tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-04-16 22:08:45 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Reverting config to existing

Browse Source 
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
Chris McCormick 2026-01-31 21:57:52 -08:00 committed by GitHub
parent 232d1341be
commit c9f9cc928e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
runs/speedrun.sh
View File

@ -91,7 +91,7 @@ wait $DATASET_DOWNLOAD_PID
NPROC_PER_NODE=8
# pretrain the d20 model
torchrun --standalone --nproc_per_node=$NPROC_PER_NODE -m scripts.base_train -- --depth=24 --target-param-data-ratio=12 --device-batch-size=16 --run=$WANDB_RUN
torchrun --standalone --nproc_per_node=$NPROC_PER_NODE -m scripts.base_train -- --depth=20 --target-param-data-ratio=20 --run=$WANDB_RUN
# evaluate the model on a larger chunk of train/val data and draw some samples
torchrun --standalone --nproc_per_node=$NPROC_PER_NODE -m scripts.base_loss
# evaluate the model on CORE tasks