sarwin/rp-embed-max

SentenceTransformer based on nreimers/MiniLM-L6-H384-uncased

This is a sentence-transformers model finetuned from nreimers/MiniLM-L6-H384-uncased. 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: nreimers/MiniLM-L6-H384-uncased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 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: 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})
)

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 = [
    'Summarizing the Evidence on the International Trade in Illegal Wildlife',
    'The global trade in illegal wildlife is a multi-billion dollar industry that threatens biodiversity and acts as a potential avenue for invasive species and disease spread. Despite the broad-sweeping implications of illegal wildlife sales, scientists have yet to describe the scope and scale of the trade. Here, we provide the most thorough and current description of the illegal wildlife trade using 12 years of seizure records compiled by TRAFFIC, the wildlife trade monitoring network. These records comprise 967 seizures including massive quantities of ivory, tiger skins, live reptiles, and other endangered wildlife and wildlife products. Most seizures originate in Southeast Asia, a recently identified hotspot for future emerging infectious diseases. To date, regulation and enforcement have been insufficient to effectively control the global trade in illegal wildlife at national and international scales. Effective control will require a multi-pronged approach including community-scale education and empowering local people to value wildlife, coordinated international regulation, and a greater allocation of national resources to on-the-ground enforcement.',
    'This paper proposes a method to represent classifiers or learned regression functions using an OWL ontology. Also proposed are methods for finding an appropriate learned function to answer a simple query. The ontology standardizes variable names and dependence properties, so that feature values can be given by users or found on the semantic web.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Training Details

Training Dataset

Unnamed Dataset

• Size: 730,454 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 5 tokens mean: 15.55 tokens max: 41 tokens	min: 21 tokens mean: 195.91 tokens max: 512 tokens

• Samples:

  sentence_0	sentence_1
  A parallel algorithm for constructing independent spanning trees in twisted cubes	A long-standing conjecture mentions that a kk-connected graph GG admits kk independent spanning trees (ISTs for short) rooted at an arbitrary node of GG. An nn-dimensional twisted cube, denoted by TQnTQn, is a variation of hypercube with connectivity nn and has many features superior to those of hypercube. Yang (2010) first proposed an algorithm to construct nn edge-disjoint spanning trees in TQnTQn for any odd integer n⩾3n⩾3 and showed that half of them are ISTs. At a later stage, Wang et al. (2012) inferred that the above conjecture in affirmative for TQnTQn by providing an O(NlogN)O(NlogN) time algorithm to construct nn ISTs, where N=2nN=2n is the number of nodes in TQnTQn. However, this algorithm is executed in a recursive fashion and thus is hard to be parallelized. In this paper, we revisit the problem of constructing ISTs in twisted cubes and present a non-recursive algorithm. Our approach can be fully parallelized to make the use of all nodes of TQnTQn as processors for computation in such a way that each node can determine its parent in all spanning trees directly by referring its address and tree indices in O(logN)O(logN) time.
  A Novel Method for Separating and Locating Multiple Partial Discharge Sources in a Substation	To separate and locate multi-partial discharge (PD) sources in a substation, the use of spectrum differences of ultra-high frequency signals radiated from various sources as characteristic parameters has been previously reported. However, the separation success rate was poor when signal-to-noise ratio was low, and the localization result was a coordinate on two-dimensional plane. In this paper, a novel method is proposed to improve the separation rate and the localization accuracy. A directional measuring platform is built using two directional antennas. The time delay (TD) of the signals captured by the antennas is calculated, and TD sequences are obtained by rotating the platform at different angles. The sequences are separated with the TD distribution feature, and the directions of the multi-PD sources are calculated. The PD sources are located by directions using the error probability method. To verify the method, a simulated model with three PD sources was established by XFdtd. Simulation results show that the separation rate is increased from 71% to 95% compared with the previous method, and an accurate three-dimensional localization result was obtained. A field test with two PD sources was carried out, and the sources were separated and located accurately by the proposed method.
  Every ternary permutation constraint satisfaction problem parameterized above average has a kernel with a quadratic number of variables	A ternary Permutation-CSP is specified by a subset @P of the symmetric group S"3. An instance of such a problem consists of a set of variables V and a multiset of constraints, which are ordered triples of distinct variables of V. The objective is to find a linear ordering @a of V that maximizes the number of triples whose rearrangement (under @a) follows a permutation in @P. We prove that every ternary Permutation-CSP parameterized above average has a kernel with a quadratic number of variables.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 5
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_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
• num_train_epochs: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: 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: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0055	500	1.6701
0.0110	1000	0.8225
0.0164	1500	0.3883
0.0219	2000	0.2685
0.0274	2500	0.2349
0.0329	3000	0.1685
0.0383	3500	0.1409
0.0438	4000	0.1262
0.0493	4500	0.1195
0.0548	5000	0.1044
0.0602	5500	0.0989
0.0657	6000	0.0787
0.0712	6500	0.0895
0.0767	7000	0.0708
0.0821	7500	0.0834
0.0876	8000	0.0634
0.0931	8500	0.0643
0.0986	9000	0.0567
0.1040	9500	0.0646
0.1095	10000	0.0607
0.1150	10500	0.0564
0.1205	11000	0.068
0.1259	11500	0.0536
0.1314	12000	0.0594
0.1369	12500	0.057
0.1424	13000	0.0555
0.1479	13500	0.0485
0.1533	14000	0.0528
0.1588	14500	0.0478
0.1643	15000	0.0586
0.1698	15500	0.0539
0.1752	16000	0.0432
0.1807	16500	0.0542
0.1862	17000	0.0536
0.1917	17500	0.0492
0.1971	18000	0.0427
0.2026	18500	0.0489
0.2081	19000	0.0502
0.2136	19500	0.0432
0.2190	20000	0.0459
0.2245	20500	0.0376
0.2300	21000	0.0489
0.2355	21500	0.0515
0.2409	22000	0.0429
0.2464	22500	0.0417
0.2519	23000	0.0478
0.2574	23500	0.0359
0.2628	24000	0.0452
0.2683	24500	0.0443
0.2738	25000	0.0409
0.2793	25500	0.0421
0.2848	26000	0.0393
0.2902	26500	0.0409
0.2957	27000	0.032
0.3012	27500	0.0468
0.3067	28000	0.0285
0.3121	28500	0.0311
0.3176	29000	0.0304
0.3231	29500	0.0349
0.3286	30000	0.0352
0.3340	30500	0.0367
0.3395	31000	0.0385
0.3450	31500	0.0325
0.3505	32000	0.0302
0.3559	32500	0.0393
0.3614	33000	0.032
0.3669	33500	0.0263
0.3724	34000	0.0343
0.3778	34500	0.0349
0.3833	35000	0.0282
0.3888	35500	0.034
0.3943	36000	0.0376
0.3998	36500	0.0265
0.4052	37000	0.0267
0.4107	37500	0.0241
0.4162	38000	0.033
0.4217	38500	0.0323
0.4271	39000	0.0278
0.4326	39500	0.025
0.4381	40000	0.0363
0.4436	40500	0.0312
0.4490	41000	0.0307
0.4545	41500	0.0305
0.4600	42000	0.028
0.4655	42500	0.0279
0.4709	43000	0.0265
0.4764	43500	0.0262
0.4819	44000	0.0308
0.4874	44500	0.0282
0.4928	45000	0.0243
0.4983	45500	0.0236
0.5038	46000	0.02
0.5093	46500	0.0254
0.5147	47000	0.0275
0.5202	47500	0.0309
0.5257	48000	0.031
0.5312	48500	0.0271
0.5367	49000	0.0218
0.5421	49500	0.0249
0.5476	50000	0.0285
0.5531	50500	0.03
0.5586	51000	0.0284
0.5640	51500	0.0258
0.5695	52000	0.0228
0.5750	52500	0.0305
0.5805	53000	0.0234
0.5859	53500	0.0209
0.5914	54000	0.0341
0.5969	54500	0.0269
0.6024	55000	0.0267
0.6078	55500	0.0245
0.6133	56000	0.0263
0.6188	56500	0.0195
0.6243	57000	0.0209
0.6297	57500	0.0313
0.6352	58000	0.0247
0.6407	58500	0.0285
0.6462	59000	0.0301
0.6516	59500	0.0227
0.6571	60000	0.0235
0.6626	60500	0.0272
0.6681	61000	0.025
0.6736	61500	0.0276
0.6790	62000	0.0289
0.6845	62500	0.0232
0.6900	63000	0.0258
0.6955	63500	0.0254
0.7009	64000	0.0205
0.7064	64500	0.0216
0.7119	65000	0.0304
0.7174	65500	0.0234
0.7228	66000	0.0233
0.7283	66500	0.0239
0.7338	67000	0.0166
0.7393	67500	0.0211
0.7447	68000	0.0212
0.7502	68500	0.0247
0.7557	69000	0.023
0.7612	69500	0.0261
0.7666	70000	0.0204
0.7721	70500	0.026
0.7776	71000	0.0299
0.7831	71500	0.0183
0.7885	72000	0.0228
0.7940	72500	0.0181
0.7995	73000	0.0237
0.8050	73500	0.0237
0.8105	74000	0.0158
0.8159	74500	0.0222
0.8214	75000	0.0196
0.8269	75500	0.0242
0.8324	76000	0.0218
0.8378	76500	0.0201
0.8433	77000	0.026
0.8488	77500	0.0232
0.8543	78000	0.0254
0.8597	78500	0.0218
0.8652	79000	0.0219
0.8707	79500	0.0255
0.8762	80000	0.0201
0.8816	80500	0.0301
0.8871	81000	0.0275
0.8926	81500	0.018
0.8981	82000	0.028
0.9035	82500	0.0223
0.9090	83000	0.0201
0.9145	83500	0.0299
0.9200	84000	0.0251
0.9254	84500	0.0203
0.9309	85000	0.0209
0.9364	85500	0.0236
0.9419	86000	0.0191
0.9474	86500	0.0168
0.9528	87000	0.017
0.9583	87500	0.0201
0.9638	88000	0.0171
0.9693	88500	0.0217
0.9747	89000	0.0208
0.9802	89500	0.0157
0.9857	90000	0.0218
0.9912	90500	0.021
0.9966	91000	0.0159
1.0021	91500	0.0189
1.0076	92000	0.0182
1.0131	92500	0.0206
1.0185	93000	0.0179
1.0240	93500	0.0168
1.0295	94000	0.019
1.0350	94500	0.0173
1.0404	95000	0.0172
1.0459	95500	0.0187
1.0514	96000	0.0199
1.0569	96500	0.0202
1.0624	97000	0.0198
1.0678	97500	0.0157
1.0733	98000	0.0178
1.0788	98500	0.0147
1.0843	99000	0.0152
1.0897	99500	0.0152
1.0952	100000	0.0126
1.1007	100500	0.0115
1.1062	101000	0.0122
1.1116	101500	0.0097
1.1171	102000	0.0149
1.1226	102500	0.0151
1.1281	103000	0.0134
1.1335	103500	0.0157
1.1390	104000	0.0141
1.1445	104500	0.0139
1.1500	105000	0.0149
1.1554	105500	0.0103
1.1609	106000	0.0138
1.1664	106500	0.0116
1.1719	107000	0.0146
1.1773	107500	0.0168
1.1828	108000	0.0166
1.1883	108500	0.0136
1.1938	109000	0.0103
1.1993	109500	0.0128
1.2047	110000	0.0112
1.2102	110500	0.0103
1.2157	111000	0.0133
1.2212	111500	0.0118
1.2266	112000	0.009
1.2321	112500	0.0151
1.2376	113000	0.0146
1.2431	113500	0.0143
1.2485	114000	0.01
1.2540	114500	0.0147
1.2595	115000	0.011
1.2650	115500	0.0121
1.2704	116000	0.0117
1.2759	116500	0.0151
1.2814	117000	0.0143
1.2869	117500	0.0163
1.2923	118000	0.0135
1.2978	118500	0.0118
1.3033	119000	0.0129
1.3088	119500	0.0062
1.3142	120000	0.0127
1.3197	120500	0.014
1.3252	121000	0.0131
1.3307	121500	0.0162
1.3362	122000	0.0107
1.3416	122500	0.0125
1.3471	123000	0.0136
1.3526	123500	0.0112
1.3581	124000	0.0126
1.3635	124500	0.0079
1.3690	125000	0.0104
1.3745	125500	0.0137
1.3800	126000	0.0075
1.3854	126500	0.0108
1.3909	127000	0.0087
1.3964	127500	0.0138
1.4019	128000	0.0056
1.4073	128500	0.0067
1.4128	129000	0.0103
1.4183	129500	0.0102
1.4238	130000	0.0119
1.4292	130500	0.0094
1.4347	131000	0.0075
1.4402	131500	0.0146
1.4457	132000	0.0103
1.4511	132500	0.0123
1.4566	133000	0.0107
1.4621	133500	0.0071
1.4676	134000	0.0087
1.4731	134500	0.0072
1.4785	135000	0.0094
1.4840	135500	0.0083
1.4895	136000	0.0104
1.4950	136500	0.0076
1.5004	137000	0.006
1.5059	137500	0.0085
1.5114	138000	0.0061
1.5169	138500	0.0106
1.5223	139000	0.0088
1.5278	139500	0.0111
1.5333	140000	0.0094
1.5388	140500	0.0079
1.5442	141000	0.0095
1.5497	141500	0.0098
1.5552	142000	0.0139
1.5607	142500	0.0085
1.5661	143000	0.0094
1.5716	143500	0.0088
1.5771	144000	0.0092
1.5826	144500	0.0071
1.5880	145000	0.0101
1.5935	145500	0.011
1.5990	146000	0.0097
1.6045	146500	0.0071
1.6100	147000	0.0114
1.6154	147500	0.0087
1.6209	148000	0.0075
1.6264	148500	0.0039
1.6319	149000	0.0091
1.6373	149500	0.0117
1.6428	150000	0.01
1.6483	150500	0.0099
1.6538	151000	0.0069
1.6592	151500	0.0084
1.6647	152000	0.0118
1.6702	152500	0.0078
1.6757	153000	0.0067
1.6811	153500	0.0133
1.6866	154000	0.0079
1.6921	154500	0.0092
1.6976	155000	0.0069
1.7030	155500	0.008
1.7085	156000	0.0124
1.7140	156500	0.0112
1.7195	157000	0.0074
1.7249	157500	0.0091
1.7304	158000	0.0088
1.7359	158500	0.0061
1.7414	159000	0.0089
1.7469	159500	0.0082
1.7523	160000	0.0103
1.7578	160500	0.0094
1.7633	161000	0.0073
1.7688	161500	0.0116
1.7742	162000	0.0112
1.7797	162500	0.0057
1.7852	163000	0.0075
1.7907	163500	0.0062
1.7961	164000	0.0046
1.8016	164500	0.0091
1.8071	165000	0.0066
1.8126	165500	0.0051
1.8180	166000	0.0066
1.8235	166500	0.0093
1.8290	167000	0.0079
1.8345	167500	0.0067
1.8399	168000	0.007
1.8454	168500	0.0133
1.8509	169000	0.0071
1.8564	169500	0.0091
1.8619	170000	0.0067
1.8673	170500	0.0091
1.8728	171000	0.0103
1.8783	171500	0.0058
1.8838	172000	0.0116
1.8892	172500	0.0089
1.8947	173000	0.0137
1.9002	173500	0.0065
1.9057	174000	0.0098
1.9111	174500	0.0083
1.9166	175000	0.0115
1.9221	175500	0.0083
1.9276	176000	0.0084
1.9330	176500	0.0091
1.9385	177000	0.0092
1.9440	177500	0.0054
1.9495	178000	0.0049
1.9549	178500	0.0072
1.9604	179000	0.0052
1.9659	179500	0.0063
1.9714	180000	0.0107
1.9768	180500	0.0061
1.9823	181000	0.0059
1.9878	181500	0.0067
1.9933	182000	0.0078
1.9988	182500	0.007
2.0042	183000	0.0065
2.0097	183500	0.0073
2.0152	184000	0.01
2.0207	184500	0.0072
2.0261	185000	0.0055
2.0316	185500	0.0087
2.0371	186000	0.0077
2.0426	186500	0.0067
2.0480	187000	0.008
2.0535	187500	0.0074
2.0590	188000	0.0072
2.0645	188500	0.0045
2.0699	189000	0.0082
2.0754	189500	0.0042
2.0809	190000	0.0076
2.0864	190500	0.0058
2.0918	191000	0.005
2.0973	191500	0.0047
2.1028	192000	0.0045
2.1083	192500	0.0043
2.1137	193000	0.0049
2.1192	193500	0.0058
2.1247	194000	0.0081
2.1302	194500	0.0057
2.1357	195000	0.0047
2.1411	195500	0.0073
2.1466	196000	0.0056
2.1521	196500	0.006
2.1576	197000	0.0061
2.1630	197500	0.0042
2.1685	198000	0.0057
2.1740	198500	0.0055
2.1795	199000	0.0053
2.1849	199500	0.0085
2.1904	200000	0.005
2.1959	200500	0.0055
2.2014	201000	0.0032
2.2068	201500	0.0054
2.2123	202000	0.0037
2.2178	202500	0.0046
2.2233	203000	0.0029
2.2287	203500	0.0043
2.2342	204000	0.0063
2.2397	204500	0.0064
2.2452	205000	0.0046
2.2506	205500	0.0061
2.2561	206000	0.0034
2.2616	206500	0.0046
2.2671	207000	0.0059
2.2726	207500	0.0044
2.2780	208000	0.0054
2.2835	208500	0.0049
2.2890	209000	0.0096
2.2945	209500	0.0045
2.2999	210000	0.0057
2.3054	210500	0.0032
2.3109	211000	0.0031
2.3164	211500	0.0043
2.3218	212000	0.0068
2.3273	212500	0.0048
2.3328	213000	0.0042
2.3383	213500	0.0068
2.3437	214000	0.0041
2.3492	214500	0.0042
2.3547	215000	0.0051
2.3602	215500	0.0049
2.3656	216000	0.0019
2.3711	216500	0.0039
2.3766	217000	0.0068
2.3821	217500	0.0033
2.3875	218000	0.0048
2.3930	218500	0.0052
2.3985	219000	0.0063
2.4040	219500	0.003
2.4095	220000	0.0036
2.4149	220500	0.004
2.4204	221000	0.006
2.4259	221500	0.0048
2.4314	222000	0.0037
2.4368	222500	0.0034
2.4423	223000	0.0049
2.4478	223500	0.0036
2.4533	224000	0.0046
2.4587	224500	0.0039
2.4642	225000	0.0021
2.4697	225500	0.0035
2.4752	226000	0.0034
2.4806	226500	0.003
2.4861	227000	0.0032
2.4916	227500	0.005
2.4971	228000	0.0025
2.5025	228500	0.0036
2.5080	229000	0.0021
2.5135	229500	0.0025
2.5190	230000	0.0036
2.5245	230500	0.0033
2.5299	231000	0.0049
2.5354	231500	0.0044
2.5409	232000	0.0029
2.5464	232500	0.0028
2.5518	233000	0.0091
2.5573	233500	0.004
2.5628	234000	0.0036
2.5683	234500	0.0029
2.5737	235000	0.0035
2.5792	235500	0.0038
2.5847	236000	0.0028
2.5902	236500	0.0041
2.5956	237000	0.0037
2.6011	237500	0.0031
2.6066	238000	0.0036
2.6121	238500	0.0052
2.6175	239000	0.0031
2.6230	239500	0.0023
2.6285	240000	0.0043
2.6340	240500	0.0027
2.6394	241000	0.0048
2.6449	241500	0.0046
2.6504	242000	0.0038
2.6559	242500	0.0033
2.6614	243000	0.003
2.6668	243500	0.0057
2.6723	244000	0.0044
2.6778	244500	0.0058
2.6833	245000	0.003
2.6887	245500	0.0042
2.6942	246000	0.0045
2.6997	246500	0.0031
2.7052	247000	0.0021
2.7106	247500	0.0043
2.7161	248000	0.0058
2.7216	248500	0.0041
2.7271	249000	0.0038
2.7325	249500	0.0019
2.7380	250000	0.0029
2.7435	250500	0.003
2.7490	251000	0.0038
2.7544	251500	0.004
2.7599	252000	0.0049
2.7654	252500	0.0039
2.7709	253000	0.005
2.7763	253500	0.0046
2.7818	254000	0.0025
2.7873	254500	0.0044
2.7928	255000	0.0023
2.7983	255500	0.0038
2.8037	256000	0.0032
2.8092	256500	0.0021
2.8147	257000	0.0023
2.8202	257500	0.0042
2.8256	258000	0.0042
2.8311	258500	0.0053
2.8366	259000	0.0021
2.8421	259500	0.0033
2.8475	260000	0.0047
2.8530	260500	0.0048
2.8585	261000	0.0022
2.8640	261500	0.0036
2.8694	262000	0.0034
2.8749	262500	0.0029
2.8804	263000	0.0038
2.8859	263500	0.0067
2.8913	264000	0.003
2.8968	264500	0.0049
2.9023	265000	0.0027
2.9078	265500	0.004
2.9132	266000	0.0042
2.9187	266500	0.0042
2.9242	267000	0.0038
2.9297	267500	0.0029
2.9352	268000	0.0039
2.9406	268500	0.0039
2.9461	269000	0.002
2.9516	269500	0.0022
2.9571	270000	0.002
2.9625	270500	0.003
2.9680	271000	0.0019
2.9735	271500	0.0044
2.9790	272000	0.0028
2.9844	272500	0.0031
2.9899	273000	0.0025
2.9954	273500	0.0021
3.0009	274000	0.0025
3.0063	274500	0.0038
3.0118	275000	0.0045
3.0173	275500	0.002
3.0228	276000	0.0035
3.0282	276500	0.0046
3.0337	277000	0.0033
3.0392	277500	0.002
3.0447	278000	0.0036
3.0501	278500	0.0025
3.0556	279000	0.0039
3.0611	279500	0.0029
3.0666	280000	0.004
3.0721	280500	0.0023
3.0775	281000	0.0019
3.0830	281500	0.0019
3.0885	282000	0.0027
3.0940	282500	0.0014
3.0994	283000	0.0019
3.1049	283500	0.0018
3.1104	284000	0.0016
3.1159	284500	0.0017
3.1213	285000	0.0049
3.1268	285500	0.0022
3.1323	286000	0.0023
3.1378	286500	0.0016
3.1432	287000	0.002
3.1487	287500	0.0025
3.1542	288000	0.0012
3.1597	288500	0.0021
3.1651	289000	0.0017
3.1706	289500	0.0019
3.1761	290000	0.0019
3.1816	290500	0.0042
3.1871	291000	0.0027
3.1925	291500	0.0011
3.1980	292000	0.002
3.2035	292500	0.0021
3.2090	293000	0.0015
3.2144	293500	0.0017
3.2199	294000	0.002
3.2254	294500	0.0012
3.2309	295000	0.0017
3.2363	295500	0.0029
3.2418	296000	0.0019
3.2473	296500	0.0017
3.2528	297000	0.0019
3.2582	297500	0.0012
3.2637	298000	0.0024
3.2692	298500	0.0017
3.2747	299000	0.0022
3.2801	299500	0.002
3.2856	300000	0.0028
3.2911	300500	0.0036
3.2966	301000	0.0015
3.3020	301500	0.0024
3.3075	302000	0.0015
3.3130	302500	0.0012
3.3185	303000	0.0022
3.3240	303500	0.0015
3.3294	304000	0.0023
3.3349	304500	0.0017
3.3404	305000	0.0021
3.3459	305500	0.0017
3.3513	306000	0.0015
3.3568	306500	0.0023
3.3623	307000	0.0014
3.3678	307500	0.0019
3.3732	308000	0.0017
3.3787	308500	0.0027
3.3842	309000	0.0016
3.3897	309500	0.0019
3.3951	310000	0.0037
3.4006	310500	0.0016
3.4061	311000	0.0012
3.4116	311500	0.0024
3.4170	312000	0.0016
3.4225	312500	0.0022
3.4280	313000	0.0015
3.4335	313500	0.0017
3.4389	314000	0.0015
3.4444	314500	0.0018
3.4499	315000	0.0015
3.4554	315500	0.0019
3.4609	316000	0.0009
3.4663	316500	0.001
3.4718	317000	0.001
3.4773	317500	0.0023
3.4828	318000	0.0012
3.4882	318500	0.0012
3.4937	319000	0.0011
3.4992	319500	0.0008
3.5047	320000	0.0018
3.5101	320500	0.0009
3.5156	321000	0.0016
3.5211	321500	0.0012
3.5266	322000	0.0015
3.5320	322500	0.0024
3.5375	323000	0.0016
3.5430	323500	0.0014
3.5485	324000	0.0014
3.5539	324500	0.0047
3.5594	325000	0.0013
3.5649	325500	0.0012
3.5704	326000	0.0013
3.5758	326500	0.0011
3.5813	327000	0.0011
3.5868	327500	0.0016
3.5923	328000	0.0022
3.5978	328500	0.0017
3.6032	329000	0.0012
3.6087	329500	0.002
3.6142	330000	0.0016
3.6197	330500	0.0009
3.6251	331000	0.0011
3.6306	331500	0.0019
3.6361	332000	0.0011
3.6416	332500	0.0021
3.6470	333000	0.0029
3.6525	333500	0.001
3.6580	334000	0.0016
3.6635	334500	0.0016
3.6689	335000	0.0036
3.6744	335500	0.0012
3.6799	336000	0.003
3.6854	336500	0.0014
3.6908	337000	0.0018
3.6963	337500	0.001
3.7018	338000	0.001
3.7073	338500	0.0016
3.7127	339000	0.0025
3.7182	339500	0.001
3.7237	340000	0.0018
3.7292	340500	0.0015
3.7347	341000	0.001
3.7401	341500	0.0009
3.7456	342000	0.0013
3.7511	342500	0.0014
3.7566	343000	0.0013
3.7620	343500	0.0011
3.7675	344000	0.0026
3.7730	344500	0.0014
3.7785	345000	0.0021
3.7839	345500	0.0015
3.7894	346000	0.0013
3.7949	346500	0.0013
3.8004	347000	0.0019
3.8058	347500	0.0009
3.8113	348000	0.0009
3.8168	348500	0.0014
3.8223	349000	0.0012
3.8277	349500	0.0032
3.8332	350000	0.0015
3.8387	350500	0.0011
3.8442	351000	0.002
3.8497	351500	0.0012
3.8551	352000	0.0026
3.8606	352500	0.001
3.8661	353000	0.0018
3.8716	353500	0.0014
3.8770	354000	0.001
3.8825	354500	0.0018
3.8880	355000	0.0027
3.8935	355500	0.0027
3.8989	356000	0.0011
3.9044	356500	0.0024
3.9099	357000	0.0012
3.9154	357500	0.0018
3.9208	358000	0.0012
3.9263	358500	0.0015
3.9318	359000	0.0015
3.9373	359500	0.0018
3.9427	360000	0.0017
3.9482	360500	0.0009
3.9537	361000	0.001
3.9592	361500	0.0013
3.9646	362000	0.0008
3.9701	362500	0.0018
3.9756	363000	0.0027
3.9811	363500	0.0009
3.9866	364000	0.0008
3.9920	364500	0.001
3.9975	365000	0.0009
4.0030	365500	0.0012
4.0085	366000	0.0011
4.0139	366500	0.0023
4.0194	367000	0.0023
4.0249	367500	0.0012
4.0304	368000	0.0018
4.0358	368500	0.0013
4.0413	369000	0.0009
4.0468	369500	0.0016
4.0523	370000	0.0011
4.0577	370500	0.0011
4.0632	371000	0.0009
4.0687	371500	0.0012
4.0742	372000	0.0011
4.0796	372500	0.0008
4.0851	373000	0.001
4.0906	373500	0.0008
4.0961	374000	0.0009
4.1015	374500	0.0008
4.1070	375000	0.0008
4.1125	375500	0.0008
4.1180	376000	0.0009
4.1235	376500	0.0021
4.1289	377000	0.0007
4.1344	377500	0.0014
4.1399	378000	0.0008
4.1454	378500	0.0015
4.1508	379000	0.0008
4.1563	379500	0.0008
4.1618	380000	0.0015
4.1673	380500	0.0008
4.1727	381000	0.0009
4.1782	381500	0.0018
4.1837	382000	0.0013
4.1892	382500	0.0012
4.1946	383000	0.0008
4.2001	383500	0.0008
4.2056	384000	0.0008
4.2111	384500	0.0008
4.2165	385000	0.001
4.2220	385500	0.0008
4.2275	386000	0.0008
4.2330	386500	0.0009
4.2384	387000	0.0008
4.2439	387500	0.0008
4.2494	388000	0.0011
4.2549	388500	0.0009
4.2604	389000	0.0007
4.2658	389500	0.001
4.2713	390000	0.0007
4.2768	390500	0.0011
4.2823	391000	0.0007
4.2877	391500	0.0019
4.2932	392000	0.0009
4.2987	392500	0.0011
4.3042	393000	0.0008
4.3096	393500	0.0006
4.3151	394000	0.0009
4.3206	394500	0.001
4.3261	395000	0.0007
4.3315	395500	0.0011
4.3370	396000	0.0008
4.3425	396500	0.0007
4.3480	397000	0.0007
4.3534	397500	0.0007
4.3589	398000	0.001
4.3644	398500	0.0008
4.3699	399000	0.001
4.3753	399500	0.0014
4.3808	400000	0.0006
4.3863	400500	0.0006
4.3918	401000	0.001
4.3973	401500	0.002
4.4027	402000	0.0006
4.4082	402500	0.0007
4.4137	403000	0.001
4.4192	403500	0.0008
4.4246	404000	0.0008
4.4301	404500	0.0009
4.4356	405000	0.0005
4.4411	405500	0.0008
4.4465	406000	0.0008
4.4520	406500	0.0007
4.4575	407000	0.0006
4.4630	407500	0.0006
4.4684	408000	0.0006
4.4739	408500	0.0006
4.4794	409000	0.0009
4.4849	409500	0.0007
4.4903	410000	0.0009
4.4958	410500	0.0006
4.5013	411000	0.0007
4.5068	411500	0.0006
4.5122	412000	0.0007
4.5177	412500	0.0006
4.5232	413000	0.0008
4.5287	413500	0.0007
4.5342	414000	0.0013
4.5396	414500	0.0006
4.5451	415000	0.0009
4.5506	415500	0.0015
4.5561	416000	0.0014
4.5615	416500	0.0007
4.5670	417000	0.0007
4.5725	417500	0.0008
4.5780	418000	0.0008
4.5834	418500	0.0007
4.5889	419000	0.0006
4.5944	419500	0.0008
4.5999	420000	0.0008
4.6053	420500	0.0006
4.6108	421000	0.001
4.6163	421500	0.0005
4.6218	422000	0.0007
4.6272	422500	0.0006
4.6327	423000	0.0007
4.6382	423500	0.0009
4.6437	424000	0.0014
4.6492	424500	0.0008
4.6546	425000	0.0006
4.6601	425500	0.0006
4.6656	426000	0.0016
4.6711	426500	0.0006
4.6765	427000	0.0006
4.6820	427500	0.0012
4.6875	428000	0.0007
4.6930	428500	0.0009
4.6984	429000	0.0006
4.7039	429500	0.0005
4.7094	430000	0.0007
4.7149	430500	0.0007
4.7203	431000	0.0006
4.7258	431500	0.0006
4.7313	432000	0.0006
4.7368	432500	0.0006
4.7422	433000	0.0006
4.7477	433500	0.0006
4.7532	434000	0.0006
4.7587	434500	0.0006
4.7641	435000	0.0006
4.7696	435500	0.0018
4.7751	436000	0.0009
4.7806	436500	0.0007
4.7861	437000	0.0007
4.7915	437500	0.0005
4.7970	438000	0.0009
4.8025	438500	0.0013
4.8080	439000	0.0007
4.8134	439500	0.0006
4.8189	440000	0.0007
4.8244	440500	0.001
4.8299	441000	0.0019
4.8353	441500	0.0006
4.8408	442000	0.0006
4.8463	442500	0.0009
4.8518	443000	0.0006
4.8572	443500	0.001
4.8627	444000	0.0011
4.8682	444500	0.0007
4.8737	445000	0.0007
4.8791	445500	0.0007
4.8846	446000	0.0018
4.8901	446500	0.0007
4.8956	447000	0.0012
4.9010	447500	0.0007
4.9065	448000	0.0009
4.9120	448500	0.0007
4.9175	449000	0.001
4.9230	449500	0.0007
4.9284	450000	0.0007
4.9339	450500	0.0007
4.9394	451000	0.0011
4.9449	451500	0.0005
4.9503	452000	0.0007
4.9558	452500	0.0006
4.9613	453000	0.0009
4.9668	453500	0.0008
4.9722	454000	0.0015
4.9777	454500	0.0008
4.9832	455000	0.0006
4.9887	455500	0.0006
4.9941	456000	0.0007
4.9996	456500	0.0006

Framework Versions

• Python: 3.12.2
• Sentence Transformers: 3.0.1
• Transformers: 4.42.3
• PyTorch: 2.3.1+cu121
• Accelerate: 0.32.1
• Datasets: 2.20.0
• 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}
}