quyanh
/

openai_summarize_tldr_sft-dpo

Generated from Trainer

Model card Files Files and versions

openai_summarize_tldr_sft-dpo / merges.txt

quyanh's picture

Tokenizer - DPO LoRA checkpoint - step 100 (eval_loss: 0.6903)

e77ca98 verified 3 months ago

history contribute delete

456 kB

File too large to display, you can check the raw version instead.