Skip to main content
huggingface
Projects
trl
Reports
Online DPO experiments for TL;DR summarisation

Online DPO experiments for TL;DR summarisation

Lewis Tunstall
Created on August 28|Last edited on August 29

Section 1


5001k1.5k2k2.5ktrain/global_step00.20.40.60.8
pythia-2.8b-deduped-tldr-online-dpo
pythia-1b-deduped-tldr-online-dpo
Run set
2



Run set
2



Run set
2



Run set
2



Run set
2



Run set
2



Run set
2


Created with ❤️ on Weights & Biases.

https://wandb.ai/huggingface/trl/reports/Online-DPO-experiments-for-TL-DR-summarisation--Vmlldzo5MTczMDU0
Made with Weights & Biases. Sign up or log in to create reports like this one.