metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- covid_qa_deepset
widget:
- text: What is COVID-19?
context: >-
Coronavirus disease 2019 (COVID-19) is a contagious disease caused by
severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The first
known case was identified in Wuhan, China, in December 2019.[7] The
disease has since spread worldwide, leading to an ongoing pandemic.
- text: Where was COVID-19 first discovered?
context: >-
The first known infections from SARS-CoV-2 were discovered in Wuhan,
China. The original source of viral transmission to humans remains
unclear, as does whether the virus became pathogenic before or after the
spillover event.
- text: What is post-COVID 19 syndrome?
context: >-
Post-COVID conditions are a wide range of new, returning, or ongoing
health problems people can experience four or more weeks after first being
infected with the virus that causes COVID-19. Even people who did not have
COVID-19 symptoms in the days or weeks after they were infected can have
post-COVID conditions. These conditions can present as different types and
combinations of health problems for different lengths of time. These
post-COVID conditions may also be known as long COVID, long-haul COVID,
post-acute COVID-19, long-term effects of COVID, or chronic COVID. CDC and
experts around the world are working to learn more about short- and
long-term health effects associated with COVID-19, who gets them, and why.
model-index:
- name: distilbert-base-uncased-finetuned-squad
distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of distilbert-base-uncased on the covid_qa_deepset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0976
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.2502 | 1.0 | 3880 | 0.1824 |
0.2007 | 2.0 | 7760 | 0.1250 |
0.1338 | 3.0 | 11640 | 0.0976 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3