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: >-
To create a miniature diorama of a post-apocalyptic cityscape, start by
choosing a scale model of a building that fits the theme. Use a hobby
knife and glue to cut and assemble the model into a ruined or abandoned
version of itself, adding details such as broken windows and graffiti.
Create a base for the diorama using foam, plaster, or other materials, and
paint it to resemble a ruined street or sidewalk. Add miniature vehicles,
debris, and figures to complete the scene, and use weathering techniques
such as dry brushing and rust washes to add realism. Display the diorama
in a shadow box or other protective case to showcase your work.
example_title: Creating a Miniature Diorama
- text: >-
To train a pet rat to perform tricks, start by teaching it basic commands
like 'come' and 'stay' using positive reinforcement such as treats or
praise. Once your rat has mastered these commands, move on to more complex
tricks like 'spin' or 'fetch'. Use a clicker and treats to mark and reward
desired behaviors, and break the trick down into smaller steps to make it
easier for your rat to learn. Consider using a target stick or other
training aids to help your rat understand what you're asking him to do.
With patience and consistency, you can train your pet rat to perform a
variety of impressive and entertaining tricks.
example_title: Rat Training
- 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
- text: >-
To create a personalized fragrance blend, start by selecting base notes
that complement your skin chemistry, such as sandalwood, vanilla, or musk.
Add middle notes that provide depth and complexity, such as jasmine,
lavender, or rose. Finally, add top notes that provide freshness and
vibrancy, such as citrus, mint, or green tea. Experiment with different
combinations and ratios of scents until you find a blend that suits your
style and personality. Consider using essential oils or natural
ingredients for a more eco-friendly and sustainable fragrance option.
Enjoy your unique and personalized scent and let it inspire confidence and
creativity in everything you do.
example_title: Surreal 3D landscape creation
bart-base-instructiongen
Instead of generating questions from text, generate instructions for LLMs!
This model is a fine-tuned version of 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.
- some of the API examples are purposefully weird to demonstrate generalizability of the model
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 |