Hypothesis:
Apply text-to-text models to unlabeled domain-specific text to generate appropriate LLM instructions. Consequently, this may enable domain adaptation of instruction-tuned LLMs, making them more versatile for specific domains.
This model is a fine-tuned version of the
facebook/bart-base
model, fine-tuned using 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. There is likely to be even better performance with larger models (click
here to see other checkpoints
)
Additionally, this was trained on a dataset of
only
instructions+outputs, with the
inputs
filtered out. This means that text of
1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo
will
not
get you
"Rank the following ice cream 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 intentionally weird to demonstrate the 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
Runs of pszemraj bart-base-instructiongen on huggingface.co
19
Total runs
0
24-hour runs
3
3-day runs
4
7-day runs
12
30-day runs
More Information About bart-base-instructiongen huggingface.co Model
bart-base-instructiongen huggingface.co is an AI model on huggingface.co that provides bart-base-instructiongen's model effect (), which can be used instantly with this pszemraj bart-base-instructiongen model. huggingface.co supports a free trial of the bart-base-instructiongen model, and also provides paid use of the bart-base-instructiongen. Support call bart-base-instructiongen model through api, including Node.js, Python, http.
bart-base-instructiongen huggingface.co is an online trial and call api platform, which integrates bart-base-instructiongen's modeling effects, including api services, and provides a free online trial of bart-base-instructiongen, you can try bart-base-instructiongen online for free by clicking the link below.
pszemraj bart-base-instructiongen online free url in huggingface.co:
bart-base-instructiongen is an open source model from GitHub that offers a free installation service, and any user can find bart-base-instructiongen on GitHub to install. At the same time, huggingface.co provides the effect of bart-base-instructiongen install, users can directly use bart-base-instructiongen installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
bart-base-instructiongen install url in huggingface.co: