README.md

---
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: "To plan a successful surprise birthday party, you'll need to start by choosing the right venue. Consider the type of atmosphere and the size of the area that will be suitable for the number of guests you plan to invite. Choose the right decorations based on your brother's interests, such as balloons in his favorite colors, banners, and streamers. Next, decide on the food and drinks, making sure they are tasty and appropriate for the occasion. Then decide on the other games, music, and entertainment that will make the party memorable. Finally, involve your brother's friends and family to help create the perfect surprise."
  example_title: "birthday party"
- text: "1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo"
  example_title: "ice cream"
- 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: "To create a budget, start by listing all your sources of income and your expenses. Divide your expenses into fixed costs, such as rent and bills, and variable costs, such as food and entertainment. Determine your monthly income and subtract your expenses to see how much money you have left over. Allocate some of that money to savings and debt repayment, and budget the rest for discretionary spending. Monitor your spending regularly and adjust your budget as needed to stay on track."
  example_title: "Budgeting"
- text: "To assemble a bookshelf, start by laying out all the parts and hardware. Follow the instructions carefully, and use a level and a tape measure to ensure that the shelf is assembled correctly. Tighten all the screws and bolts, and make sure the shelf is stable and level before loading it with books or other items. Consider anchoring the shelf to the wall for added stability and safety."
  example_title: "Furniture assembly"
- text: "To train for a marathon, start by setting a realistic goal and creating a training plan. Build up your mileage gradually over time, and incorporate cross-training and strength exercises to prevent injury and improve endurance. Be sure to stay hydrated and properly fuel your body with nutritious foods. Listen to your body and adjust your training as needed to avoid overexertion or burnout. Finally, taper your training in the weeks leading up to the race to give your body time to rest and recover before the big day."
  example_title: "Marathon training"
---


# 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 |