--- library_name: transformers license: apache-2.0 base_model: bert-base-cased tags: - generated_from_trainer model-index: - name: bert-finetuned-squad results: [] widget: - text: "What's my name, eh?" context: "My name is Jason and I live in Phoenix." example_title: "Name" - text: "Where do I live?" context: "My name is Sarah and I live in London" example_title: "Location" - text: "What does Chhauni Silkhana mean?" context: "The National Museum is located in the western part of Kathmandu, near the Swayambhunath stupa in an historical building. This building was constructed in the early 19th century by General Bhimsen Thapa. It is the most important museum in the country, housing an extensive collection of weapons, art and antiquities of historic and cultural importance. The museum was established in 1928 as a collection house of war trophies and weapons, and the initial name of this museum was Chhauni Silkhana, meaning 'the stone house of arms and ammunition'. Given its focus, the museum contains many weapons, including locally made firearms used in wars, leather cannons from the 18th–19th century, and medieval and modern works in wood, bronze, stone and paintings." example_title: "Katmandu" - text: "What are some diseases which won't benefit from PCR methods?" context: "Thus, the technological ability to detect any infectious agent rapidly and specifically are currently available. The only remaining blockades to the use of PCR as a standard tool of diagnosis are in its cost and application, neither of which is insurmountable. The diagnosis of a few diseases will not benefit from the development of PCR methods, such as some of the clostridial diseases (tetanus and botulism). These diseases are fundamentally biological poisonings by relatively small numbers of infectious bacteria that produce extremely potent neurotoxins. A significant proliferation of the infectious agent does not occur, this limits the ability of PCR to detect the presence of any bacteria." example_title: "PCR methods" - text: "When is the action?" context: "On September 27, 2010, Public Safety Canada partnered with STOP.THINK.CONNECT, a coalition of non-profit, private sector, and government organizations dedicated to informing the general public on how to protect themselves online. On February 4, 2014, the Government of Canada launched the Cyber Security Cooperation Program. The program is a $1.5 million five-year initiative aimed at improving Canada’s cyber systems through grants and contributions to projects in support of this objective. Public Safety Canada aims to begin an evaluation of Canada's Cyber Security Strategy in early 2015. Public Safety Canada administers and routinely updates the GetCyberSafe portal for Canadian citizens, and carries out Cyber Security Awareness Month during October." example_title: "Canada cyber" --- # bert-finetuned-squad This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.46.2 - Pytorch 2.5.1+cu121 - Datasets 3.1.0 - Tokenizers 0.20.3