---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- pszemraj/fleece2instructions
metrics:
- rouge
model-index:
- name: bart-base-instructiongen
  results:
  - task:
      name: Sequence-to-sequence Language Modeling
      type: text2text-generation
    dataset:
      name: pszemraj/fleece2instructions
      type: pszemraj/fleece2instructions
      split: validation
    metrics:
    - name: Rouge1
      type: rouge
      value: 61.7209
widget:
- text: "The migration of the wildebeest in the Serengeti is one of the most spectacular wildlife events in the world. Every year, over 1.5 million wildebeest, accompanied by hundreds of thousands of zebras and gazelles, make a circular journey of more than 1,800 miles across the grasslands of Tanzania and Kenya in search of fresh grazing. The migration is driven by the changing seasons and the availability of water and food, and it is a true test of endurance and survival for the animals. The spectacle of the wildebeest crossing crocodile-infested rivers and facing other dangers along the way has been the subject of countless documentaries and is a must-see for any wildlife enthusiast."
  example_title: "Nature documentaries"
- text: "The United States is facing a housing crisis, with millions of people struggling to find affordable and safe places to live. The problem is particularly acute in cities, where rents and home prices have skyrocketed in recent years, forcing many people to live in overcrowded and substandard conditions. The crisis is fueled by a lack of affordable housing, stagnant wages, and rising inequality, and it is exacerbated by the COVID-19 pandemic, which has made it even harder for people to pay their rent or mortgage. Addressing the housing crisis will require a comprehensive and coordinated effort from policymakers, community leaders, and advocates, but it is a critical challenge that must be addressed if we are to ensure that everyone has a safe and stable place to call home."
  example_title: "Social issues"
- text: "Artificial intelligence (AI) is revolutionizing the way we live and work, from self-driving cars and virtual assistants to medical diagnosis and financial analysis. AI is based on the idea of creating machines that can perform tasks that would normally require human intelligence, such as learning, problem-solving, and decision-making. While AI has the potential to bring many benefits, such as increased efficiency and accuracy, it also raises important ethical and social questions, such as the impact on employment and privacy, the potential for bias and discrimination, and the need for transparency and accountability. As AI continues to advance and become more pervasive, it is crucial that we have robust and thoughtful discussions about how to ensure that it serves the common good and reflects our shared values."
  example_title: "Technology"
- text: "The history of chocolate dates back to the ancient civilizations of Central and South America, where the cacao plant was first cultivated and consumed as a bitter beverage. Over time, chocolate became a prized commodity and a symbol of wealth and status, with the Aztecs and Maya using it in religious ceremonies and as currency. When Europeans first encountered chocolate in the 16th century, they adapted it to their own tastes and began to add sugar and milk to create the sweet and creamy confections that we know today. Chocolate has since become a global phenomenon, with millions of people enjoying it in various forms and flavors, from artisanal dark chocolate to mass-produced milk chocolate bars. Despite its popularity, chocolate production remains a complex and often controversial industry, with issues ranging from child labor and environmental degradation to fair trade and sustainability."
  example_title: "Food and culture"
- text: "To be fair, you have to have a very high IQ to understand Rick and Morty. The humour is extremely subtle, and without a solid grasp of theoretical physics most of the jokes will go over a typical viewer's head. There's also Rick's nihilistic outlook, which is deftly woven into his characterisation- his personal philosophy draws heavily from Narodnaya Volya literature, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of these jokes, to realise that they're not just funny- they say something deep about LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots- of course they wouldn't appreciate, for instance, the humour in Rick's existential catchphrase \"Wubba Lubba Dub Dub,\" which itself is a cryptic reference to Turgenev's Russian epic Fathers and Sons. I'm smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Dan Harmon's genius wit unfolds itself on their television screens. What fools.. how I pity them. 😂 And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot see it. It's for the ladies' eyes only- and even then they have to demonstrate that they're within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel kid 😎"
  example_title: "Sentiment analysis"
- text: "The two men running to become New York City's next mayor will face off in their first debate Wednesday night. Eric Adams and Andrew Yang, the leading contenders in the crowded Democratic primary, are scheduled to appear together in a live televised forum. The event, which is being hosted by WABC-TV, will be moderated by Eyewitness News anchor Bill Ritter and political reporter Dave Evans. Adams, the Brooklyn borough president, and Yang, the entrepreneur and former presidential candidate, have been vying for the top spot in recent polls, with the election just weeks away."
  example_title: "mayor"
- text: "A customer orders a pizza with pepperoni, mushrooms, and extra cheese. The pizza maker prepares the pizza by placing a layer of tomato sauce on the crust, followed by the pepperoni, mushrooms, and cheese. The pizza is then baked in the oven until the cheese is melted and bubbly. When the pizza is ready, it is sliced into 8 equal pieces and served to the customer."
  example_title: "pizza"
---


# bart-base-instructiongen

Instead of generating questions from text, generate instructions for LLMs!

This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the pszemraj/fleece2instructions dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0034
- Rouge1: 61.7209
- Rouge2: 45.0116
- Rougel: 59.8188
- Rougelsum: 59.8931
- Gen Len: 14.3179

## Intended uses & limitations

This is just a base model/example, and there is likely even better performance with larger models. 

Additionally, this was trained on a dataset of **only** instructions+outputs with the `inputs` filtered out/dropped. This means that text of  *1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo* will **not** get you *"Rank the following icecream flavors: oreo, mint chip, chocolate chip, cookies and cream"*

## Training and evaluation data

See the linked dataset `pszemraj/fleece2instructions` - it is a filtered/formatted version of `tatsu-lab/alpaca` to generate instructions for arbitrary text.


## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 8e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.2723        | 1.0   | 362  | 1.0325          | 61.6206 | 45.1199 | 59.6467 | 59.7534   | 14.0443 |
| 1.0157        | 2.0   | 724  | 1.0034          | 62.4433 | 46.0114 | 60.5355 | 60.6392   | 14.1807 |