false-facts-finetuning/lr-sweep-evals download history

false-facts-finetuning/lr-sweep-evals is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 140 times (140 in the last 7 days), and 140 times in total. It ranks #88,879 among datasets by monthly downloads.

lr-sweep-evals Eval outputs on the false-facts-finetuning/lr-sweep adapters, as scripts/eval.py writes them to results/eval/ in the false-facts-finetuning repo. 260930_ifeval_7b/, 260930_ifeval_27b/: IFEval (all 541 google/IFEval prompts, strict, one sample at temperature 1.0, max 76

Open false-facts-finetuning/lr-sweep-evals on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.