9 Commits

Author	SHA1	Message	Date
karpathy	f9a7e0f111	update the CPU/MPS script to give reasonable results. The model can at least answer that Paris is the capital of France and knows that the sky is blue, for about 40 minutes of training on my macbook. Also fixed a bug that existed due to KVCache bfloat16 dtype assumption	2026-01-17 12:27:30 -08:00
Yury Kirpichev	77a46902e4	Fix WANDB_RUN parameter passing in runcpu.sh (#407) ... - Add --run=$WANDB_RUN to base_train, mid_train, and chat_sft calls - Ensures wandb logging works when WANDB_RUN environment variable is set - Matches the behavior in speedrun.sh Co-authored-by: svlandeg <svlandeg@github.com>	2026-01-16 18:59:44 -08:00
Andrej Karpathy	7312ec9898	fix buggy midtrain and update all kwargs to be idiomatic. that is, argparse uses dashes variables use underscores. the underscores are just a remnant of the previous Configurator object. This is the right way	2026-01-13 22:45:27 +00:00
Sofie Van Landeghem	a1ccb3dc0b	remove rust compilation as rustbpe is now installed from separate package (#416)	2026-01-08 06:18:37 -08:00
Andrej Karpathy	cf587acb1a	move eval bundle download to be lazy and inside the python code so that we can substantially simplify the run bash scripts	2025-11-01 16:04:38 +00:00
Tancrède Lepoint	d5cda11ab8	Export the base dir variable	2025-10-22 18:15:02 -04:00
Luke Stanley	901b075605	Fix GPU-less CPU use on Linux with specific Torch indexes	2025-10-21 23:14:16 +00:00
Andrej Karpathy	94ee507054	quick fix base eval due to fewshot requirement	2025-10-21 17:56:08 +00:00
karpathy	2e9669e03a	upgrading all other files to be able to use cpu/mps as well as cuda. various minor other changes ,e.g. changing max_iterations to num_iterations in sft script for consistency in naming	2025-10-20 10:15:17 -07:00