This is a sentence-transformers model trained on the parquet dataset. It maps sentences & paragraphs to a 512-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

Maximum Sequence Length: 512 tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- parquet

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': 512, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("pankajrajdeo/Bioformer-8L-UMLS-Pubmed_PMC-Forward_TCE-Epoch-3")
# Run inference
sentences = [
    'De Garengeot Hernia, an acute appendicitis in the right femoral hernia canal, and successful management with transabdominal closure and appendectomy: a case Report.',
    'Incarceration of the appendix within a femoral hernia is a rare condition of abdominal wall hernia about 0.1 to 0.5% in reported femoral hernia. We report a case of a 56-year-old female whose appendix was trapped in the right femoral canal. There are few reports in the literature on entrapment of the appendix within a femoral hernia. The management of this condition includes antibiotics, drainage appendectomy, hernioplasty and mesh repair.',
    "With the increasing population worldwide more wastewater is created by human activities and discharged into the waterbodies. This is causing the contamination of aquatic bodies, thus disturbing the marine ecosystems. The rising population is also posing a challenge to meet the demands of fresh drinking water in the water-scarce regions of the world, where drinking water is made available to people by desalination process. The fouling of composite membranes remains a major challenge in water desalination. In this innovative study, we present a novel probabilistic approach to analyse and anticipate the predominant fouling mechanisms in the filtration process. Our establishment of a robust theoretical framework hinges upon the utilization of both the geometric law and the Hermia model, elucidating the concept of resistance in series (RIS). By manipulating the transmembrane pressure, we demonstrate effective management of permeate flux rate and overall product quality. Our investigations reveal a decrease in permeate flux in three distinct phases over time, with the final stage marked by a significant reduction due to the accumulation of a denser cake layer. Additionally, an increase in transmembrane pressure leads to a correlative rise in permeate flux, while also exerting negative effects such as membrane ruptures. Our study highlights the minimal immediate impact of the intermediate blocking mechanism (n = 1) on permeate flux, necessitating continuous monitoring for potential long-term effects. Additionally, we note a reduced membrane selectivity across all three fouling types (n = 0, n = 1.5, n = 2). Ultimately, our findings indicate that the membrane undergoes complete fouling with a probability of P = 0.9 in the presence of all three fouling mechanisms. This situation renders the membrane unable to produce water at its previous flow rate, resulting in a significant reduction in the desalination plant's productivity. I have demonstrated that higher pressure values notably correlate with increased permeate flux across all four membrane types. This correlation highlights the significant role of TMP in enhancing the production rate of purified water or desired substances through membrane filtration systems. Our innovative approach opens new perspectives for water desalination management and optimization, providing crucial insights into fouling mechanisms and proposing potential strategies to address associated challenges.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

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

Training Details

Training Dataset

parquet

Dataset: parquet
Size: 33,870,508 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 5 tokens
mean: 36.24 tokens
max: 106 tokens
min: 30 tokens
mean: 282.68 tokens
max: 512 tokens

Samples:

anchor	positive
`How TO OBTAIN THE BRAIN OF THE CAT.`	`How to obtain the Brain of the Cat, (Wilder).-Correction: Page 158, second column, line 7, "grains," should be "grams;" page 159, near middle of 2nd column, "successily," should be "successively;" page 161, the number of Flower's paper is 3.`
`ADDRESS OF COL. GARRICK MALLERY, U. S. ARMY.`	It may be conceded that after man had all his present faculties, he did not choose between the adoption of voice and gesture, and never with those faculties, was in a state where the one was used, to the absolute exclusion of the other. The epoch, however, to which our speculations relate is that in which he had not reached the present symmetric development of his intellect and of his bodily organs, and the inquiry is: Which mode of communication was earliest adopted to his single wants and informed intelligence? With the voice he could imitate distinictively but few sounds of nature, while with gesture he could exhibit actions, motions, positions, forms, dimensions, directions and distances, with their derivations and analogues. It would seem from this unequal division of capacity that oral speech remained rudimentary long after gesture had become an efficient mode of communication. With due allowance for all purely imitative sounds, and for the spontaneous action of vocal organs unde...
`DOLBEAR ON THE NATURE AND CONSTITUTION OF MATTER.`	`Mr. Dopp desires to make the following correction in his paper in the last issue: "In my article on page 200 of "Science", the expression and should have been and being the velocity of light.`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Evaluation Dataset

parquet

Dataset: parquet
Size: 33,870,508 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 6 tokens
mean: 24.64 tokens
max: 64 tokens
min: 9 tokens
mean: 279.56 tokens
max: 512 tokens

Samples:

anchor	positive
`Noticing education campaigns or public health messages about vaping among youth in the United States, Canada and England from 2018 to 2022.`	Public health campaigns have the potential to correct vaping misperceptions. However, campaigns highlighting vaping harms to youth may increase misperceptions that vaping is equally/more harmful than smoking. Vaping campaigns have been implemented in the United States and Canada since 2018 and in England since 2017 but with differing focus: youth vaping prevention. Over half of youth reported noticing vaping campaigns, and noticing increased from August 2018 to February 2020. Consistent with implementation of youth vaping prevention campaigns in the United States and Canada, most youth reported noticing vaping campaigns/messages, and most were perceived to negatively portray vaping.
`Comprehensive performance evaluation of six bioaerosol samplers based on an aerosol wind tunnel.`	Choosing a suitable bioaerosol sampler for atmospheric microbial monitoring has been a challenge to researchers interested in environmental microbiology, especially during a pandemic. However, a comprehensive and integrated evaluation method to fully assess bioaerosol sampler performance is still lacking. Herein, we constructed a customized wind tunnel operated at 2-20 km/h wind speed to systematically and efficiently evaluate the performance of six frequently used samplers, where various aerosols, including Arizona test dust, bacterial spores, gram-positive and gram-negative bacteria, phages, and viruses, were generated. After 10 or 60 min of sampling, the physical and biological sampling efficiency and short or long-term sampling capabilities were determined by performing aerodynamic particle size analysis, live microbial culturing, and a qPCR assay. The results showed that AGI-30 and BioSampler impingers have good physical and biological sampling efficiencies for short-term sampling...
`The occurrence, sources, and health risks of substituted polycyclic aromatic hydrocarbons (SPAHs) cannot be ignored.`	Similar to parent polycyclic aromatic hydrocarbons (PPAHs), substituted PAHs (SPAHs) are prevalent in the environment and harmful to humans. However, they have not received much attention. This study investigated the occurrence, distribution, and sources of 10 PPAHs and 15 SPAHs in soil, water, and indoor and outdoor PM2.5 and dust in high-exposure areas (EAH) near industrial parks and low-exposure areas (EAL) far from industrial parks. PAH pollution in all media was more severe in the EAH than in the EAL. All SPAHs were detected in this study, with alkylated and oxygenated PAHs being predominant. Additionally, 3-OH-BaP and 1-OH-Pyr were detected in all dust samples in this study, and 6-N-Chr, a compound with carcinogenicity 10 times higher than that of BaP, was detected at high levels in all tap water samples. According to the indoor-outdoor ratio, PAHs in indoor PM2.5 in the EAH mainly originated from indoor pollution sources; however, those in the EAL were simultaneously affected by...

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
learning_rate: 2e-05
max_steps: 754146
log_level: info
fp16: True
dataloader_num_workers: 16
load_best_model_at_end: True
resume_from_checkpoint: 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: 8
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: 3
max_steps: 754146
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: info
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: 16
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
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: True
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
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
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.0000	1	4.0337	-
0.0040	1000	1.0731	-
0.0080	2000	0.2694	-
0.0119	3000	0.204	-
0.0159	4000	0.2225	-
0.0199	5000	0.1825	-
0.0239	6000	0.1539	-
0.0278	7000	0.1408	-
0.0318	8000	0.1364	-
0.0358	9000	0.1276	-
0.0398	10000	0.1185	-
0.0438	11000	0.1028	-
0.0477	12000	0.1086	-
0.0517	13000	0.1172	-
0.0557	14000	0.1129	-
0.0597	15000	0.1063	-
0.0636	16000	0.1774	-
0.0676	17000	0.0872	-
0.0716	18000	0.1404	-
0.0756	19000	0.0798	-
0.0796	20000	0.1644	-
0.0835	21000	0.0848	-
0.0875	22000	0.1551	-
0.0915	23000	0.0884	-
0.0955	24000	0.0923	-
0.0994	25000	0.0754	-
0.1034	26000	0.1395	-
0.1074	27000	0.0813	-
0.1114	28000	0.1574	-
0.1154	29000	0.09	-
0.1193	30000	0.1319	-
0.1233	31000	0.116	-
0.1273	32000	0.0806	-
0.1313	33000	0.2095	-
0.1353	34000	0.0716	-
0.1392	35000	0.0909	-
0.1432	36000	0.1333	-
0.1472	37000	0.067	-
0.1512	38000	0.1183	-
0.1551	39000	0.0739	-
0.1591	40000	0.0662	-
0.1631	41000	0.1371	-
0.1671	42000	0.0913	-
0.1711	43000	0.0867	-
0.1750	44000	0.1184	-
0.1790	45000	0.0913	-
0.1830	46000	0.0857	-
0.1870	47000	0.1223	-
0.1909	48000	0.0731	-
0.1949	49000	0.1028	-
0.1989	50000	0.1107	-
0.2029	51000	0.0726	-
0.2069	52000	0.076	-
0.2108	53000	0.0923	-
0.2148	54000	0.0896	-
0.2188	55000	0.0755	-
0.2228	56000	0.0627	-
0.2267	57000	0.0837	-
0.2307	58000	0.0732	-
0.2347	59000	0.0655	-
0.2387	60000	0.0653	-
0.2427	61000	0.0845	-
0.2466	62000	0.0568	-
0.2506	63000	0.0534	-
0.2546	64000	0.0723	-
0.2586	65000	0.0873	-
0.2625	66000	0.0615	-
0.2665	67000	0.0598	-
0.2705	68000	0.0573	-
0.2745	69000	0.062	-
0.2785	70000	0.1152	-
0.2824	71000	0.0945	-
0.2864	72000	0.0853	-
0.2904	73000	0.0457	-
0.2944	74000	0.0604	-
0.2983	75000	0.1008	-
0.3023	76000	0.0564	-
0.3063	77000	0.1009	-
0.3103	78000	0.0531	-
0.3143	79000	0.0966	-
0.3182	80000	0.0991	-
0.3222	81000	0.0617	-
0.3262	82000	0.0685	-
0.3302	83000	0.0895	-
0.3342	84000	0.0424	-
0.3381	85000	0.0646	-
0.3421	86000	0.0796	-
0.3461	87000	0.0599	-
0.3501	88000	0.1033	-
0.3540	89000	0.0475	-
0.3580	90000	0.0366	-
0.3620	91000	0.0402	-
0.3660	92000	0.0587	-
0.3700	93000	0.0661	-
0.3739	94000	0.077	-
0.3779	95000	0.0906	-
0.3819	96000	0.05	-
0.3859	97000	0.0505	-
0.3898	98000	0.0413	-
0.3938	99000	0.038	-
0.3978	100000	0.0478	-
0.4018	101000	0.073	-
0.4058	102000	0.0527	-
0.4097	103000	0.0351	-
0.4137	104000	0.0377	-
0.4177	105000	0.0347	-
0.4217	106000	0.0431	-
0.4256	107000	0.0613	-
0.4296	108000	0.0825	-
0.4336	109000	0.0546	-
0.4376	110000	0.0335	-
0.4416	111000	0.0232	-
0.4455	112000	0.0525	-
0.4495	113000	0.0473	-
0.4535	114000	0.0342	-
0.4575	115000	0.0346	-
0.4614	116000	0.0279	-
0.4654	117000	0.034	-
0.4694	118000	0.0778	-
0.4734	119000	0.0788	-
0.4774	120000	0.0703	-
0.4813	121000	0.0708	-
0.4853	122000	0.0393	-
0.4893	123000	0.037	-
0.4933	124000	0.0426	-
0.4972	125000	0.0335	-
0.5012	126000	0.0317	-
0.5052	127000	0.0406	-
0.5092	128000	0.0302	-
0.5132	129000	0.0284	-
0.5171	130000	0.0416	-
0.5211	131000	0.065	-
0.5251	132000	0.0402	-
0.5291	133000	0.0348	-
0.5331	134000	0.033	-
0.5370	135000	0.0485	-
0.5410	136000	0.0364	-
0.5450	137000	0.0686	-
0.5490	138000	0.0648	-
0.5529	139000	0.0652	-
0.5569	140000	0.0626	-
0.5609	141000	0.0684	-
0.5649	142000	0.0482	-
0.5689	143000	0.0517	-
0.5728	144000	0.0389	-
0.5768	145000	0.0435	-
0.5808	146000	0.044	-
0.5848	147000	0.03	-
0.5887	148000	0.0254	-
0.5927	149000	0.0268	-
0.5967	150000	0.0409	-
0.6007	151000	0.0401	-
0.6047	152000	0.0317	-
0.6086	153000	0.0309	-
0.6126	154000	0.0389	-
0.6166	155000	0.0368	-
0.6206	156000	0.0434	-
0.6245	157000	0.0469	-
0.6285	158000	0.0734	-
0.6325	159000	0.0544	-
0.6365	160000	0.0498	-
0.6405	161000	0.0256	-
0.6444	162000	0.0302	-
0.6484	163000	0.0398	-
0.6524	164000	0.0657	-
0.6564	165000	0.0548	-
0.6603	166000	0.0638	-
0.6643	167000	0.0288	-
0.6683	168000	0.0273	-
0.6723	169000	0.0323	-
0.6763	170000	0.045	-
0.6802	171000	0.0416	-
0.6842	172000	0.0281	-
0.6882	173000	0.0554	-
0.6922	174000	0.0435	-
0.6961	175000	0.0375	-
0.7001	176000	0.0354	-
0.7041	177000	0.038	-
0.7081	178000	0.0319	-
0.7121	179000	0.0329	-
0.7160	180000	0.0492	-
0.7200	181000	0.0545	-
0.7240	182000	0.051	-
0.7280	183000	0.045	-
0.7320	184000	0.0342	-
0.7359	185000	0.0237	-
0.7399	186000	0.0369	-
0.7439	187000	0.0437	-
0.7479	188000	0.0467	-
0.7518	189000	0.0424	-
0.7558	190000	0.0458	-
0.7598	191000	0.0434	-
0.7638	192000	0.0471	-
0.7678	193000	0.0404	-
0.7717	194000	0.0373	-
0.7757	195000	0.0254	-
0.7797	196000	0.0235	-
0.7837	197000	0.0212	-
0.7876	198000	0.0236	-
0.7916	199000	0.0226	-
0.7956	200000	0.0208	-
0.7996	201000	0.0276	-
0.8036	202000	0.0235	-
0.8075	203000	0.0358	-
0.8115	204000	0.0451	-
0.8155	205000	0.0442	-
0.8195	206000	0.0411	-
0.8234	207000	0.0447	-
0.8274	208000	0.0427	-
0.8314	209000	0.0259	-
0.8354	210000	0.0219	-
0.8394	211000	0.0253	-
0.8433	212000	0.0253	-
0.8473	213000	0.0242	-
0.8513	214000	0.0251	-
0.8553	215000	0.0223	-
0.8592	216000	0.0253	-
0.8632	217000	0.024	-
0.8672	218000	0.0249	-
0.8712	219000	0.0234	-
0.8752	220000	0.0232	-
0.8791	221000	0.0231	-
0.8831	222000	0.0264	-
0.8871	223000	0.051	-
0.8911	224000	0.0436	-
0.8950	225000	0.0429	-
0.8990	226000	0.0406	-
0.9030	227000	0.0363	-
0.9070	228000	0.0316	-
0.9110	229000	0.023	-
0.9149	230000	0.0239	-
0.9189	231000	0.0225	-
0.9229	232000	0.0223	-
0.9269	233000	0.0225	-
0.9309	234000	0.0223	-
0.9348	235000	0.0191	-
0.9388	236000	0.0202	-
0.9428	237000	0.0149	-
0.9468	238000	0.0215	-
0.9507	239000	0.012	-
0.9547	240000	0.0141	-
0.9587	241000	0.0152	-
0.9627	242000	0.0311	-
0.9667	243000	0.0344	-
0.9706	244000	0.0209	-
0.9746	245000	0.0145	-
0.9786	246000	0.0128	-
0.9826	247000	0.0124	-
0.9865	248000	0.0123	-
0.9905	249000	0.0141	-
0.9945	250000	0.0115	-
0.9985	251000	0.0131	-
1.0000	251382	-	0.0022
1.0025	252000	0.3338	-
1.0064	253000	0.1293	-
1.0104	254000	0.0893	-
1.0144	255000	0.0811	-
1.0184	256000	0.0863	-
1.0223	257000	0.0872	-
1.0263	258000	0.0693	-
1.0303	259000	0.0643	-
1.0343	260000	0.0638	-
1.0383	261000	0.0511	-
1.0422	262000	0.0554	-
1.0462	263000	0.0643	-
1.0502	264000	0.0492	-
1.0542	265000	0.0583	-
1.0581	266000	0.0738	-
1.0621	267000	0.079	-
1.0661	268000	0.0823	-
1.0701	269000	0.0673	-
1.0741	270000	0.059	-
1.0780	271000	0.0946	-
1.0820	272000	0.0494	-
1.0860	273000	0.0958	-
1.0900	274000	0.0561	-
1.0939	275000	0.0517	-
1.0979	276000	0.0502	-
1.1019	277000	0.0874	-
1.1059	278000	0.0463	-
1.1099	279000	0.0472	-
1.1138	280000	0.1038	-
1.1178	281000	0.0542	-
1.1218	282000	0.1036	-
1.1258	283000	0.05	-
1.1298	284000	0.1052	-
1.1337	285000	0.073	-
1.1377	286000	0.041	-
1.1417	287000	0.0981	-
1.1457	288000	0.0415	-
1.1496	289000	0.0561	-
1.1536	290000	0.0612	-
1.1576	291000	0.0426	-
1.1616	292000	0.0711	-
1.1656	293000	0.0703	-
1.1695	294000	0.0508	-
1.1735	295000	0.0756	-
1.1775	296000	0.053	-
1.1815	297000	0.0581	-
1.1854	298000	0.0793	-
1.1894	299000	0.0476	-
1.1934	300000	0.0601	-
1.1974	301000	0.0713	-
1.2014	302000	0.0501	-
1.2053	303000	0.0457	-
1.2093	304000	0.0471	-
1.2133	305000	0.0682	-
1.2173	306000	0.0544	-
1.2212	307000	0.0359	-
1.2252	308000	0.047	-
1.2292	309000	0.0527	-
1.2332	310000	0.0437	-
1.2372	311000	0.0384	-
1.2411	312000	0.0508	-
1.2451	313000	0.0383	-
1.2491	314000	0.0376	-
1.2531	315000	0.0376	-
1.2570	316000	0.0441	-
1.2610	317000	0.0557	-
1.2650	318000	0.0384	-
1.2690	319000	0.0295	-
1.2730	320000	0.0409	-
1.2769	321000	0.0671	-
1.2809	322000	0.0603	-
1.2849	323000	0.0668	-
1.2889	324000	0.026	-
1.2928	325000	0.0264	-
1.2968	326000	0.056	-
1.3008	327000	0.0399	-
1.3048	328000	0.074	-
1.3088	329000	0.0364	-
1.3127	330000	0.0306	-
1.3167	331000	0.0727	-
1.3207	332000	0.0325	-
1.3247	333000	0.0439	-
1.3286	334000	0.0563	-
1.3326	335000	0.0274	-
1.3366	336000	0.0274	-
1.3406	337000	0.0721	-
1.3446	338000	0.0286	-
1.3485	339000	0.0558	-
1.3525	340000	0.0452	-
1.3565	341000	0.0201	-
1.3605	342000	0.0275	-
1.3645	343000	0.0189	-
1.3684	344000	0.0543	-
1.3724	345000	0.0469	-
1.3764	346000	0.067	-
1.3804	347000	0.0289	-
1.3843	348000	0.0366	-
1.3883	349000	0.026	-
1.3923	350000	0.0286	-
1.3963	351000	0.024	-
1.4003	352000	0.0403	-
1.4042	353000	0.0429	-
1.4082	354000	0.0216	-
1.4122	355000	0.027	-
1.4162	356000	0.0184	-
1.4201	357000	0.0266	-
1.4241	358000	0.0332	-
1.4281	359000	0.0427	-
1.4321	360000	0.0456	-
1.4361	361000	0.0229	-
1.4400	362000	0.0161	-
1.4440	363000	0.025	-
1.4480	364000	0.031	-
1.4520	365000	0.0256	-
1.4559	366000	0.0195	-
1.4599	367000	0.0224	-
1.4639	368000	0.0163	-
1.4679	369000	0.037	-
1.4719	370000	0.0471	-
1.4758	371000	0.0452	-
1.4798	372000	0.0448	-
1.4838	373000	0.034	-
1.4878	374000	0.022	-
1.4917	375000	0.0216	-
1.4957	376000	0.0247	-
1.4997	377000	0.0172	-
1.5037	378000	0.0218	-
1.5077	379000	0.023	-
1.5116	380000	0.0138	-
1.5156	381000	0.025	-
1.5196	382000	0.0361	-
1.5236	383000	0.0295	-
1.5275	384000	0.0257	-
1.5315	385000	0.0162	-
1.5355	386000	0.0283	-
1.5395	387000	0.0246	-
1.5435	388000	0.0379	-
1.5474	389000	0.0411	-
1.5514	390000	0.0424	-
1.5554	391000	0.0384	-
1.5594	392000	0.0458	-
1.5634	393000	0.039	-
1.5673	394000	0.0273	-
1.5713	395000	0.0338	-
1.5753	396000	0.0276	-
1.5793	397000	0.0277	-
1.5832	398000	0.0231	-
1.5872	399000	0.0168	-
1.5912	400000	0.0135	-
1.5952	401000	0.0262	-
1.5992	402000	0.0253	-
1.6031	403000	0.0235	-
1.6071	404000	0.0189	-
1.6111	405000	0.024	-
1.6151	406000	0.0244	-
1.6190	407000	0.0281	-
1.6230	408000	0.0223	-
1.6270	409000	0.0515	-
1.6310	410000	0.0374	-
1.6350	411000	0.0419	-
1.6389	412000	0.0151	-
1.6429	413000	0.0196	-
1.6469	414000	0.0164	-
1.6509	415000	0.0413	-
1.6548	416000	0.0375	-
1.6588	417000	0.0431	-
1.6628	418000	0.0287	-
1.6668	419000	0.0189	-
1.6708	420000	0.0175	-
1.6747	421000	0.0286	-
1.6787	422000	0.0291	-
1.6827	423000	0.0215	-
1.6867	424000	0.027	-
1.6906	425000	0.0366	-
1.6946	426000	0.0285	-
1.6986	427000	0.0216	-
1.7026	428000	0.0268	-
1.7066	429000	0.0255	-
1.7105	430000	0.0209	-
1.7145	431000	0.0257	-
1.7185	432000	0.0407	-
1.7225	433000	0.0349	-
1.7264	434000	0.0342	-
1.7304	435000	0.0235	-
1.7344	436000	0.0216	-
1.7384	437000	0.0201	-
1.7424	438000	0.0257	-
1.7463	439000	0.0269	-
1.7503	440000	0.0305	-
1.7543	441000	0.0319	-
1.7583	442000	0.0292	-
1.7623	443000	0.0311	-
1.7662	444000	0.0304	-
1.7702	445000	0.0263	-
1.7742	446000	0.0195	-
1.7782	447000	0.0162	-
1.7821	448000	0.0122	-
1.7861	449000	0.0156	-
1.7901	450000	0.0148	-
1.7941	451000	0.0126	-
1.7981	452000	0.0162	-
1.8020	453000	0.0154	-
1.8060	454000	0.0157	-
1.8100	455000	0.0321	-
1.8140	456000	0.0296	-
1.8179	457000	0.0296	-
1.8219	458000	0.0305	-
1.8259	459000	0.0285	-
1.8299	460000	0.0263	-
1.8339	461000	0.0116	-
1.8378	462000	0.0156	-
1.8418	463000	0.0172	-
1.8458	464000	0.0154	-
1.8498	465000	0.0162	-
1.8537	466000	0.0151	-
1.8577	467000	0.0162	-
1.8617	468000	0.0149	-
1.8657	469000	0.0157	-
1.8697	470000	0.0161	-
1.8736	471000	0.0159	-
1.8776	472000	0.0152	-
1.8816	473000	0.0148	-
1.8856	474000	0.0315	-
1.8895	475000	0.0282	-
1.8935	476000	0.0331	-
1.8975	477000	0.0284	-
1.9015	478000	0.0272	-
1.9055	479000	0.026	-
1.9094	480000	0.0159	-
1.9134	481000	0.0153	-
1.9174	482000	0.0158	-
1.9214	483000	0.014	-
1.9253	484000	0.0153	-
1.9293	485000	0.0146	-
1.9333	486000	0.0137	-
1.9373	487000	0.0129	-
1.9413	488000	0.0112	-
1.9452	489000	0.0139	-
1.9492	490000	0.0076	-
1.9532	491000	0.0074	-
1.9572	492000	0.0097	-
1.9612	493000	0.0136	-
1.9651	494000	0.0269	-
1.9691	495000	0.0192	-
1.9731	496000	0.0092	-
1.9771	497000	0.0086	-
1.9810	498000	0.0078	-
1.9850	499000	0.0073	-
1.9890	500000	0.0093	-
1.9930	501000	0.0071	-
1.9970	502000	0.0075	-
2.0000	502764	-	0.0018
2.0009	503000	0.1807	-
2.0049	504000	0.1676	-
2.0089	505000	0.0704	-
2.0129	506000	0.0733	-
2.0168	507000	0.0713	-
2.0208	508000	0.0633	-
2.0248	509000	0.0562	-
2.0288	510000	0.0521	-
2.0328	511000	0.0517	-
2.0367	512000	0.0516	-
2.0407	513000	0.047	-
2.0447	514000	0.0411	-
2.0487	515000	0.0445	-
2.0526	516000	0.0493	-
2.0566	517000	0.0618	-
2.0606	518000	0.0335	-
2.0646	519000	0.1001	-
2.0686	520000	0.0349	-
2.0725	521000	0.0675	-
2.0765	522000	0.0376	-
2.0805	523000	0.0838	-
2.0845	524000	0.0411	-
2.0884	525000	0.0798	-
2.0924	526000	0.0401	-
2.0964	527000	0.0455	-
2.1004	528000	0.0312	-
2.1044	529000	0.0778	-
2.1083	530000	0.0368	-
2.1123	531000	0.0872	-
2.1163	532000	0.0411	-
2.1203	533000	0.0906	-
2.1242	534000	0.0409	-
2.1282	535000	0.0523	-
2.1322	536000	0.0986	-
2.1362	537000	0.0332	-
2.1402	538000	0.0668	-
2.1441	539000	0.0472	-
2.1481	540000	0.035	-
2.1521	541000	0.0588	-
2.1561	542000	0.0349	-
2.1601	543000	0.036	-
2.1640	544000	0.0706	-
2.1680	545000	0.0458	-
2.1720	546000	0.0525	-
2.1760	547000	0.0489	-
2.1799	548000	0.0493	-
2.1839	549000	0.044	-
2.1879	550000	0.064	-
2.1919	551000	0.0423	-
2.1959	552000	0.0503	-
2.1998	553000	0.0562	-
2.2038	554000	0.0335	-
2.2078	555000	0.0394	-
2.2118	556000	0.0527	-
2.2157	557000	0.0452	-
2.2197	558000	0.0342	-
2.2237	559000	0.0314	-
2.2277	560000	0.0458	-
2.2317	561000	0.0343	-
2.2356	562000	0.0295	-
2.2396	563000	0.0341	-
2.2436	564000	0.04	-
2.2476	565000	0.0302	-
2.2515	566000	0.0266	-
2.2555	567000	0.0373	-
2.2595	568000	0.0447	-
2.2635	569000	0.03	-
2.2675	570000	0.0252	-
2.2714	571000	0.0313	-
2.2754	572000	0.0472	-
2.2794	573000	0.0495	-
2.2834	574000	0.0588	-
2.2873	575000	0.0249	-
2.2913	576000	0.0221	-
2.2953	577000	0.0303	-
2.2993	578000	0.0416	-
2.3033	579000	0.064	-
2.3072	580000	0.0227	-
2.3112	581000	0.0263	-
2.3152	582000	0.051	-
2.3192	583000	0.0344	-
2.3231	584000	0.0342	-
2.3271	585000	0.0368	-
2.3311	586000	0.0303	-
2.3351	587000	0.0206	-
2.3391	588000	0.0597	-
2.3430	589000	0.0232	-
2.3470	590000	0.0342	-
2.3510	591000	0.0477	-
2.3550	592000	0.015	-
2.3590	593000	0.0169	-
2.3629	594000	0.0209	-
2.3669	595000	0.0392	-
2.3709	596000	0.0299	-
2.3749	597000	0.0362	-
2.3788	598000	0.0503	-
2.3828	599000	0.0262	-
2.3868	600000	0.0275	-
2.3908	601000	0.0217	-
2.3948	602000	0.0185	-
2.3987	603000	0.0251	-
2.4027	604000	0.036	-
2.4067	605000	0.0202	-
2.4107	606000	0.018	-
2.4146	607000	0.0178	-
2.4186	608000	0.0201	-
2.4226	609000	0.0183	-
2.4266	610000	0.0325	-
2.4306	611000	0.0391	-
2.4345	612000	0.0229	-
2.4385	613000	0.0165	-
2.4425	614000	0.0123	-
2.4465	615000	0.0257	-
2.4504	616000	0.022	-
2.4544	617000	0.0167	-
2.4584	618000	0.0167	-
2.4624	619000	0.0127	-
2.4664	620000	0.0201	-
2.4703	621000	0.0364	-
2.4743	622000	0.0368	-
2.4783	623000	0.0352	-
2.4823	624000	0.0319	-
2.4862	625000	0.0171	-
2.4902	626000	0.0185	-
2.4942	627000	0.0206	-
2.4982	628000	0.0138	-
2.5022	629000	0.0151	-
2.5061	630000	0.019	-
2.5101	631000	0.0122	-
2.5141	632000	0.0139	-
2.5181	633000	0.0203	-
2.5220	634000	0.0295	-
2.5260	635000	0.0217	-
2.5300	636000	0.0132	-
2.5340	637000	0.0183	-
2.5380	638000	0.0208	-
2.5419	639000	0.0217	-
2.5459	640000	0.0333	-
2.5499	641000	0.036	-
2.5539	642000	0.0317	-
2.5578	643000	0.034	-
2.5618	644000	0.0365	-
2.5658	645000	0.023	-
2.5698	646000	0.0288	-
2.5738	647000	0.0211	-
2.5777	648000	0.0211	-
2.5817	649000	0.023	-
2.5857	650000	0.0137	-
2.5897	651000	0.0115	-
2.5937	652000	0.0141	-
2.5976	653000	0.0209	-
2.6016	654000	0.0207	-
2.6056	655000	0.0149	-
2.6096	656000	0.0173	-
2.6135	657000	0.0196	-
2.6175	658000	0.0198	-
2.6215	659000	0.0217	-
2.6255	660000	0.0306	-
2.6295	661000	0.0383	-
2.6334	662000	0.0286	-
2.6374	663000	0.0228	-
2.6414	664000	0.0135	-
2.6454	665000	0.0148	-
2.6493	666000	0.0221	-
2.6533	667000	0.0347	-
2.6573	668000	0.0293	-
2.6613	669000	0.0333	-
2.6653	670000	0.015	-
2.6692	671000	0.0143	-
2.6732	672000	0.0195	-
2.6772	673000	0.0251	-
2.6812	674000	0.0212	-
2.6851	675000	0.0155	-
2.6891	676000	0.0306	-
2.6931	677000	0.0231	-
2.6971	678000	0.0202	-
2.7011	679000	0.0215	-
2.7050	680000	0.0212	-
2.7090	681000	0.0192	-
2.7130	682000	0.0187	-
2.7170	683000	0.0305	-
2.7209	684000	0.0286	-
2.7249	685000	0.0282	-
2.7289	686000	0.0229	-
2.7329	687000	0.0211	-
2.7369	688000	0.0124	-
2.7408	689000	0.0227	-
2.7448	690000	0.0205	-
2.7488	691000	0.0246	-
2.7528	692000	0.0234	-
2.7567	693000	0.0245	-
2.7607	694000	0.0239	-
2.7647	695000	0.0261	-
2.7687	696000	0.0227	-
2.7727	697000	0.0181	-
2.7766	698000	0.014	-
2.7806	699000	0.0103	-
2.7846	700000	0.0119	-
2.7886	701000	0.0115	-
2.7926	702000	0.0102	-
2.7965	703000	0.0113	-
2.8005	704000	0.0124	-
2.8045	705000	0.0119	-
2.8085	706000	0.0218	-
2.8124	707000	0.0239	-
2.8164	708000	0.024	-
2.8204	709000	0.0237	-
2.8244	710000	0.0242	-
2.8284	711000	0.0252	-
2.8323	712000	0.011	-
2.8363	713000	0.0129	-
2.8403	714000	0.0129	-
2.8443	715000	0.0133	-
2.8482	716000	0.0117	-
2.8522	717000	0.013	-
2.8562	718000	0.0133	-
2.8602	719000	0.0116	-
2.8642	720000	0.0126	-
2.8681	721000	0.0131	-
2.8721	722000	0.0124	-
2.8761	723000	0.0122	-
2.8801	724000	0.0109	-
2.8840	725000	0.0233	-
2.8880	726000	0.0241	-
2.8920	727000	0.0266	-
2.8960	728000	0.0244	-
2.9000	729000	0.0234	-
2.9039	730000	0.0215	-
2.9079	731000	0.0166	-
2.9119	732000	0.0135	-
2.9159	733000	0.013	-
2.9198	734000	0.0127	-
2.9238	735000	0.0118	-
2.9278	736000	0.0131	-
2.9318	737000	0.0108	-
2.9358	738000	0.0099	-
2.9397	739000	0.011	-
2.9437	740000	0.0068	-
2.9477	741000	0.0103	-
2.9517	742000	0.0054	-
2.9556	743000	0.0071	-
2.9596	744000	0.0076	-
2.9636	745000	0.0206	-
2.9676	746000	0.0212	-
2.9716	747000	0.0075	-
2.9755	748000	0.0078	-
2.9795	749000	0.0067	-
2.9835	750000	0.0057	-
2.9875	751000	0.0062	-
2.9915	752000	0.0075	-
2.9954	753000	0.006	-
2.9994	754000	0.0073	-
3.0000	754146	-	0.0013

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.2
PyTorch: 2.6.0+cu124
Accelerate: 1.3.0
Datasets: 3.2.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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}
}

	anchor	positive
type	string	string
details	min: 5 tokens mean: 36.24 tokens max: 106 tokens	min: 30 tokens mean: 282.68 tokens max: 512 tokens