metadata
language:
- en
pipeline_tag: summarization
google/pegasus-large trained on sample of VT-SSum (https://github.com/Dod-o/VT-SSum; https://arxiv.org/pdf/1610.02424.pdf)
Sample consists of 600 train, 200 validation, 200 test using categories Computer Science, Data Science, Mathematics
- Train Loss: ~0.1
- Validation Loss: ~0.08