--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:44978 - loss:ReasoningGuidedRankingLoss base_model: google-bert/bert-base-uncased widget: - source_sentence: Severe weather rips through Alabama university, takes aim at Southeast sentences: - The second text provides a detailed elaboration of the first text. It expands on the initial statement about severe weather in Alabama, providing specific details about the damage at Jacksonville State University, the impact on the surrounding areas, and the broader effects of the storm. - 'The labor movement has been living in the shadow of a national assault on public-sector collective bargaining for a while now. We’ve talked a lot about Harris v. Quinn, how labor dodged a bullet with that case, and dodged another with the death of Scalia before the Friedrichs case could be decided. But Janus v. American Federation of State, County, and Municipal Employees, Council 31 is likely to be the case labor has been dreading, and we break it down for you today with Andy Stettner of the Century Foundation. We also look at Uber’s failures in London and neoliberalism’s failures in France, a union drive at the Los Angeles Times and a labor solidarity mission to Puerto Rico post-hurricanes. For Argh, we consider forced labor “rehab” facilities, and how moving left is the solution to the rise of the populist right. If you think our work is worth supporting as we soldier on through Trumplandia, please consider becoming a sustaining member of Belabored or donating or subscribing to Dissent. Help keep us going for the next 136 episodes!' - 'Severe weather that spawned at least one tornado slammed Alabama’s Jacksonville State University on Monday night and took aim at the rest of the southeast. Alabama state troopers said the damage in Jacksonville, Ala. left the city looking like a “war zone.” Strong winds downed trees and damaged buildings as the National Weather Service confirmed a “damaging and possibly large tornado near Jacksonville and Calhoun counties and was moving east. Jacksonville State University Athletic Director Greg Seitz wrote in a tweet that there was significant damage to campus, including to the newly renovated Pete Mathews Coliseum. "I can confirm we have major roof damage at Pete Mathews Coliseum, but The Pete is not completely destroyed," Seitz said in a tweet. Tuscaloosa County Sheriff’s Office Lt. Andy Norris said in a tweet that troopers called Jacksonville a “war zone.” He said the arena’s roof “took major damage.” Photos seen on social media showed the extent of the damage Jacksonville took. Alabama Gov. Kay Ivey confirmed in a statement late Monday there was “significant damage” throughout the state, according to WBRC-TV. Cities in northern Alabama reported power outages and the NWS in Huntsville reported at least three tornadoes in the area. The severe weather moved into Georgia late Monday night. Flights at Hartsfield Airport in Atlanta were not officially grounded as the damaging winds moved into the area. However, the airport warned on Twitter that delays were likely. Meanwhile, more than 150 people reportedly took cover into a historic cave in Cave Springs, Ga. The storms knocked out power to at least 15,000 homes and businesses in Alabama. Georgia Power was rpeorting more than 26,000 of their customers were without power, according to Cobb County News. The Associated Press contributed to this report.' - source_sentence: NCAA Sexual Violence Policy Criticized as Weak sentences: - The second text provides details that elaborate on the criticism mentioned in the first text. It describes the NCAA's new rules and then presents a specific critique, highlighting the perceived weaknesses in the policy, such as the lack of strong enforcement and accountability, thus supporting the initial claim of weakness. - 'CHAMPAIGN -- Illinois had one final chance to finish this week on a recruiting strong note. After missing out on three Class of 2018 forwards early in the week, the Illini were still in the running for four-star Georgia prospect Landers Nolley. Until Friday morning. Nolley, a 6-foot-7 wing who played his sophomore season at Curie in Chicago before moving to Georgia, narrowed his choices to Georgia and Virginia Tech. Nolley''s almost final decision left Illinois 0 for 4 on 2018 targets this week after Lukas Kisunas (UConn), George Conditt (Iowa State) and Colin Castleton (Michigan) all committed elsewhere. That leaves the Illini in further pursuit of in-state targets like Morgan Park''s Ayo Dosunmu, who will start an official visit at Illinois on Oct. 13, and Simeon''s Talen Horton-Tucker.' - 'The National Collegiate Athletic Association adopted rules last week that require key administrators to complete annual training on sexual violence prevention, and to certify annually that the institution''s teams and programs are familiar with policies and processes to prevent sexual violence or to deal with incidents that take place. Further, the rules require institutions to provide information to athletes on institutional policies and procedures. A column in The Huffington Post noted that the NCAA rules are largely similar to what federal law requires of colleges, and that they don''t address issues related to athletes found to have assaulted others. What the rules lack, the column said, "is enforcement or accountability that approaches penalties reaching the [same] level as the purchase of a hamburger for a student athlete."' - source_sentence: William few Pkwy and Chamblin Rd new traffic signal - WFXG FOX 54 - News Now sentences: - The second text elaborates on the first by providing details about the traffic signal mentioned in the title. It specifies the location (William Few Parkway and Chamblin Road) and the schedule for the signal's operation, including the dates it will be in flashing and normal modes. - 'Columbia County wants to inform the driving public of a new traffic signal installation. It’s located at William Few Parkway and Chamblin Road. The light is scheduled to go into flashing mode on Friday October 6th, 2017. The signal will remain in flashing mode for the remainder of this week, including the weekend. The signal is scheduled to be placed into normal stop and go operation on Tuesday, October 10, 2017. Copyright 2017 WFXG. All rights reserved.' - 'NEWPORT BEACH, Calif. (AP) — The Latest on a fatal helicopter crash in Southern California (all times local): 10:07 a.m. California authorities have released the name of all three people killed when a small helicopter crashed in a Newport Beach neighborhood. The Orange County Sheriff''s Department says the dead are 60-year-old Joseph Anthony Tena of Newport Beach, 45-year-old Kimberly Lynne Watzman of Santa Monica and 56-year-old Brian R. Reichelt of Hollywood. The crash Wednesday in a neighborhood involved four people in the helicopter and a bystander. Newport Beach police spokeswoman Jennifer Manzella says all three people killed were in the helicopter. There''s no information about two people who were injured. ___ 11:03 p.m. Officials say three people were killed and two more injured when a helicopter crashed into a home in a suburban Southern California neighborhood. Authorities say four people were aboard the Robinson R44 helicopter when it went down in Newport Beach on Tuesday afternoon just a few minutes after taking off from John Wayne Airport. One person who was outside on the ground was involved in the crash, though officials did not specify who died and who was injured. Neighbor Marian Michaels says she thought it was an earthquake when the helicopter slammed into the house. Another neighbor, Roger Johnson, says he heard a scream that sounded like it was from a horror movie before rushing to the scene to try to help.' - source_sentence: 'Former AG, ex-Jordanian PM top contenders for Pak''s ICJ ad-hoc judge choice: report' sentences: - The second text elaborates on the first by providing details about the contenders for the ad-hoc judge position. It names specific individuals (ex-AG and former Jordanian PM) and provides context about the case at the ICJ, the nomination process, and the sources of the information. The report confirms the information presented in the title. - 'Image caption The last confirmed sighting of Brian McGowan was in Plean on 21 September Police searching for a man who has not been seen for more than two weeks are asking the public to check outbuildings and gardens for any trace of him. Brian McGowan, 42, was last seen in the Gillespie Terrace area of Plean, near Stirling, at 16:00 on 21 September. Investigations have uncovered a "probable" sighting of him in the Gallamuir Drive area at 01:30 the following day. Police said that since then he has not returned home or contacted anyone. Insp Donna Bryans said: "Brian has now been missing for two weeks and it is vital that we find him. "I would like to thank the local community who have come out to search for Brian and helped with our investigations so far. "I would ask residents and visitors to Plean, as well as visitors to Plean Country Park, to be vigilant and report any sighting of anyone seen matching Brian''s description." Insp Bryans said a search of gardens and outbuildings in the area could help officers discover Mr McGowan''s whereabouts. He is described as 5ft 10 tall, of slim build with short dark hair. He had blue eyes and tattoos on his fingers and speaks with a local accent. When last seen he was wearing a black baseball cap, a black G-Star jacket, grey Armani jumper, grey Adidas tracksuit bottoms with black stripes on the sides and black and grey Adidas Y3 trainers.' - 'ISLAMABAD: The Pakistan government has begun consultations over the nomination of an ad-hoc judge for the Kulbhushan Jadhav case being heard at the International Court of Justice with an ex-attorney general and a former Jordanian premier emerging as the top contenders, a media report said today. India had moved the Hague-based International Court of Justice (ICJ) against Jadhav''s death penalty handed down by a Pakistani military court. The ICJ had on May 18 restrained Pakistan from executing the death sentence.Pakistan government''s functionaries have started consultations for the nomination of an ad-hoc judge, Express Tribune reported, citing sources.During the tenure of ousted prime minister Nawaz Sharif , former Supreme Court judge Khalilur Rehman Ramday was approached, but he declined the nomination, the report said.Sources were quoted by the daily as saying that the Attorney General for Pakistan''s (AGP) office has recommended the names of senior lawyer Makhdoom Ali Khan and former Jordanian prime minister Awn Shawkat Al-Khasawneh to the Prime Minister''s Office for the nomination of one name as an ad-hoc judge.Khasawneh served as an ICJ judge for over a decade, while Khan, a former Attorney General who is seen as the favourite for the job, also has experience in international arbitration cases, having represented eight different countries in international courts.The nomination of the ad-hoc judge will be finalised after getting inputs from the Foreign Office and the military establishment, the sources said, adding that earlier, government functionaries had also considered the name of former chief justice of Pakistan Tassaduq Hussain Jillani.An official was quoted as saying that the name of the ad- hoc judge will be finalised next month, soon after the Indian side files its documents.Meanwhile, Pakistan Bar Council (PBC) representative Raheel Kamran Sheikh has called upon the government to seek Parliament''s approval on the appointment of the ad-hoc judge.Only one person has previously been appointed as ICJ judge in Pakistan''s history -- former foreign minister Zafarullah Khan, who was appointed in 1954 and later became the president of the court.Yaqub Ali Khan and Sharifuddin Pirzada both served as ad-hoc judges, as did Zafarullah.' - source_sentence: Energy advocates call for new commitment to renewable growth sentences: - The second text elaborates on the first by providing details about the specific context of the energy advocates' call for renewable growth. It identifies the advocates (CFE, VoteSolar, Environment Connecticut), the specific renewable energy program (community solar), and the reasons for their call, including program delays and design flaws. - 'The piece below was submitted by CFE, VoteSolar, and Environment Connecticut in response to the latest delay in the shared solar pilot program. Solar and environmental advocates are calling for a new community solar program in Connecticut that will expand solar access, energy choices and consumer savings for families, municipalities, and businesses statewide. The demand follows today’s Department of Energy and Environmental Protection (DEEP) technical hearing where attendees reviewed the state’s current Shared Clean Energy Facilities pilot program. The pilot has stalled several times over the last two years, most recently following DEEP’s decision to scrap all the proposals they have received and issue a new request for projects. DEEP heard from many advocates and developers at the hearing who are frustrated with this latest delay and skeptical about the long term success of the pilot. The current pilot program was meant to expand solar access to Connecticut energy customers who can’t put solar on their own roof, but it contained flaws that have prevented any development to date. As set out in the legislation, the program has several poor design elements and a goal too small to draw significant private sector interest. Below are statements from stakeholders in Connecticut’s clean energy economy: “For years, Connecticut has missed out on the opportunity to bring solar energy choices to all consumers and more clean energy jobs to the state,” said Sean Garren, Northeast Regional director for Vote Solar. “Connecticut’s lackluster community solar program hasn’t unlocked the benefits of solar access for a single resident to date due to poor design and a lack of ambition at the scale needed, brought about by the electric utilities’ intervention. We’re calling on the legislature to catch up to the rest of New England — and the nation — with a smart, well-structured community solar program designed to serve consumers statewide.” “Two years of foot dragging and refusal by the Department of Energy and Environmental Protection to follow the law and implement a community solar program is preventing tens of thousands of Connecticut families from gaining access to clean, affordable, secure solar power,” said Chris Phelps, State Director for Environment Connecticut. “Community solar is helping other states accelerate solar growth, create jobs, and cut pollution. Connecticut policy makers should take action now to create a bold community solar program.” “Shared solar programs have been sweeping the nation for the last decade, but Connecticut has been left in the shade — losing out on healthier air, investment dollars, and green jobs that would accompany a full-scale, statewide shared solar program,” said Claire Coleman, Climate and Energy Attorney for Connecticut Fund for the Environment. “DEEP’s decision to start over with the already overly-restrictive shared solar pilot puts Connecticut further in the dark. Our climate and economy cannot wait any longer. Connecticut’s leaders must move quickly to ramp up in-state renewables through a full-scale shared solar program if Connecticut is going to have any chance of meeting its obligations under the Global Warming Solutions Act to reduce greenhouse gas emissions.” Vote Solar is a nonprofit organization working to foster economic development and energy independence by bringing solar energy to the mainstream nationwide. Learn more at votesolar.org.' - 'BEIJING: China will waive income tax for three years for foreign investors trading the country’s new crude futures contract, the Ministry of Finance said on Tuesday, in a bid to attract overseas capital for the much anticipated launch. The start of trading on Monday will mark the culmination of a years-long push by China to create Asia’s first oil futures benchmark, and is aimed at giving the world’s biggest oil importer more clout in pricing crude sold to Asia. It will potentially give the Shanghai International Energy Exchange, which will operate the new contract, a share of the trillions of dollars each year in oil futures trading. The finance ministry said foreign brokers will be exempted from paying income tax on commissions they earn from dealing in the new Shanghai crude futures. The tax exemption could help encourage foreign players to engage with the new contract, despite concerns about issues such as foreign exchange conversion and potential capital curbs. The number of foreign investors seeking to open non-resident accounts to allow trading has so far been below expectations, a source at CITIC, one of eight banks that is handling margin deposits for foreign investors, said. The source declined to be named as he is not authorized to talk with media. The oil market is closely watching the liquidity of the contract, as institutional investors and brokers expect trading volumes and open interest to be relatively small compared with China’s iron ore, copper and steel futures contracts. China in recent days has provided more details on the contract, including margins, trading limits and transaction fees, and has approved the use of six bonded storage warehouses.' datasets: - bwang0911/reasoning_pairs_filtered_w_reason_ccnews pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on google-bert/bert-base-uncased results: - task: type: information-retrieval name: Information Retrieval dataset: name: mteb/nfcorpus type: mteb/nfcorpus metrics: - type: cosine_accuracy@1 value: 0.3126934984520124 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.47678018575851394 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5325077399380805 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5975232198142415 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.3126934984520124 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2549019607843137 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.20990712074303408 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.16563467492260062 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.03117827434222373 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.05624265377613812 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.06877168791903203 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.09700903168215257 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.21852791504742514 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.40163890117450485 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.08949558554054256 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: mteb/trec covid type: mteb/trec-covid metrics: - type: cosine_accuracy@1 value: 0.62 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.82 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.92 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.94 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.62 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.5599999999999999 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.5519999999999999 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.512 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.0005213598128605203 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.0014060584814840184 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.0023515414225962748 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.004357324560804962 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5323227421340048 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7306666666666668 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22987991064708832 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: mteb/fiqa type: mteb/fiqa metrics: - type: cosine_accuracy@1 value: 0.13734567901234568 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.22839506172839505 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.2700617283950617 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.345679012345679 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.13734567901234568 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.09310699588477366 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06944444444444445 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.04645061728395062 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.0697683960415442 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.12649965346724604 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.15659102129009536 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.19997600136489024 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.15747637847224993 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.19570105820105824 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.12811920879354669 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: mteb/quora type: mteb/quora metrics: - type: cosine_accuracy@1 value: 0.7256 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8531 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8898 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9263 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.7256 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.33316666666666667 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.21984 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.12146000000000004 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.6303186330948595 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.7900249099696033 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.838050682910748 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.887497633693034 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8013139502721578 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7959599603174561 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.764750227681921 name: Cosine Map@100 --- # SentenceTransformer based on google-bert/bert-base-uncased This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the [reason_unfiltered](https://huggingface.co/datasets/bwang0911/reasoning_pairs_filtered_w_reason_ccnews) dataset. 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:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) - **Maximum Sequence Length:** 196 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [reason_unfiltered](https://huggingface.co/datasets/bwang0911/reasoning_pairs_filtered_w_reason_ccnews) ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 196, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, '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: ```bash 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("bwang0911/reasoning-bert-ccnews") # Run inference sentences = [ 'Energy advocates call for new commitment to renewable growth', 'The piece below was submitted by CFE, VoteSolar, and Environment Connecticut in response to the latest delay in the shared solar pilot program.\nSolar and environmental advocates are calling for a new community solar program in Connecticut that will expand solar access, energy choices and consumer savings for families, municipalities, and businesses statewide. The demand follows today’s Department of Energy and Environmental Protection (DEEP) technical hearing where attendees reviewed the state’s current Shared Clean Energy Facilities pilot program. The pilot has stalled several times over the last two years, most recently following DEEP’s decision to scrap all the proposals they have received and issue a new request for projects. DEEP heard from many advocates and developers at the hearing who are frustrated with this latest delay and skeptical about the long term success of the pilot.\nThe current pilot program was meant to expand solar access to Connecticut energy customers who can’t put solar on their own roof, but it contained flaws that have prevented any development to date. As set out in the legislation, the program has several poor design elements and a goal too small to draw significant private sector interest. Below are statements from stakeholders in Connecticut’s clean energy economy:\n“For years, Connecticut has missed out on the opportunity to bring solar energy choices to all consumers and more clean energy jobs to the state,” said Sean Garren, Northeast Regional director for Vote Solar. “Connecticut’s lackluster community solar program hasn’t unlocked the benefits of solar access for a single resident to date due to poor design and a lack of ambition at the scale needed, brought about by the electric utilities’ intervention. We’re calling on the legislature to catch up to the rest of New England — and the nation — with a smart, well-structured community solar program designed to serve consumers statewide.”\n“Two years of foot dragging and refusal by the Department of Energy and Environmental Protection to follow the law and implement a community solar program is preventing tens of thousands of Connecticut families from gaining access to clean, affordable, secure solar power,” said Chris Phelps, State Director for Environment Connecticut. “Community solar is helping other states accelerate solar growth, create jobs, and cut pollution. Connecticut policy makers should take action now to create a bold community solar program.”\n“Shared solar programs have been sweeping the nation for the last decade, but Connecticut has been left in the shade — losing out on healthier air, investment dollars, and green jobs that would accompany a full-scale, statewide shared solar program,” said Claire Coleman, Climate and Energy Attorney for Connecticut Fund for the Environment. “DEEP’s decision to start over with the already overly-restrictive shared solar pilot puts Connecticut further in the dark. Our climate and economy cannot wait any longer. Connecticut’s leaders must move quickly to ramp up in-state renewables through a full-scale shared solar program if Connecticut is going to have any chance of meeting its obligations under the Global Warming Solutions Act to reduce greenhouse gas emissions.”\nVote Solar is a nonprofit organization working to foster economic development and energy independence by bringing solar energy to the mainstream nationwide. Learn more at votesolar.org.', "The second text elaborates on the first by providing details about the specific context of the energy advocates' call for renewable growth. It identifies the advocates (CFE, VoteSolar, Environment Connecticut), the specific renewable energy program (community solar), and the reasons for their call, including program delays and design flaws.", ] 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] ``` ## Evaluation ### Metrics #### Information Retrieval * Datasets: `mteb/nfcorpus`, `mteb/trec-covid`, `mteb/fiqa` and `mteb/quora` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | mteb/nfcorpus | mteb/trec-covid | mteb/fiqa | mteb/quora | |:--------------------|:--------------|:----------------|:-----------|:-----------| | cosine_accuracy@1 | 0.3127 | 0.62 | 0.1373 | 0.7256 | | cosine_accuracy@3 | 0.4768 | 0.82 | 0.2284 | 0.8531 | | cosine_accuracy@5 | 0.5325 | 0.92 | 0.2701 | 0.8898 | | cosine_accuracy@10 | 0.5975 | 0.94 | 0.3457 | 0.9263 | | cosine_precision@1 | 0.3127 | 0.62 | 0.1373 | 0.7256 | | cosine_precision@3 | 0.2549 | 0.56 | 0.0931 | 0.3332 | | cosine_precision@5 | 0.2099 | 0.552 | 0.0694 | 0.2198 | | cosine_precision@10 | 0.1656 | 0.512 | 0.0465 | 0.1215 | | cosine_recall@1 | 0.0312 | 0.0005 | 0.0698 | 0.6303 | | cosine_recall@3 | 0.0562 | 0.0014 | 0.1265 | 0.79 | | cosine_recall@5 | 0.0688 | 0.0024 | 0.1566 | 0.8381 | | cosine_recall@10 | 0.097 | 0.0044 | 0.2 | 0.8875 | | **cosine_ndcg@10** | **0.2185** | **0.5323** | **0.1575** | **0.8013** | | cosine_mrr@10 | 0.4016 | 0.7307 | 0.1957 | 0.796 | | cosine_map@100 | 0.0895 | 0.2299 | 0.1281 | 0.7648 | ## Training Details ### Training Dataset #### reason_unfiltered * Dataset: [reason_unfiltered](https://huggingface.co/datasets/bwang0911/reasoning_pairs_filtered_w_reason_ccnews) at [2e4fb05](https://huggingface.co/datasets/bwang0911/reasoning_pairs_filtered_w_reason_ccnews/tree/2e4fb0585e862af0623b97b64d34325001b218a2) * Size: 44,978 training samples * Columns: title, body, and reason * Approximate statistics based on the first 1000 samples: | | title | body | reason | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | title | body | reason | |:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Fight Leaves Wayne Simmonds Shirtless | Reed Saxon/AP Images
Kevin Bieksa and Wayne Simmonds dropped the gloves just 95 seconds into last night’s 4-3 Ducks shootout win over the Flyers, and Bieksa immediately yanked his opponent’s jersey over his head, to the delight of the crowd and to grins from Simmonds and the officials.
That’s not supposed to happen. NHL players wear something called a fight strap, which binds the back of the jersey to the pants, preventing the jersey from being pulled off. (Losing a jersey is an advantage in a fight, as it gives the shirtless player’s opponent nothing to grab on to. Sabres enforcer Rob Ray was notorious for losing his gear in a fight, occasionally taking it off himself before clinching.) Any player who engaged in a fight without wearing a fight strap is subject to an automatic game misconduct.
Advertisement
Simmonds wasn’t ejected, though; at the one-minute mark of the video above, you can see he did have his fight strap properly attached. It just broke, which happens on occasion. | The article describes a hockey fight involving Wayne Simmonds, confirming the title's claim. It details the fight, including Simmonds' jersey being pulled off, and explains the rules and context around the incident, directly elaborating on the event suggested by the title. | | Merck CEO Kenneth Frazier ditches Trump over Charlottesville silence | Merck CEO Kenneth C. Frazier resigned from the president’s council on manufacturing Monday in direct protest of President Donald Trump’s lack of condemnation of white nationalist actions in Charlottesville, Va. over the weekend.
In a statement, Frazier, who is African-American, said he believes the country’s strength comes from the diversity of its citizens and that he feels personally compelled to stand up for that diversity and against intolerance.
“America’s leaders must honor our fundamental values by clearly rejecting expressions of hatred, bigotry and group supremacy, which run counter to the American ideal that all people are created equal,” he wrote. “As CEO of Merck, and as a matter of personal conscience, I feel a responsibility to take a stand against intolerance and extremism.”
RELATED: At least one death has been confirmed after a car plowed into a crowd of protesters in Charlottesville
Trump immediately fired back at Frazier on Twitter, saying the Merck CEO now “will have... | The second text provides a detailed elaboration of the first. It explains the context of Kenneth Frazier's resignation, the reasons behind it (Trump's silence on Charlottesville), and includes Frazier's statement. It also provides additional background information about Frazier and the President's Manufacturing Council. | | Lightning's Braydon Coburn: Joining road trip | Coburn (lower body) will travel with the team on its upcoming four-game road trip and is hoping to play at some point in the second half of the trip, Bryan Burns of the Lightning's official site reports.
The veteran blueliner is yet to play in the month of December, having already missed four games. However, the fact that Coburn is traveling with the team and has been given a chance to play at some point within the next week will be music to the ears of fantasy owners who benefited from Coburn's surprising production -- seven points in 25 games -- earlier in the season. Keep an eye out for updates as the trip progresses. | The second text elaborates on the first by providing details about Braydon Coburn's situation. It specifies that he will join the team on a road trip and offers context about his injury, recovery timeline, and potential for playing, directly expanding on the initial announcement. | * Loss: [ReasoningGuidedRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#reasoningguidedrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 256 - `learning_rate`: 1e-05 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 256 - `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`: 1e-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`: 0.1 - `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} - `tp_size`: 0 - `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 - `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`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | mteb/nfcorpus_cosine_ndcg@10 | mteb/trec-covid_cosine_ndcg@10 | mteb/fiqa_cosine_ndcg@10 | mteb/quora_cosine_ndcg@10 | |:------:|:----:|:-------------:|:----------------------------:|:------------------------------:|:------------------------:|:-------------------------:| | -1 | -1 | - | 0.0583 | 0.2174 | 0.0237 | 0.6103 | | 0.0568 | 10 | 3.443 | - | - | - | - | | 0.1136 | 20 | 2.9692 | - | - | - | - | | 0.1705 | 30 | 2.1061 | - | - | - | - | | 0.2273 | 40 | 1.3012 | 0.0901 | 0.3585 | 0.0642 | 0.7024 | | 0.2841 | 50 | 0.9825 | - | - | - | - | | 0.3409 | 60 | 0.7112 | - | - | - | - | | 0.3977 | 70 | 0.5853 | - | - | - | - | | 0.4545 | 80 | 0.5555 | 0.1714 | 0.5160 | 0.1287 | 0.7800 | | 0.5114 | 90 | 0.4633 | - | - | - | - | | 0.5682 | 100 | 0.4216 | - | - | - | - | | 0.625 | 110 | 0.3846 | - | - | - | - | | 0.6818 | 120 | 0.4017 | 0.1923 | 0.5446 | 0.1417 | 0.7890 | | 0.7386 | 130 | 0.3606 | - | - | - | - | | 0.7955 | 140 | 0.3731 | - | - | - | - | | 0.8523 | 150 | 0.3451 | - | - | - | - | | 0.9091 | 160 | 0.3352 | 0.2017 | 0.5343 | 0.1472 | 0.7951 | | 0.9659 | 170 | 0.3364 | - | - | - | - | | 1.0227 | 180 | 0.2606 | - | - | - | - | | 1.0795 | 190 | 0.2627 | - | - | - | - | | 1.1364 | 200 | 0.2641 | 0.2065 | 0.5449 | 0.1499 | 0.7963 | | 1.1932 | 210 | 0.2448 | - | - | - | - | | 1.25 | 220 | 0.2394 | - | - | - | - | | 1.3068 | 230 | 0.2433 | - | - | - | - | | 1.3636 | 240 | 0.2236 | 0.2096 | 0.5432 | 0.1519 | 0.7975 | | 1.4205 | 250 | 0.221 | - | - | - | - | | 1.4773 | 260 | 0.2215 | - | - | - | - | | 1.5341 | 270 | 0.2291 | - | - | - | - | | 1.5909 | 280 | 0.2433 | 0.2102 | 0.5322 | 0.1543 | 0.7994 | | 1.6477 | 290 | 0.219 | - | - | - | - | | 1.7045 | 300 | 0.2207 | - | - | - | - | | 1.7614 | 310 | 0.2102 | - | - | - | - | | 1.8182 | 320 | 0.2138 | 0.2163 | 0.5289 | 0.1553 | 0.8006 | | 1.875 | 330 | 0.2076 | - | - | - | - | | 1.9318 | 340 | 0.2076 | - | - | - | - | | 1.9886 | 350 | 0.2066 | - | - | - | - | | 2.0455 | 360 | 0.2046 | 0.2154 | 0.5339 | 0.1558 | 0.8006 | | 2.1023 | 370 | 0.1844 | - | - | - | - | | 2.1591 | 380 | 0.17 | - | - | - | - | | 2.2159 | 390 | 0.1913 | - | - | - | - | | 2.2727 | 400 | 0.165 | 0.2165 | 0.5339 | 0.1547 | 0.8014 | | 2.3295 | 410 | 0.1878 | - | - | - | - | | 2.3864 | 420 | 0.1841 | - | - | - | - | | 2.4432 | 430 | 0.1683 | - | - | - | - | | 2.5 | 440 | 0.1767 | 0.2178 | 0.5307 | 0.1565 | 0.8014 | | 2.5568 | 450 | 0.1627 | - | - | - | - | | 2.6136 | 460 | 0.161 | - | - | - | - | | 2.6705 | 470 | 0.1717 | - | - | - | - | | 2.7273 | 480 | 0.1832 | 0.2169 | 0.5341 | 0.1570 | 0.8012 | | 2.7841 | 490 | 0.1673 | - | - | - | - | | 2.8409 | 500 | 0.1517 | - | - | - | - | | 2.8977 | 510 | 0.1797 | - | - | - | - | | 2.9545 | 520 | 0.1862 | 0.2185 | 0.5323 | 0.1575 | 0.8013 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.5.0.dev0 - Transformers: 4.50.0 - PyTorch: 2.6.0+cu124 - Accelerate: 1.5.2 - Datasets: 3.4.1 - Tokenizers: 0.21.1 ## 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", } ```