diff --git a/scaling_laws.sh b/scaling_laws.sh index 321b286..7c269c6 100644 --- a/scaling_laws.sh +++ b/scaling_laws.sh @@ -1,5 +1,7 @@ #!/bin/bash +LABEL="jan16" + FLOPS_BUDGETS=( 1e18 3e18 @@ -7,14 +9,14 @@ FLOPS_BUDGETS=( ) DEPTHS=(8 10 12 14 16 18 20) NPROC_PER_NODE="${NPROC_PER_NODE:-8}" -WANDB_RUN="${WANDB_RUN:-scaling}" +WANDB_RUN="${WANDB_RUN:-scaling_${LABEL}}" EVAL_TOKENS=$((100 * 524288)) # ~100M tokens for final eval (default is ~10M) export OMP_NUM_THREADS=1 export NANOCHAT_BASE_DIR="${NANOCHAT_BASE_DIR:-$HOME/.cache/nanochat}" source .venv/bin/activate -RESULTS_DIR="$NANOCHAT_BASE_DIR/scaling_laws_results" +RESULTS_DIR="$NANOCHAT_BASE_DIR/scaling_laws_results_${LABEL}" mkdir -p "$RESULTS_DIR" RESULTS_FILE="$RESULTS_DIR/results.csv"