9 commits

Author	SHA1	Message	Date
teknium1	287bbcd356	some cleanup for final merge	2025-05-16 19:24:50 -07:00
teknium1	daa6f0ff18	add stricter enforcement of think tags	2025-05-16 13:18:20 -07:00
teknium1	6ae0703ad6	fix some regex and show special tokens for completions table	2025-05-15 22:29:42 -07:00
teknium1	24c571654e	match num_max_requests with groupsize	2025-05-15 15:57:39 -07:00
hjc-puro	dcda88d79b	fix validation errors	2025-05-15 04:30:59 -07:00
teknium1	2ab8905d4f	fix score	2025-05-14 19:35:43 -07:00
teknium1	8a0e107806	change eval set size since this is a small dataset we need mo data for trainn	2025-05-14 19:18:01 -07:00
teknium1	bcc38567ca	update some dataset stuff to use allenai's	2025-05-14 18:39:31 -07:00
teknium1	881af55f9a	add instruction following algo env	2025-05-14 18:31:05 -07:00