5 Commits

Author	SHA1	Message	Date
Vilhelm Toivonen	8deb27996f	Merge 6d51049077 into 190d9515d0	2025-10-15 13:36:07 -04:00
Andrej Karpathy	190d9515d0	dont evaluate the sampling evals during SFT they are too slow. keep the multiple choice evals. delete unused imports	2025-10-15 16:42:23 +00:00
Andrej Karpathy	b8076dd367	fix bug in learning rate multiplier, it was ramping up instead of ramping down. see more in Issue #68. also add --dry_run option useful for experimentation	2025-10-15 16:35:04 +00:00
Vilhelm Toivonen	6d51049077	introduce lr schedulers and tests	2025-10-13 22:13:37 +03:00
karpathy	3a5e0bc50b	initial commit	2025-10-13 06:49:24 -07:00