.5467	515	0.0353
0.5478	516	0.0469
0.5488	517	0.0517
0.5499	518	0.0523
0.5510	519	0.058
0.5520	520	0.0432
0.5531	521	0.0442
0.5541	522	0.0551
0.5552	523	0.0488
0.5563	524	0.0482
0.5573	525	0.0474
0.5584	526	0.0577
0.5594	527	0.0375
0.5605	528	0.0401
0.5616	529	0.0574
0.5626	530	0.0496
0.5637	531	0.0422
0.5648	532	0.047
0.5658	533	0.0455
0.5669	534	0.0405
0.5679	535	0.0391
0.5690	536	0.0495
0.5701	537	0.0464
0.5711	538	0.0457
0.5722	539	0.0449
0.5732	540	0.0583
0.5743	541	0.0591
0.5754	542	0.0487
0.5764	543	0.0456
0.5775	544	0.0423
0.5786	545	0.0571
0.5796	546	0.0472
0.5807	547	0.0556
0.5817	548	0.0483
0.5828	549	0.0424
0.5839	550	0.0557
0.5849	551	0.038
0.5860	552	0.0394
0.5870	553	0.0481
0.5881	554	0.0617
0.5892	555	0.0455
0.5902	556	0.0411
0.5913	557	0.0433
0.5924	558	0.0456
0.5934	559	0.0488
0.5945	560	0.0517
0.5955	561	0.0549
0.5966	562	0.0406
0.5977	563	0.045
0.5987	564	0.049
0.5998	565	0.0547
0.6008	566	0.0529
0.6019	567	0.0524
0.6030	568	0.0472
0.6040	569	0.039
0.6051	570	0.041
0.6062	571	0.0508
0.6072	572	0.0486
0.6083	573	0.0375
0.6093	574	0.0585
0.6104	575	0.05
0.6115	576	0.0509
0.6125	577	0.0394
0.6136	578	0.0467
0.6146	579	0.0371
0.6157	580	0.0415
0.6168	581	0.046
0.6178	582	0.0385
0.6189	583	0.056
0.6200	584	0.0416
0.6210	585	0.0578
0.6221	586	0.0443
0.6231	587	0.0407
0.6242	588	0.0499
0.6253	589	0.056
0.6263	590	0.0456
0.6274	591	0.0412
0.6285	592	0.0473
0.6295	593	0.0378
0.6306	594	0.0544
0.6316	595	0.0502
0.6327	596	0.042
0.6338	597	0.0414
0.6348	598	0.0506
0.6359	599	0.0372
0.6369	600	0.0411
0.6380	601	0.0387
0.6391	602	0.0588
0.6401	603	0.0404
0.6412	604	0.056
0.6423	605	0.0524
0.6433	606	0.0484
0.6444	607	0.0398
0.6454	608	0.0523
0.6465	609	0.0469
0.6476	610	0.0504
0.6486	611	0.0496
0.6497	612	0.0501
0.6507	613	0.0426
0.6518	614	0.0454
0.6529	615	0.0564
0.6539	616	0.0798
0.6550	617	0.0444
0.6561	618	0.039
0.6571	619	0.0428
0.6582	620	0.0504
0.6592	621	0.0525
0.6603	622	0.0471
0.6614	623	0.0402
0.6624	624	0.0456
0.6635	625	0.0384
0.6645	626	0.0446
0.6656	627	0.0468
0.6667	628	0.047
0.6677	629	0.0442
0.6688	630	0.0466
0.6699	631	0.0457
0.6709	632	0.0538
0.6720	633	0.0434
0.6730	634	0.0443
0.6741	635	0.0481
0.6752	636	0.0483
0.6762	637	0.0434
0.6773	638	0.0389
0.6783	639	0.0541
0.6794	640	0.0453
0.6805	641	0.0508
0.6815	642	0.0469
0.6826	643	0.0431
0.6837	644	0.0446
0.6847	645	0.0427
0.6858	646	0.0543
0.6868	647	0.0458
0.6879	648	0.046
0.6890	649	0.0669
0.6900	650	0.046
0.6911	651	0.0462
0.6921	652	0.0493
0.6932	653	0.0484
0.6943	654	0.0466
0.6953	655	0.048
0.6964	656	0.0406
0.6975	657	0.0512
0.6985	658	0.0469
0.6996	659	0.0461
0.7006	660	0.039
0.7017	661	0.0403
0.7028	662	0.0419
0.7038	663	0.0538
0.7049	664	0.0364
0.7059	665	0.039
0.7070	666	0.0417
0.7081	667	0.0478
0.7091	668	0.0443
0.7102	669	0.0394
0.7113	670	0.0417
0.7123	671	0.0412
0.7134	672	0.0493
0.7144	673	0.0532
0.7155	674	0.0371
0.7166	675	0.0344
0.7176	676	0.0421
0.7187	677	0.0489
0.7197	678	0.0362
0.7208	679	0.0539
0.7219	680	0.0404
0.7229	681	0.0607
0.7240	682	0.0456
0.7251	683	0.0507
0.7261	684	0.0415
0.7272	685	0.0361
0.7282	686	0.053
0.7293	687	0.0431
0.7304	688	0.0463
0.7314	689	0.0401
0.7325	690	0.0549
0.7335	691	0.0335
0.7346	692	0.05
0.7357	693	0.0472
0.7367	694	0.0474
0.7378	695	0.0556
0.7389	696	0.0456
0.7399	697	0.0481
0.7410	698	0.0388
0.7420	699	0.0381
0.7431	700	0.0491
0.7442	701	0.0436
0.7452	702	0.0522
0.7463	703	0.0471
0.7473	704	0.0367
0.7484	705	0.0393
0.7495	706	0.0418
0.7505	707	0.0371
0.7516	708	0.0315
0.7527	709	0.0508
0.7537	710	0.0535
0.7548	711	0.0453
0.7558	712	0.0352
0.7569	713	0.0507
0.7580	714	0.046
0.7590	715	0.0393
0.7601	716	0.0453
0.7611	717	0.0403
0.7622	718	0.0346
0.7633	719	0.0492
0.7643	720	0.0437
0.7654	721	0.042
0.7665	722	0.052
0.7675	723	0.043
0.7686	724	0.0524
0.7696	725	0.0385
0.7707	726	0.0484
0.7718	727	0.0454
0.7728	728	0.0478
0.7739	729	0.0411
0.7749	730	0.0415
0.7760	731	0.0323
0.7771	732	0.0492
0.7781	733	0.0429
0.7792	734	0.0445
0.7803	735	0.0484
0.7813	736	0.042
0.7824	737	0.0486
0.7834	738	0.0349
0.7845	739	0.0472
0.7856	740	0.0413
0.7866	741	0.0476
0.7877	742	0.0519
0.7887	743	0.0405
0.7898	744	0.0439
0.7909	745	0.035
0.7919	746	0.0478
0.7930	747	0.0476
0.7941	748	0.0382
0.7951	749	0.0568
0.7962	750	0.0505
0.7972	751	0.0572
0.7983	752	0.0352
0.7994	753	0.0405
0.8004	754	0.0505
0.8015	755	0.0478
0.8025	756	0.0465
0.8036	757	0.0493
0.8047	758	0.0414
0.8057	759	0.0438
0.8068	760	0.0559
0.8079	761	0.044
0.8089	762	0.0385
0.8100	763	0.0414
0.8110	764	0.0516
0.8121	765	0.0475
0.8132	766	0.0394
0.8142	767	0.0566
0.8153	768	0.0385
0.8163	769	0.0405
0.8174	770	0.0392
0.8185	771	0.0364
0.8195	772	0.0501
0.8206	773	0.0462
0.8217	774	0.0436
0.8227	775	0.0548
0.8238	776	0.0429
0.8248	777	0.0416
0.8259	778	0.043
0.8270	779	0.0481
0.8280	780	0.0382
0.8291	781	0.0439
0.8301	782	0.0369
0.8312	783	0.0377
0.8323	784	0.0463
0.8333	785	0.0372
0.8344	786	0.0563
0.8355	787	0.0447
0.8365	788	0.0366
0.8376	789	0.0466
0.8386	790	0.049
0.8397	791	0.0557
0.8408	792	0.0495
0.8418	793	0.0359
0.8429	794	0.0519
0.8439	795	0.0538
0.8450	796	0.0388
0.8461	797	0.0431
0.8471	798	0.0513
0.8482	799	0.047
0.8493	800	0.0485
0.8503	801	0.052
0.8514	802	0.032
0.8524	803	0.0419
0.8535	804	0.0439
0.8546	805	0.0548
0.8556	806	0.0433
0.8567	807	0.0407
0.8577	808	0.0467
0.8588	809	0.0494
0.8599	810	0.0516
0.8609	811	0.0418
0.8620	812	0.0344
0.8631	813	0.0505
0.8641	814	0.0477
0.8652	815	0.0533
0.8662	816	0.0431
0.8673	817	0.0439
0.8684	818	0.0321
0.8694	819	0.0418
0.8705	820	0.043
0.8715	821	0.035
0.8726	822	0.0473
0.8737	823	0.0294
0.8747	824	0.0573
0.8758	825	0.038
0.8769	826	0.04
0.8779	827	0.0406
0.8790	828	0.0413
0.8800	829	0.0416
0.8811	830	0.0344
0.8822	831	0.0511
0.8832	832	0.0403
0.8843	833	0.0613
0.8854	834	0.0384
0.8864	835	0.0363
0.8875	836	0.0324
0.8885	837	0.0472
0.8896	838	0.049
0.8907	839	0.0465
0.8917	840	0.0419
0.8928	841	0.0455
0.8938	842	0.0481
0.8949	843	0.0463
0.8960	844	0.0352
0.8970	845	0.0527
0.8981	846	0.0561
0.8992	847	0.0381
0.9002	848	0.0434
0.9013	849	0.0436
0.9023	850	0.0462
0.9034	851	0.0503
0.9045	852	0.0479
0.9055	853	0.0451
0.9066	854	0.0459
0.9076	855	0.0508
0.9087	856	0.0453
0.9098	857	0.0444
0.9108	858	0.0461
0.9119	859	0.056
0.9130	860	0.0449
0.9140	861	0.0477
0.9151	862	0.0422
0.9161	863	0.0481
0.9172	864	0.0508
0.9183	865	0.037
0.9193	866	0.0491
0.9204	867	0.0627
0.9214	868	0.0432
0.9225	869	0.0377
0.9236	870	0.0448
0.9246	871	0.0366
0.9257	872	0.0406
0.9268	873	0.0445
0.9278	874	0.0424
0.9289	875	0.0322
0.9299	876	0.0441
0.9310	877	0.0498
0.9321	878	0.0418
0.9331	879	0.0524
0.9342	880	0.06
0.9352	881	0.0428
0.9363	882	0.0428
0.9374	883	0.0509
0.9384	884	0.0428
0.9395	885	0.0295
0.9406	886	0.0535
0.9416	887	0.04
0.9427	888	0.0425
0.9437	889	0.0583
0.9448	890	0.0374
0.9459	891	0.0489
0.9469	892	0.0472
0.9480	893	0.0449
0.9490	894	0.0342
0.9501	895	0.0604
0.9512	896	0.047
0.9522	897	0.0433
0.9533	898	0.0355
0.9544	899	0.0419
0.9554	900	0.044
0.9565	901	0.0457
0.9575	902	0.0377
0.9586	903	0.0416
0.9597	904	0.0505
0.9607	905	0.0487
0.9618	906	0.0473
0.9628	907	0.0521
0.9639	908	0.0336
0.9650	909	0.0446
0.9660	910	0.0423
0.9671	911	0.0442
0.9682	912	0.0505
0.9692	913	0.0488
0.9703	914	0.0367
0.9713	915	0.0382
0.9724	916	0.0487
0.9735	917	0.061
0.9745	918	0.0461
0.9756	919	0.0377
0.9766	920	0.0398
0.9777	921	0.0363
0.9788	922	0.0375
0.9798	923	0.0503
0.9809	924	0.0493
0.9820	925	0.04
0.9830	926	0.0379
0.9841	927	0.0422
0.9851	928	0.0517
0.9862	929	0.0488
0.9873	930	0.057
0.9883	931	0.0388
0.9894	932	0.0374
0.9904	933	0.0374
0.9915	934	0.0504
0.9926	935	0.056
0.9936	936	0.0478
0.9947	937	0.0286
0.9958	938	0.0415
0.9968	939	0.037
0.9979	940	0.0445
0.9989	941	0.0451
1.0	942	0.036
1.0011	943	0.0346
1.0021	944	0.044
1.0032	945	0.044
1.0042	946	0.0487
1.0053	947	0.0411
1.0064	948	0.0385
1.0074	949	0.0414
1.0085	950	0.0369
1.0096	951	0.0381
1.0106	952	0.0358
1.0117	953	0.0455
1.0127	954	0.0414
1.0138	955	0.0327
1.0149	956	0.0492
1.0159	957	0.0552
1.0170	958	0.0399
1.0180	959	0.0442
1.0191	960	0.0398
1.0202	961	0.0418
1.0212	962	0.037
1.0223	963	0.0433
1.0234	964	0.0405
1.0244	965	0.0429
1.0255	966	0.0364
1.0265	967	0.0424
1.0276	968	0.0419
1.0287	969	0.044
1.0297	970	0.0326
1.0308	971	0.0391
1.0318	972	0.0436
1.0329	973	0.0466
1.0340	974	0.0357
1.0350	975	0.0562
1.0361	976	0.0328
1.0372	977	0.0423
1.0382	978	0.0316
1.0393	979	0.0488
1.0403	980	0.0352
1.0414	981	0.0383
1.0425	982	0.0544
1.0435	983	0.0336
1.0446	984	0.0426
1.0456	985	0.0301
1.0467	986	0.048
1.0478	987	0.0398
1.0488	988	0.048
1.0499	989	0.0451
1.0510	990	0.0477
1.0520	991	0.0437
1.0531	992	0.0367
1.0541	993	0.0438
1.0552	994	0.0482
1.0563	995	0.0445
1.0573	996	0.0499
1.0584	997	0.0409
1.0594	998	0.0426
1.0605	999	0.0417
1.0616	1000	0.0498

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.2.1
• Transformers: 4.44.2
• PyTorch: 2.3.1+cu121
• Accelerate: 1.1.1
• Datasets: 2.21.0
• Tokenizers: 0.19.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}