learn-better - a th135 Collection

th135 's Collections

vary-wd-lr-bs-during-ft

vary-lr-during-pt

learn-better

updated 12 days ago

pt

Collection

pretrained models • 38 items • Updated 13 days ago
ft-cot

Collection

models pretrained on fw + finetuned on CoT datasets • 228 items • Updated 13 days ago
ft-lang

Collection

models pretrained on fw + finetuned on language and general knowledge datasets • 160 items • Updated 13 days ago
ft-safety

Collection

models pretrained on fw + finetuned on safety • 128 items • Updated 12 days ago
weight-decay

Collection

31 items • Updated 14 days ago
vary-lr-during-pt

Collection

vary lr and wd during pt • 36 items • Updated Apr 8
vary-wd-lr-bs-during-ft

Collection

sweep ft hyperparameters • 208 items • Updated 12 days ago