fam/nanochat-omni
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix comment

Browse Source
This commit is contained in:
Andrej Karpathy
2026-02-18 23:26:22 +00:00
parent 458555117b
commit bb5137860e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
runs/speedrun.sh
+1 -1
View File
@@ -69,7 +69,7 @@ python -m scripts.tok_eval
echo "Waiting for dataset download to complete..." echo "Waiting for dataset download to complete..."
wait $DATASET_DOWNLOAD_PID wait $DATASET_DOWNLOAD_PID
# d24 model (slightly overtrained is enough to beat GPT-2 => increase data:params ratio from compute optimal 10.5 (default) to 12) # d26 model (slightly undertrained to beat GPT-2 => decrease data:params ratio from compute optimal 10.5 (default) to 8.25)
torchrun --standalone --nproc_per_node=8 -m scripts.base_train -- --depth=26 --target-param-data-ratio=8.25 --device-batch-size=16 --fp8 --run=$WANDB_RUN torchrun --standalone --nproc_per_node=8 -m scripts.base_train -- --depth=26 --target-param-data-ratio=8.25 --device-batch-size=16 --fp8 --run=$WANDB_RUN
# evaluate the model: CORE metric, BPB on train/val, and draw samples # evaluate the model: CORE metric, BPB on train/val, and draw samples
torchrun --standalone --nproc_per_node=8 -m scripts.base_eval -- --device-batch-size=16 torchrun --standalone --nproc_per_node=8 -m scripts.base_eval -- --device-batch-size=16