small tweaks

miniseries.sh

@@ -61,7 +61,6 @@ for d in "${DEPTHS[@]}"; do
     # No --target-flops, let it use the default ratio from base_train
     torchrun --standalone --nproc_per_node=$NPROC_PER_NODE -m scripts.base_train -- \
         --depth=$d \
-        --target-param-data-ratio=8 \
         --run="${WANDB_RUN}_d${d}" \
         --model-tag="${TAG}" \
         --core-metric-every=999999 \

scaling_laws.sh

@@ -7,7 +7,8 @@ FLOPS_BUDGETS=(
     3e18
     6e18
 )
-DEPTHS=(8 10 12 14 16 18 20)
+DEPTHS=(6 7 8 9 10 11 12 13 14)
+
 NPROC_PER_NODE="${NPROC_PER_NODE:-8}"
 WANDB_RUN="${WANDB_RUN:-scaling_${LABEL}}"
 EVAL_TOKENS=$((100 * 524288))  # ~100M tokens for final eval (default is ~10M)