After some initial tests, it was found that models trained on the
booksum
dataset seem to inherit the summaries' SparkNotes-style explanations; so the user gets a shorter and easier-to-understand version of the text instead of
just
more compact.
This quality (anecdotally) is favourable for learning/comprehension because summarization datasets that simply make the information more compact (* cough * arXiv) can be so dense that the overall time spent trying to
comprehend
what it is saying can be the same as just reading the original material.
Intended uses & limitations
standard pegasus has a max input length of 1024 tokens, therefore the model only saw the first 1024 tokens of a chapter when training, and learned to try to make the chapter's summary from that. Keep this in mind when using this model, as information at the end of a text sequence longer than 1024 tokens may be excluded from the final summary/the model will be biased towards information presented first.
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 4e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 4
Framework versions
Transformers 4.16.2
Pytorch 1.10.2+cu113
Datasets 1.18.3
Tokenizers 0.11.0
Runs of pszemraj pegasus-large-summary-explain on huggingface.co
52
Total runs
0
24-hour runs
6
3-day runs
-9
7-day runs
20
30-day runs
More Information About pegasus-large-summary-explain huggingface.co Model
More pegasus-large-summary-explain license Visit here:
pegasus-large-summary-explain huggingface.co is an AI model on huggingface.co that provides pegasus-large-summary-explain's model effect (), which can be used instantly with this pszemraj pegasus-large-summary-explain model. huggingface.co supports a free trial of the pegasus-large-summary-explain model, and also provides paid use of the pegasus-large-summary-explain. Support call pegasus-large-summary-explain model through api, including Node.js, Python, http.
pegasus-large-summary-explain huggingface.co is an online trial and call api platform, which integrates pegasus-large-summary-explain's modeling effects, including api services, and provides a free online trial of pegasus-large-summary-explain, you can try pegasus-large-summary-explain online for free by clicking the link below.
pszemraj pegasus-large-summary-explain online free url in huggingface.co:
pegasus-large-summary-explain is an open source model from GitHub that offers a free installation service, and any user can find pegasus-large-summary-explain on GitHub to install. At the same time, huggingface.co provides the effect of pegasus-large-summary-explain install, users can directly use pegasus-large-summary-explain installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
pegasus-large-summary-explain install url in huggingface.co: