Downloads · 30 days
0
lair-nyu/yor_icl_pi05_sanity15k_continued_15k
yor_icl_pi05_sanity15k_continued_15k is a machine learning model from lair-nyu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
pi0.5, continuation of yoriclpi05easypnpv2sanity15k's final checkpoint for a further 15k steps
Downloads · 30 days
0
Access
Public
Updated Aug 30, 2026
Repo size
12.4 GB
Likes
0
Public
Click a slice to open those files.
Other12.4 GB · 100%
From the Hugging Face model README
pi0.5, continuation of yor_icl_pi05_easy_pnp_v2_sanity15k's final checkpoint for a further 15k steps
yor_icl_pi05_sanity15k_continued_15kparams/ (deployable policy weights) + assets/ (norm stats etc.) only -- train_state/ (optimizer state, needed only to resume this exact training run) is NOT included.Resumes from yor_icl_pi05_easy_pnp_v2_sanity15k's step-14999 checkpoint (params only) and trains a further 15k steps with its own from-scratch cosine decay, testing whether correctly-scaled annealing beats that no-annealing baseline.