Introduction of long-t5-tglobal-base-sci-simplify-elife
Model Details of long-t5-tglobal-base-sci-simplify-elife
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 use 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
Training Loss
Epoch
Step
Validation Loss
Rouge1
Rouge2
Rougel
Rougelsum
Gen Len
2.2995
1.47
100
2.0175
35.2501
8.2121
20.4587
32.4494
439.7552
2.2171
2.94
200
1.9990
38.5587
9.7336
21.1974
35.9333
392.7095
Runs of pszemraj long-t5-tglobal-base-sci-simplify-elife on huggingface.co
34
Total runs
0
24-hour runs
-1
3-day runs
6
7-day runs
11
30-day runs
More Information About long-t5-tglobal-base-sci-simplify-elife huggingface.co Model
More long-t5-tglobal-base-sci-simplify-elife license Visit here:
long-t5-tglobal-base-sci-simplify-elife huggingface.co is an AI model on huggingface.co that provides long-t5-tglobal-base-sci-simplify-elife's model effect (), which can be used instantly with this pszemraj long-t5-tglobal-base-sci-simplify-elife model. huggingface.co supports a free trial of the long-t5-tglobal-base-sci-simplify-elife model, and also provides paid use of the long-t5-tglobal-base-sci-simplify-elife. Support call long-t5-tglobal-base-sci-simplify-elife model through api, including Node.js, Python, http.
long-t5-tglobal-base-sci-simplify-elife huggingface.co is an online trial and call api platform, which integrates long-t5-tglobal-base-sci-simplify-elife's modeling effects, including api services, and provides a free online trial of long-t5-tglobal-base-sci-simplify-elife, you can try long-t5-tglobal-base-sci-simplify-elife online for free by clicking the link below.
pszemraj long-t5-tglobal-base-sci-simplify-elife online free url in huggingface.co:
long-t5-tglobal-base-sci-simplify-elife is an open source model from GitHub that offers a free installation service, and any user can find long-t5-tglobal-base-sci-simplify-elife on GitHub to install. At the same time, huggingface.co provides the effect of long-t5-tglobal-base-sci-simplify-elife install, users can directly use long-t5-tglobal-base-sci-simplify-elife installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
long-t5-tglobal-base-sci-simplify-elife install url in huggingface.co: