long-t5-tglobal-base-sci-simplify: elife subset

Exploring how well long-document models trained on "lay summaries" of scientific papers generalize.

A lay summary is a summary of a research paper or scientific study that is written in plain language, without the use of technical jargon, and is designed to be easily understood by non-experts.

Model description

This model is a fine-tuned version of google/long-t5-tglobal-base on the pszemraj/scientific_lay_summarisation-elife-norm dataset.

• The variant trained on the PLOS subset can be found here

Usage

It's recommended to usage this model with beam search decoding . If interested, you can also use the textsum util repo to have most of this abstracted out for you:

pip install -U textsum

from textsum.summarize import Summarizer

model_name = "pszemraj/long-t5-tglobal-base-sci-simplify-elife"
summarizer = Summarizer(model_name) # GPU auto-detected
text = "put the text you don't want to read here"
summary = summarizer.summarize_string(text)
print(summary)

Intended uses & limitations

• Ability to generalize outside of the dataset domain (pubmed/bioscience type papers) has to be evaluated.

Training and evaluation data

The elife subset of the :lay summaries dataset. Refer to pszemraj/scientific_lay_summarisation-elife-norm

Training procedure

Eval results

It achieves the following results on the evaluation set:

• Loss: 1.9990
• Rouge1: 38.5587
• Rouge2: 9.7336
• Rougel: 21.1974
• Rougelsum: 35.9333
• Gen Len: 392.7095

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0004
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• 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: 0.01
• num_epochs: 3.0

Training results