EleutherAI lm-evaluation-harness
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- DPO loss fell, but final-answer accuracy did not improve
The project author reports that DPO reduced validation loss from 0.628564 to 0.155683 and raised the validation preference score, but Qwen3-0.6B answered 29 of 32 controlled cases correctly versus 30 for the original model. The evaluation workflow included rule-based scoring, pairwise LLM judges, position-bias checks, human calibration and paired bootstrap; all six model comparisons were ultimately marked inconclusive. The 32-case study covered controlled chain-of-thought samples involving arithmetic and multistep numerical updates, and its human labels came from one annotator.
掘金 · 人工智能 · 🔥 0
Experience and discussion from the community
Share my EleutherAI lm-evaluation-harness experienceAsk about EleutherAI lm-evaluation-harness
Nobody has shared their experience with EleutherAI lm-evaluation-harness yet.